From 9dc791874ae127b3162efacb151672f05f1ac936 Mon Sep 17 00:00:00 2001 From: Stefanie Molin <24376333+stefmolin@users.noreply.github.com> Date: Sat, 29 Jun 2024 17:21:07 -0400 Subject: [PATCH 01/20] Update environment; start rerunning notebooks --- environment.yml | 14 +++--- notebooks/0-check_your_env.ipynb | 2 +- notebooks/1-getting_started_with_pandas.ipynb | 44 +++++++++---------- requirements.txt | 10 ++--- 4 files changed, 35 insertions(+), 35 deletions(-) diff --git a/environment.yml b/environment.yml index b1f4372..e9bcc4f 100644 --- a/environment.yml +++ b/environment.yml @@ -1,11 +1,11 @@ name: pandas_workshop -channels: +channels: - conda-forge dependencies: - - python>=3.8.0,<=3.11.30 - - jupyterlab>=3.5.2 - - matplotlib=3.7.1 - - numpy=1.24.2 - - pandas=2.0.0 + - python>=3.8.0,<=3.12.30 + - jupyterlab>=4.2.3 + - matplotlib=3.8.4 + - numpy=2.0.0 + - pandas=2.2.2 - requests - - seaborn=0.12.2 + - seaborn=0.13.2 diff --git a/notebooks/0-check_your_env.ipynb b/notebooks/0-check_your_env.ipynb index 6ea5687..f5cca56 100644 --- a/notebooks/0-check_your_env.ipynb +++ b/notebooks/0-check_your_env.ipynb @@ -56,7 +56,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.3" + "version": "3.12.4" } }, "nbformat": 4, diff --git a/notebooks/1-getting_started_with_pandas.ipynb b/notebooks/1-getting_started_with_pandas.ipynb index 6676c78..54e2bf2 100644 --- a/notebooks/1-getting_started_with_pandas.ipynb +++ b/notebooks/1-getting_started_with_pandas.ipynb @@ -158,8 +158,8 @@ "" ], "text/plain": [ - " name id nametype recclass mass (g) fall \n", - "0 Aachen 1 Valid L5 21 Fell \\\n", + " name id nametype recclass mass (g) fall \\\n", + "0 Aachen 1 Valid L5 21 Fell \n", "1 Aarhus 2 Valid H6 720 Fell \n", "2 Abee 6 Valid EH4 107000 Fell \n", "3 Acapulco 10 Valid Acapulcoite 1914 Fell \n", @@ -504,13 +504,13 @@ "" ], "text/plain": [ - " name id nametype recclass mass fall year \n", - "0 Aachen 1 Valid L5 21 Fell 1880-01-01T00:00:00.000 \\\n", + " name id nametype recclass mass fall year \\\n", + "0 Aachen 1 Valid L5 21 Fell 1880-01-01T00:00:00.000 \n", "1 Aarhus 2 Valid H6 720 Fell 1951-01-01T00:00:00.000 \n", "2 Abee 6 Valid EH4 107000 Fell 1952-01-01T00:00:00.000 \n", "\n", - " reclat reclong geolocation \n", - "0 50.775000 6.083330 {'latitude': '50.775', 'longitude': '6.08333'} \\\n", + " reclat reclong geolocation \\\n", + "0 50.775000 6.083330 {'latitude': '50.775', 'longitude': '6.08333'} \n", "1 56.183330 10.233330 {'latitude': '56.18333', 'longitude': '10.23333'} \n", "2 54.216670 -113.000000 {'latitude': '54.21667', 'longitude': '-113.0'} \n", "\n", @@ -809,8 +809,8 @@ "" ], "text/plain": [ - " name id nametype recclass mass (g) fall \n", - "0 Aachen 1 Valid L5 21.0 Fell \\\n", + " name id nametype recclass mass (g) fall \\\n", + "0 Aachen 1 Valid L5 21.0 Fell \n", "1 Aarhus 2 Valid H6 720.0 Fell \n", "2 Abee 6 Valid EH4 107000.0 Fell \n", "3 Acapulco 10 Valid Acapulcoite 1914.0 Fell \n", @@ -958,8 +958,8 @@ "" ], "text/plain": [ - " name id nametype recclass mass (g) fall \n", - "45711 Zillah 002 31356 Valid Eucrite 172.0 Found \\\n", + " name id nametype recclass mass (g) fall \\\n", + "45711 Zillah 002 31356 Valid Eucrite 172.0 Found \n", "45712 Zinder 30409 Valid Pallasite, ungrouped 46.0 Found \n", "45713 Zlin 30410 Valid H4 3.3 Found \n", "45714 Zubkovsky 31357 Valid L6 2167.0 Found \n", @@ -1380,8 +1380,8 @@ "" ], "text/plain": [ - " name id nametype recclass mass (g) fall \n", - "100 Benton 5026 Valid LL6 2840.0 Fell \\\n", + " name id nametype recclass mass (g) fall \\\n", + "100 Benton 5026 Valid LL6 2840.0 Fell \n", "101 Berduc 48975 Valid L6 270.0 Fell \n", "102 Béréba 5028 Valid Eucrite-mmict 18000.0 Fell \n", "103 Berlanguillas 5029 Valid L6 1440.0 Fell \n", @@ -1794,8 +1794,8 @@ "" ], "text/plain": [ - " name id nametype recclass mass (g) fall \n", - "29 Allende 2278 Valid CV3 2000000.0 Fell \\\n", + " name id nametype recclass mass (g) fall \\\n", + "29 Allende 2278 Valid CV3 2000000.0 Fell \n", "419 Jilin 12171 Valid H5 4000000.0 Fell \n", "506 Kunya-Urgench 12379 Valid H5 1100000.0 Fell \n", "707 Norton County 17922 Valid Aubrite 1100000.0 Fell \n", @@ -1954,8 +1954,8 @@ "" ], "text/plain": [ - " name id nametype recclass mass (g) fall \n", - "29 Allende 2278 Valid CV3 2000000.0 Fell \\\n", + " name id nametype recclass mass (g) fall \\\n", + "29 Allende 2278 Valid CV3 2000000.0 Fell \n", "419 Jilin 12171 Valid H5 4000000.0 Fell \n", "506 Kunya-Urgench 12379 Valid H5 1100000.0 Fell \n", "707 Norton County 17922 Valid Aubrite 1100000.0 Fell \n", @@ -2078,7 +2078,7 @@ { "data": { "text/plain": [ - "13278.078548601512" + "np.float64(13278.078548601512)" ] }, "execution_count": 25, @@ -2164,7 +2164,7 @@ { "data": { "text/plain": [ - "32.6" + "np.float64(32.6)" ] }, "execution_count": 27, @@ -2198,7 +2198,7 @@ { "data": { "text/plain": [ - "60000000.0" + "np.float64(60000000.0)" ] }, "execution_count": 28, @@ -2534,8 +2534,8 @@ "" ], "text/plain": [ - " name id nametype recclass mass (g) fall \n", - "count 45716 45716.000000 45716 45716 4.558500e+04 45716 \\\n", + " name id nametype recclass mass (g) fall \\\n", + "count 45716 45716.000000 45716 45716 4.558500e+04 45716 \n", "unique 45716 NaN 2 466 NaN 2 \n", "top Aachen NaN Valid L6 NaN Found \n", "freq 1 NaN 45641 8285 NaN 44609 \n", @@ -2661,7 +2661,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.3" + "version": "3.12.4" } }, "nbformat": 4, diff --git a/requirements.txt b/requirements.txt index 8badf7c..f02fb81 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,6 +1,6 @@ -jupyterlab>=3.5.2 -matplotlib==3.7.1 -numpy==1.24.2 -pandas==2.0.0 +jupyterlab>=4.2.3 +matplotlib==3.8.4 +numpy==2.0.0 +pandas==2.2.2 requests -seaborn==0.12.2 +seaborn==0.13.2 From 2489e6a23efa5b0ede7c1968ab4d36aff9d2ca1e Mon Sep 17 00:00:00 2001 From: Stefanie Molin <24376333+stefmolin@users.noreply.github.com> Date: Sat, 29 Jun 2024 17:21:31 -0400 Subject: [PATCH 02/20] Update intro --- slides/0-introduction.ipynb | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/slides/0-introduction.ipynb b/slides/0-introduction.ipynb index 4379675..ddb2592 100644 --- a/slides/0-introduction.ipynb +++ b/slides/0-introduction.ipynb @@ -48,11 +48,11 @@ "source": [ "## Bio\n", "\n", - "- Software engineer and data scientist at Bloomberg in New York City\n", - "- Working in information security\n", - "- Author of [Hands-On Data Analysis with Pandas](https://www.amazon.com/Hands-Data-Analysis-Pandas-visualization-dp-1800563450/dp/1800563450/) (currently in its second edition; translated into Korean)\n", - "- BS in operations research from Columbia University\n", - "- MS in computer science (ML specialization) from Georgia Tech" + "- 👩‍💻 Software engineer at Bloomberg in NYC\n", + "- 🚀 Core developer of [numpydoc](https://github.com/numpy/numpydoc)\n", + "- ✍️ Author of [Hands-On Data Analysis with Pandas](https://www.amazon.com/Hands-Data-Analysis-Pandas-visualization-dp-1800563450/dp/1800563450/) (currently in its second edition; translated into Korean and Simplified Chinese)\n", + "- 🎓 BS in operations research from Columbia University\n", + "- 🎓 MS in computer science (ML specialization) from Georgia Tech" ] }, { @@ -127,7 +127,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.3" + "version": "3.12.4" } }, "nbformat": 4, From 980f7f5e1d95ab3632a412b6db09a66e31f5513a Mon Sep 17 00:00:00 2001 From: Stefanie Molin <24376333+stefmolin@users.noreply.github.com> Date: Sat, 29 Jun 2024 17:25:01 -0400 Subject: [PATCH 03/20] Rerun for section 1 slides --- slides/1-getting_started_with_pandas.ipynb | 60 +++++++++++----------- 1 file changed, 30 insertions(+), 30 deletions(-) diff --git a/slides/1-getting_started_with_pandas.ipynb b/slides/1-getting_started_with_pandas.ipynb index 9a3d4e3..6d232cc 100644 --- a/slides/1-getting_started_with_pandas.ipynb +++ b/slides/1-getting_started_with_pandas.ipynb @@ -186,8 +186,8 @@ "" ], "text/plain": [ - " name id nametype recclass mass (g) fall \n", - "0 Aachen 1 Valid L5 21 Fell \\\n", + " name id nametype recclass mass (g) fall \\\n", + "0 Aachen 1 Valid L5 21 Fell \n", "1 Aarhus 2 Valid H6 720 Fell \n", "2 Abee 6 Valid EH4 107000 Fell \n", "3 Acapulco 10 Valid Acapulcoite 1914 Fell \n", @@ -550,13 +550,13 @@ "" ], "text/plain": [ - " name id nametype recclass mass fall year \n", - "0 Aachen 1 Valid L5 21 Fell 1880-01-01T00:00:00.000 \\\n", + " name id nametype recclass mass fall year \\\n", + "0 Aachen 1 Valid L5 21 Fell 1880-01-01T00:00:00.000 \n", "1 Aarhus 2 Valid H6 720 Fell 1951-01-01T00:00:00.000 \n", "2 Abee 6 Valid EH4 107000 Fell 1952-01-01T00:00:00.000 \n", "\n", - " reclat reclong geolocation \n", - "0 50.775000 6.083330 {'latitude': '50.775', 'longitude': '6.08333'} \\\n", + " reclat reclong geolocation \\\n", + "0 50.775000 6.083330 {'latitude': '50.775', 'longitude': '6.08333'} \n", "1 56.183330 10.233330 {'latitude': '56.18333', 'longitude': '10.23333'} \n", "2 54.216670 -113.000000 {'latitude': '54.21667', 'longitude': '-113.0'} \n", "\n", @@ -882,8 +882,8 @@ "" ], "text/plain": [ - " name id nametype recclass mass (g) fall \n", - "0 Aachen 1 Valid L5 21.0 Fell \\\n", + " name id nametype recclass mass (g) fall \\\n", + "0 Aachen 1 Valid L5 21.0 Fell \n", "1 Aarhus 2 Valid H6 720.0 Fell \n", "2 Abee 6 Valid EH4 107000.0 Fell \n", "3 Acapulco 10 Valid Acapulcoite 1914.0 Fell \n", @@ -1033,8 +1033,8 @@ "" ], "text/plain": [ - " name id nametype recclass mass (g) fall \n", - "45711 Zillah 002 31356 Valid Eucrite 172.0 Found \\\n", + " name id nametype recclass mass (g) fall \\\n", + "45711 Zillah 002 31356 Valid Eucrite 172.0 Found \n", "45712 Zinder 30409 Valid Pallasite, ungrouped 46.0 Found \n", "45713 Zlin 30410 Valid H4 3.3 Found \n", "45714 Zubkovsky 31357 Valid L6 2167.0 Found \n", @@ -1315,29 +1315,29 @@ "" ], "text/plain": [ - " vendorid tpep_pickup_datetime tpep_dropoff_datetime \n", - "0 2 2019-10-23T16:39:42.000 2019-10-23T17:14:10.000 \\\n", + " vendorid tpep_pickup_datetime tpep_dropoff_datetime \\\n", + "0 2 2019-10-23T16:39:42.000 2019-10-23T17:14:10.000 \n", "1 1 2019-10-23T16:32:08.000 2019-10-23T16:45:26.000 \n", "2 2 2019-10-23T16:08:44.000 2019-10-23T16:21:11.000 \n", "3 2 2019-10-23T16:22:44.000 2019-10-23T16:43:26.000 \n", "4 2 2019-10-23T16:45:11.000 2019-10-23T16:58:49.000 \n", "\n", - " passenger_count trip_distance ratecodeid store_and_fwd_flag \n", - "0 1 7.93 1 N \\\n", + " passenger_count trip_distance ratecodeid store_and_fwd_flag \\\n", + "0 1 7.93 1 N \n", "1 1 2.00 1 N \n", "2 1 1.36 1 N \n", "3 1 1.00 1 N \n", "4 1 1.96 1 N \n", "\n", - " pulocationid dolocationid payment_type fare_amount extra mta_tax \n", - "0 138 170 1 29.5 1.0 0.5 \\\n", + " pulocationid dolocationid payment_type fare_amount extra mta_tax \\\n", + "0 138 170 1 29.5 1.0 0.5 \n", "1 11 26 1 10.5 1.0 0.5 \n", "2 163 162 1 9.5 1.0 0.5 \n", "3 170 163 1 13.0 1.0 0.5 \n", "4 163 236 1 10.5 1.0 0.5 \n", "\n", - " tip_amount tolls_amount improvement_surcharge total_amount \n", - "0 7.98 6.12 0.3 47.90 \\\n", + " tip_amount tolls_amount improvement_surcharge total_amount \\\n", + "0 7.98 6.12 0.3 47.90 \n", "1 0.00 0.00 0.3 12.30 \n", "2 2.00 0.00 0.3 15.80 \n", "3 4.32 0.00 0.3 21.62 \n", @@ -1735,8 +1735,8 @@ "" ], "text/plain": [ - " name id nametype recclass mass (g) fall \n", - "100 Benton 5026 Valid LL6 2840.0 Fell \\\n", + " name id nametype recclass mass (g) fall \\\n", + "100 Benton 5026 Valid LL6 2840.0 Fell \n", "101 Berduc 48975 Valid L6 270.0 Fell \n", "102 Béréba 5028 Valid Eucrite-mmict 18000.0 Fell \n", "103 Berlanguillas 5029 Valid L6 1440.0 Fell \n", @@ -2153,8 +2153,8 @@ "" ], "text/plain": [ - " name id nametype recclass mass (g) fall \n", - "29 Allende 2278 Valid CV3 2000000.0 Fell \\\n", + " name id nametype recclass mass (g) fall \\\n", + "29 Allende 2278 Valid CV3 2000000.0 Fell \n", "419 Jilin 12171 Valid H5 4000000.0 Fell \n", "506 Kunya-Urgench 12379 Valid H5 1100000.0 Fell \n", "707 Norton County 17922 Valid Aubrite 1100000.0 Fell \n", @@ -2317,8 +2317,8 @@ "" ], "text/plain": [ - " name id nametype recclass mass (g) fall \n", - "29 Allende 2278 Valid CV3 2000000.0 Fell \\\n", + " name id nametype recclass mass (g) fall \\\n", + "29 Allende 2278 Valid CV3 2000000.0 Fell \n", "419 Jilin 12171 Valid H5 4000000.0 Fell \n", "506 Kunya-Urgench 12379 Valid H5 1100000.0 Fell \n", "707 Norton County 17922 Valid Aubrite 1100000.0 Fell \n", @@ -2466,7 +2466,7 @@ { "data": { "text/plain": [ - "13278.078548601512" + "np.float64(13278.078548601512)" ] }, "execution_count": 25, @@ -2554,7 +2554,7 @@ { "data": { "text/plain": [ - "32.6" + "np.float64(32.6)" ] }, "execution_count": 27, @@ -2590,7 +2590,7 @@ { "data": { "text/plain": [ - "60000000.0" + "np.float64(60000000.0)" ] }, "execution_count": 28, @@ -2948,8 +2948,8 @@ "" ], "text/plain": [ - " name id nametype recclass mass (g) fall \n", - "count 45716 45716.000000 45716 45716 4.558500e+04 45716 \\\n", + " name id nametype recclass mass (g) fall \\\n", + "count 45716 45716.000000 45716 45716 4.558500e+04 45716 \n", "unique 45716 NaN 2 466 NaN 2 \n", "top Aachen NaN Valid L6 NaN Found \n", "freq 1 NaN 45641 8285 NaN 44609 \n", @@ -3252,7 +3252,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.3" + "version": "3.12.4" } }, "nbformat": 4, From 48e77135830ab35844c04c9960998b3becfd1a0e Mon Sep 17 00:00:00 2001 From: Stefanie Molin <24376333+stefmolin@users.noreply.github.com> Date: Sat, 29 Jun 2024 17:44:22 -0400 Subject: [PATCH 04/20] Update section 2 --- notebooks/2-data_wrangling.ipynb | 501 ++++++++--------------------- slides/2-data_wrangling.ipynb | 525 +++++++++---------------------- 2 files changed, 269 insertions(+), 757 deletions(-) diff --git a/notebooks/2-data_wrangling.ipynb b/notebooks/2-data_wrangling.ipynb index d4a8646..b4cfd64 100644 --- a/notebooks/2-data_wrangling.ipynb +++ b/notebooks/2-data_wrangling.ipynb @@ -204,29 +204,29 @@ "" ], "text/plain": [ - " vendorid tpep_pickup_datetime tpep_dropoff_datetime \n", - "0 2 2019-10-23T16:39:42.000 2019-10-23T17:14:10.000 \\\n", + " vendorid tpep_pickup_datetime tpep_dropoff_datetime \\\n", + "0 2 2019-10-23T16:39:42.000 2019-10-23T17:14:10.000 \n", "1 1 2019-10-23T16:32:08.000 2019-10-23T16:45:26.000 \n", "2 2 2019-10-23T16:08:44.000 2019-10-23T16:21:11.000 \n", "3 2 2019-10-23T16:22:44.000 2019-10-23T16:43:26.000 \n", "4 2 2019-10-23T16:45:11.000 2019-10-23T16:58:49.000 \n", "\n", - " passenger_count trip_distance ratecodeid store_and_fwd_flag \n", - "0 1 7.93 1 N \\\n", + " passenger_count trip_distance ratecodeid store_and_fwd_flag \\\n", + "0 1 7.93 1 N \n", "1 1 2.00 1 N \n", "2 1 1.36 1 N \n", "3 1 1.00 1 N \n", "4 1 1.96 1 N \n", "\n", - " pulocationid dolocationid payment_type fare_amount extra mta_tax \n", - "0 138 170 1 29.5 1.0 0.5 \\\n", + " pulocationid dolocationid payment_type fare_amount extra mta_tax \\\n", + "0 138 170 1 29.5 1.0 0.5 \n", "1 11 26 1 10.5 1.0 0.5 \n", "2 163 162 1 9.5 1.0 0.5 \n", "3 170 163 1 13.0 1.0 0.5 \n", "4 163 236 1 10.5 1.0 0.5 \n", "\n", - " tip_amount tolls_amount improvement_surcharge total_amount \n", - "0 7.98 6.12 0.3 47.90 \\\n", + " tip_amount tolls_amount improvement_surcharge total_amount \\\n", + "0 7.98 6.12 0.3 47.90 \n", "1 0.00 0.00 0.3 12.30 \n", "2 2.00 0.00 0.3 15.80 \n", "3 4.32 0.00 0.3 21.62 \n", @@ -437,15 +437,15 @@ "" ], "text/plain": [ - " tpep_pickup_datetime tpep_dropoff_datetime passenger_count \n", - "0 2019-10-23T16:39:42.000 2019-10-23T17:14:10.000 1 \\\n", + " tpep_pickup_datetime tpep_dropoff_datetime passenger_count \\\n", + "0 2019-10-23T16:39:42.000 2019-10-23T17:14:10.000 1 \n", "1 2019-10-23T16:32:08.000 2019-10-23T16:45:26.000 1 \n", "2 2019-10-23T16:08:44.000 2019-10-23T16:21:11.000 1 \n", "3 2019-10-23T16:22:44.000 2019-10-23T16:43:26.000 1 \n", "4 2019-10-23T16:45:11.000 2019-10-23T16:58:49.000 1 \n", "\n", - " trip_distance payment_type fare_amount extra mta_tax tip_amount \n", - "0 7.93 1 29.5 1.0 0.5 7.98 \\\n", + " trip_distance payment_type fare_amount extra mta_tax tip_amount \\\n", + "0 7.93 1 29.5 1.0 0.5 7.98 \n", "1 2.00 1 10.5 1.0 0.5 0.00 \n", "2 1.36 1 9.5 1.0 0.5 2.00 \n", "3 1.00 1 13.0 1.0 0.5 4.32 \n", @@ -792,16 +792,16 @@ "" ], "text/plain": [ - " pickup dropoff passenger_count trip_distance \n", - "0 2019-10-23 16:39:42 2019-10-23 17:14:10 1 7.93 \\\n", + " pickup dropoff passenger_count trip_distance \\\n", + "0 2019-10-23 16:39:42 2019-10-23 17:14:10 1 7.93 \n", "1 2019-10-23 16:32:08 2019-10-23 16:45:26 1 2.00 \n", "\n", - " payment_type fare_amount extra mta_tax tip_amount tolls_amount \n", - "0 1 29.5 1.0 0.5 7.98 6.12 \\\n", + " payment_type fare_amount extra mta_tax tip_amount tolls_amount \\\n", + "0 1 29.5 1.0 0.5 7.98 6.12 \n", "1 1 10.5 1.0 0.5 0.00 0.00 \n", "\n", - " improvement_surcharge total_amount congestion_surcharge elapsed_time \n", - "0 0.3 47.9 2.5 0 days 00:34:28 \\\n", + " improvement_surcharge total_amount congestion_surcharge elapsed_time \\\n", + "0 0.3 47.9 2.5 0 days 00:34:28 \n", "1 0.3 12.3 0.0 0 days 00:13:18 \n", "\n", " cost_before_tip tip_pct fees avg_speed \n", @@ -1006,22 +1006,22 @@ "" ], "text/plain": [ - " pickup dropoff passenger_count trip_distance \n", - "5997 2019-10-23 15:55:19 2019-10-23 16:08:25 6 1.58 \\\n", + " pickup dropoff passenger_count trip_distance \\\n", + "5997 2019-10-23 15:55:19 2019-10-23 16:08:25 6 1.58 \n", "443 2019-10-23 15:56:59 2019-10-23 16:04:33 6 1.46 \n", "8722 2019-10-23 15:57:33 2019-10-23 16:03:34 6 0.62 \n", "4198 2019-10-23 15:57:38 2019-10-23 16:05:07 6 1.18 \n", "8238 2019-10-23 15:58:31 2019-10-23 16:29:29 6 3.23 \n", "\n", - " payment_type fare_amount extra mta_tax tip_amount tolls_amount \n", - "5997 2 10.0 1.0 0.5 0.0 0.0 \\\n", + " payment_type fare_amount extra mta_tax tip_amount tolls_amount \\\n", + "5997 2 10.0 1.0 0.5 0.0 0.0 \n", "443 2 7.5 1.0 0.5 0.0 0.0 \n", "8722 1 5.5 1.0 0.5 0.7 0.0 \n", "4198 1 7.0 1.0 0.5 1.0 0.0 \n", "8238 2 19.5 1.0 0.5 0.0 0.0 \n", "\n", - " improvement_surcharge total_amount congestion_surcharge \n", - "5997 0.3 14.3 2.5 \\\n", + " improvement_surcharge total_amount congestion_surcharge \\\n", + "5997 0.3 14.3 2.5 \n", "443 0.3 11.8 2.5 \n", "8722 0.3 10.5 2.5 \n", "4198 0.3 12.3 2.5 \n", @@ -1173,18 +1173,18 @@ "" ], "text/plain": [ - " pickup dropoff passenger_count trip_distance \n", - "7576 2019-10-23 16:52:51 2019-10-24 16:51:44 1 3.75 \\\n", + " pickup dropoff passenger_count trip_distance \\\n", + "7576 2019-10-23 16:52:51 2019-10-24 16:51:44 1 3.75 \n", "6902 2019-10-23 16:51:42 2019-10-24 16:50:22 1 11.19 \n", "4975 2019-10-23 16:18:51 2019-10-24 16:17:30 1 0.70 \n", "\n", - " payment_type fare_amount extra mta_tax tip_amount tolls_amount \n", - "7576 1 17.5 1.0 0.5 0.0 0.0 \\\n", + " payment_type fare_amount extra mta_tax tip_amount tolls_amount \\\n", + "7576 1 17.5 1.0 0.5 0.0 0.0 \n", "6902 2 39.5 1.0 0.5 0.0 0.0 \n", "4975 2 7.0 1.0 0.5 0.0 0.0 \n", "\n", - " improvement_surcharge total_amount congestion_surcharge \n", - "7576 0.3 21.8 2.5 \\\n", + " improvement_surcharge total_amount congestion_surcharge \\\n", + "7576 0.3 21.8 2.5 \n", "6902 0.3 41.3 0.0 \n", "4975 0.3 11.3 2.5 \n", "\n", @@ -1389,27 +1389,27 @@ "" ], "text/plain": [ - " dropoff passenger_count trip_distance \n", + " dropoff passenger_count trip_distance \\\n", "pickup \n", - "2019-10-23 16:39:42 2019-10-23 17:14:10 1 7.93 \\\n", + "2019-10-23 16:39:42 2019-10-23 17:14:10 1 7.93 \n", "2019-10-23 16:32:08 2019-10-23 16:45:26 1 2.00 \n", "2019-10-23 16:08:44 2019-10-23 16:21:11 1 1.36 \n", "\n", - " payment_type fare_amount extra mta_tax tip_amount \n", + " payment_type fare_amount extra mta_tax tip_amount \\\n", "pickup \n", - "2019-10-23 16:39:42 1 29.5 1.0 0.5 7.98 \\\n", + "2019-10-23 16:39:42 1 29.5 1.0 0.5 7.98 \n", "2019-10-23 16:32:08 1 10.5 1.0 0.5 0.00 \n", "2019-10-23 16:08:44 1 9.5 1.0 0.5 2.00 \n", "\n", - " tolls_amount improvement_surcharge total_amount \n", + " tolls_amount improvement_surcharge total_amount \\\n", "pickup \n", - "2019-10-23 16:39:42 6.12 0.3 47.9 \\\n", + "2019-10-23 16:39:42 6.12 0.3 47.9 \n", "2019-10-23 16:32:08 0.00 0.3 12.3 \n", "2019-10-23 16:08:44 0.00 0.3 15.8 \n", "\n", - " congestion_surcharge elapsed_time cost_before_tip \n", + " congestion_surcharge elapsed_time cost_before_tip \\\n", "pickup \n", - "2019-10-23 16:39:42 2.5 0 days 00:34:28 39.92 \\\n", + "2019-10-23 16:39:42 2.5 0 days 00:34:28 39.92 \n", "2019-10-23 16:32:08 0.0 0 days 00:13:18 12.30 \n", "2019-10-23 16:08:44 2.5 0 days 00:12:27 13.80 \n", "\n", @@ -1611,27 +1611,27 @@ "" ], "text/plain": [ - " dropoff passenger_count trip_distance \n", + " dropoff passenger_count trip_distance \\\n", "pickup \n", - "2019-10-23 07:48:58 2019-10-23 07:52:09 1 0.67 \\\n", + "2019-10-23 07:48:58 2019-10-23 07:52:09 1 0.67 \n", "2019-10-23 08:02:09 2019-10-24 07:42:32 1 8.38 \n", "2019-10-23 08:18:47 2019-10-23 08:36:05 1 2.39 \n", "\n", - " payment_type fare_amount extra mta_tax tip_amount \n", + " payment_type fare_amount extra mta_tax tip_amount \\\n", "pickup \n", - "2019-10-23 07:48:58 2 4.5 1.0 0.5 0.0 \\\n", + "2019-10-23 07:48:58 2 4.5 1.0 0.5 0.0 \n", "2019-10-23 08:02:09 1 32.0 1.0 0.5 5.5 \n", "2019-10-23 08:18:47 2 12.5 1.0 0.5 0.0 \n", "\n", - " tolls_amount improvement_surcharge total_amount \n", + " tolls_amount improvement_surcharge total_amount \\\n", "pickup \n", - "2019-10-23 07:48:58 0.0 0.3 8.8 \\\n", + "2019-10-23 07:48:58 0.0 0.3 8.8 \n", "2019-10-23 08:02:09 0.0 0.3 41.8 \n", "2019-10-23 08:18:47 0.0 0.3 16.8 \n", "\n", - " congestion_surcharge elapsed_time cost_before_tip \n", + " congestion_surcharge elapsed_time cost_before_tip \\\n", "pickup \n", - "2019-10-23 07:48:58 2.5 0 days 00:03:11 8.8 \\\n", + "2019-10-23 07:48:58 2.5 0 days 00:03:11 8.8 \n", "2019-10-23 08:02:09 2.5 0 days 23:40:23 36.3 \n", "2019-10-23 08:18:47 2.5 0 days 00:17:18 16.8 \n", "\n", @@ -1776,24 +1776,24 @@ "" ], "text/plain": [ - " dropoff passenger_count trip_distance \n", + " dropoff passenger_count trip_distance \\\n", "pickup \n", - "2019-10-23 08:02:09 2019-10-24 07:42:32 1 8.38 \\\n", + "2019-10-23 08:02:09 2019-10-24 07:42:32 1 8.38 \n", "2019-10-23 08:18:47 2019-10-23 08:36:05 1 2.39 \n", "\n", - " payment_type fare_amount extra mta_tax tip_amount \n", + " payment_type fare_amount extra mta_tax tip_amount \\\n", "pickup \n", - "2019-10-23 08:02:09 1 32.0 1.0 0.5 5.5 \\\n", + "2019-10-23 08:02:09 1 32.0 1.0 0.5 5.5 \n", "2019-10-23 08:18:47 2 12.5 1.0 0.5 0.0 \n", "\n", - " tolls_amount improvement_surcharge total_amount \n", + " tolls_amount improvement_surcharge total_amount \\\n", "pickup \n", - "2019-10-23 08:02:09 0.0 0.3 41.8 \\\n", + "2019-10-23 08:02:09 0.0 0.3 41.8 \n", "2019-10-23 08:18:47 0.0 0.3 16.8 \n", "\n", - " congestion_surcharge elapsed_time cost_before_tip \n", + " congestion_surcharge elapsed_time cost_before_tip \\\n", "pickup \n", - "2019-10-23 08:02:09 2.5 0 days 23:40:23 36.3 \\\n", + "2019-10-23 08:02:09 2.5 0 days 23:40:23 36.3 \n", "2019-10-23 08:18:47 2.5 0 days 00:17:18 16.8 \n", "\n", " tip_pct fees avg_speed \n", @@ -1984,22 +1984,22 @@ "" ], "text/plain": [ - " pickup dropoff passenger_count trip_distance \n", - "0 2019-10-23 07:05:34 2019-10-23 08:03:16 3 14.68 \\\n", + " pickup dropoff passenger_count trip_distance \\\n", + "0 2019-10-23 07:05:34 2019-10-23 08:03:16 3 14.68 \n", "1 2019-10-23 07:48:58 2019-10-23 07:52:09 1 0.67 \n", "2 2019-10-23 08:02:09 2019-10-24 07:42:32 1 8.38 \n", "3 2019-10-23 08:18:47 2019-10-23 08:36:05 1 2.39 \n", "4 2019-10-23 09:27:16 2019-10-23 09:33:13 2 1.11 \n", "\n", - " payment_type fare_amount extra mta_tax tip_amount tolls_amount \n", - "0 1 50.0 1.0 0.5 4.0 0.0 \\\n", + " payment_type fare_amount extra mta_tax tip_amount tolls_amount \\\n", + "0 1 50.0 1.0 0.5 4.0 0.0 \n", "1 2 4.5 1.0 0.5 0.0 0.0 \n", "2 1 32.0 1.0 0.5 5.5 0.0 \n", "3 2 12.5 1.0 0.5 0.0 0.0 \n", "4 2 6.0 1.0 0.5 0.0 0.0 \n", "\n", - " improvement_surcharge total_amount congestion_surcharge elapsed_time \n", - "0 0.3 55.8 0.0 0 days 00:57:42 \\\n", + " improvement_surcharge total_amount congestion_surcharge elapsed_time \\\n", + "0 0.3 55.8 0.0 0 days 00:57:42 \n", "1 0.3 8.8 2.5 0 days 00:03:11 \n", "2 0.3 41.8 2.5 0 days 23:40:23 \n", "3 0.3 16.8 2.5 0 days 00:17:18 \n", @@ -2164,8 +2164,8 @@ "" ], "text/plain": [ - " Date 2021 Traveler Throughput 2020 Traveler Throughput \n", - "0 2021-05-14 1716561.0 250467 \\\n", + " Date 2021 Traveler Throughput 2020 Traveler Throughput \\\n", + "0 2021-05-14 1716561.0 250467 \n", "1 2021-05-13 1743515.0 234928 \n", "2 2021-05-12 1424664.0 176667 \n", "3 2021-05-11 1315493.0 163205 \n", @@ -2802,9 +2802,9 @@ "" ], "text/plain": [ - "day_in_march 1 2 3 4 5 \n", + "day_in_march 1 2 3 4 5 \\\n", "year \n", - "2019 2257920.0 1979558.0 2143619.0 2402692.0 2543689.0 \\\n", + "2019 2257920.0 1979558.0 2143619.0 2402692.0 2543689.0 \n", "2020 2089641.0 1736393.0 1877401.0 2130015.0 2198517.0 \n", "2021 1049692.0 744812.0 826924.0 1107534.0 1168734.0 \n", "\n", @@ -3237,8 +3237,8 @@ "tsa_melted_holiday_travel = tsa_melted_holidays.assign(\n", " holiday=lambda x:\n", " x.holiday\\\n", - " .fillna(method='ffill', limit=1)\\\n", - " .fillna(method='bfill', limit=2)\n", + " .ffill(limit=1)\\\n", + " .bfill(limit=2)\n", ")" ] }, @@ -3252,7 +3252,7 @@ "tags": [] }, "source": [ - "*Tip: Check out the [documentation](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.fillna.html) for the full list of functionality available with the `fillna()` method.*" + "*Tip: Check out the [`fillna()` method documentation](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.fillna.html) for additional functionality for replacing `NA`/`NaN` values.*" ] }, { @@ -3510,9 +3510,9 @@ "" ], "text/plain": [ - "holiday Christmas Day Christmas Eve July 4th Labor Day Memorial Day \n", + "holiday Christmas Day Christmas Eve July 4th Labor Day Memorial Day \\\n", "year \n", - "2019 5053366.0 6470862.0 9414228.0 8314811.0 9720691.0 \\\n", + "2019 5053366.0 6470862.0 9414228.0 8314811.0 9720691.0 \n", "2020 1745242.0 3029810.0 2682541.0 2993653.0 1126253.0 \n", "2021 NaN NaN NaN NaN NaN \n", "\n", @@ -3621,31 +3621,31 @@ " \n", " \n", " 2021\n", - " 0.000000\n", - " 0.000000\n", - " 0.000000\n", - " 0.000000\n", - " 0.000000\n", + " NaN\n", + " NaN\n", + " NaN\n", + " NaN\n", + " NaN\n", " -0.554856\n", - " 0.000000\n", - " 0.000000\n", + " NaN\n", + " NaN\n", " \n", " \n", "\n", "" ], "text/plain": [ - "holiday Christmas Day Christmas Eve July 4th Labor Day Memorial Day \n", + "holiday Christmas Day Christmas Eve July 4th Labor Day Memorial Day \\\n", "year \n", - "2019 NaN NaN NaN NaN NaN \\\n", + "2019 NaN NaN NaN NaN NaN \n", "2020 -0.654638 -0.531776 -0.715055 -0.639961 -0.884139 \n", - "2021 0.000000 0.000000 0.000000 0.000000 0.000000 \n", + "2021 NaN NaN NaN NaN NaN \n", "\n", "holiday New Year's Day New Year's Eve Thanksgiving \n", "year \n", "2019 NaN NaN NaN \n", "2020 0.004224 -0.532176 -0.629903 \n", - "2021 -0.554856 0.000000 0.000000 " + "2021 -0.554856 NaN NaN " ] }, "execution_count": 33, @@ -3657,7 +3657,7 @@ "tsa_melted_holiday_travel.pivot_table(\n", " index='year', columns='holiday', \n", " values='travelers', aggfunc='sum'\n", - ").pct_change()" + ").pct_change(fill_method=None)" ] }, { @@ -3788,9 +3788,9 @@ "" ], "text/plain": [ - "holiday Christmas July 4th Labor Day Memorial Day New Year's \n", + "holiday Christmas July 4th Labor Day Memorial Day New Year's \\\n", "year \n", - "2019 11,524,228 9,414,228 8,314,811 9,720,691 11,006,965 \\\n", + "2019 11,524,228 9,414,228 8,314,811 9,720,691 11,006,965 \n", "2020 4,775,052 2,682,541 2,993,653 1,126,253 7,547,837 \n", "2021 NaN NaN NaN NaN 1,998,871 \n", "Total 16,299,280 12,096,769 11,308,464 10,846,944 20,553,673 \n", @@ -4118,10 +4118,10 @@ "" ], "text/plain": [ - " travelers \n", + " travelers \\\n", " count mean std min 25% 50% \n", "year \n", - "2019 365.0 2.309482e+06 285061.490784 1534386.0 2091116.0 2358007.0 \\\n", + "2019 365.0 2.309482e+06 285061.490784 1534386.0 2091116.0 2358007.0 \n", "2020 365.0 8.818674e+05 639775.194297 87534.0 507129.0 718310.0 \n", "2021 134.0 1.112632e+06 338040.673782 468933.0 807156.0 1117391.0 \n", "\n", @@ -4336,10 +4336,10 @@ "" ], "text/plain": [ - " travelers holiday_travelers \n", + " travelers holiday_travelers \\\n", " mean std mean std \n", "year \n", - "2019 2.309482e+06 285061.490784 2.271977e+06 303021.675751 \\\n", + "2019 2.309482e+06 285061.490784 2.271977e+06 303021.675751 \n", "2020 8.818674e+05 639775.194297 8.649882e+05 489938.240989 \n", "2021 1.112632e+06 338040.673782 9.994355e+05 273573.249680 \n", "\n", @@ -4708,24 +4708,24 @@ "" ], "text/plain": [ - " pickup passenger_count trip_distance \n", + " pickup passenger_count trip_distance \\\n", "dropoff \n", - "2019-10-24 12:30:08 2019-10-23 13:25:42 4 0.76 \\\n", + "2019-10-24 12:30:08 2019-10-23 13:25:42 4 0.76 \n", "2019-10-24 12:42:01 2019-10-23 13:34:03 2 1.58 \n", "\n", - " payment_type fare_amount extra mta_tax tip_amount \n", + " payment_type fare_amount extra mta_tax tip_amount \\\n", "dropoff \n", - "2019-10-24 12:30:08 2 5.0 1.0 0.5 0.00 \\\n", + "2019-10-24 12:30:08 2 5.0 1.0 0.5 0.00 \n", "2019-10-24 12:42:01 1 7.5 1.0 0.5 2.36 \n", "\n", - " tolls_amount improvement_surcharge total_amount \n", + " tolls_amount improvement_surcharge total_amount \\\n", "dropoff \n", - "2019-10-24 12:30:08 0.0 0.3 9.30 \\\n", + "2019-10-24 12:30:08 0.0 0.3 9.30 \n", "2019-10-24 12:42:01 0.0 0.3 14.16 \n", "\n", - " congestion_surcharge elapsed_time cost_before_tip \n", + " congestion_surcharge elapsed_time cost_before_tip \\\n", "dropoff \n", - "2019-10-24 12:30:08 2.5 0 days 23:04:26 9.3 \\\n", + "2019-10-24 12:30:08 2.5 0 days 23:04:26 9.3 \n", "2019-10-24 12:42:01 2.5 0 days 23:07:58 11.8 \n", "\n", " tip_pct fees avg_speed \n", @@ -4868,24 +4868,24 @@ "" ], "text/plain": [ - " pickup passenger_count trip_distance \n", + " pickup passenger_count trip_distance \\\n", "dropoff \n", - "2019-10-24 12:30:08 2019-10-23 13:25:42 4 0.76 \\\n", + "2019-10-24 12:30:08 2019-10-23 13:25:42 4 0.76 \n", "2019-10-24 12:42:01 2019-10-23 13:34:03 2 1.58 \n", "\n", - " payment_type fare_amount extra mta_tax tip_amount \n", + " payment_type fare_amount extra mta_tax tip_amount \\\n", "dropoff \n", - "2019-10-24 12:30:08 2 5.0 1.0 0.5 0.00 \\\n", + "2019-10-24 12:30:08 2 5.0 1.0 0.5 0.00 \n", "2019-10-24 12:42:01 1 7.5 1.0 0.5 2.36 \n", "\n", - " tolls_amount improvement_surcharge total_amount \n", + " tolls_amount improvement_surcharge total_amount \\\n", "dropoff \n", - "2019-10-24 12:30:08 0.0 0.3 9.30 \\\n", + "2019-10-24 12:30:08 0.0 0.3 9.30 \n", "2019-10-24 12:42:01 0.0 0.3 14.16 \n", "\n", - " congestion_surcharge elapsed_time cost_before_tip \n", + " congestion_surcharge elapsed_time cost_before_tip \\\n", "dropoff \n", - "2019-10-24 12:30:08 2.5 0 days 23:04:26 9.3 \\\n", + "2019-10-24 12:30:08 2.5 0 days 23:04:26 9.3 \n", "2019-10-24 12:42:01 2.5 0 days 23:07:58 11.8 \n", "\n", " tip_pct fees avg_speed \n", @@ -5061,27 +5061,27 @@ "" ], "text/plain": [ - " pickup passenger_count trip_distance \n", + " pickup passenger_count trip_distance \\\n", "dropoff \n", - "2019-10-23 12:53:49 2019-10-23 12:35:27 5 2.49 \\\n", + "2019-10-23 12:53:49 2019-10-23 12:35:27 5 2.49 \n", "2019-10-24 12:30:08 2019-10-23 13:25:42 4 0.76 \n", "2019-10-24 12:42:01 2019-10-23 13:34:03 2 1.58 \n", "\n", - " payment_type fare_amount extra mta_tax tip_amount \n", + " payment_type fare_amount extra mta_tax tip_amount \\\n", "dropoff \n", - "2019-10-23 12:53:49 1 13.5 1.0 0.5 2.20 \\\n", + "2019-10-23 12:53:49 1 13.5 1.0 0.5 2.20 \n", "2019-10-24 12:30:08 2 5.0 1.0 0.5 0.00 \n", "2019-10-24 12:42:01 1 7.5 1.0 0.5 2.36 \n", "\n", - " tolls_amount improvement_surcharge total_amount \n", + " tolls_amount improvement_surcharge total_amount \\\n", "dropoff \n", - "2019-10-23 12:53:49 0.0 0.3 20.00 \\\n", + "2019-10-23 12:53:49 0.0 0.3 20.00 \n", "2019-10-24 12:30:08 0.0 0.3 9.30 \n", "2019-10-24 12:42:01 0.0 0.3 14.16 \n", "\n", - " congestion_surcharge elapsed_time cost_before_tip \n", + " congestion_surcharge elapsed_time cost_before_tip \\\n", "dropoff \n", - "2019-10-23 12:53:49 2.5 0 days 00:18:22 17.8 \\\n", + "2019-10-23 12:53:49 2.5 0 days 00:18:22 17.8 \n", "2019-10-24 12:30:08 2.5 0 days 23:04:26 9.3 \n", "2019-10-24 12:42:01 2.5 0 days 23:07:58 11.8 \n", "\n", @@ -5114,249 +5114,6 @@ "*Tip: The `at_time()` method can be used to extract all entries at a given time (e.g., 12:35:27).*" ] }, - { - "cell_type": "markdown", - "id": "6b6abd12-4ad3-47ed-be2f-c4a3bb6b1fbf", - "metadata": { - "slideshow": { - "slide_type": "subslide" - }, - "tags": [] - }, - "source": [ - "Finally, `head()` and `tail()` limit us to a number of rows, but we may be interested in rows within the first/last 2 hours (or any other time interval) of the data, in which case, we should use `first()` / `last()`:" - ] - }, - { - "cell_type": "code", - "execution_count": 48, - "id": "e0e31dc9-dc86-4481-97b1-1cbb9d5490a6", - "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
pickuppassenger_counttrip_distancepayment_typefare_amountextramta_taxtip_amounttolls_amountimprovement_surchargetotal_amountcongestion_surchargeelapsed_timecost_before_tiptip_pctfeesavg_speed
dropoff
2019-10-23 07:52:092019-10-23 07:48:5810.6724.51.00.50.00.00.38.82.50 days 00:03:118.80.000004.312.628272
2019-10-23 08:03:162019-10-23 07:05:34314.68150.01.00.54.00.00.355.80.00 days 00:57:4251.80.077221.815.265165
2019-10-23 08:36:052019-10-23 08:18:4712.39212.51.00.50.00.00.316.82.50 days 00:17:1816.80.000004.38.289017
2019-10-23 09:33:132019-10-23 09:27:1621.1126.01.00.50.00.00.37.80.00 days 00:05:577.80.000001.811.193277
2019-10-23 09:49:312019-10-23 09:47:2520.47252.04.50.50.00.00.359.82.50 days 00:02:0659.80.000007.813.428571
\n", - "
" - ], - "text/plain": [ - " pickup passenger_count trip_distance \n", - "dropoff \n", - "2019-10-23 07:52:09 2019-10-23 07:48:58 1 0.67 \\\n", - "2019-10-23 08:03:16 2019-10-23 07:05:34 3 14.68 \n", - "2019-10-23 08:36:05 2019-10-23 08:18:47 1 2.39 \n", - "2019-10-23 09:33:13 2019-10-23 09:27:16 2 1.11 \n", - "2019-10-23 09:49:31 2019-10-23 09:47:25 2 0.47 \n", - "\n", - " payment_type fare_amount extra mta_tax tip_amount \n", - "dropoff \n", - "2019-10-23 07:52:09 2 4.5 1.0 0.5 0.0 \\\n", - "2019-10-23 08:03:16 1 50.0 1.0 0.5 4.0 \n", - "2019-10-23 08:36:05 2 12.5 1.0 0.5 0.0 \n", - "2019-10-23 09:33:13 2 6.0 1.0 0.5 0.0 \n", - "2019-10-23 09:49:31 2 52.0 4.5 0.5 0.0 \n", - "\n", - " tolls_amount improvement_surcharge total_amount \n", - "dropoff \n", - "2019-10-23 07:52:09 0.0 0.3 8.8 \\\n", - "2019-10-23 08:03:16 0.0 0.3 55.8 \n", - "2019-10-23 08:36:05 0.0 0.3 16.8 \n", - "2019-10-23 09:33:13 0.0 0.3 7.8 \n", - "2019-10-23 09:49:31 0.0 0.3 59.8 \n", - "\n", - " congestion_surcharge elapsed_time cost_before_tip \n", - "dropoff \n", - "2019-10-23 07:52:09 2.5 0 days 00:03:11 8.8 \\\n", - "2019-10-23 08:03:16 0.0 0 days 00:57:42 51.8 \n", - "2019-10-23 08:36:05 2.5 0 days 00:17:18 16.8 \n", - "2019-10-23 09:33:13 0.0 0 days 00:05:57 7.8 \n", - "2019-10-23 09:49:31 2.5 0 days 00:02:06 59.8 \n", - "\n", - " tip_pct fees avg_speed \n", - "dropoff \n", - "2019-10-23 07:52:09 0.00000 4.3 12.628272 \n", - "2019-10-23 08:03:16 0.07722 1.8 15.265165 \n", - "2019-10-23 08:36:05 0.00000 4.3 8.289017 \n", - "2019-10-23 09:33:13 0.00000 1.8 11.193277 \n", - "2019-10-23 09:49:31 0.00000 7.8 13.428571 " - ] - }, - "execution_count": 48, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "taxis.first('2H')" - ] - }, - { - "cell_type": "markdown", - "id": "7f0c8566-4a05-4710-8146-773089a05a07", - "metadata": {}, - "source": [ - "*Tip: Available date/time offsets can be found in the pandas documentation [here](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects).* " - ] - }, { "cell_type": "markdown", "id": "b8c0485e-4730-4124-8e71-493e7e9c45d6", @@ -5372,7 +5129,7 @@ }, { "cell_type": "code", - "execution_count": 49, + "execution_count": 48, "id": "1a06c5b3-cb6b-4f02-9559-208fd94a78ed", "metadata": {}, "outputs": [], @@ -5395,7 +5152,7 @@ }, { "cell_type": "code", - "execution_count": 50, + "execution_count": 49, "id": "7a554fda-2363-4c87-b8f3-17773c511c43", "metadata": {}, "outputs": [ @@ -5535,7 +5292,7 @@ "2020-01-10 2020 2183734.0 NaN 495760.0 -238538.0" ] }, - "execution_count": 50, + "execution_count": 49, "metadata": {}, "output_type": "execute_result" } @@ -5566,12 +5323,12 @@ }, "source": [ "### Resampling\n", - "We can use resampling to aggregate time series data to a new frequency:" + "We can use resampling to aggregate time series data to a new [frequency](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#offset-aliases):" ] }, { "cell_type": "code", - "execution_count": 51, + "execution_count": 50, "id": "0093c590-342a-4add-9999-0fb063cfa5e7", "metadata": {}, "outputs": [ @@ -5689,14 +5446,14 @@ "2021-03-31 86094635.0 9.566071e+05 280399.809061" ] }, - "execution_count": 51, + "execution_count": 50, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tsa_melted_holiday_travel['2019':'2021-Q1'].select_dtypes(include='number')\\\n", - " .resample('Q').agg(['sum', 'mean', 'std'])" + " .resample('QE').agg(['sum', 'mean', 'std'])" ] }, { @@ -5729,7 +5486,7 @@ }, { "cell_type": "code", - "execution_count": 52, + "execution_count": 51, "id": "d83c0d2e-16db-49de-b15b-ba30792a89e7", "metadata": {}, "outputs": [ @@ -5869,7 +5626,7 @@ "2020-01-10 2020 2183734.0 NaN 1.972969e+06 2.072344e+06" ] }, - "execution_count": 52, + "execution_count": 51, "metadata": {}, "output_type": "execute_result" } @@ -5898,7 +5655,7 @@ }, { "cell_type": "code", - "execution_count": 53, + "execution_count": 52, "id": "da84fa52-b2a9-4ab8-9d6d-643a3b43b94e", "metadata": {}, "outputs": [], @@ -5935,7 +5692,7 @@ }, { "cell_type": "code", - "execution_count": 54, + "execution_count": 53, "id": "3e31834c-3299-44b0-8ac3-6939b91b9be0", "metadata": {}, "outputs": [ @@ -5950,11 +5707,11 @@ " \n", " \n", " \n", - " (c) 2021-2023 Stefanie Molin\n", + " (c) 2021-2024 Stefanie Molin\n", " image/svg+xml\n", " \n", " \n", - " Matplotlib v3.7.1, https://matplotlib.org/\n", + " Matplotlib v3.8.4, https://matplotlib.org/\n", " \n", " \n", " \n", @@ -6993,7 +6750,7 @@ "L 383.779058 151.639797 \n", "L 384.668523 177.17847 \n", "L 384.668523 177.17847 \n", - "\" clip-path=\"url(#pd6e3d2542f)\" style=\"fill: none; stroke: #1f77b4; stroke-opacity: 0.8; stroke-width: 1.5; stroke-linecap: square\"/>\n", + "\" clip-path=\"url(#p0c735aba0c)\" style=\"fill: none; stroke: #1f77b4; stroke-opacity: 0.8; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p0c735aba0c)\" style=\"fill: none; stroke: #ff7f0e; stroke-opacity: 0.8; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p0c735aba0c)\" style=\"fill: none; stroke: #2ca02c; stroke-opacity: 0.8; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", @@ -7900,7 +7657,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.3" + "version": "3.12.4" } }, "nbformat": 4, diff --git a/slides/2-data_wrangling.ipynb b/slides/2-data_wrangling.ipynb index 387a991..e3d191b 100644 --- a/slides/2-data_wrangling.ipynb +++ b/slides/2-data_wrangling.ipynb @@ -232,29 +232,29 @@ "" ], "text/plain": [ - " vendorid tpep_pickup_datetime tpep_dropoff_datetime \n", - "0 2 2019-10-23T16:39:42.000 2019-10-23T17:14:10.000 \\\n", + " vendorid tpep_pickup_datetime tpep_dropoff_datetime \\\n", + "0 2 2019-10-23T16:39:42.000 2019-10-23T17:14:10.000 \n", "1 1 2019-10-23T16:32:08.000 2019-10-23T16:45:26.000 \n", "2 2 2019-10-23T16:08:44.000 2019-10-23T16:21:11.000 \n", "3 2 2019-10-23T16:22:44.000 2019-10-23T16:43:26.000 \n", "4 2 2019-10-23T16:45:11.000 2019-10-23T16:58:49.000 \n", "\n", - " passenger_count trip_distance ratecodeid store_and_fwd_flag \n", - "0 1 7.93 1 N \\\n", + " passenger_count trip_distance ratecodeid store_and_fwd_flag \\\n", + "0 1 7.93 1 N \n", "1 1 2.00 1 N \n", "2 1 1.36 1 N \n", "3 1 1.00 1 N \n", "4 1 1.96 1 N \n", "\n", - " pulocationid dolocationid payment_type fare_amount extra mta_tax \n", - "0 138 170 1 29.5 1.0 0.5 \\\n", + " pulocationid dolocationid payment_type fare_amount extra mta_tax \\\n", + "0 138 170 1 29.5 1.0 0.5 \n", "1 11 26 1 10.5 1.0 0.5 \n", "2 163 162 1 9.5 1.0 0.5 \n", "3 170 163 1 13.0 1.0 0.5 \n", "4 163 236 1 10.5 1.0 0.5 \n", "\n", - " tip_amount tolls_amount improvement_surcharge total_amount \n", - "0 7.98 6.12 0.3 47.90 \\\n", + " tip_amount tolls_amount improvement_surcharge total_amount \\\n", + "0 7.98 6.12 0.3 47.90 \n", "1 0.00 0.00 0.3 12.30 \n", "2 2.00 0.00 0.3 15.80 \n", "3 4.32 0.00 0.3 21.62 \n", @@ -467,15 +467,15 @@ "" ], "text/plain": [ - " tpep_pickup_datetime tpep_dropoff_datetime passenger_count \n", - "0 2019-10-23T16:39:42.000 2019-10-23T17:14:10.000 1 \\\n", + " tpep_pickup_datetime tpep_dropoff_datetime passenger_count \\\n", + "0 2019-10-23T16:39:42.000 2019-10-23T17:14:10.000 1 \n", "1 2019-10-23T16:32:08.000 2019-10-23T16:45:26.000 1 \n", "2 2019-10-23T16:08:44.000 2019-10-23T16:21:11.000 1 \n", "3 2019-10-23T16:22:44.000 2019-10-23T16:43:26.000 1 \n", "4 2019-10-23T16:45:11.000 2019-10-23T16:58:49.000 1 \n", "\n", - " trip_distance payment_type fare_amount extra mta_tax tip_amount \n", - "0 7.93 1 29.5 1.0 0.5 7.98 \\\n", + " trip_distance payment_type fare_amount extra mta_tax tip_amount \\\n", + "0 7.93 1 29.5 1.0 0.5 7.98 \n", "1 2.00 1 10.5 1.0 0.5 0.00 \n", "2 1.36 1 9.5 1.0 0.5 2.00 \n", "3 1.00 1 13.0 1.0 0.5 4.32 \n", @@ -828,16 +828,16 @@ "" ], "text/plain": [ - " pickup dropoff passenger_count trip_distance \n", - "0 2019-10-23 16:39:42 2019-10-23 17:14:10 1 7.93 \\\n", + " pickup dropoff passenger_count trip_distance \\\n", + "0 2019-10-23 16:39:42 2019-10-23 17:14:10 1 7.93 \n", "1 2019-10-23 16:32:08 2019-10-23 16:45:26 1 2.00 \n", "\n", - " payment_type fare_amount extra mta_tax tip_amount tolls_amount \n", - "0 1 29.5 1.0 0.5 7.98 6.12 \\\n", + " payment_type fare_amount extra mta_tax tip_amount tolls_amount \\\n", + "0 1 29.5 1.0 0.5 7.98 6.12 \n", "1 1 10.5 1.0 0.5 0.00 0.00 \n", "\n", - " improvement_surcharge total_amount congestion_surcharge elapsed_time \n", - "0 0.3 47.9 2.5 0 days 00:34:28 \\\n", + " improvement_surcharge total_amount congestion_surcharge elapsed_time \\\n", + "0 0.3 47.9 2.5 0 days 00:34:28 \n", "1 0.3 12.3 0.0 0 days 00:13:18 \n", "\n", " cost_before_tip tip_pct fees avg_speed \n", @@ -1044,22 +1044,22 @@ "" ], "text/plain": [ - " pickup dropoff passenger_count trip_distance \n", - "5997 2019-10-23 15:55:19 2019-10-23 16:08:25 6 1.58 \\\n", + " pickup dropoff passenger_count trip_distance \\\n", + "5997 2019-10-23 15:55:19 2019-10-23 16:08:25 6 1.58 \n", "443 2019-10-23 15:56:59 2019-10-23 16:04:33 6 1.46 \n", "8722 2019-10-23 15:57:33 2019-10-23 16:03:34 6 0.62 \n", "4198 2019-10-23 15:57:38 2019-10-23 16:05:07 6 1.18 \n", "8238 2019-10-23 15:58:31 2019-10-23 16:29:29 6 3.23 \n", "\n", - " payment_type fare_amount extra mta_tax tip_amount tolls_amount \n", - "5997 2 10.0 1.0 0.5 0.0 0.0 \\\n", + " payment_type fare_amount extra mta_tax tip_amount tolls_amount \\\n", + "5997 2 10.0 1.0 0.5 0.0 0.0 \n", "443 2 7.5 1.0 0.5 0.0 0.0 \n", "8722 1 5.5 1.0 0.5 0.7 0.0 \n", "4198 1 7.0 1.0 0.5 1.0 0.0 \n", "8238 2 19.5 1.0 0.5 0.0 0.0 \n", "\n", - " improvement_surcharge total_amount congestion_surcharge \n", - "5997 0.3 14.3 2.5 \\\n", + " improvement_surcharge total_amount congestion_surcharge \\\n", + "5997 0.3 14.3 2.5 \n", "443 0.3 11.8 2.5 \n", "8722 0.3 10.5 2.5 \n", "4198 0.3 12.3 2.5 \n", @@ -1213,18 +1213,18 @@ "" ], "text/plain": [ - " pickup dropoff passenger_count trip_distance \n", - "7576 2019-10-23 16:52:51 2019-10-24 16:51:44 1 3.75 \\\n", + " pickup dropoff passenger_count trip_distance \\\n", + "7576 2019-10-23 16:52:51 2019-10-24 16:51:44 1 3.75 \n", "6902 2019-10-23 16:51:42 2019-10-24 16:50:22 1 11.19 \n", "4975 2019-10-23 16:18:51 2019-10-24 16:17:30 1 0.70 \n", "\n", - " payment_type fare_amount extra mta_tax tip_amount tolls_amount \n", - "7576 1 17.5 1.0 0.5 0.0 0.0 \\\n", + " payment_type fare_amount extra mta_tax tip_amount tolls_amount \\\n", + "7576 1 17.5 1.0 0.5 0.0 0.0 \n", "6902 2 39.5 1.0 0.5 0.0 0.0 \n", "4975 2 7.0 1.0 0.5 0.0 0.0 \n", "\n", - " improvement_surcharge total_amount congestion_surcharge \n", - "7576 0.3 21.8 2.5 \\\n", + " improvement_surcharge total_amount congestion_surcharge \\\n", + "7576 0.3 21.8 2.5 \n", "6902 0.3 41.3 0.0 \n", "4975 0.3 11.3 2.5 \n", "\n", @@ -1372,8 +1372,8 @@ "" ], "text/plain": [ - " name id nametype recclass mass fall \n", - "16392 Hoba 11890 Valid Iron, IVB 60000000.0 Found \\\n", + " name id nametype recclass mass fall \\\n", + "16392 Hoba 11890 Valid Iron, IVB 60000000.0 Found \n", "5373 Cape York 5262 Valid Iron, IIIAB 58200000.0 Found \n", "5365 Campo del Cielo 5247 Valid Iron, IAB-MG 50000000.0 Found \n", "5370 Canyon Diablo 5257 Valid Iron, IAB-MG 30000000.0 Found \n", @@ -1588,27 +1588,27 @@ "" ], "text/plain": [ - " dropoff passenger_count trip_distance \n", + " dropoff passenger_count trip_distance \\\n", "pickup \n", - "2019-10-23 16:39:42 2019-10-23 17:14:10 1 7.93 \\\n", + "2019-10-23 16:39:42 2019-10-23 17:14:10 1 7.93 \n", "2019-10-23 16:32:08 2019-10-23 16:45:26 1 2.00 \n", "2019-10-23 16:08:44 2019-10-23 16:21:11 1 1.36 \n", "\n", - " payment_type fare_amount extra mta_tax tip_amount \n", + " payment_type fare_amount extra mta_tax tip_amount \\\n", "pickup \n", - "2019-10-23 16:39:42 1 29.5 1.0 0.5 7.98 \\\n", + "2019-10-23 16:39:42 1 29.5 1.0 0.5 7.98 \n", "2019-10-23 16:32:08 1 10.5 1.0 0.5 0.00 \n", "2019-10-23 16:08:44 1 9.5 1.0 0.5 2.00 \n", "\n", - " tolls_amount improvement_surcharge total_amount \n", + " tolls_amount improvement_surcharge total_amount \\\n", "pickup \n", - "2019-10-23 16:39:42 6.12 0.3 47.9 \\\n", + "2019-10-23 16:39:42 6.12 0.3 47.9 \n", "2019-10-23 16:32:08 0.00 0.3 12.3 \n", "2019-10-23 16:08:44 0.00 0.3 15.8 \n", "\n", - " congestion_surcharge elapsed_time cost_before_tip \n", + " congestion_surcharge elapsed_time cost_before_tip \\\n", "pickup \n", - "2019-10-23 16:39:42 2.5 0 days 00:34:28 39.92 \\\n", + "2019-10-23 16:39:42 2.5 0 days 00:34:28 39.92 \n", "2019-10-23 16:32:08 0.0 0 days 00:13:18 12.30 \n", "2019-10-23 16:08:44 2.5 0 days 00:12:27 13.80 \n", "\n", @@ -1814,27 +1814,27 @@ "" ], "text/plain": [ - " dropoff passenger_count trip_distance \n", + " dropoff passenger_count trip_distance \\\n", "pickup \n", - "2019-10-23 07:48:58 2019-10-23 07:52:09 1 0.67 \\\n", + "2019-10-23 07:48:58 2019-10-23 07:52:09 1 0.67 \n", "2019-10-23 08:02:09 2019-10-24 07:42:32 1 8.38 \n", "2019-10-23 08:18:47 2019-10-23 08:36:05 1 2.39 \n", "\n", - " payment_type fare_amount extra mta_tax tip_amount \n", + " payment_type fare_amount extra mta_tax tip_amount \\\n", "pickup \n", - "2019-10-23 07:48:58 2 4.5 1.0 0.5 0.0 \\\n", + "2019-10-23 07:48:58 2 4.5 1.0 0.5 0.0 \n", "2019-10-23 08:02:09 1 32.0 1.0 0.5 5.5 \n", "2019-10-23 08:18:47 2 12.5 1.0 0.5 0.0 \n", "\n", - " tolls_amount improvement_surcharge total_amount \n", + " tolls_amount improvement_surcharge total_amount \\\n", "pickup \n", - "2019-10-23 07:48:58 0.0 0.3 8.8 \\\n", + "2019-10-23 07:48:58 0.0 0.3 8.8 \n", "2019-10-23 08:02:09 0.0 0.3 41.8 \n", "2019-10-23 08:18:47 0.0 0.3 16.8 \n", "\n", - " congestion_surcharge elapsed_time cost_before_tip \n", + " congestion_surcharge elapsed_time cost_before_tip \\\n", "pickup \n", - "2019-10-23 07:48:58 2.5 0 days 00:03:11 8.8 \\\n", + "2019-10-23 07:48:58 2.5 0 days 00:03:11 8.8 \n", "2019-10-23 08:02:09 2.5 0 days 23:40:23 36.3 \n", "2019-10-23 08:18:47 2.5 0 days 00:17:18 16.8 \n", "\n", @@ -1979,24 +1979,24 @@ "" ], "text/plain": [ - " dropoff passenger_count trip_distance \n", + " dropoff passenger_count trip_distance \\\n", "pickup \n", - "2019-10-23 08:02:09 2019-10-24 07:42:32 1 8.38 \\\n", + "2019-10-23 08:02:09 2019-10-24 07:42:32 1 8.38 \n", "2019-10-23 08:18:47 2019-10-23 08:36:05 1 2.39 \n", "\n", - " payment_type fare_amount extra mta_tax tip_amount \n", + " payment_type fare_amount extra mta_tax tip_amount \\\n", "pickup \n", - "2019-10-23 08:02:09 1 32.0 1.0 0.5 5.5 \\\n", + "2019-10-23 08:02:09 1 32.0 1.0 0.5 5.5 \n", "2019-10-23 08:18:47 2 12.5 1.0 0.5 0.0 \n", "\n", - " tolls_amount improvement_surcharge total_amount \n", + " tolls_amount improvement_surcharge total_amount \\\n", "pickup \n", - "2019-10-23 08:02:09 0.0 0.3 41.8 \\\n", + "2019-10-23 08:02:09 0.0 0.3 41.8 \n", "2019-10-23 08:18:47 0.0 0.3 16.8 \n", "\n", - " congestion_surcharge elapsed_time cost_before_tip \n", + " congestion_surcharge elapsed_time cost_before_tip \\\n", "pickup \n", - "2019-10-23 08:02:09 2.5 0 days 23:40:23 36.3 \\\n", + "2019-10-23 08:02:09 2.5 0 days 23:40:23 36.3 \n", "2019-10-23 08:18:47 2.5 0 days 00:17:18 16.8 \n", "\n", " tip_pct fees avg_speed \n", @@ -2189,22 +2189,22 @@ "" ], "text/plain": [ - " pickup dropoff passenger_count trip_distance \n", - "0 2019-10-23 07:05:34 2019-10-23 08:03:16 3 14.68 \\\n", + " pickup dropoff passenger_count trip_distance \\\n", + "0 2019-10-23 07:05:34 2019-10-23 08:03:16 3 14.68 \n", "1 2019-10-23 07:48:58 2019-10-23 07:52:09 1 0.67 \n", "2 2019-10-23 08:02:09 2019-10-24 07:42:32 1 8.38 \n", "3 2019-10-23 08:18:47 2019-10-23 08:36:05 1 2.39 \n", "4 2019-10-23 09:27:16 2019-10-23 09:33:13 2 1.11 \n", "\n", - " payment_type fare_amount extra mta_tax tip_amount tolls_amount \n", - "0 1 50.0 1.0 0.5 4.0 0.0 \\\n", + " payment_type fare_amount extra mta_tax tip_amount tolls_amount \\\n", + "0 1 50.0 1.0 0.5 4.0 0.0 \n", "1 2 4.5 1.0 0.5 0.0 0.0 \n", "2 1 32.0 1.0 0.5 5.5 0.0 \n", "3 2 12.5 1.0 0.5 0.0 0.0 \n", "4 2 6.0 1.0 0.5 0.0 0.0 \n", "\n", - " improvement_surcharge total_amount congestion_surcharge elapsed_time \n", - "0 0.3 55.8 0.0 0 days 00:57:42 \\\n", + " improvement_surcharge total_amount congestion_surcharge elapsed_time \\\n", + "0 0.3 55.8 0.0 0 days 00:57:42 \n", "1 0.3 8.8 2.5 0 days 00:03:11 \n", "2 0.3 41.8 2.5 0 days 23:40:23 \n", "3 0.3 16.8 2.5 0 days 00:17:18 \n", @@ -2381,9 +2381,9 @@ "" ], "text/plain": [ - " name nametype recclass mass (g) fall year reclat \n", + " name nametype recclass mass (g) fall year reclat \\\n", "id \n", - "10036 Enigma Valid H4 94.0 Found 1967.0 31.33333 \\\n", + "10036 Enigma Valid H4 94.0 Found 1967.0 31.33333 \n", "10037 Enon Valid Iron, ungrouped 763.0 Found 1883.0 39.86667 \n", "10038 Enshi Valid H5 8000.0 Fell 1974.0 30.30000 \n", "10039 Ensisheim Valid LL6 127000.0 Fell 1491.0 47.86667 \n", @@ -2563,9 +2563,9 @@ "" ], "text/plain": [ - " name nametype recclass mass (g) fall year \n", + " name nametype recclass mass (g) fall year \\\n", "id \n", - "57150 Northwest Africa 7701 Valid CK6 55.0 Found 2101.0 \\\n", + "57150 Northwest Africa 7701 Valid CK6 55.0 Found 2101.0 \n", "\n", " reclat reclong GeoLocation pre_1970 \n", "id \n", @@ -2704,8 +2704,8 @@ "" ], "text/plain": [ - " Date 2021 Traveler Throughput 2020 Traveler Throughput \n", - "0 2021-05-14 1716561.0 250467 \\\n", + " Date 2021 Traveler Throughput 2020 Traveler Throughput \\\n", + "0 2021-05-14 1716561.0 250467 \n", "1 2021-05-13 1743515.0 234928 \n", "2 2021-05-12 1424664.0 176667 \n", "3 2021-05-11 1315493.0 163205 \n", @@ -3348,9 +3348,9 @@ "" ], "text/plain": [ - "day_in_march 1 2 3 4 5 \n", + "day_in_march 1 2 3 4 5 \\\n", "year \n", - "2019 2257920.0 1979558.0 2143619.0 2402692.0 2543689.0 \\\n", + "2019 2257920.0 1979558.0 2143619.0 2402692.0 2543689.0 \n", "2020 2089641.0 1736393.0 1877401.0 2130015.0 2198517.0 \n", "2021 1049692.0 744812.0 826924.0 1107534.0 1168734.0 \n", "\n", @@ -3789,8 +3789,8 @@ "tsa_melted_holiday_travel = tsa_melted_holidays.assign(\n", " holiday=lambda x:\n", " x.holiday\\\n", - " .fillna(method='ffill', limit=1)\\\n", - " .fillna(method='bfill', limit=2)\n", + " .ffill(limit=1)\\\n", + " .bfill(limit=2)\n", ")" ] }, @@ -3804,7 +3804,7 @@ "tags": [] }, "source": [ - "*Tip: Check out the [documentation](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.fillna.html) for the full list of functionality available with the `fillna()` method.*" + "*Tip: Check out the [`fillna()` method documentation](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.fillna.html) for additional functionality for replacing `NA`/`NaN` values.*" ] }, { @@ -4085,9 +4085,9 @@ "" ], "text/plain": [ - "holiday Christmas Day Christmas Eve July 4th Labor Day Memorial Day \n", + "holiday Christmas Day Christmas Eve July 4th Labor Day Memorial Day \\\n", "year \n", - "2019 5053366.0 6470862.0 9414228.0 8314811.0 9720691.0 \\\n", + "2019 5053366.0 6470862.0 9414228.0 8314811.0 9720691.0 \n", "2020 1745242.0 3029810.0 2682541.0 2993653.0 1126253.0 \n", "2021 NaN NaN NaN NaN NaN \n", "\n", @@ -4198,31 +4198,31 @@ " \n", " \n", " 2021\n", - " 0.000000\n", - " 0.000000\n", - " 0.000000\n", - " 0.000000\n", - " 0.000000\n", + " NaN\n", + " NaN\n", + " NaN\n", + " NaN\n", + " NaN\n", " -0.554856\n", - " 0.000000\n", - " 0.000000\n", + " NaN\n", + " NaN\n", " \n", " \n", "\n", "" ], "text/plain": [ - "holiday Christmas Day Christmas Eve July 4th Labor Day Memorial Day \n", + "holiday Christmas Day Christmas Eve July 4th Labor Day Memorial Day \\\n", "year \n", - "2019 NaN NaN NaN NaN NaN \\\n", + "2019 NaN NaN NaN NaN NaN \n", "2020 -0.654638 -0.531776 -0.715055 -0.639961 -0.884139 \n", - "2021 0.000000 0.000000 0.000000 0.000000 0.000000 \n", + "2021 NaN NaN NaN NaN NaN \n", "\n", "holiday New Year's Day New Year's Eve Thanksgiving \n", "year \n", "2019 NaN NaN NaN \n", "2020 0.004224 -0.532176 -0.629903 \n", - "2021 -0.554856 0.000000 0.000000 " + "2021 -0.554856 NaN NaN " ] }, "execution_count": 33, @@ -4234,7 +4234,7 @@ "tsa_melted_holiday_travel.pivot_table(\n", " index='year', columns='holiday', \n", " values='travelers', aggfunc='sum'\n", - ").pct_change()" + ").pct_change(fill_method=None)" ] }, { @@ -4369,9 +4369,9 @@ "" ], "text/plain": [ - "holiday Christmas July 4th Labor Day Memorial Day New Year's \n", + "holiday Christmas July 4th Labor Day Memorial Day New Year's \\\n", "year \n", - "2019 11,524,228 9,414,228 8,314,811 9,720,691 11,006,965 \\\n", + "2019 11,524,228 9,414,228 8,314,811 9,720,691 11,006,965 \n", "2020 4,775,052 2,682,541 2,993,653 1,126,253 7,547,837 \n", "2021 NaN NaN NaN NaN 1,998,871 \n", "Total 16,299,280 12,096,769 11,308,464 10,846,944 20,553,673 \n", @@ -4835,10 +4835,10 @@ "" ], "text/plain": [ - " travelers \n", + " travelers \\\n", " count mean std min 25% 50% \n", "year \n", - "2019 365.0 2.309482e+06 285061.490784 1534386.0 2091116.0 2358007.0 \\\n", + "2019 365.0 2.309482e+06 285061.490784 1534386.0 2091116.0 2358007.0 \n", "2020 365.0 8.818674e+05 639775.194297 87534.0 507129.0 718310.0 \n", "2021 134.0 1.112632e+06 338040.673782 468933.0 807156.0 1117391.0 \n", "\n", @@ -5057,10 +5057,10 @@ "" ], "text/plain": [ - " travelers holiday_travelers \n", + " travelers holiday_travelers \\\n", " mean std mean std \n", "year \n", - "2019 2.309482e+06 285061.490784 2.271977e+06 303021.675751 \\\n", + "2019 2.309482e+06 285061.490784 2.271977e+06 303021.675751 \n", "2020 8.818674e+05 639775.194297 8.649882e+05 489938.240989 \n", "2021 1.112632e+06 338040.673782 9.994355e+05 273573.249680 \n", "\n", @@ -5355,9 +5355,9 @@ "" ], "text/plain": [ - " count mean std min 25% 50% 75% \n", + " count mean std min 25% 50% 75% \\\n", "fall \n", - "Fell 1075.0 47070.715023 717067.125826 0.1 686.00 2800.0 10450.0 \\\n", + "Fell 1075.0 47070.715023 717067.125826 0.1 686.00 2800.0 10450.0 \n", "Found 44510.0 12461.922983 571105.752311 0.0 6.94 30.5 178.0 \n", "\n", " max \n", @@ -5566,24 +5566,24 @@ "" ], "text/plain": [ - " pickup passenger_count trip_distance \n", + " pickup passenger_count trip_distance \\\n", "dropoff \n", - "2019-10-24 12:30:08 2019-10-23 13:25:42 4 0.76 \\\n", + "2019-10-24 12:30:08 2019-10-23 13:25:42 4 0.76 \n", "2019-10-24 12:42:01 2019-10-23 13:34:03 2 1.58 \n", "\n", - " payment_type fare_amount extra mta_tax tip_amount \n", + " payment_type fare_amount extra mta_tax tip_amount \\\n", "dropoff \n", - "2019-10-24 12:30:08 2 5.0 1.0 0.5 0.00 \\\n", + "2019-10-24 12:30:08 2 5.0 1.0 0.5 0.00 \n", "2019-10-24 12:42:01 1 7.5 1.0 0.5 2.36 \n", "\n", - " tolls_amount improvement_surcharge total_amount \n", + " tolls_amount improvement_surcharge total_amount \\\n", "dropoff \n", - "2019-10-24 12:30:08 0.0 0.3 9.30 \\\n", + "2019-10-24 12:30:08 0.0 0.3 9.30 \n", "2019-10-24 12:42:01 0.0 0.3 14.16 \n", "\n", - " congestion_surcharge elapsed_time cost_before_tip \n", + " congestion_surcharge elapsed_time cost_before_tip \\\n", "dropoff \n", - "2019-10-24 12:30:08 2.5 0 days 23:04:26 9.3 \\\n", + "2019-10-24 12:30:08 2.5 0 days 23:04:26 9.3 \n", "2019-10-24 12:42:01 2.5 0 days 23:07:58 11.8 \n", "\n", " tip_pct fees avg_speed \n", @@ -5726,24 +5726,24 @@ "" ], "text/plain": [ - " pickup passenger_count trip_distance \n", + " pickup passenger_count trip_distance \\\n", "dropoff \n", - "2019-10-24 12:30:08 2019-10-23 13:25:42 4 0.76 \\\n", + "2019-10-24 12:30:08 2019-10-23 13:25:42 4 0.76 \n", "2019-10-24 12:42:01 2019-10-23 13:34:03 2 1.58 \n", "\n", - " payment_type fare_amount extra mta_tax tip_amount \n", + " payment_type fare_amount extra mta_tax tip_amount \\\n", "dropoff \n", - "2019-10-24 12:30:08 2 5.0 1.0 0.5 0.00 \\\n", + "2019-10-24 12:30:08 2 5.0 1.0 0.5 0.00 \n", "2019-10-24 12:42:01 1 7.5 1.0 0.5 2.36 \n", "\n", - " tolls_amount improvement_surcharge total_amount \n", + " tolls_amount improvement_surcharge total_amount \\\n", "dropoff \n", - "2019-10-24 12:30:08 0.0 0.3 9.30 \\\n", + "2019-10-24 12:30:08 0.0 0.3 9.30 \n", "2019-10-24 12:42:01 0.0 0.3 14.16 \n", "\n", - " congestion_surcharge elapsed_time cost_before_tip \n", + " congestion_surcharge elapsed_time cost_before_tip \\\n", "dropoff \n", - "2019-10-24 12:30:08 2.5 0 days 23:04:26 9.3 \\\n", + "2019-10-24 12:30:08 2.5 0 days 23:04:26 9.3 \n", "2019-10-24 12:42:01 2.5 0 days 23:07:58 11.8 \n", "\n", " tip_pct fees avg_speed \n", @@ -5921,27 +5921,27 @@ "" ], "text/plain": [ - " pickup passenger_count trip_distance \n", + " pickup passenger_count trip_distance \\\n", "dropoff \n", - "2019-10-23 12:53:49 2019-10-23 12:35:27 5 2.49 \\\n", + "2019-10-23 12:53:49 2019-10-23 12:35:27 5 2.49 \n", "2019-10-24 12:30:08 2019-10-23 13:25:42 4 0.76 \n", "2019-10-24 12:42:01 2019-10-23 13:34:03 2 1.58 \n", "\n", - " payment_type fare_amount extra mta_tax tip_amount \n", + " payment_type fare_amount extra mta_tax tip_amount \\\n", "dropoff \n", - "2019-10-23 12:53:49 1 13.5 1.0 0.5 2.20 \\\n", + "2019-10-23 12:53:49 1 13.5 1.0 0.5 2.20 \n", "2019-10-24 12:30:08 2 5.0 1.0 0.5 0.00 \n", "2019-10-24 12:42:01 1 7.5 1.0 0.5 2.36 \n", "\n", - " tolls_amount improvement_surcharge total_amount \n", + " tolls_amount improvement_surcharge total_amount \\\n", "dropoff \n", - "2019-10-23 12:53:49 0.0 0.3 20.00 \\\n", + "2019-10-23 12:53:49 0.0 0.3 20.00 \n", "2019-10-24 12:30:08 0.0 0.3 9.30 \n", "2019-10-24 12:42:01 0.0 0.3 14.16 \n", "\n", - " congestion_surcharge elapsed_time cost_before_tip \n", + " congestion_surcharge elapsed_time cost_before_tip \\\n", "dropoff \n", - "2019-10-23 12:53:49 2.5 0 days 00:18:22 17.8 \\\n", + "2019-10-23 12:53:49 2.5 0 days 00:18:22 17.8 \n", "2019-10-24 12:30:08 2.5 0 days 23:04:26 9.3 \n", "2019-10-24 12:42:01 2.5 0 days 23:07:58 11.8 \n", "\n", @@ -5974,251 +5974,6 @@ "*Tip: The `at_time()` method can be used to extract all entries at a given time (e.g., 12:35:27).*" ] }, - { - "cell_type": "markdown", - "id": "a52afa7f-0038-4e35-9cfe-b861feae7fb3", - "metadata": { - "slideshow": { - "slide_type": "subslide" - }, - "tags": [ - "id_first-and-last" - ] - }, - "source": [ - "Finally, `head()` and `tail()` limit us to a number of rows, but we may be interested in rows within the first/last 2 hours (or any other time interval) of the data, in which case, we should use `first()` / `last()`:" - ] - }, - { - "cell_type": "code", - "execution_count": 48, - "id": "f8efeac6-8eda-433a-88d1-f6f3189c2279", - "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
pickuppassenger_counttrip_distancepayment_typefare_amountextramta_taxtip_amounttolls_amountimprovement_surchargetotal_amountcongestion_surchargeelapsed_timecost_before_tiptip_pctfeesavg_speed
dropoff
2019-10-23 07:52:092019-10-23 07:48:5810.6724.51.00.50.00.00.38.82.50 days 00:03:118.80.000004.312.628272
2019-10-23 08:03:162019-10-23 07:05:34314.68150.01.00.54.00.00.355.80.00 days 00:57:4251.80.077221.815.265165
2019-10-23 08:36:052019-10-23 08:18:4712.39212.51.00.50.00.00.316.82.50 days 00:17:1816.80.000004.38.289017
2019-10-23 09:33:132019-10-23 09:27:1621.1126.01.00.50.00.00.37.80.00 days 00:05:577.80.000001.811.193277
2019-10-23 09:49:312019-10-23 09:47:2520.47252.04.50.50.00.00.359.82.50 days 00:02:0659.80.000007.813.428571
\n", - "
" - ], - "text/plain": [ - " pickup passenger_count trip_distance \n", - "dropoff \n", - "2019-10-23 07:52:09 2019-10-23 07:48:58 1 0.67 \\\n", - "2019-10-23 08:03:16 2019-10-23 07:05:34 3 14.68 \n", - "2019-10-23 08:36:05 2019-10-23 08:18:47 1 2.39 \n", - "2019-10-23 09:33:13 2019-10-23 09:27:16 2 1.11 \n", - "2019-10-23 09:49:31 2019-10-23 09:47:25 2 0.47 \n", - "\n", - " payment_type fare_amount extra mta_tax tip_amount \n", - "dropoff \n", - "2019-10-23 07:52:09 2 4.5 1.0 0.5 0.0 \\\n", - "2019-10-23 08:03:16 1 50.0 1.0 0.5 4.0 \n", - "2019-10-23 08:36:05 2 12.5 1.0 0.5 0.0 \n", - "2019-10-23 09:33:13 2 6.0 1.0 0.5 0.0 \n", - "2019-10-23 09:49:31 2 52.0 4.5 0.5 0.0 \n", - "\n", - " tolls_amount improvement_surcharge total_amount \n", - "dropoff \n", - "2019-10-23 07:52:09 0.0 0.3 8.8 \\\n", - "2019-10-23 08:03:16 0.0 0.3 55.8 \n", - "2019-10-23 08:36:05 0.0 0.3 16.8 \n", - "2019-10-23 09:33:13 0.0 0.3 7.8 \n", - "2019-10-23 09:49:31 0.0 0.3 59.8 \n", - "\n", - " congestion_surcharge elapsed_time cost_before_tip \n", - "dropoff \n", - "2019-10-23 07:52:09 2.5 0 days 00:03:11 8.8 \\\n", - "2019-10-23 08:03:16 0.0 0 days 00:57:42 51.8 \n", - "2019-10-23 08:36:05 2.5 0 days 00:17:18 16.8 \n", - "2019-10-23 09:33:13 0.0 0 days 00:05:57 7.8 \n", - "2019-10-23 09:49:31 2.5 0 days 00:02:06 59.8 \n", - "\n", - " tip_pct fees avg_speed \n", - "dropoff \n", - "2019-10-23 07:52:09 0.00000 4.3 12.628272 \n", - "2019-10-23 08:03:16 0.07722 1.8 15.265165 \n", - "2019-10-23 08:36:05 0.00000 4.3 8.289017 \n", - "2019-10-23 09:33:13 0.00000 1.8 11.193277 \n", - "2019-10-23 09:49:31 0.00000 7.8 13.428571 " - ] - }, - "execution_count": 48, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "taxis.first('2H')" - ] - }, - { - "cell_type": "markdown", - "id": "105118a4-4c0f-434c-bc31-eca06ede7120", - "metadata": {}, - "source": [ - "*Tip: Available date/time offsets can be found in the pandas documentation [here](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects).* " - ] - }, { "cell_type": "markdown", "id": "1bc7af6d-fbd2-4028-99e3-deac76074f63", @@ -6234,7 +5989,7 @@ }, { "cell_type": "code", - "execution_count": 49, + "execution_count": 48, "id": "327eae28-526b-4f16-a813-164141a793da", "metadata": {}, "outputs": [], @@ -6259,7 +6014,7 @@ }, { "cell_type": "code", - "execution_count": 50, + "execution_count": 49, "id": "2138f995-7db1-4f0f-b7dc-ad11873d4563", "metadata": {}, "outputs": [ @@ -6399,7 +6154,7 @@ "2020-01-10 2020 2183734.0 NaN 495760.0 -238538.0" ] }, - "execution_count": 50, + "execution_count": 49, "metadata": {}, "output_type": "execute_result" } @@ -6432,12 +6187,12 @@ }, "source": [ "### Resampling\n", - "We can use resampling to aggregate time series data to a new frequency:" + "We can use resampling to aggregate time series data to a new [frequency](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#offset-aliases):" ] }, { "cell_type": "code", - "execution_count": 51, + "execution_count": 50, "id": "6593acbe-6bab-438d-a160-3784f4d3131c", "metadata": {}, "outputs": [ @@ -6555,14 +6310,14 @@ "2021-03-31 86094635.0 9.566071e+05 280399.809061" ] }, - "execution_count": 51, + "execution_count": 50, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tsa_melted_holiday_travel['2019':'2021-Q1'].select_dtypes(include='number')\\\n", - " .resample('Q').agg(['sum', 'mean', 'std'])" + " .resample('QE').agg(['sum', 'mean', 'std'])" ] }, { @@ -6613,7 +6368,7 @@ }, { "cell_type": "code", - "execution_count": 52, + "execution_count": 51, "id": "3dc35819-cc7a-4235-97ed-37ee2351b6ad", "metadata": {}, "outputs": [ @@ -6753,7 +6508,7 @@ "2020-01-10 2020 2183734.0 NaN 1.972969e+06 2.072344e+06" ] }, - "execution_count": 52, + "execution_count": 51, "metadata": {}, "output_type": "execute_result" } @@ -6782,7 +6537,7 @@ }, { "cell_type": "code", - "execution_count": 53, + "execution_count": 52, "id": "71ec5579-1f12-4e5e-8ef6-076811dc715e", "metadata": {}, "outputs": [], @@ -6819,7 +6574,7 @@ }, { "cell_type": "code", - "execution_count": 54, + "execution_count": 53, "id": "a2b79c72-d7b4-45e4-bc2c-4f990d9bf278", "metadata": {}, "outputs": [ @@ -6834,11 +6589,11 @@ " \n", " \n", " \n", - " (c) 2021-2023 Stefanie Molin\n", + " (c) 2021-2024 Stefanie Molin\n", " image/svg+xml\n", " \n", " \n", - " Matplotlib v3.7.1, https://matplotlib.org/\n", + " Matplotlib v3.8.4, https://matplotlib.org/\n", " \n", " \n", " \n", @@ -7877,7 +7632,7 @@ "L 383.779058 151.639797 \n", "L 384.668523 177.17847 \n", "L 384.668523 177.17847 \n", - "\" clip-path=\"url(#pd6e3d2542f)\" style=\"fill: none; stroke: #1f77b4; stroke-opacity: 0.8; stroke-width: 1.5; stroke-linecap: square\"/>\n", + "\" clip-path=\"url(#p0c735aba0c)\" style=\"fill: none; stroke: #1f77b4; stroke-opacity: 0.8; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p0c735aba0c)\" style=\"fill: none; stroke: #ff7f0e; stroke-opacity: 0.8; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p0c735aba0c)\" style=\"fill: none; stroke: #2ca02c; stroke-opacity: 0.8; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", @@ -8767,7 +8522,7 @@ }, { "cell_type": "code", - "execution_count": 55, + "execution_count": 54, "id": "eac8caa8-73c0-4dd7-a8ba-eea5b701f8f7", "metadata": { "slideshow": { @@ -8860,7 +8615,7 @@ "2019-10-23 19:00:00 98.59 268.00 24.48 25.74" ] }, - "execution_count": 55, + "execution_count": 54, "metadata": {}, "output_type": "execute_result" } @@ -8872,7 +8627,7 @@ " '../data/2019_Yellow_Taxi_Trip_Data.csv',\n", " parse_dates=True, index_col='tpep_dropoff_datetime'\n", ")\n", - "taxis.resample('1H')[[\n", + "taxis.resample('1h')[[\n", " 'trip_distance', 'fare_amount', 'tolls_amount', 'tip_amount'\n", "]].sum().nlargest(5, 'tip_amount')" ] @@ -8909,7 +8664,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.3" + "version": "3.12.4" } }, "nbformat": 4, From 7184607a5bc2304eaf6fa837314ce48bef4ef063 Mon Sep 17 00:00:00 2001 From: Stefanie Molin <24376333+stefmolin@users.noreply.github.com> Date: Sat, 29 Jun 2024 17:49:37 -0400 Subject: [PATCH 05/20] Rerun section 3 --- notebooks/3-data_visualization.ipynb | 356 +++++++-------- slides/3-data_visualization.ipynb | 618 +++++++++++++-------------- 2 files changed, 487 insertions(+), 487 deletions(-) diff --git a/notebooks/3-data_visualization.ipynb b/notebooks/3-data_visualization.ipynb index 4919229..44ea6a3 100644 --- a/notebooks/3-data_visualization.ipynb +++ b/notebooks/3-data_visualization.ipynb @@ -259,11 +259,11 @@ " \n", " \n", " \n", - " (c) 2021-2023 Stefanie Molin\n", + " (c) 2021-2024 Stefanie Molin\n", " image/svg+xml\n", " \n", " \n", - " Matplotlib v3.7.1, https://matplotlib.org/\n", + " Matplotlib v3.8.4, https://matplotlib.org/\n", " \n", " \n", " \n", @@ -1302,7 +1302,7 @@ "L 383.779058 151.639797 \n", "L 384.668523 177.17847 \n", "L 384.668523 177.17847 \n", - "\" clip-path=\"url(#p95724de445)\" style=\"fill: none; stroke: #1f77b4; stroke-opacity: 0.8; stroke-width: 1.5; stroke-linecap: square\"/>\n", + "\" clip-path=\"url(#pe10e3a9817)\" style=\"fill: none; stroke: #1f77b4; stroke-opacity: 0.8; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pe10e3a9817)\" style=\"fill: none; stroke: #ff7f0e; stroke-opacity: 0.8; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pe10e3a9817)\" style=\"fill: none; stroke: #2ca02c; stroke-opacity: 0.8; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", @@ -2288,7 +2288,7 @@ { "data": { "text/plain": [ - "" + "" ] }, "execution_count": 5, @@ -2306,11 +2306,11 @@ " \n", " \n", " \n", - " (c) 2021-2023 Stefanie Molin\n", + " (c) 2021-2024 Stefanie Molin\n", " image/svg+xml\n", " \n", " \n", - " Matplotlib v3.7.1, https://matplotlib.org/\n", + " Matplotlib v3.8.4, https://matplotlib.org/\n", " \n", " \n", " \n", @@ -2343,7 +2343,7 @@ "L 67.909375 46.305483 \n", "L 61.709375 46.305483 \n", "z\n", - "\" clip-path=\"url(#p2d0205e871)\" style=\"fill: #1f77b4\"/>\n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #1f77b4\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #1f77b4\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #1f77b4\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #1f77b4\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #1f77b4\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #1f77b4\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #1f77b4\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #1f77b4\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #1f77b4\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #1f77b4\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #1f77b4\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #1f77b4\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #ff7f0e\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #ff7f0e\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #ff7f0e\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #ff7f0e\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #ff7f0e\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #ff7f0e\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #ff7f0e\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #ff7f0e\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #ff7f0e\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #ff7f0e\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #ff7f0e\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #ff7f0e\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #2ca02c\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #2ca02c\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #2ca02c\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #2ca02c\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #2ca02c\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #2ca02c\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #2ca02c\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #2ca02c\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #2ca02c\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #2ca02c\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #2ca02c\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #2ca02c\"/>\n", " \n", " \n", " \n", @@ -3669,7 +3669,7 @@ " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", @@ -3773,11 +3773,11 @@ " \n", " \n", " \n", - " (c) 2021-2023 Stefanie Molin\n", + " (c) 2021-2024 Stefanie Molin\n", " image/svg+xml\n", " \n", " \n", - " Matplotlib v3.7.1, https://matplotlib.org/\n", + " Matplotlib v3.8.4, https://matplotlib.org/\n", " \n", " \n", " \n", @@ -3810,7 +3810,7 @@ "L 252.438052 67.575535 \n", "L 242.738941 67.575535 \n", "z\n", - "\" clip-path=\"url(#p0197499134)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", + "\" clip-path=\"url(#p2037a6220a)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p2037a6220a)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p2037a6220a)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p2037a6220a)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p2037a6220a)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p2037a6220a)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p2037a6220a)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p2037a6220a)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p2037a6220a)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p2037a6220a)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", @@ -4265,7 +4265,7 @@ "L 359.09915 74.807557 \n", "L 388.225611 74.811458 \n", "L 388.225611 74.811458 \n", - "\" clip-path=\"url(#p0197499134)\" style=\"fill: none; stroke: #0000ff; stroke-width: 1.5; stroke-linecap: square\"/>\n", + "\" clip-path=\"url(#p2037a6220a)\" style=\"fill: none; stroke: #0000ff; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p13d289d687)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p13d289d687)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p13d289d687)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p13d289d687)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p13d289d687)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p13d289d687)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p13d289d687)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p13d289d687)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p13d289d687)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p13d289d687)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", @@ -4864,7 +4864,7 @@ "L 376.41745 158.864774 \n", "L 399.764716 158.864792 \n", "L 399.764716 158.864792 \n", - "\" clip-path=\"url(#p2f77aa5d54)\" style=\"fill: none; stroke: #0000ff; stroke-width: 1.5; stroke-linecap: square\"/>\n", + "\" clip-path=\"url(#p13d289d687)\" style=\"fill: none; stroke: #0000ff; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p08b592445e)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p08b592445e)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p08b592445e)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p08b592445e)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p08b592445e)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p08b592445e)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p08b592445e)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p08b592445e)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p08b592445e)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p08b592445e)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", @@ -5240,7 +5240,7 @@ "L 293.155413 242.917224 \n", "L 303.616548 242.91812 \n", "L 303.616548 242.91812 \n", - "\" clip-path=\"url(#p1982966d98)\" style=\"fill: none; stroke: #0000ff; stroke-width: 1.5; stroke-linecap: square\"/>\n", + "\" clip-path=\"url(#p08b592445e)\" style=\"fill: none; stroke: #0000ff; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", @@ -5424,7 +5424,7 @@ { "data": { "text/plain": [ - "" + "" ] }, "execution_count": 11, @@ -5442,11 +5442,11 @@ " \n", " \n", " \n", - " (c) 2021-2023 Stefanie Molin\n", + " (c) 2021-2024 Stefanie Molin\n", " image/svg+xml\n", " \n", " \n", - " Matplotlib v3.7.1, https://matplotlib.org/\n", + " Matplotlib v3.8.4, https://matplotlib.org/\n", " \n", " \n", " \n", @@ -5479,7 +5479,7 @@ "L 65.883702 134.118437 \n", "L 53.678491 134.118437 \n", "z\n", - "\" clip-path=\"url(#pc81759c7c4)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", + "\" clip-path=\"url(#pf8e32acb71)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pf8e32acb71)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pf8e32acb71)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pf8e32acb71)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pf8e32acb71)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pf8e32acb71)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pf8e32acb71)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pf8e32acb71)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pf8e32acb71)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pf8e32acb71)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pf8e32acb71)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", @@ -6146,7 +6146,7 @@ "L 187.26115 125.230034 \n", "L 187.93581 127.054898 \n", "L 187.93581 127.054898 \n", - "\" clip-path=\"url(#pc81759c7c4)\" style=\"fill: none; stroke: #1f77b4; stroke-width: 1.5; stroke-linecap: square\"/>\n", + "\" clip-path=\"url(#pf8e32acb71)\" style=\"fill: none; stroke: #1f77b4; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p305ab10607)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p305ab10607)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p305ab10607)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p305ab10607)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p305ab10607)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p305ab10607)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p305ab10607)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p305ab10607)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p305ab10607)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p305ab10607)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p305ab10607)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", @@ -6500,7 +6500,7 @@ "L 348.712511 133.387225 \n", "L 352.08581 133.781404 \n", "L 352.08581 133.781404 \n", - "\" clip-path=\"url(#p5aa6b7cda3)\" style=\"fill: none; stroke: #1f77b4; stroke-width: 1.5; stroke-linecap: square\"/>\n", + "\" clip-path=\"url(#p305ab10607)\" style=\"fill: none; stroke: #1f77b4; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p6b5573fdf4)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p6b5573fdf4)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p6b5573fdf4)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p6b5573fdf4)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p6b5573fdf4)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p6b5573fdf4)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p6b5573fdf4)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p6b5573fdf4)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p6b5573fdf4)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p6b5573fdf4)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p6b5573fdf4)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", @@ -6775,7 +6775,7 @@ "L 494.646693 134.118437 \n", "L 516.23581 134.118437 \n", "L 516.23581 134.118437 \n", - "\" clip-path=\"url(#pcf4e6b8396)\" style=\"fill: none; stroke: #1f77b4; stroke-width: 1.5; stroke-linecap: square\"/>\n", + "\" clip-path=\"url(#p6b5573fdf4)\" style=\"fill: none; stroke: #1f77b4; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", @@ -7015,11 +7015,11 @@ " \n", " \n", " \n", - " (c) 2021-2023 Stefanie Molin\n", + " (c) 2021-2024 Stefanie Molin\n", " image/svg+xml\n", " \n", " \n", - " Matplotlib v3.7.1, https://matplotlib.org/\n", + " Matplotlib v3.8.4, https://matplotlib.org/\n", " \n", " \n", " \n", @@ -7052,217 +7052,217 @@ "L 143.785125 44.494125 \n", "L 48.553125 44.494125 \n", "L 48.553125 22.318125 \n", - "\" clip-path=\"url(#p187671821b)\" style=\"fill: #2474b7\"/>\n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #2474b7\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #1d6cb1\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #c1d9ed\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #2c7cba\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #2171b5\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #bed8ec\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #08488e\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #99c7e0\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #7db8da\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #084f99\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #f7fbff\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #69add5\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #084184\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #edf4fc\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: none\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #083979\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #dae8f6\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: none\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #08306b\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #cadef0\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: none\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #084082\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #c8dcf0\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: none\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #115ca5\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #c8dcf0\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: none\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #084990\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #b9d6ea\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: none\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #0b559f\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #b9d6ea\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: none\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #08509b\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #b5d4e9\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: none\"/>\n", " \n", " \n", " \n", @@ -8819,7 +8819,7 @@ " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", @@ -8952,11 +8952,11 @@ " \n", " \n", " \n", - " (c) 2021-2023 Stefanie Molin\n", + " (c) 2021-2024 Stefanie Molin\n", " image/svg+xml\n", " \n", " \n", - " Matplotlib v3.7.1, https://matplotlib.org/\n", + " Matplotlib v3.8.4, https://matplotlib.org/\n", " \n", " \n", " \n", @@ -8989,7 +8989,7 @@ "L 208.841021 22.318125 \n", "L 208.841021 133.198125 \n", "z\n", - "\" clip-path=\"url(#pb1b257dad8)\" style=\"fill: #808080; opacity: 0.2; stroke: #808080; stroke-linejoin: miter\"/>\n", + "\" clip-path=\"url(#p1a0f5a9f41)\" style=\"fill: #808080; opacity: 0.2; stroke: #808080; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p1a0f5a9f41)\" style=\"fill: #808080; opacity: 0.2; stroke: #808080; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p1a0f5a9f41)\" style=\"fill: #808080; opacity: 0.2; stroke: #808080; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p1a0f5a9f41)\" style=\"fill: #808080; opacity: 0.2; stroke: #808080; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", @@ -10212,7 +10212,7 @@ "L 555.429754 27.358125 \n", "L 557.7875 50.100526 \n", "L 557.7875 50.100526 \n", - "\" clip-path=\"url(#pb1b257dad8)\" style=\"fill: none; stroke: #1f77b4; stroke-width: 1.5; stroke-linecap: square\"/>\n", + "\" clip-path=\"url(#p1a0f5a9f41)\" style=\"fill: none; stroke: #1f77b4; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", @@ -10372,11 +10372,11 @@ " \n", " \n", " \n", - " (c) 2021-2023 Stefanie Molin\n", + " (c) 2021-2024 Stefanie Molin\n", " image/svg+xml\n", " \n", " \n", - " Matplotlib v3.7.1, https://matplotlib.org/\n", + " Matplotlib v3.8.4, https://matplotlib.org/\n", " \n", " \n", " \n", @@ -12053,7 +12053,7 @@ "L 556.40783 83.393946 \n", "L 557.7875 64.028354 \n", "L 557.7875 64.028354 \n", - "\" clip-path=\"url(#pb1b257dad8)\" style=\"fill: none; stroke: #1f77b4; stroke-width: 1.5; stroke-linecap: square\"/>\n", + "\" clip-path=\"url(#p1a0f5a9f41)\" style=\"fill: none; stroke: #1f77b4; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", @@ -12368,7 +12368,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.3" + "version": "3.12.4" } }, "nbformat": 4, diff --git a/slides/3-data_visualization.ipynb b/slides/3-data_visualization.ipynb index 51946fe..555ae32 100644 --- a/slides/3-data_visualization.ipynb +++ b/slides/3-data_visualization.ipynb @@ -306,11 +306,11 @@ " \n", " \n", " \n", - " (c) 2021-2023 Stefanie Molin\n", + " (c) 2021-2024 Stefanie Molin\n", " image/svg+xml\n", " \n", " \n", - " Matplotlib v3.7.1, https://matplotlib.org/\n", + " Matplotlib v3.8.4, https://matplotlib.org/\n", " \n", " \n", " \n", @@ -1349,7 +1349,7 @@ "L 383.779058 151.639797 \n", "L 384.668523 177.17847 \n", "L 384.668523 177.17847 \n", - "\" clip-path=\"url(#p95724de445)\" style=\"fill: none; stroke: #1f77b4; stroke-opacity: 0.8; stroke-width: 1.5; stroke-linecap: square\"/>\n", + "\" clip-path=\"url(#pe10e3a9817)\" style=\"fill: none; stroke: #1f77b4; stroke-opacity: 0.8; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pe10e3a9817)\" style=\"fill: none; stroke: #ff7f0e; stroke-opacity: 0.8; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pe10e3a9817)\" style=\"fill: none; stroke: #2ca02c; stroke-opacity: 0.8; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", @@ -2339,7 +2339,7 @@ { "data": { "text/plain": [ - "" + "" ] }, "execution_count": 5, @@ -2357,11 +2357,11 @@ " \n", " \n", " \n", - " (c) 2021-2023 Stefanie Molin\n", + " (c) 2021-2024 Stefanie Molin\n", " image/svg+xml\n", " \n", " \n", - " Matplotlib v3.7.1, https://matplotlib.org/\n", + " Matplotlib v3.8.4, https://matplotlib.org/\n", " \n", " \n", " \n", @@ -2394,7 +2394,7 @@ "L 67.909375 46.305483 \n", "L 61.709375 46.305483 \n", "z\n", - "\" clip-path=\"url(#p2d0205e871)\" style=\"fill: #1f77b4\"/>\n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #1f77b4\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #1f77b4\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #1f77b4\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #1f77b4\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #1f77b4\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #1f77b4\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #1f77b4\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #1f77b4\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #1f77b4\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #1f77b4\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #1f77b4\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #1f77b4\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #ff7f0e\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #ff7f0e\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #ff7f0e\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #ff7f0e\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #ff7f0e\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #ff7f0e\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #ff7f0e\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #ff7f0e\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #ff7f0e\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #ff7f0e\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #ff7f0e\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #ff7f0e\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #2ca02c\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #2ca02c\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #2ca02c\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #2ca02c\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #2ca02c\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #2ca02c\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #2ca02c\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #2ca02c\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #2ca02c\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #2ca02c\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #2ca02c\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pa09185341f)\" style=\"fill: #2ca02c\"/>\n", " \n", " \n", " \n", @@ -3720,7 +3720,7 @@ " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", @@ -3828,11 +3828,11 @@ " \n", " \n", " \n", - " (c) 2021-2023 Stefanie Molin\n", + " (c) 2021-2024 Stefanie Molin\n", " image/svg+xml\n", " \n", " \n", - " Matplotlib v3.7.1, https://matplotlib.org/\n", + " Matplotlib v3.8.4, https://matplotlib.org/\n", " \n", " \n", " \n", @@ -3865,7 +3865,7 @@ "L 252.438052 67.575535 \n", "L 242.738941 67.575535 \n", "z\n", - "\" clip-path=\"url(#p0197499134)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", + "\" clip-path=\"url(#p2037a6220a)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p2037a6220a)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p2037a6220a)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p2037a6220a)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p2037a6220a)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p2037a6220a)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p2037a6220a)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p2037a6220a)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p2037a6220a)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p2037a6220a)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", @@ -4320,7 +4320,7 @@ "L 359.09915 74.807557 \n", "L 388.225611 74.811458 \n", "L 388.225611 74.811458 \n", - "\" clip-path=\"url(#p0197499134)\" style=\"fill: none; stroke: #0000ff; stroke-width: 1.5; stroke-linecap: square\"/>\n", + "\" clip-path=\"url(#p2037a6220a)\" style=\"fill: none; stroke: #0000ff; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p13d289d687)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p13d289d687)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p13d289d687)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p13d289d687)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p13d289d687)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p13d289d687)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p13d289d687)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p13d289d687)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p13d289d687)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p13d289d687)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", @@ -4919,7 +4919,7 @@ "L 376.41745 158.864774 \n", "L 399.764716 158.864792 \n", "L 399.764716 158.864792 \n", - "\" clip-path=\"url(#p2f77aa5d54)\" style=\"fill: none; stroke: #0000ff; stroke-width: 1.5; stroke-linecap: square\"/>\n", + "\" clip-path=\"url(#p13d289d687)\" style=\"fill: none; stroke: #0000ff; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p08b592445e)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p08b592445e)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p08b592445e)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p08b592445e)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p08b592445e)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p08b592445e)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p08b592445e)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p08b592445e)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p08b592445e)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p08b592445e)\" style=\"fill: #1f77b4; opacity: 0.8\"/>\n", " \n", " \n", " \n", @@ -5295,7 +5295,7 @@ "L 293.155413 242.917224 \n", "L 303.616548 242.91812 \n", "L 303.616548 242.91812 \n", - "\" clip-path=\"url(#p1982966d98)\" style=\"fill: none; stroke: #0000ff; stroke-width: 1.5; stroke-linecap: square\"/>\n", + "\" clip-path=\"url(#p08b592445e)\" style=\"fill: none; stroke: #0000ff; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", @@ -5526,11 +5526,11 @@ " \n", " \n", " \n", - " (c) 2021-2023 Stefanie Molin\n", + " (c) 2021-2024 Stefanie Molin\n", " image/svg+xml\n", " \n", " \n", - " Matplotlib v3.7.1, https://matplotlib.org/\n", + " Matplotlib v3.8.4, https://matplotlib.org/\n", " \n", " \n", " \n", @@ -6116,27 +6116,27 @@ "L 133.310375 64.23079 \n", "L 97.598375 64.23079 \n", "L 97.598375 102.9386 \n", - "\" clip-path=\"url(#p4acf5855ee)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", @@ -6145,27 +6145,27 @@ "L 252.350375 198.773547 \n", "L 216.638375 198.773547 \n", "L 216.638375 240.021214 \n", - "\" clip-path=\"url(#p4acf5855ee)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", @@ -6181,7 +6181,7 @@ "z\n", "\" style=\"stroke: #000000\"/>\n", " \n", - " \n", + " \n", " \n", " \n", " \n", @@ -6254,43 +6254,43 @@ "L 371.390375 161.938112 \n", "L 335.678375 161.938112 \n", "L 335.678375 214.056048 \n", - "\" clip-path=\"url(#p4acf5855ee)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #2ca02c\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #2ca02c\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #2ca02c\"/>\n", " \n", " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", @@ -6604,7 +6604,7 @@ { "data": { "text/plain": [ - "" + "" ] }, "execution_count": 11, @@ -6622,11 +6622,11 @@ " \n", " \n", " \n", - " (c) 2021-2023 Stefanie Molin\n", + " (c) 2021-2024 Stefanie Molin\n", " image/svg+xml\n", " \n", " \n", - " Matplotlib v3.7.1, https://matplotlib.org/\n", + " Matplotlib v3.8.4, https://matplotlib.org/\n", " \n", " \n", " \n", @@ -6659,7 +6659,7 @@ "L 65.883702 134.118437 \n", "L 53.678491 134.118437 \n", "z\n", - "\" clip-path=\"url(#pc81759c7c4)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", + "\" clip-path=\"url(#pf8e32acb71)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pf8e32acb71)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pf8e32acb71)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pf8e32acb71)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pf8e32acb71)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pf8e32acb71)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pf8e32acb71)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pf8e32acb71)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pf8e32acb71)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pf8e32acb71)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pf8e32acb71)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", @@ -7326,7 +7326,7 @@ "L 187.26115 125.230034 \n", "L 187.93581 127.054898 \n", "L 187.93581 127.054898 \n", - "\" clip-path=\"url(#pc81759c7c4)\" style=\"fill: none; stroke: #1f77b4; stroke-width: 1.5; stroke-linecap: square\"/>\n", + "\" clip-path=\"url(#pf8e32acb71)\" style=\"fill: none; stroke: #1f77b4; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p305ab10607)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p305ab10607)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p305ab10607)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p305ab10607)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p305ab10607)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p305ab10607)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p305ab10607)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p305ab10607)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p305ab10607)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p305ab10607)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p305ab10607)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", @@ -7680,7 +7680,7 @@ "L 348.712511 133.387225 \n", "L 352.08581 133.781404 \n", "L 352.08581 133.781404 \n", - "\" clip-path=\"url(#p5aa6b7cda3)\" style=\"fill: none; stroke: #1f77b4; stroke-width: 1.5; stroke-linecap: square\"/>\n", + "\" clip-path=\"url(#p305ab10607)\" style=\"fill: none; stroke: #1f77b4; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p6b5573fdf4)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p6b5573fdf4)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p6b5573fdf4)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p6b5573fdf4)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p6b5573fdf4)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p6b5573fdf4)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p6b5573fdf4)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p6b5573fdf4)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p6b5573fdf4)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p6b5573fdf4)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p6b5573fdf4)\" style=\"fill: #1f77b4; fill-opacity: 0.5; stroke: #000000; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", @@ -7955,7 +7955,7 @@ "L 494.646693 134.118437 \n", "L 516.23581 134.118437 \n", "L 516.23581 134.118437 \n", - "\" clip-path=\"url(#pcf4e6b8396)\" style=\"fill: none; stroke: #1f77b4; stroke-width: 1.5; stroke-linecap: square\"/>\n", + "\" clip-path=\"url(#p6b5573fdf4)\" style=\"fill: none; stroke: #1f77b4; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", @@ -8197,11 +8197,11 @@ " \n", " \n", " \n", - " (c) 2021-2023 Stefanie Molin\n", + " (c) 2021-2024 Stefanie Molin\n", " image/svg+xml\n", " \n", " \n", - " Matplotlib v3.7.1, https://matplotlib.org/\n", + " Matplotlib v3.8.4, https://matplotlib.org/\n", " \n", " \n", " \n", @@ -8234,217 +8234,217 @@ "L 143.785125 44.494125 \n", "L 48.553125 44.494125 \n", "L 48.553125 22.318125 \n", - "\" clip-path=\"url(#p187671821b)\" style=\"fill: #2474b7\"/>\n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #2474b7\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #1d6cb1\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #c1d9ed\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #2c7cba\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #2171b5\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #bed8ec\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #08488e\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #99c7e0\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #7db8da\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #084f99\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #f7fbff\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #69add5\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #084184\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #edf4fc\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: none\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #083979\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #dae8f6\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: none\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #08306b\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #cadef0\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: none\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #084082\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #c8dcf0\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: none\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #115ca5\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #c8dcf0\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: none\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #084990\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #b9d6ea\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: none\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #0b559f\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #b9d6ea\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: none\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #08509b\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: #b5d4e9\"/>\n", " \n", + "\" clip-path=\"url(#pafbb675ef2)\" style=\"fill: none\"/>\n", " \n", " \n", " \n", @@ -10001,7 +10001,7 @@ " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", @@ -10184,11 +10184,11 @@ " \n", " \n", " \n", - " (c) 2021-2023 Stefanie Molin\n", + " (c) 2021-2024 Stefanie Molin\n", " image/svg+xml\n", " \n", " \n", - " Matplotlib v3.7.1, https://matplotlib.org/\n", + " Matplotlib v3.8.4, https://matplotlib.org/\n", " \n", " \n", " \n", @@ -10221,505 +10221,505 @@ "L 73.765813 73.7715 \n", "L 49.957813 73.7715 \n", "L 49.957813 35.7555 \n", - "\" clip-path=\"url(#pbabb56a130)\" style=\"fill: #afd1e7\"/>\n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #afd1e7\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #81badb\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #1966ad\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #1865ac\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #1562a9\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #125ea6\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #105ba4\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #3888c1\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #8abfdd\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #58a1cf\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #7fb9da\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #94c4df\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #e0ecf8\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #dce9f6\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #0e59a2\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #1460a8\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #08478d\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #083877\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #083573\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #09529d\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #2070b4\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #105ba4\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #2d7dbb\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #2e7ebc\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #dbe9f6\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #aacfe5\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #61a7d2\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #a5cde3\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #0b559f\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #08306b\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #08306b\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #084488\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #1561a9\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #084f99\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #1967ad\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #1a68ae\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #a8cee4\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #4e9acb\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #135fa7\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #206fb4\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #7ab6d9\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #3989c1\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #3787c0\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #69add5\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #bfd8ed\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #b9d6ea\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #95c5df\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #66abd4\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #82bbdb\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #81badb\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #3181bd\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #2171b5\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #1562a9\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #084285\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #083370\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #09529d\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #1d6cb1\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #0f5aa3\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #2d7dbb\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #2a7ab9\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #f7fbff\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #c3daee\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #7ab6d9\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #6fb0d7\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #3888c1\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #084488\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #08488e\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #0b559f\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #2f7fbc\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #206fb4\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #2c7cba\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #3383be\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #a9cfe5\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #71b1d7\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #65aad4\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #519ccc\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #3d8dc4\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #2474b7\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #1c6bb0\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #4a98c9\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #a1cbe2\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #8abfdd\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #8cc0dd\"/>\n", " \n", + "\" clip-path=\"url(#p729afc49fc)\" style=\"fill: #a3cce3\"/>\n", " \n", " \n", " \n", @@ -12863,7 +12863,7 @@ " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", @@ -12950,11 +12950,11 @@ " \n", " \n", " \n", - " (c) 2021-2023 Stefanie Molin\n", + " (c) 2021-2024 Stefanie Molin\n", " image/svg+xml\n", " \n", " \n", - " Matplotlib v3.7.1, https://matplotlib.org/\n", + " Matplotlib v3.8.4, https://matplotlib.org/\n", " \n", " \n", " \n", @@ -12987,7 +12987,7 @@ "L 208.841021 22.318125 \n", "L 208.841021 133.198125 \n", "z\n", - "\" clip-path=\"url(#pb1b257dad8)\" style=\"fill: #808080; opacity: 0.2; stroke: #808080; stroke-linejoin: miter\"/>\n", + "\" clip-path=\"url(#p1a0f5a9f41)\" style=\"fill: #808080; opacity: 0.2; stroke: #808080; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p1a0f5a9f41)\" style=\"fill: #808080; opacity: 0.2; stroke: #808080; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p1a0f5a9f41)\" style=\"fill: #808080; opacity: 0.2; stroke: #808080; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#p1a0f5a9f41)\" style=\"fill: #808080; opacity: 0.2; stroke: #808080; stroke-linejoin: miter\"/>\n", " \n", " \n", " \n", @@ -14210,7 +14210,7 @@ "L 555.429754 27.358125 \n", "L 557.7875 50.100526 \n", "L 557.7875 50.100526 \n", - "\" clip-path=\"url(#pb1b257dad8)\" style=\"fill: none; stroke: #1f77b4; stroke-width: 1.5; stroke-linecap: square\"/>\n", + "\" clip-path=\"url(#p1a0f5a9f41)\" style=\"fill: none; stroke: #1f77b4; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", @@ -14372,11 +14372,11 @@ " \n", " \n", " \n", - " (c) 2021-2023 Stefanie Molin\n", + " (c) 2021-2024 Stefanie Molin\n", " image/svg+xml\n", " \n", " \n", - " Matplotlib v3.7.1, https://matplotlib.org/\n", + " Matplotlib v3.8.4, https://matplotlib.org/\n", " \n", " \n", " \n", @@ -16053,7 +16053,7 @@ "L 556.40783 83.393946 \n", "L 557.7875 64.028354 \n", "L 557.7875 64.028354 \n", - "\" clip-path=\"url(#pb1b257dad8)\" style=\"fill: none; stroke: #1f77b4; stroke-width: 1.5; stroke-linecap: square\"/>\n", + "\" clip-path=\"url(#p1a0f5a9f41)\" style=\"fill: none; stroke: #1f77b4; stroke-width: 1.5; stroke-linecap: square\"/>\n", " \n", " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", @@ -16440,11 +16440,11 @@ " \n", " \n", " \n", - " (c) 2021-2023 Stefanie Molin\n", + " (c) 2021-2024 Stefanie Molin\n", " image/svg+xml\n", " \n", " \n", - " Matplotlib v3.7.1, https://matplotlib.org/\n", + " Matplotlib v3.8.4, https://matplotlib.org/\n", " \n", " \n", " \n", @@ -17030,27 +17030,27 @@ "L 133.310375 64.23079 \n", "L 97.598375 64.23079 \n", "L 97.598375 102.9386 \n", - "\" clip-path=\"url(#p4acf5855ee)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", @@ -17059,27 +17059,27 @@ "L 252.350375 198.773547 \n", "L 216.638375 198.773547 \n", "L 216.638375 240.021214 \n", - "\" clip-path=\"url(#p4acf5855ee)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", @@ -17095,7 +17095,7 @@ "z\n", "\" style=\"stroke: #000000\"/>\n", " \n", - " \n", + " \n", " \n", " \n", " \n", @@ -17168,43 +17168,43 @@ "L 371.390375 161.938112 \n", "L 335.678375 161.938112 \n", "L 335.678375 214.056048 \n", - "\" clip-path=\"url(#p4acf5855ee)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #1f77b4; stroke-linecap: square\"/>\n", " \n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #2ca02c\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #2ca02c\"/>\n", " \n", " \n", " \n", + "\" clip-path=\"url(#pc422e88a88)\" style=\"fill: none; stroke: #2ca02c\"/>\n", " \n", " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", @@ -17552,7 +17552,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.3" + "version": "3.12.4" } }, "nbformat": 4, From be13c3c666003b8bc0cc21158c7789c7d3d57138 Mon Sep 17 00:00:00 2001 From: Stefanie Molin <24376333+stefmolin@users.noreply.github.com> Date: Sat, 29 Jun 2024 18:01:44 -0400 Subject: [PATCH 06/20] Rerun remaining sections --- asynchronous_lab/asynchronous_lab.ipynb | 4 +- asynchronous_lab/solutions.ipynb | 36 ++++----- notebooks/4-hands_on_data_analysis_lab.ipynb | 4 +- notebooks/workbook.ipynb | 2 +- slides/4-hands_on_data_analysis_lab.ipynb | 79 ++------------------ slides/5-outro.ipynb | 26 ++++++- 6 files changed, 55 insertions(+), 96 deletions(-) diff --git a/asynchronous_lab/asynchronous_lab.ipynb b/asynchronous_lab/asynchronous_lab.ipynb index 79a04b0..afcdf86 100644 --- a/asynchronous_lab/asynchronous_lab.ipynb +++ b/asynchronous_lab/asynchronous_lab.ipynb @@ -260,7 +260,7 @@ ], "metadata": { "kernelspec": { - "display_name": "Python 3", + "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, @@ -274,7 +274,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.3" + "version": "3.12.4" } }, "nbformat": 4, diff --git a/asynchronous_lab/solutions.ipynb b/asynchronous_lab/solutions.ipynb index 64e9df9..bb0591b 100644 --- a/asynchronous_lab/solutions.ipynb +++ b/asynchronous_lab/solutions.ipynb @@ -195,22 +195,22 @@ "" ], "text/plain": [ - " passengers freight mail distance unique_carrier airline_id \n", - "0 0.0 53185.0 0.0 8165.0 EK 20392 \\\n", + " passengers freight mail distance unique_carrier airline_id \\\n", + "0 0.0 53185.0 0.0 8165.0 EK 20392 \n", "1 0.0 9002.0 0.0 6849.0 EK 20392 \n", "2 0.0 2220750.0 0.0 7247.0 EK 20392 \n", "3 0.0 1201490.0 0.0 8165.0 EK 20392 \n", "4 0.0 248642.0 0.0 6849.0 EK 20392 \n", "\n", - " unique_carrier_name unique_carrier_entity region carrier ... dest_state_nm \n", - "0 Emirates 9678A I EK ... Texas \\\n", + " unique_carrier_name unique_carrier_entity region carrier ... dest_state_nm \\\n", + "0 Emirates 9678A I EK ... Texas \n", "1 Emirates 9678A I EK ... New York \n", "2 Emirates 9678A I EK ... Illinois \n", "3 Emirates 9678A I EK ... NaN \n", "4 Emirates 9678A I EK ... NaN \n", "\n", - " dest_country dest_country_name dest_wac year quarter month \n", - "0 US United States 74 2019 1 3 \\\n", + " dest_country dest_country_name dest_wac year quarter month \\\n", + "0 US United States 74 2019 1 3 \n", "1 US United States 22 2019 1 3 \n", "2 US United States 41 2019 1 3 \n", "3 AE United Arab Emirates 678 2019 1 3 \n", @@ -1055,9 +1055,9 @@ "" ], "text/plain": [ - "international_country United Kingdom Mexico Canada Germany \n", + "international_country United Kingdom Mexico Canada Germany \\\n", "us_city \n", - "New York, NY 3599328.0 860173.0 1566104.0 853674.0 \\\n", + "New York, NY 3599328.0 860173.0 1566104.0 853674.0 \n", "Miami, FL 1037798.0 854086.0 412699.0 375279.0 \n", "Atlanta, GA 773873.0 1569084.0 741236.0 659374.0 \n", "Newark, NJ 1240972.0 633896.0 332936.0 881199.0 \n", @@ -1068,9 +1068,9 @@ "Dallas/Fort Worth, TX 751539.0 2047306.0 446766.0 359896.0 \n", "Fort Lauderdale, FL 45007.0 396294.0 227229.0 NaN \n", "\n", - "international_country Dominican Republic Japan Jamaica Netherlands \n", + "international_country Dominican Republic Japan Jamaica Netherlands \\\n", "us_city \n", - "New York, NY 2443025.0 3832.0 740717.0 323223.0 \\\n", + "New York, NY 2443025.0 3832.0 740717.0 323223.0 \n", "Miami, FL 916565.0 NaN 540691.0 NaN \n", "Atlanta, GA 462258.0 191342.0 502099.0 499415.0 \n", "Newark, NJ 868299.0 210033.0 145932.0 151797.0 \n", @@ -1368,9 +1368,9 @@ "" ], "text/plain": [ - "international_country Brazil Canada China Colombia \n", + "international_country Brazil Canada China Colombia \\\n", "us_city \n", - "Atlanta, GA 0.073838 0.035586 0.019355 0.037853 \\\n", + "Atlanta, GA 0.073838 0.035586 0.019355 0.037853 \n", "Chicago, IL 0.037089 0.071433 0.063844 0.002887 \n", "Dallas/Fort Worth, TX 0.041950 0.026075 0.036498 0.019071 \n", "Houston, TX 0.059782 0.033252 0.017368 0.045179 \n", @@ -1381,9 +1381,9 @@ "San Francisco, CA NaN 0.058750 0.143582 NaN \n", "Washington, DC 0.027989 0.030353 0.031496 0.020569 \n", "\n", - "international_country Dominican Republic France Germany Italy \n", + "international_country Dominican Republic France Germany Italy \\\n", "us_city \n", - "Atlanta, GA 0.060782 0.097139 0.060561 0.075241 \\\n", + "Atlanta, GA 0.060782 0.097139 0.060561 0.075241 \n", "Chicago, IL 0.032785 0.041849 0.099252 0.060731 \n", "Dallas/Fort Worth, TX 0.004950 0.028932 0.033055 0.021876 \n", "Houston, TX 0.006499 0.017999 0.050199 NaN \n", @@ -1394,9 +1394,9 @@ "San Francisco, CA NaN 0.068619 0.088452 0.008179 \n", "Washington, DC 0.013370 0.057686 0.082315 0.035564 \n", "\n", - "international_country Jamaica Japan Mexico Netherlands South Korea \n", + "international_country Jamaica Japan Mexico Netherlands South Korea \\\n", "us_city \n", - "Atlanta, GA 0.113234 0.019115 0.053810 0.127279 0.072975 \\\n", + "Atlanta, GA 0.113234 0.019115 0.053810 0.127279 0.072975 \n", "Chicago, IL 0.038491 0.058029 0.084269 0.045159 0.044433 \n", "Dallas/Fort Worth, TX 0.021488 0.045049 0.106572 0.010794 0.049176 \n", "Houston, TX 0.027450 0.031631 0.123727 0.052429 NaN \n", @@ -1464,7 +1464,7 @@ }, { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "
" ] @@ -1511,7 +1511,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.3" + "version": "3.12.4" } }, "nbformat": 4, diff --git a/notebooks/4-hands_on_data_analysis_lab.ipynb b/notebooks/4-hands_on_data_analysis_lab.ipynb index 71685aa..1a4c19a 100644 --- a/notebooks/4-hands_on_data_analysis_lab.ipynb +++ b/notebooks/4-hands_on_data_analysis_lab.ipynb @@ -40,7 +40,7 @@ ], "metadata": { "kernelspec": { - "display_name": "Python 3", + "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, @@ -54,7 +54,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.3" + "version": "3.12.4" } }, "nbformat": 4, diff --git a/notebooks/workbook.ipynb b/notebooks/workbook.ipynb index 01ee60d..f838f6f 100644 --- a/notebooks/workbook.ipynb +++ b/notebooks/workbook.ipynb @@ -254,7 +254,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.10.2" + "version": "3.12.4" } }, "nbformat": 4, diff --git a/slides/4-hands_on_data_analysis_lab.ipynb b/slides/4-hands_on_data_analysis_lab.ipynb index a97d06d..d186604 100644 --- a/slides/4-hands_on_data_analysis_lab.ipynb +++ b/slides/4-hands_on_data_analysis_lab.ipynb @@ -66,77 +66,12 @@ ] }, { - "cell_type": "markdown", - "id": "b6c1e37c-eff2-4451-9cf4-2c63427ee3af", - "metadata": { - "slideshow": { - "slide_type": "slide" - }, - "tags": [ - "id_related-content" - ] - }, - "source": [ - "# Related content\n", - "\n", - "*All examples herein were developed exclusively for this workshop – check out [Hands-On Data Analysis with Pandas](https://www.amazon.com/Hands-Data-Analysis-Pandas-visualization-dp-1800563450/dp/1800563450/) and my [Beyond the Basics: Data Visualization in Python](https://stefaniemolin.com/workshops/python-data-viz-workshop/) workshop for more.*\n", - "\n", - "
\n", - " \n", - "
\n", - " stefaniemolin.com\n", - "
\n", - "
" - ] - }, - { - "cell_type": "markdown", - "id": "0f37ebbc-a5f8-4a61-8a18-c74528ee1220", - "metadata": { - "slideshow": { - "slide_type": "skip" - }, - "tags": [] - }, - "source": [ - "# Thank you!\n", - "\n", - "*I hope you enjoyed the session. You can follow my work on the following platforms:*\n", - "\n", - "\n", - "
\n", - "
\n", - " \n", - "
\n", - "\n", - "
\n", - "
\n", - " \n", - " \n", - " stefaniemolin.com\n", - " \n", - "
\n", - "
\n", - " \n", - " \n", - " github.com/stefmolin\n", - " \n", - "
\n", - " \n", - " \n", - "
\n", - "
" - ] + "cell_type": "code", + "execution_count": null, + "id": "2a524590-e4fc-45d2-9985-d7ae7d455eba", + "metadata": {}, + "outputs": [], + "source": [] } ], "metadata": { @@ -155,7 +90,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.3" + "version": "3.12.4" } }, "nbformat": 4, diff --git a/slides/5-outro.ipynb b/slides/5-outro.ipynb index d6fce47..0300778 100644 --- a/slides/5-outro.ipynb +++ b/slides/5-outro.ipynb @@ -1,5 +1,29 @@ { "cells": [ + { + "cell_type": "markdown", + "id": "d8eb612f-36d3-4935-ac0d-fb22911881d4", + "metadata": { + "slideshow": { + "slide_type": "slide" + }, + "tags": [ + "id_related-content" + ] + }, + "source": [ + "# Related content\n", + "\n", + "*All examples herein were developed exclusively for this workshop – check out [Hands-On Data Analysis with Pandas](https://www.amazon.com/Hands-Data-Analysis-Pandas-visualization-dp-1800563450/dp/1800563450/) and my [Beyond the Basics: Data Visualization in Python](https://stefaniemolin.com/workshops/python-data-viz-workshop/) workshop for more.*\n", + "\n", + "
\n", + " \n", + "
\n", + " stefaniemolin.com\n", + "
\n", + "
" + ] + }, { "cell_type": "markdown", "id": "cd8d474a-0d3a-4387-b726-dea2df655ce1", @@ -67,7 +91,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.3" + "version": "3.12.4" } }, "nbformat": 4, From d2b7c01cc7c15504febfa782be22edd4918e4710 Mon Sep 17 00:00:00 2001 From: Stefanie Molin <24376333+stefmolin@users.noreply.github.com> Date: Sat, 29 Jun 2024 18:02:36 -0400 Subject: [PATCH 07/20] Update installation instructions --- README.md | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 126b995..67bd568 100644 --- a/README.md +++ b/README.md @@ -40,7 +40,10 @@ You can work through the notebooks locally or in your browser. Pick the installa ### Local Installation **Warning**: It is highly recommended that you use your personal laptop for the installation. -0. Install Python >= version 3.8 and <= version 3.11 OR install [Anaconda](https://docs.anaconda.com/anaconda/install/)/[Miniconda](https://docs.conda.io/en/latest/miniconda.html). Note that Anaconda/Miniconda is recommended if you are working on a Windows machine and are not very comfortable with the command line. Alternatively, depending on server availability, you can use [this](https://mybinder.org/v2/gh/stefmolin/pandas-workshop/main?urlpath=lab) Binder environment if you don't want to install anything on your machine. +0. Install the following, if not already installed: + - Python >= version 3.8 and <= version 3.13 OR install [Anaconda](https://docs.anaconda.com/anaconda/install/)/[Miniconda](https://docs.conda.io/en/latest/miniconda.html). Note that Anaconda/Miniconda is recommended if you are working on a Windows machine and are not very comfortable with the command line. + - [Git](https://git-scm.com/book/en/v2/Getting-Started-Installing-Git) + 1. Fork this repository: ![location of fork button in GitHub](./media/fork_button.png) From 0da2aaa89d4d35872c1d8608f65fb486e7a88c9a Mon Sep 17 00:00:00 2001 From: Stefanie Molin <24376333+stefmolin@users.noreply.github.com> Date: Sat, 29 Jun 2024 18:03:02 -0400 Subject: [PATCH 08/20] Update env check action --- .github/workflows/env-checks.yml | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/.github/workflows/env-checks.yml b/.github/workflows/env-checks.yml index e273d44..2b13e7d 100644 --- a/.github/workflows/env-checks.yml +++ b/.github/workflows/env-checks.yml @@ -1,6 +1,6 @@ # This workflow builds the workshop environment on Mac, Linux, and Windows for # multiple versions of Python to confirm it can be properly installed. -# +# # Author: Stefanie Molin name: Env Build @@ -33,7 +33,7 @@ jobs: # The type of runner that the job will run on runs-on: ${{ matrix.os }} - + defaults: run: shell: bash -el {0} @@ -42,13 +42,13 @@ jobs: fail-fast: false matrix: os: [macos-latest, ubuntu-latest, windows-latest] - python-version: ["3.8", "3.9", "3.10", "3.11"] + python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"] # Steps represent a sequence of tasks that will be executed as part of the job steps: # checks-out your repository under $GITHUB_WORKSPACE, so your job can access it - - uses: actions/checkout@v3 - + - uses: actions/checkout@v4 + # remove the Python version from the file for testing - name: strip hardcoded Python version from environment for testing run: | @@ -59,12 +59,13 @@ jobs: fi; # create the conda env - - uses: conda-incubator/setup-miniconda@v2 + - uses: conda-incubator/setup-miniconda@v3 with: python-version: ${{ matrix.python-version }} auto-update-conda: true miniforge-variant: Mambaforge - use-mamba: true + mamba-version: "*" + channels: conda-forge channel-priority: true activate-environment: pandas_workshop environment-file: environment.yml From de859a97761f59322ea2478d2e020d2fdd0482b2 Mon Sep 17 00:00:00 2001 From: Stefanie Molin <24376333+stefmolin@users.noreply.github.com> Date: Sat, 29 Jun 2024 18:03:42 -0400 Subject: [PATCH 09/20] Update luxon dependency --- slides/templates/larger_font/index.html.j2 | 2 +- slides/templates/regular/index.html.j2 | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/slides/templates/larger_font/index.html.j2 b/slides/templates/larger_font/index.html.j2 index fa45aa3..2747dcb 100644 --- a/slides/templates/larger_font/index.html.j2 +++ b/slides/templates/larger_font/index.html.j2 @@ -264,7 +264,7 @@ require( [ "{{ reveal_url_prefix }}/dist/reveal.js", "{{ reveal_url_prefix }}/plugin/notes/notes.js", - "https://cdn.jsdelivr.net/npm/luxon@3.2.1/build/global/luxon.min.js" + "https://cdn.jsdelivr.net/npm/luxon@3.4.4/build/global/luxon.min.js" ], function(Reveal, RevealNotes){ diff --git a/slides/templates/regular/index.html.j2 b/slides/templates/regular/index.html.j2 index e194363..bc6d00b 100644 --- a/slides/templates/regular/index.html.j2 +++ b/slides/templates/regular/index.html.j2 @@ -260,7 +260,7 @@ require( [ "{{ reveal_url_prefix }}/dist/reveal.js", "{{ reveal_url_prefix }}/plugin/notes/notes.js", - "https://cdn.jsdelivr.net/npm/luxon@3.2.1/build/global/luxon.min.js" + "https://cdn.jsdelivr.net/npm/luxon@3.4.4/build/global/luxon.min.js" ], function(Reveal, RevealNotes){ From b65578f7fb323931041022bd7f4cc999a42671b7 Mon Sep 17 00:00:00 2001 From: Stefanie Molin <24376333+stefmolin@users.noreply.github.com> Date: Sat, 29 Jun 2024 18:20:19 -0400 Subject: [PATCH 10/20] Tweak section 3 for css changes --- notebooks/3-data_visualization.ipynb | 195 ++++++++++++++++++----- slides/3-data_visualization.ipynb | 221 ++++++++++++++++++++++----- 2 files changed, 344 insertions(+), 72 deletions(-) diff --git a/notebooks/3-data_visualization.ipynb b/notebooks/3-data_visualization.ipynb index 44ea6a3..9c48cf7 100644 --- a/notebooks/3-data_visualization.ipynb +++ b/notebooks/3-data_visualization.ipynb @@ -229,14 +229,145 @@ "source": [ "### Line plots\n", "\n", - "The `plot()` method will generate line plots for all numeric columns by default:" + "Let's continue with the example of rolling and expanding calculations:" ] }, { "cell_type": "code", "execution_count": 3, + "id": "2e6fc032-939f-4e3a-8cb7-ee57718f0c46", + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
travelersholiday7D MAYTD mean
date
2020-01-012311732.0New Year's Day2311732.02311732.0
2020-01-022178656.0New Year's Day2245194.02245194.0
2020-01-032422272.0NaN2304220.02304220.0
2020-01-042210542.0NaN2280800.52280800.5
2020-01-051806480.0NaN2185936.42185936.4
\n", + "
" + ], + "text/plain": [ + " travelers holiday 7D MA YTD mean\n", + "date \n", + "2020-01-01 2311732.0 New Year's Day 2311732.0 2311732.0\n", + "2020-01-02 2178656.0 New Year's Day 2245194.0 2245194.0\n", + "2020-01-03 2422272.0 NaN 2304220.0 2304220.0\n", + "2020-01-04 2210542.0 NaN 2280800.5 2280800.5\n", + "2020-01-05 1806480.0 NaN 2185936.4 2185936.4" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "plot_data = tsa_melted_holiday_travel.drop(columns='year').loc['2020'].assign(\n", + " **{\n", + " '7D MA': lambda x: x.travelers.rolling('7D').mean(),\n", + " 'YTD mean': lambda x: x.travelers.expanding().mean()\n", + " }\n", + ")\n", + "plot_data.head()" + ] + }, + { + "cell_type": "markdown", + "id": "616bc44c-4c63-4d9a-9558-8f4de0b5b3e0", + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "subslide" + }, + "tags": [] + }, + "source": [ + "The `plot()` method will generate line plots for all numeric columns by default:" + ] + }, + { + "cell_type": "code", + "execution_count": 4, "id": "7d30f224-a4c3-4083-981e-a3340f4a26b0", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -244,7 +375,7 @@ "" ] }, - "execution_count": 3, + "execution_count": 4, "metadata": {}, "output_type": "execute_result" }, @@ -2135,12 +2266,7 @@ } ], "source": [ - "tsa_melted_holiday_travel.drop(columns='year').loc['2020'].assign(\n", - " **{\n", - " '7D MA': lambda x: x.travelers.rolling('7D').mean(),\n", - " 'YTD mean': lambda x: x.travelers.expanding().mean()\n", - " }\n", - ").plot(title='2020 TSA Traveler Throughput', ylabel='travelers', alpha=0.8)" + "plot_data.plot(title='2020 TSA Traveler Throughput', ylabel='travelers', alpha=0.8)" ] }, { @@ -2173,7 +2299,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 5, "id": "babbc6d8-fff4-4505-ad88-8af332416208", "metadata": {}, "outputs": [ @@ -2254,7 +2380,7 @@ "5 74617773.0 7244733.0 NaN" ] }, - "execution_count": 4, + "execution_count": 5, "metadata": {}, "output_type": "execute_result" } @@ -2281,17 +2407,17 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 6, "id": "d1776fcf-d50f-44b1-8b11-26675347fec5", "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "" + "" ] }, - "execution_count": 5, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" }, @@ -3735,7 +3861,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 7, "id": "5f2d78a2-ced4-48c2-b40c-993d72833828", "metadata": {}, "outputs": [], @@ -3758,7 +3884,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 8, "id": "604d6112-2b33-403d-9383-982ab81e667c", "metadata": {}, "outputs": [ @@ -5335,8 +5461,9 @@ "cell_type": "markdown", "id": "b3baba7d-e807-4e33-9ccb-f21e62af9c1a", "metadata": { + "editable": true, "slideshow": { - "slide_type": "fragment" + "slide_type": "subslide" }, "tags": [] }, @@ -5356,7 +5483,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 9, "id": "243f8298-be40-4d6a-a4be-06abb85b0fa6", "metadata": {}, "outputs": [], @@ -5366,7 +5493,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 10, "id": "7df8b0db-bda6-4a7f-bc63-18fa2a0304f2", "metadata": {}, "outputs": [], @@ -5376,7 +5503,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 11, "id": "4bfc7ad9-ae6d-440e-b15f-eb3fa16d47ed", "metadata": {}, "outputs": [], @@ -5417,17 +5544,17 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 12, "id": "b68a741f-9c37-4925-84b9-615c34ea0297", "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "" + "" ] }, - "execution_count": 11, + "execution_count": 12, "metadata": {}, "output_type": "execute_result" }, @@ -6850,7 +6977,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 13, "id": "46eafd2b-ffef-4aec-9a88-05342ac3fff6", "metadata": {}, "outputs": [ @@ -6980,7 +7107,7 @@ "12 70219363.0 26391765.0 NaN" ] }, - "execution_count": 12, + "execution_count": 13, "metadata": {}, "output_type": "execute_result" } @@ -6995,7 +7122,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 14, "id": "efccdcd6-2a4f-4c20-856c-9b996da95935", "metadata": { "slideshow": { @@ -8876,7 +9003,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 15, "id": "e3379920-013d-4df5-9abc-b321060a6891", "metadata": {}, "outputs": [], @@ -8886,7 +9013,7 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 16, "id": "0ec9abff-224b-49cb-ac0c-bd6955b5dcaf", "metadata": {}, "outputs": [], @@ -8896,7 +9023,7 @@ }, { "cell_type": "code", - "execution_count": 16, + "execution_count": 17, "id": "6d410276-25aa-4c16-9987-4e17930ebced", "metadata": {}, "outputs": [], @@ -8937,7 +9064,7 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": 18, "id": "681a84a7-6b72-4db8-bfd2-994f98b6494c", "metadata": {}, "outputs": [ @@ -10357,7 +10484,7 @@ }, { "cell_type": "code", - "execution_count": 18, + "execution_count": 19, "id": "cd8a781f-3a17-445f-8ff2-742086122b67", "metadata": {}, "outputs": [ @@ -12309,7 +12436,7 @@ }, { "cell_type": "code", - "execution_count": 19, + "execution_count": 20, "id": "583f952c-2c2e-40ed-9235-fd80a7fe43b7", "metadata": {}, "outputs": [], @@ -12319,7 +12446,7 @@ }, { "cell_type": "code", - "execution_count": 20, + "execution_count": 21, "id": "0b182f1a-33b0-4dde-9d54-e55d7bfeeae3", "metadata": {}, "outputs": [], @@ -12329,7 +12456,7 @@ }, { "cell_type": "code", - "execution_count": 21, + "execution_count": 22, "id": "07394de8-c5fa-4c90-ac5c-e5b6452838c7", "metadata": {}, "outputs": [], diff --git a/slides/3-data_visualization.ipynb b/slides/3-data_visualization.ipynb index 555ae32..b67f152 100644 --- a/slides/3-data_visualization.ipynb +++ b/slides/3-data_visualization.ipynb @@ -61,6 +61,7 @@ "cell_type": "markdown", "id": "c9f34c93-4ca5-4893-b02a-ba1844432576", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -81,6 +82,7 @@ "cell_type": "markdown", "id": "bed5ec02-0cbf-4378-bb63-33e0d4e2eb30", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -99,6 +101,7 @@ "cell_type": "markdown", "id": "1e8fa056-2863-4442-9c39-533352b6240e", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -116,6 +119,7 @@ "cell_type": "markdown", "id": "4d76e200-28d8-417b-bce7-bd4713a30f0a", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -130,6 +134,10 @@ "execution_count": 1, "id": "154aa658-0a4f-4eaa-8f86-c47a4a687633", "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, "tags": [] }, "outputs": [ @@ -229,6 +237,7 @@ "cell_type": "markdown", "id": "f4f708b4-7d14-4d6b-9c37-a2dd71998307", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -242,7 +251,13 @@ "cell_type": "code", "execution_count": 2, "id": "3addc447-062a-48b8-b1d6-f85ca9565f8f", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [], "source": [ "import matplotlib_inline\n", @@ -257,7 +272,13 @@ { "cell_type": "markdown", "id": "46cc6aa3-92f0-4d29-953f-5cfe0f55efab", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "source": [ "*Note: The second argument is optional and is used here to make the SVG output reproducible by setting the `hashsalt` along with some metadata, which will be used by Matplotlib when generating any SVG output (see the `utils.py` file for more details). Without this argument, different runs of the same plotting code will generate plots that are visually identical, but differ at the HTML level due to different IDs, metadata, etc.*" ] @@ -266,6 +287,7 @@ "cell_type": "markdown", "id": "02bf0fd6-d328-4266-b082-7a9f29507030", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -276,12 +298,137 @@ "source": [ "### Line plots\n", "\n", - "The `plot()` method will generate line plots for all numeric columns by default:" + "Let's continue with the example of rolling and expanding calculations:" ] }, { "cell_type": "code", "execution_count": 3, + "id": "08a8d3b5-ac5a-438b-9fbe-5bd6c27ec526", + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
travelersholiday7D MAYTD mean
date
2020-01-012311732.0New Year's Day2311732.02311732.0
2020-01-022178656.0New Year's Day2245194.02245194.0
2020-01-032422272.0NaN2304220.02304220.0
2020-01-042210542.0NaN2280800.52280800.5
2020-01-051806480.0NaN2185936.42185936.4
\n", + "
" + ], + "text/plain": [ + " travelers holiday 7D MA YTD mean\n", + "date \n", + "2020-01-01 2311732.0 New Year's Day 2311732.0 2311732.0\n", + "2020-01-02 2178656.0 New Year's Day 2245194.0 2245194.0\n", + "2020-01-03 2422272.0 NaN 2304220.0 2304220.0\n", + "2020-01-04 2210542.0 NaN 2280800.5 2280800.5\n", + "2020-01-05 1806480.0 NaN 2185936.4 2185936.4" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "plot_data = tsa_melted_holiday_travel.drop(columns='year').loc['2020'].assign(\n", + " **{\n", + " '7D MA': lambda x: x.travelers.rolling('7D').mean(),\n", + " 'YTD mean': lambda x: x.travelers.expanding().mean()\n", + " }\n", + ")\n", + "plot_data.head()" + ] + }, + { + "cell_type": "markdown", + "id": "0d371030-9926-4063-bc8e-e2b38f4c8541", + "metadata": { + "editable": false, + "slideshow": { + "slide_type": "subslide" + }, + "tags": [] + }, + "source": [ + "The `plot()` method will generate line plots for all numeric columns by default:" + ] + }, + { + "cell_type": "code", + "execution_count": 4, "id": "729c9323-a128-46c6-a8b0-2f652ec5e02c", "metadata": {}, "outputs": [ @@ -291,7 +438,7 @@ "" ] }, - "execution_count": 3, + "execution_count": 4, "metadata": {}, "output_type": "execute_result" }, @@ -2182,12 +2329,9 @@ } ], "source": [ - "tsa_melted_holiday_travel.drop(columns='year').loc['2020'].assign(\n", - " **{\n", - " '7D MA': lambda x: x.travelers.rolling('7D').mean(),\n", - " 'YTD mean': lambda x: x.travelers.expanding().mean()\n", - " }\n", - ").plot(title='2020 TSA Traveler Throughput', ylabel='travelers', alpha=0.8)" + "plot_data.plot(\n", + " title='2020 TSA Traveler Throughput', ylabel='travelers', alpha=0.8\n", + ")" ] }, { @@ -2222,7 +2366,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 5, "id": "6b4b550f-3bcc-45cf-a35f-000db7cf31bb", "metadata": {}, "outputs": [ @@ -2303,7 +2447,7 @@ "5 74617773.0 7244733.0 NaN" ] }, - "execution_count": 4, + "execution_count": 5, "metadata": {}, "output_type": "execute_result" } @@ -2332,17 +2476,17 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 6, "id": "67a1f840-1935-4dae-89ca-35d55ccb2d3b", "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "" + "" ] }, - "execution_count": 5, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" }, @@ -3788,7 +3932,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 7, "id": "caee65fb-01d9-47ad-b486-e96cb2995bd2", "metadata": {}, "outputs": [], @@ -3813,7 +3957,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 8, "id": "f43dcd68-a39a-4cca-add5-8d89f83f9921", "metadata": {}, "outputs": [ @@ -5390,8 +5534,9 @@ "cell_type": "markdown", "id": "6f9d2369-9c36-4834-aee9-ddb61f3413be", "metadata": { + "editable": true, "slideshow": { - "slide_type": "fragment" + "slide_type": "subslide" }, "tags": [] }, @@ -5446,7 +5591,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 9, "id": "b69f5951-a6b1-4f14-b6aa-a025e159deb7", "metadata": {}, "outputs": [], @@ -5470,7 +5615,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 10, "id": "ae2251ce-6a5c-4bce-b62a-795712840c1e", "metadata": {}, "outputs": [], @@ -5499,7 +5644,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 11, "id": "939a3b91-652e-4653-93ea-326bf1bbd1b1", "metadata": { "tags": [] @@ -5511,7 +5656,7 @@ "" ] }, - "execution_count": 10, + "execution_count": 11, "metadata": {}, "output_type": "execute_result" }, @@ -6597,17 +6742,17 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 12, "id": "12d29c5f-aba9-458e-92aa-1e399c4ef719", "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "" + "" ] }, - "execution_count": 11, + "execution_count": 12, "metadata": {}, "output_type": "execute_result" }, @@ -8032,7 +8177,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 13, "id": "2c62ab83-8474-44d8-adc7-02eeb277ad71", "metadata": {}, "outputs": [ @@ -8162,7 +8307,7 @@ "12 70219363.0 26391765.0 NaN" ] }, - "execution_count": 12, + "execution_count": 13, "metadata": {}, "output_type": "execute_result" } @@ -8177,7 +8322,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 14, "id": "81424c63-a69f-472e-8266-374c4e449528", "metadata": { "slideshow": { @@ -10093,7 +10238,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 15, "id": "01bd0785-980f-4c6e-b174-71884010d2fe", "metadata": {}, "outputs": [], @@ -10120,7 +10265,7 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 16, "id": "82672758-975f-4b76-82a5-1a4a323bbb17", "metadata": {}, "outputs": [], @@ -10159,7 +10304,7 @@ }, { "cell_type": "code", - "execution_count": 16, + "execution_count": 17, "id": "9667ee49-e475-464d-86ad-55d10ec9018b", "metadata": {}, "outputs": [ @@ -10169,7 +10314,7 @@ "" ] }, - "execution_count": 16, + "execution_count": 17, "metadata": {}, "output_type": "execute_result" }, @@ -12935,7 +13080,7 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": 18, "id": "63853309-4eb8-4de7-889b-4c4cc5ea33e0", "metadata": {}, "outputs": [ @@ -14357,7 +14502,7 @@ }, { "cell_type": "code", - "execution_count": 18, + "execution_count": 19, "id": "018c1147-dfc3-49b1-a579-07850db539ef", "metadata": {}, "outputs": [ @@ -16344,7 +16489,7 @@ }, { "cell_type": "code", - "execution_count": 19, + "execution_count": 20, "id": "bc5dbd63-4182-4c18-b94c-17bc8c8cd81a", "metadata": {}, "outputs": [], @@ -16377,7 +16522,7 @@ }, { "cell_type": "code", - "execution_count": 20, + "execution_count": 21, "id": "a28c948e-a69c-4cbc-b7ea-99ebda67b1c0", "metadata": {}, "outputs": [], @@ -16413,7 +16558,7 @@ }, { "cell_type": "code", - "execution_count": 21, + "execution_count": 22, "id": "18a749dd-b6a3-417c-a0e9-1a1f7ff5dffe", "metadata": { "tags": [] @@ -16425,7 +16570,7 @@ "" ] }, - "execution_count": 21, + "execution_count": 22, "metadata": {}, "output_type": "execute_result" }, From 07f224d477376d5ef60b68f33a09640a17d5ec2c Mon Sep 17 00:00:00 2001 From: Stefanie Molin <24376333+stefmolin@users.noreply.github.com> Date: Sat, 29 Jun 2024 18:20:40 -0400 Subject: [PATCH 11/20] Fix extra empty cell --- slides/4-hands_on_data_analysis_lab.ipynb | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/slides/4-hands_on_data_analysis_lab.ipynb b/slides/4-hands_on_data_analysis_lab.ipynb index d186604..db254e4 100644 --- a/slides/4-hands_on_data_analysis_lab.ipynb +++ b/slides/4-hands_on_data_analysis_lab.ipynb @@ -4,6 +4,7 @@ "cell_type": "markdown", "id": "cd969b0d-8764-468e-9ab1-0e7aabbdfa1b", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -55,6 +56,7 @@ "cell_type": "markdown", "id": "87f2f8d9-4f35-431a-abcd-a0819e4fc47c", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -64,14 +66,6 @@ "## Section 4 Complete 🎉\n", "\"Panda" ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "2a524590-e4fc-45d2-9985-d7ae7d455eba", - "metadata": {}, - "outputs": [], - "source": [] } ], "metadata": { From 9e3d7c4658dffa072075eaa35ca397a4a21453ba Mon Sep 17 00:00:00 2001 From: Stefanie Molin <24376333+stefmolin@users.noreply.github.com> Date: Sat, 29 Jun 2024 18:22:40 -0400 Subject: [PATCH 12/20] Update slides --- slides/html/workshop.slides.html | 47742 +++++++---------------------- 1 file changed, 10303 insertions(+), 37439 deletions(-) diff --git a/slides/html/workshop.slides.html b/slides/html/workshop.slides.html index 7f6a8dc..72f3270 100644 --- a/slides/html/workshop.slides.html +++ b/slides/html/workshop.slides.html @@ -1,9 +1,8 @@ + - + - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + Introduction to Data Analysis Using Pandas workshop slides | Stefanie Molin - - - - - - - - + + + + + + + - + - + - - + - - - - - - - - - - - - + + - - + -
- Introduction to Data Analysis Using Pandas – Stefanie Molin + Introduction to Data Analysis Using Pandas – Stefanie Molin - -
+
-
-
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
+
-
-
+
-
+
-
+
-
+
-
-
+
-
+
-
+
- +
+
+
-
+
-
+
-
+
-
+ -
-
+
-
+ -
-
+
-
+
-
+
-
+
+
-
+
- + +
+
-
+
-
+
- + +
+
-
+
-
+
+
-
+
-
+
-
-
+
-
+
- + +
+
-
+
-
+
- + +
+
+ +
-
+
-
+
-
+
-
-
+
-
+
- + +
+
-
+
-
+
- + +
+
-
+
- + +
+
-
+
-
+
-
+
-
-
+
-
+
- + +
+
-
+
-
+
-
-
+
-
+
-
+
- - - - - - - + - From b52332f35249d3ea32999fde712ac5ba9153f536 Mon Sep 17 00:00:00 2001 From: Stefanie Molin <24376333+stefmolin@users.noreply.github.com> Date: Sat, 29 Jun 2024 19:49:10 -0400 Subject: [PATCH 13/20] Add utility functions for explaining the reshaping goal --- notebooks/2-data_wrangling.ipynb | 881 +++++++++++++++++++++++++++---- notebooks/utils.py | 31 ++ slides/2-data_wrangling.ipynb | 835 +++++++++++++++++++++++++---- slides/utils.py | 31 ++ 4 files changed, 1551 insertions(+), 227 deletions(-) diff --git a/notebooks/2-data_wrangling.ipynb b/notebooks/2-data_wrangling.ipynb index b4cfd64..6a01a7d 100644 --- a/notebooks/2-data_wrangling.ipynb +++ b/notebooks/2-data_wrangling.ipynb @@ -4,6 +4,7 @@ "cell_type": "markdown", "id": "2ea64fb3-084e-4467-90ce-f3f6356cd3c3", "metadata": { + "editable": true, "slideshow": { "slide_type": "skip" }, @@ -20,6 +21,7 @@ "cell_type": "markdown", "id": "03ad7f69-c3e9-4ce8-a044-fd12502fd622", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -35,6 +37,7 @@ "cell_type": "markdown", "id": "d1acd617-c093-4406-9ea8-61289e29e12c", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -50,7 +53,13 @@ "cell_type": "code", "execution_count": 1, "id": "c91ca2ea-c35b-455d-bbc9-312b47c864e4", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -255,7 +264,13 @@ { "cell_type": "markdown", "id": "d65aa6c3-092a-4ed9-95aa-57e8ec41e131", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "source": [ "*Source: [NYC Open Data](https://data.cityofnewyork.us/Transportation/2019-Yellow-Taxi-Trip-Data/2upf-qytp) collected via [SODA](https://dev.socrata.com/foundry/data.cityofnewyork.us/2upf-qytp).*" ] @@ -264,6 +279,7 @@ "cell_type": "markdown", "id": "79315a59-bc5b-4bd2-a25a-8f2de24217e2", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -279,6 +295,7 @@ "execution_count": 2, "id": "e782b52c-dc8c-4aac-ba6d-f3b3cd7b5f2c", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -309,6 +326,7 @@ "execution_count": 3, "id": "bc0652f8-87af-43dd-82d0-07ba120b05f8", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -473,6 +491,7 @@ "cell_type": "markdown", "id": "b6581776-8391-41a3-a7fa-c65af402da77", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -486,6 +505,7 @@ "cell_type": "markdown", "id": "23cc920e-4af6-456b-a0ce-87ade2b189ac", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -501,7 +521,13 @@ "cell_type": "code", "execution_count": 4, "id": "32ec2dc4-c8c3-424d-ae36-d732907b9f59", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -531,6 +557,7 @@ "cell_type": "markdown", "id": "d74d21a8-d733-4afa-a140-29ccdcd83b46", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -546,7 +573,13 @@ "cell_type": "code", "execution_count": 5, "id": "b5ff546c-4a66-4102-b947-1d9147e89369", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -580,6 +613,7 @@ "cell_type": "markdown", "id": "fa644cbb-24dd-4a62-a350-f773c54c50fe", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -593,7 +627,13 @@ "cell_type": "code", "execution_count": 6, "id": "01299409-aace-4d41-bea5-7bd40a85e620", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -628,7 +668,13 @@ { "cell_type": "markdown", "id": "837ea457-45d8-4dae-aa0e-746be381f4da", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "source": [ "*Tip: There are other ways to perform type conversion. For numeric values, we can use the `pd.to_numeric()` function, and we will see the `astype()` method, which is a more generic method, a little later.*" ] @@ -637,6 +683,7 @@ "cell_type": "markdown", "id": "5a8fafca-8cf2-4402-ab34-758dabe955e2", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -658,6 +705,7 @@ "execution_count": 7, "id": "644ba83f-f834-4296-971e-5e7b07b955a8", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -679,7 +727,13 @@ { "cell_type": "markdown", "id": "8d2cabea-d370-4ea9-951a-a22290fe182f", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "source": [ "*Tip: New to `lambda` functions? These small, anonymous functions can receive multiple arguments, but can only contain one expression (the return value). You will see these a lot in pandas code. Read more about them [here](https://realpython.com/python-lambda/).*" ] @@ -688,6 +742,7 @@ "cell_type": "markdown", "id": "b0b2af8a-0727-4e08-a07d-64ddb73a71dd", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -701,7 +756,13 @@ "cell_type": "code", "execution_count": 8, "id": "ec0a2df8-4f40-4bb0-8cd8-0f558d218fd6", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -822,6 +883,7 @@ "cell_type": "markdown", "id": "15049dfd-dd9e-4365-8ecf-0a74f5fe3498", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -837,6 +899,7 @@ "cell_type": "markdown", "id": "f1ebce53-9f31-4aa0-806d-a1a9fa43ece1", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -852,7 +915,13 @@ "cell_type": "code", "execution_count": 9, "id": "77dbdd94-e6b7-4fb9-b6b1-718633b0a38a", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -1048,6 +1117,7 @@ "cell_type": "markdown", "id": "e8d98a7c-7f12-43b7-9450-f0c0fa3162d3", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -1061,7 +1131,13 @@ "cell_type": "code", "execution_count": 10, "id": "e1a26519-acb9-49e5-af1c-f5b055413bf8", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -1206,7 +1282,13 @@ { "cell_type": "markdown", "id": "fbe64c0c-41ab-4fd0-99b0-4f97790c87b8", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "source": [ "### [Exercise 2.1](./workbook.ipynb#Exercise-2.1)\n", "\n", @@ -1217,7 +1299,13 @@ "cell_type": "code", "execution_count": 11, "id": "62bd241b-c87a-41e4-b87f-7a2336f4903e", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [], "source": [ "# Complete this exercise in the workbook.ipynb file\n", @@ -1231,6 +1319,7 @@ "cell_type": "markdown", "id": "97d61c46-b1f4-4531-8a2c-0ac8fcce6007", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -1246,6 +1335,7 @@ "cell_type": "markdown", "id": "cacbf64c-6356-4a2d-8a86-bd143d42914d", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -1261,7 +1351,13 @@ "cell_type": "code", "execution_count": 12, "id": "223e2254-fef2-463f-841b-7b62e04cab4b", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -1434,6 +1530,7 @@ "cell_type": "markdown", "id": "1e150b7a-cc6c-4b2a-a32c-13513e1fd518", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -1447,7 +1544,13 @@ "cell_type": "code", "execution_count": 13, "id": "10477bf0-2d83-478c-8f9a-f15ba363b74c", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [], "source": [ "taxis = taxis.sort_index()" @@ -1457,6 +1560,7 @@ "cell_type": "markdown", "id": "a1c718db-b445-4290-b5bc-6afa51e45eac", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -1470,6 +1574,7 @@ "cell_type": "markdown", "id": "b44074fe-6b74-4a2d-80b0-e5ed7fc7c9f6", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -1483,7 +1588,13 @@ "cell_type": "code", "execution_count": 14, "id": "825b2083-236c-4cfe-957d-4242619c659d", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -1655,6 +1766,7 @@ "cell_type": "markdown", "id": "c88bc8bb-a159-4347-84f5-654315facd1e", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -1668,7 +1780,13 @@ "cell_type": "code", "execution_count": 15, "id": "fef82610-a9ca-47f3-b8f9-fca6cb8215c6", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -1815,6 +1933,7 @@ "cell_type": "markdown", "id": "0684e96e-6c5e-4405-8103-92ae722d9c3e", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -1830,7 +1949,13 @@ "cell_type": "code", "execution_count": 16, "id": "18a6c75b-fa89-4602-b9df-e18ea51d73b6", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -2026,7 +2151,13 @@ { "cell_type": "markdown", "id": "569bcb48-b6bb-4e6c-9cc2-bc352047fb3e", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "source": [ "### [Exercise 2.2](./workbook.ipynb#Exercise-2.2)\n", "\n", @@ -2043,7 +2174,13 @@ "cell_type": "code", "execution_count": 17, "id": "ef0097f4-18cb-4778-9118-cf89a39d9447", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [], "source": [ "# Complete this exercise in the workbook.ipynb file" @@ -2053,7 +2190,13 @@ "cell_type": "code", "execution_count": 18, "id": "d0c55eab-4901-4b05-9bf5-c2c0f6e1bda4", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [], "source": [ "# Click on `Exercise 2.2` above to open the workbook.ipynb file" @@ -2063,7 +2206,13 @@ "cell_type": "code", "execution_count": 19, "id": "c06312d7-838d-45c0-b093-f263ae3f9290", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [], "source": [ "# WARNING: if you complete the exercise here, your cell numbers\n", @@ -2074,6 +2223,7 @@ "cell_type": "markdown", "id": "25a31c80-88f8-4f4d-9192-80a7bf7e9689", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -2090,6 +2240,7 @@ "execution_count": 20, "id": "f9fc17ff-40a4-4e01-b56a-fea6ed3ca471", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -2192,7 +2343,13 @@ { "cell_type": "markdown", "id": "43a2f0b0-affe-4ec4-906c-26401b750dc0", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "source": [ "*Source: [TSA.gov](https://www.tsa.gov/coronavirus/passenger-throughput)*" ] @@ -2201,6 +2358,7 @@ "cell_type": "markdown", "id": "71419100-c9d2-4e8d-a0e3-440d0d9ebded", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -2214,7 +2372,13 @@ "cell_type": "code", "execution_count": 21, "id": "cdaa7ddd-57f4-41ca-b8ff-24d93d44f0b5", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -2306,6 +2470,7 @@ "cell_type": "markdown", "id": "2a39b842-3f40-4951-9a38-7dfd492ef608", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -2315,10 +2480,223 @@ "Now, we can work on reshaping it." ] }, + { + "cell_type": "markdown", + "id": "4315fa3f-9279-439b-ad38-5c2b4d80db6e", + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "subslide" + }, + "tags": [] + }, + "source": [ + "Starting with long format data:" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "id": "10b770ab-a7d0-4978-a684-3d9a6901c00d", + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, + "outputs": [ + { + "data": { + "text/html": [ + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
 date202120202019
02021-05-14 00:00:001716561.0000002504672664549
12021-05-13 00:00:001743515.0000002349282611324
22021-05-12 00:00:001424664.0000001766672343675
32021-05-11 00:00:001315493.0000001632052191387
42021-05-10 00:00:001657722.0000002156452512315
\n" + ], + "text/plain": [ + "" + ] + }, + "execution_count": 22, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from utils import highlight_long_format\n", + "\n", + "colors = {'2021': 'pink', '2020': 'skyblue', '2019': 'lightgreen'}\n", + "highlight_long_format(tsa.head(), colors)" + ] + }, + { + "cell_type": "markdown", + "id": "163e0e33-52a0-46f3-baf1-8200aa8fb832", + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "fragment" + }, + "tags": [] + }, + "source": [ + "We want to transform it into wide format so that we can look at the evolution of the throughput over time:" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "id": "21cc40ea-52f3-4f89-af0c-58643786641b", + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, + "outputs": [ + { + "data": { + "text/html": [ + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
 dateyeartravelers
32021-05-11 00:00:0020211315493.000000
72020-05-12 00:00:002020176667.000000
62020-05-13 00:00:002020234928.000000
22021-05-12 00:00:0020211424664.000000
102019-05-14 00:00:0020192664549.000000
\n" + ], + "text/plain": [ + "" + ] + }, + "execution_count": 23, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from utils import highlight_wide_format\n", + "\n", + "highlight_wide_format(tsa.head(), colors)" + ] + }, { "cell_type": "markdown", "id": "fc0b0c08-5cb6-4523-9dcc-4ea9a7e2607f", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -2332,9 +2710,15 @@ }, { "cell_type": "code", - "execution_count": 22, + "execution_count": 24, "id": "ebcfe696-5e4c-49e9-b281-1b7722cad24b", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -2406,7 +2790,7 @@ "867 2020-12-28 2019 2500396.0" ] }, - "execution_count": 22, + "execution_count": 24, "metadata": {}, "output_type": "execute_result" } @@ -2424,6 +2808,7 @@ "cell_type": "markdown", "id": "91ad2a4f-fd5f-4de6-b974-e37e6119b1f7", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -2435,9 +2820,15 @@ }, { "cell_type": "code", - "execution_count": 23, + "execution_count": 25, "id": "7ad04dde-d03b-4a32-9a47-6b1a388a8169", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -2509,7 +2900,7 @@ "867 2019-12-28 2019 2500396.0" ] }, - "execution_count": 23, + "execution_count": 25, "metadata": {}, "output_type": "execute_result" } @@ -2525,6 +2916,7 @@ "cell_type": "markdown", "id": "28a312aa-f671-4df7-8e09-ea65ba7d6d70", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -2536,9 +2928,15 @@ }, { "cell_type": "code", - "execution_count": 24, + "execution_count": 26, "id": "8f415932-fe42-4e11-a8ac-521c7612147e", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -2596,7 +2994,7 @@ "134 2021-12-31 2021 NaN" ] }, - "execution_count": 24, + "execution_count": 26, "metadata": {}, "output_type": "execute_result" } @@ -2609,6 +3007,7 @@ "cell_type": "markdown", "id": "323970e9-0e9c-46f1-8910-a630fbd4d1b3", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -2620,9 +3019,15 @@ }, { "cell_type": "code", - "execution_count": 25, + "execution_count": 27, "id": "c0ed0555-2467-4966-9cfb-31ff5982c0bb", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -2680,7 +3085,7 @@ "0 2021-05-14 2021 1716561.0" ] }, - "execution_count": 25, + "execution_count": 27, "metadata": {}, "output_type": "execute_result" } @@ -2694,6 +3099,7 @@ "cell_type": "markdown", "id": "6a77b4fc-265e-42d8-ae27-689e3f7f8dc6", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -2707,9 +3113,15 @@ }, { "cell_type": "code", - "execution_count": 26, + "execution_count": 28, "id": "5deb2bd9-e4eb-4775-bbf1-b483c56edf16", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -2815,7 +3227,7 @@ "2021 992406.0 1278557.0 1119303.0 825745.0 974221.0 " ] }, - "execution_count": 26, + "execution_count": 28, "metadata": {}, "output_type": "execute_result" } @@ -2832,6 +3244,7 @@ "cell_type": "markdown", "id": "370ed66f-5b39-4adf-ae0d-651c4ae1981b", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -2845,6 +3258,7 @@ "cell_type": "markdown", "id": "e292be99-e3d6-403c-abce-56efa8b1948d", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -2858,9 +3272,15 @@ }, { "cell_type": "code", - "execution_count": 27, + "execution_count": 29, "id": "c8a7bb2d-77c0-461b-9963-224b5bd633d2", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -2974,7 +3394,7 @@ "10 2187298.0 1702686.0 974221.0" ] }, - "execution_count": 27, + "execution_count": 29, "metadata": {}, "output_type": "execute_result" } @@ -2987,6 +3407,7 @@ "cell_type": "markdown", "id": "65da6408-d946-4420-8fec-327094bf46e9", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -3000,9 +3421,15 @@ }, { "cell_type": "code", - "execution_count": 28, + "execution_count": 30, "id": "df6a13e1-af80-4d5e-9aa6-24495d7197cd", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -3082,7 +3509,7 @@ "2019-12-31 New Year's Eve" ] }, - "execution_count": 28, + "execution_count": 30, "metadata": {}, "output_type": "execute_result" } @@ -3096,6 +3523,7 @@ "cell_type": "markdown", "id": "a0832a27-605c-48bd-b564-0901c2796b90", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -3107,9 +3535,13 @@ }, { "cell_type": "code", - "execution_count": 29, + "execution_count": 31, "id": "367b9ccb-04f6-4400-88b2-ce548990bb6f", "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, "tags": [] }, "outputs": [ @@ -3189,7 +3621,7 @@ "859 2019-01-05 2019 1975947.0 NaN" ] }, - "execution_count": 29, + "execution_count": 31, "metadata": {}, "output_type": "execute_result" } @@ -3205,6 +3637,7 @@ "cell_type": "markdown", "id": "29efc7c8-f2c6-4a28-a36f-25e9da612d14", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -3218,6 +3651,7 @@ "cell_type": "markdown", "id": "6d79f677-5759-4790-9004-cb1a6361a0a8", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -3229,9 +3663,15 @@ }, { "cell_type": "code", - "execution_count": 30, + "execution_count": 32, "id": "a589df8f-5870-41ea-b4c1-e413fa76ad31", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [], "source": [ "tsa_melted_holiday_travel = tsa_melted_holidays.assign(\n", @@ -3246,6 +3686,7 @@ "cell_type": "markdown", "id": "eb5a331c-143a-4b3e-bb90-9d948da4d148", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -3259,6 +3700,7 @@ "cell_type": "markdown", "id": "1c86a8f0-124b-4837-9c09-21923fbcb926", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -3270,9 +3712,15 @@ }, { "cell_type": "code", - "execution_count": 31, + "execution_count": 33, "id": "c895269f-37b5-4246-974a-d8a91730f346", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -3382,7 +3830,7 @@ "869 2019-12-26 2019 2470786.0 Christmas Day" ] }, - "execution_count": 31, + "execution_count": 33, "metadata": {}, "output_type": "execute_result" } @@ -3398,6 +3846,7 @@ "cell_type": "markdown", "id": "84597dd2-780e-451c-8263-c02fdadb857b", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -3413,6 +3862,7 @@ "cell_type": "markdown", "id": "350010f2-30ac-4167-8aa6-41e71933ef74", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -3425,9 +3875,15 @@ }, { "cell_type": "code", - "execution_count": 32, + "execution_count": 34, "id": "944749f0-d9e1-4a6e-ad15-c8f33e737080", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -3523,7 +3979,7 @@ "2021 1998871.0 NaN NaN " ] }, - "execution_count": 32, + "execution_count": 34, "metadata": {}, "output_type": "execute_result" } @@ -3539,6 +3995,7 @@ "cell_type": "markdown", "id": "9a189e47-9347-4922-a345-471206d8192c", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -3550,9 +4007,15 @@ }, { "cell_type": "code", - "execution_count": 33, + "execution_count": 35, "id": "ad480312-626f-401b-93d3-0ffd6a6392bb", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -3648,7 +4111,7 @@ "2021 -0.554856 NaN NaN " ] }, - "execution_count": 33, + "execution_count": 35, "metadata": {}, "output_type": "execute_result" } @@ -3664,6 +4127,7 @@ "cell_type": "markdown", "id": "30a2f712-13e2-4f84-a6aa-d234b8d65dff", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -3675,9 +4139,15 @@ }, { "cell_type": "code", - "execution_count": 34, + "execution_count": 36, "id": "33a98f21-ea62-432c-8f7f-ee0d542b155b", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [], "source": [ "pd.set_option('display.float_format', '{:,.0f}'.format)" @@ -3687,6 +4157,7 @@ "cell_type": "markdown", "id": "d5ccd3b9-2179-45ac-85a2-6b57f220b1ed", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -3698,9 +4169,15 @@ }, { "cell_type": "code", - "execution_count": 35, + "execution_count": 37, "id": "98ab467c-f26d-436d-9f73-7ea35fc5fa86", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -3803,7 +4280,7 @@ "Total 12,454,836 83,559,966 " ] }, - "execution_count": 35, + "execution_count": 37, "metadata": {}, "output_type": "execute_result" } @@ -3828,6 +4305,7 @@ "cell_type": "markdown", "id": "145150cd-3fde-48c1-87d4-857c858d8494", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -3839,9 +4317,15 @@ }, { "cell_type": "code", - "execution_count": 36, + "execution_count": 38, "id": "55e95c66-fb5b-4ee2-a1ce-8ead82a2715a", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [], "source": [ "pd.reset_option('display.float_format')" @@ -3851,6 +4335,7 @@ "cell_type": "markdown", "id": "fa6dc364-f48f-482b-86be-152d6d16961f", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -3863,7 +4348,13 @@ { "cell_type": "markdown", "id": "87b782d9-3404-4e68-b0eb-cdc201393cb3", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "source": [ "### [Exercise 2.3](./workbook.ipynb#Exercise-2.3)\n", "\n", @@ -3872,9 +4363,15 @@ }, { "cell_type": "code", - "execution_count": 37, + "execution_count": 39, "id": "86157a08-5379-4ffd-af34-da2ef32a2633", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [], "source": [ "# Complete this exercise in the workbook.ipynb file\n", @@ -3888,6 +4385,7 @@ "cell_type": "markdown", "id": "2d988e70-5547-4a15-ab6c-b0eade8fb8b9", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -3900,9 +4398,15 @@ }, { "cell_type": "code", - "execution_count": 38, + "execution_count": 40, "id": "27d17ef2-b8be-43df-aab8-a2d7f5d228f5", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -3967,7 +4471,7 @@ "high 323 44 0" ] }, - "execution_count": 38, + "execution_count": 40, "metadata": {}, "output_type": "execute_result" } @@ -3987,6 +4491,7 @@ "cell_type": "markdown", "id": "7aceb604-c3e9-4b1a-b62d-ada3f86ad897", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -4000,6 +4505,7 @@ "cell_type": "markdown", "id": "cb00efed-de93-4adf-92b2-4d88ae07565e", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -4013,6 +4519,7 @@ "cell_type": "markdown", "id": "08c2a7b6-7e1d-4c91-9360-888335dc26df", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -4025,9 +4532,15 @@ }, { "cell_type": "code", - "execution_count": 39, + "execution_count": 41, "id": "638ecd3d-48e9-4fea-96eb-1a6be49bb43d", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -4133,7 +4646,7 @@ "2021 1409377.75 1743515.0 " ] }, - "execution_count": 39, + "execution_count": 41, "metadata": {}, "output_type": "execute_result" } @@ -4146,6 +4659,7 @@ "cell_type": "markdown", "id": "72053860-fe4d-4e16-971c-91dedd14f522", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -4157,9 +4671,15 @@ }, { "cell_type": "code", - "execution_count": 40, + "execution_count": 42, "id": "7c5f7495-7d00-4b7b-a3b6-76c1f47457c4", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -4225,7 +4745,7 @@ "1 2021-05-13 2021 1743515.0 NaN 1.0" ] }, - "execution_count": 40, + "execution_count": 42, "metadata": {}, "output_type": "execute_result" } @@ -4240,6 +4760,7 @@ "cell_type": "markdown", "id": "bc57c29a-cd58-4ff5-9c69-9e8f68b05168", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -4251,9 +4772,15 @@ }, { "cell_type": "code", - "execution_count": 41, + "execution_count": 43, "id": "ce014d66-ba8b-4537-b8f1-9548dccab5b9", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -4351,7 +4878,7 @@ "2021 1.114347e+06 339479.298658 " ] }, - "execution_count": 41, + "execution_count": 43, "metadata": {}, "output_type": "execute_result" } @@ -4368,6 +4895,7 @@ "cell_type": "markdown", "id": "f7484d71-3091-4d8f-9e2d-53b07871ebaf", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -4381,6 +4909,7 @@ "cell_type": "markdown", "id": "7f012232-0ac4-48ce-9ae3-ed936657ef24", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -4392,9 +4921,15 @@ }, { "cell_type": "code", - "execution_count": 42, + "execution_count": 44, "id": "3080e40b-4ac7-4395-a76e-e773d16901fc", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -4474,7 +5009,7 @@ "2021 9.994355e+05 273573.249680 1 2" ] }, - "execution_count": 42, + "execution_count": 44, "metadata": {}, "output_type": "execute_result" } @@ -4493,6 +5028,7 @@ "cell_type": "markdown", "id": "73fc6c25-387e-4ff6-aaa0-7e212f766c2e", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -4510,6 +5046,7 @@ "cell_type": "markdown", "id": "fd7409b7-6eec-4ed0-8a09-c8b6333ef75d", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -4522,7 +5059,13 @@ { "cell_type": "markdown", "id": "f35e0f4b-916e-4a99-ba99-4d4a02d4d884", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "source": [ "### [Exercise 2.4](./workbook.ipynb#Exercise-2.4)\n", "\n", @@ -4531,9 +5074,15 @@ }, { "cell_type": "code", - "execution_count": 43, + "execution_count": 45, "id": "32e4f6ff-a57c-4d50-9911-fd74b4522125", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [], "source": [ "# Complete this exercise in the workbook.ipynb file\n", @@ -4547,6 +5096,7 @@ "cell_type": "markdown", "id": "6f39b28e-9c9b-4b97-93be-41ade4dcd8f8", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -4562,6 +5112,7 @@ "cell_type": "markdown", "id": "1bb690d8-a77e-4dd7-a8ac-4a4fcfc3a156", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -4575,9 +5126,15 @@ }, { "cell_type": "code", - "execution_count": 44, + "execution_count": 46, "id": "e1556b7a-ccde-432b-81a9-8b2c80b67d68", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [], "source": [ "taxis = taxis.set_index('dropoff').sort_index()" @@ -4587,6 +5144,7 @@ "cell_type": "markdown", "id": "ef86c832-5ed4-4a86-8a84-93fb179b9df4", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -4598,9 +5156,15 @@ }, { "cell_type": "code", - "execution_count": 45, + "execution_count": 47, "id": "f41a0a74-0bc8-4649-8b86-f44cdfb1062a", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -4734,7 +5298,7 @@ "2019-10-24 12:42:01 0.2 4.3 0.068301 " ] }, - "execution_count": 45, + "execution_count": 47, "metadata": {}, "output_type": "execute_result" } @@ -4747,6 +5311,7 @@ "cell_type": "markdown", "id": "c286a4f6-54fc-409d-b10a-8f6ac2734347", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -4758,9 +5323,15 @@ }, { "cell_type": "code", - "execution_count": 46, + "execution_count": 48, "id": "9e6b26c9-4048-4207-8454-b9f018a56816", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -4894,7 +5465,7 @@ "2019-10-24 12:42:01 0.2 4.3 0.068301 " ] }, - "execution_count": 46, + "execution_count": 48, "metadata": {}, "output_type": "execute_result" } @@ -4907,6 +5478,7 @@ "cell_type": "markdown", "id": "8705d663-67c8-4f6f-b3e9-52bceeea122f", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -4920,6 +5492,7 @@ "cell_type": "markdown", "id": "78093e7d-ce53-424b-b484-820c4d98ace0", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -4931,9 +5504,15 @@ }, { "cell_type": "code", - "execution_count": 47, + "execution_count": 49, "id": "915f528c-639f-4b8b-99cc-9c83bb0cad4d", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -5092,7 +5671,7 @@ "2019-10-24 12:42:01 0.200000 4.3 0.068301 " ] }, - "execution_count": 47, + "execution_count": 49, "metadata": {}, "output_type": "execute_result" } @@ -5105,6 +5684,7 @@ "cell_type": "markdown", "id": "98520264-8284-414c-9c23-0c054af076f5", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -5118,6 +5698,7 @@ "cell_type": "markdown", "id": "b8c0485e-4730-4124-8e71-493e7e9c45d6", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -5129,9 +5710,15 @@ }, { "cell_type": "code", - "execution_count": 48, + "execution_count": 50, "id": "1a06c5b3-cb6b-4f02-9559-208fd94a78ed", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [], "source": [ "tsa_melted_holiday_travel = tsa_melted_holiday_travel.set_index('date')" @@ -5141,6 +5728,7 @@ "cell_type": "markdown", "id": "20ae3a50-f2f4-4880-8463-a16bb7932ba2", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -5152,9 +5740,15 @@ }, { "cell_type": "code", - "execution_count": 49, + "execution_count": 51, "id": "7a554fda-2363-4c87-b8f3-17773c511c43", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -5292,7 +5886,7 @@ "2020-01-10 2020 2183734.0 NaN 495760.0 -238538.0" ] }, - "execution_count": 49, + "execution_count": 51, "metadata": {}, "output_type": "execute_result" } @@ -5307,7 +5901,13 @@ { "cell_type": "markdown", "id": "4938d37c-9e59-4c5b-88c1-32709c0b68d9", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "source": [ "*Tip: To perform operations other than subtraction, take a look at the `shift()` method. It also makes it possible to perform operations across columns.*" ] @@ -5316,6 +5916,7 @@ "cell_type": "markdown", "id": "86e9b6a3-7547-4d38-93ec-1a27e64615cf", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -5328,9 +5929,15 @@ }, { "cell_type": "code", - "execution_count": 50, + "execution_count": 52, "id": "0093c590-342a-4add-9999-0fb063cfa5e7", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -5446,7 +6053,7 @@ "2021-03-31 86094635.0 9.566071e+05 280399.809061" ] }, - "execution_count": 50, + "execution_count": 52, "metadata": {}, "output_type": "execute_result" } @@ -5460,6 +6067,7 @@ "cell_type": "markdown", "id": "c169d6c8-a744-462a-bfbb-a5cadd29eca9", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -5475,6 +6083,7 @@ "cell_type": "markdown", "id": "acdebc2e-20f9-4963-9aeb-90a6d91db14e", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -5486,9 +6095,15 @@ }, { "cell_type": "code", - "execution_count": 51, + "execution_count": 53, "id": "d83c0d2e-16db-49de-b15b-ba30792a89e7", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -5626,7 +6241,7 @@ "2020-01-10 2020 2183734.0 NaN 1.972969e+06 2.072344e+06" ] }, - "execution_count": 51, + "execution_count": 53, "metadata": {}, "output_type": "execute_result" } @@ -5644,6 +6259,7 @@ "cell_type": "markdown", "id": "8dab1843-9179-415f-be5b-1ebafaef3690", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -5655,9 +6271,15 @@ }, { "cell_type": "code", - "execution_count": 52, + "execution_count": 54, "id": "da84fa52-b2a9-4ab8-9d6d-643a3b43b94e", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [], "source": [ "import matplotlib_inline\n", @@ -5672,7 +6294,13 @@ { "cell_type": "markdown", "id": "81e00227-a79d-464f-bbbf-318992b6a5a4", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "source": [ "*Tip: For most use cases, only the first argument is necessary – we will discuss the second argument in more detail in the next section.*" ] @@ -5681,6 +6309,7 @@ "cell_type": "markdown", "id": "474adada-c6c6-4306-ab85-a23a6bebaca7", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -5692,9 +6321,15 @@ }, { "cell_type": "code", - "execution_count": 53, + "execution_count": 55, "id": "3e31834c-3299-44b0-8ac3-6939b91b9be0", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -7595,6 +8230,7 @@ "cell_type": "markdown", "id": "4fe90855-8228-4cf6-9c8b-375b416071b7", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -7609,7 +8245,13 @@ { "cell_type": "markdown", "id": "bc18799b-77d4-4699-9967-9797d76d3539", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "source": [ "### [Exercise 2.5](./workbook.ipynb#Exercise-2.5)\n", "\n", @@ -7618,9 +8260,15 @@ }, { "cell_type": "code", - "execution_count": 55, + "execution_count": 56, "id": "c5ce22c9-ea36-4d60-b291-c67e1deeeabf", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [], "source": [ "# Complete this exercise in the workbook.ipynb file\n", @@ -7631,6 +8279,7 @@ "cell_type": "markdown", "id": "94ab60e4-a8de-4453-8598-4112bb86f098", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, diff --git a/notebooks/utils.py b/notebooks/utils.py index c13dcf4..041c9c8 100644 --- a/notebooks/utils.py +++ b/notebooks/utils.py @@ -2,6 +2,8 @@ import datetime as dt +import pandas as pd + def mpl_svg_config(hashsalt): """Help configure the SVG backend for Matplotlib and make it reproducible.""" @@ -13,3 +15,32 @@ def mpl_svg_config(hashsalt): 'Date': f'(c) 2021-{dt.date.today().year} Stefanie Molin' } } + +def highlight_long_format(df, colors): + """Highlight long format columns in the data.""" + + def get_style(x): + if color := colors.get(x): + return f'background-color: {color}' + return None + + def highlight_column(x): + return [get_style(x.name)] * x.shape[0] + + return df.style\ + .apply_index(lambda x: x.apply(get_style), axis=1)\ + .apply(highlight_column, axis=0) + +def highlight_wide_format(df, colors): + """Highlight wide format columns in the melted data.""" + + def highlight_melt(x): + color = colors[x.year] + return [f"background-color: {color};"] * 2 + + return df.melt(id_vars='date', var_name='year', value_name='travelers')\ + .assign( + date=lambda x: pd.to_datetime(x.year + x.date.dt.strftime('-%m-%d')) + )\ + .sample(5, random_state=1)\ + .style.apply(highlight_melt, subset=['year', 'travelers'], axis=1) diff --git a/slides/2-data_wrangling.ipynb b/slides/2-data_wrangling.ipynb index e3d191b..d611380 100644 --- a/slides/2-data_wrangling.ipynb +++ b/slides/2-data_wrangling.ipynb @@ -20,6 +20,7 @@ "cell_type": "markdown", "id": "a0745604-3c71-4c7f-8b5c-b6cc0ecec3c3", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -42,6 +43,7 @@ "cell_type": "markdown", "id": "3cfd9085-0758-475d-846d-a2607bdc478c", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -61,6 +63,7 @@ "cell_type": "markdown", "id": "9848c0e0-b1df-4273-b37a-c155f69db4e0", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -78,7 +81,13 @@ "cell_type": "code", "execution_count": 1, "id": "ede5b9c9-32b8-47b7-a120-1ed969c147a3", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -283,7 +292,13 @@ { "cell_type": "markdown", "id": "3dd3c1fe-19e4-4986-9feb-462d8e6068d6", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "source": [ "*Source: [NYC Open Data](https://data.cityofnewyork.us/Transportation/2019-Yellow-Taxi-Trip-Data/2upf-qytp) collected via [SODA](https://dev.socrata.com/foundry/data.cityofnewyork.us/2upf-qytp).*" ] @@ -292,6 +307,7 @@ "cell_type": "markdown", "id": "d08f2fdb-87b2-4664-a295-84ce81617c7f", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -309,6 +325,7 @@ "execution_count": 2, "id": "0966f1df-b5c2-4383-aedb-f1d03b2be5d1", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -339,6 +356,7 @@ "execution_count": 3, "id": "6b7cd6d9-a7fb-4be0-9d34-1dd57ddca9c0", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -503,6 +521,7 @@ "cell_type": "markdown", "id": "db7f5fca-b5cc-477c-bbf2-3c2cbcc2ae04", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -516,6 +535,7 @@ "cell_type": "markdown", "id": "ad7cdd18-ef14-4a67-a4ad-8a1d8015cbb9", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -533,7 +553,13 @@ "cell_type": "code", "execution_count": 4, "id": "b3dbfd72-0d37-4fce-b6c1-a3178afc59b1", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -563,6 +589,7 @@ "cell_type": "markdown", "id": "0750fd20-a823-4eed-961c-d3f0cf9a18aa", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -580,7 +607,13 @@ "cell_type": "code", "execution_count": 5, "id": "4654ced7-f1aa-4be8-ba67-d3ce7a4d3a84", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -614,6 +647,7 @@ "cell_type": "markdown", "id": "d847ee9a-93b0-4ae9-a202-2ff99fbd0561", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -627,7 +661,13 @@ "cell_type": "code", "execution_count": 6, "id": "d17a0e74-52fc-47ff-b28e-b594e3ce01c2", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -662,7 +702,13 @@ { "cell_type": "markdown", "id": "01779303-7f6d-49c7-8a7a-640cfdff2251", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "source": [ "*Tip: There are other ways to perform type conversion. For numeric values, we can use the `pd.to_numeric()` function, and we will see the `astype()` method, which is a more generic method, a little later.*" ] @@ -671,6 +717,7 @@ "cell_type": "markdown", "id": "989cfa03-5fae-4a9a-82e3-4153ad3f2c27", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -694,6 +741,7 @@ "execution_count": 7, "id": "b95a6701-7070-4525-95f1-44d02b847d8f", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -715,7 +763,13 @@ { "cell_type": "markdown", "id": "6c87ad15-a398-46a3-b0d6-d50312f9e5c3", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "source": [ "*Tip: New to `lambda` functions? These small, anonymous functions can receive multiple arguments, but can only contain one expression (the return value). You will see these a lot in pandas code. Read more about them [here](https://realpython.com/python-lambda/).*" ] @@ -724,6 +778,7 @@ "cell_type": "markdown", "id": "91d1480f-22ca-4092-9f9b-ef0b8fe92226", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -737,7 +792,13 @@ "cell_type": "code", "execution_count": 8, "id": "80c0d81d-7d8a-4ecf-9410-37fc2a5c7221", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -858,6 +919,7 @@ "cell_type": "markdown", "id": "2753e957-b033-4642-a353-bd369d0672e1", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -873,6 +935,7 @@ "cell_type": "markdown", "id": "c2d275c1-c1c6-4bd2-a645-4921e2955884", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -890,7 +953,13 @@ "cell_type": "code", "execution_count": 9, "id": "e22b6e1c-56ae-4800-bedd-bad7006a8a7f", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -1086,6 +1155,7 @@ "cell_type": "markdown", "id": "61ae6ae1-1a3d-4e50-bade-15126240e2f5", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -1101,7 +1171,13 @@ "cell_type": "code", "execution_count": 10, "id": "a76377c8-b3a7-4da4-b763-36bd974fe89e", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -1247,6 +1323,7 @@ "cell_type": "markdown", "id": "f35f3408-f512-4468-95d0-602a95f930ef", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -1264,6 +1341,7 @@ "cell_type": "markdown", "id": "53f793de-d52d-4cf0-b36a-ea2ab525a5f4", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -1280,6 +1358,7 @@ "execution_count": 11, "id": "2938458e-2767-45ec-a3d8-b0867bc53ec2", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -1407,6 +1486,7 @@ "cell_type": "markdown", "id": "e0788e52-404b-480b-bf10-b4e63a2536d5", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -1426,6 +1506,7 @@ "cell_type": "markdown", "id": "65a2afee-3b1a-4fa8-9491-ab323eab54d9", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -1443,6 +1524,7 @@ "cell_type": "markdown", "id": "8a589beb-41f8-4aa2-b5f0-8452b16b75a2", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -1460,7 +1542,13 @@ "cell_type": "code", "execution_count": 12, "id": "a83c91d3-40e2-4adc-b729-92376706a58d", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -1633,6 +1721,7 @@ "cell_type": "markdown", "id": "2b209530-e30a-4ff9-9f70-acb770eba330", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -1648,7 +1737,13 @@ "cell_type": "code", "execution_count": 13, "id": "f611ff93-6978-4eab-83ea-c289ccdfd6ff", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [], "source": [ "taxis = taxis.sort_index()" @@ -1658,6 +1753,7 @@ "cell_type": "markdown", "id": "ec63259e-8f77-45d0-ba23-984fba6e95a0", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -1671,6 +1767,7 @@ "cell_type": "markdown", "id": "829f2df1-1ad6-4176-a21c-b8006aa26945", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -1686,7 +1783,13 @@ "cell_type": "code", "execution_count": 14, "id": "5fcec2d3-a1d1-4464-a3f1-2a19c5ead98b", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -1858,6 +1961,7 @@ "cell_type": "markdown", "id": "bc2ade37-8578-47cd-9981-3d702fb459aa", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -1871,7 +1975,13 @@ "cell_type": "code", "execution_count": 15, "id": "f0a86342-95f1-4561-8b07-7b97f1e4e887", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -2018,6 +2128,7 @@ "cell_type": "markdown", "id": "71c7720b-8503-4643-a552-10965b59c624", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -2035,7 +2146,13 @@ "cell_type": "code", "execution_count": 16, "id": "c2a21903-3ad8-4dba-9169-eba54743f434", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -2232,6 +2349,7 @@ "cell_type": "markdown", "id": "316d01c1-c8cb-4c56-8496-3402d007e8d0", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -2255,6 +2373,7 @@ "cell_type": "markdown", "id": "8d00bb60-3e40-4283-8820-6ad571ddc110", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -2271,6 +2390,7 @@ "execution_count": 17, "id": "e402ec63-0fe9-44c2-9564-5726f2c84cc9", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -2415,6 +2535,7 @@ "cell_type": "markdown", "id": "08e03522-8d67-43a6-ba35-eca5432f2822", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -2436,6 +2557,7 @@ "cell_type": "markdown", "id": "fa11fd1a-cbf0-4338-b5cb-7e94d9a2815e", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -2450,6 +2572,7 @@ "execution_count": 18, "id": "187dd516-27b7-49b1-b2f3-b5084b743320", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -2483,6 +2606,7 @@ "cell_type": "markdown", "id": "b0ab2e51-a49d-486e-ad09-aaa39f0d4358", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -2496,7 +2620,13 @@ "cell_type": "code", "execution_count": 19, "id": "ef66c16e-1546-4831-8cdb-51d92f3c81bc", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -2584,7 +2714,13 @@ { "cell_type": "markdown", "id": "10b3e913-e6d0-4b61-928e-da3eca59b08d", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "source": [ "###### Oops! This meteorite actually was found in 2010 (more information [here](https://www.lpi.usra.edu/meteor/metbull.php?code=57150))." ] @@ -2593,6 +2729,7 @@ "cell_type": "markdown", "id": "1a4e882e-d57d-40d6-ac10-9463303080f2", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -2612,6 +2749,7 @@ "cell_type": "markdown", "id": "02934923-bf47-4245-ab1d-758bf221eb21", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -2630,8 +2768,9 @@ "execution_count": 20, "id": "b06e3e74-cf37-418e-966d-4b98d3c4ec71", "metadata": { + "editable": true, "slideshow": { - "slide_type": "fragment" + "slide_type": "" }, "tags": [] }, @@ -2732,7 +2871,13 @@ { "cell_type": "markdown", "id": "fe40e4dc-fcb9-41f6-b198-feed4f4069b4", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "source": [ "*Source: [TSA.gov](https://www.tsa.gov/coronavirus/passenger-throughput)*" ] @@ -2741,6 +2886,7 @@ "cell_type": "markdown", "id": "c5f42086-13f3-452d-8878-57f6cf0f97d1", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -2754,7 +2900,13 @@ "cell_type": "code", "execution_count": 21, "id": "4f7e3c3d-b830-4ac5-957e-778a72e58185", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -2846,8 +2998,9 @@ "cell_type": "markdown", "id": "6e24d581-09cb-47f5-8ca6-8b71bc41d1d4", "metadata": { + "editable": true, "slideshow": { - "slide_type": "fragment" + "slide_type": "" }, "tags": [] }, @@ -2855,10 +3008,223 @@ "Now, we can work on reshaping it." ] }, + { + "cell_type": "markdown", + "id": "fa35300e-9a40-4ea2-8c20-adf98c2e1568", + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "subslide" + }, + "tags": [] + }, + "source": [ + "Starting with long format data:" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "id": "00789ab3-9d92-4c68-aefe-c9097df8ff13", + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, + "outputs": [ + { + "data": { + "text/html": [ + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
 date202120202019
02021-05-14 00:00:001716561.0000002504672664549
12021-05-13 00:00:001743515.0000002349282611324
22021-05-12 00:00:001424664.0000001766672343675
32021-05-11 00:00:001315493.0000001632052191387
42021-05-10 00:00:001657722.0000002156452512315
\n" + ], + "text/plain": [ + "" + ] + }, + "execution_count": 22, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from utils import highlight_long_format\n", + "\n", + "colors = {'2021': 'pink', '2020': 'skyblue', '2019': 'lightgreen'}\n", + "highlight_long_format(tsa.head(), colors)" + ] + }, + { + "cell_type": "markdown", + "id": "55d4ae45-0a86-46af-89b6-4c78ce1cd688", + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "fragment" + }, + "tags": [] + }, + "source": [ + "We want to transform it into wide format so that we can look at the evolution of the throughput over time:" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "id": "b0a77c53-3ba9-4bf1-a8cf-b128962e6b8f", + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, + "outputs": [ + { + "data": { + "text/html": [ + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
 dateyeartravelers
32021-05-11 00:00:0020211315493.000000
72020-05-12 00:00:002020176667.000000
62020-05-13 00:00:002020234928.000000
22021-05-12 00:00:0020211424664.000000
102019-05-14 00:00:0020192664549.000000
\n" + ], + "text/plain": [ + "" + ] + }, + "execution_count": 23, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from utils import highlight_wide_format\n", + "\n", + "highlight_wide_format(tsa.head(), colors)" + ] + }, { "cell_type": "markdown", "id": "fd52c051-596f-4962-8e01-e1845f853b7f", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -2874,9 +3240,15 @@ }, { "cell_type": "code", - "execution_count": 22, + "execution_count": 24, "id": "d2cf07ed-890c-47f7-9ecb-8412102fd65b", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -2948,7 +3320,7 @@ "867 2020-12-28 2019 2500396.0" ] }, - "execution_count": 22, + "execution_count": 24, "metadata": {}, "output_type": "execute_result" } @@ -2966,6 +3338,7 @@ "cell_type": "markdown", "id": "4d7e95ce-c58c-4328-9f97-1a2711b7e8cf", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -2977,9 +3350,15 @@ }, { "cell_type": "code", - "execution_count": 23, + "execution_count": 25, "id": "c591736f-19af-4576-a1c2-f308e88e0ba3", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -3051,7 +3430,7 @@ "867 2019-12-28 2019 2500396.0" ] }, - "execution_count": 23, + "execution_count": 25, "metadata": {}, "output_type": "execute_result" } @@ -3067,6 +3446,7 @@ "cell_type": "markdown", "id": "acf5a87a-84d9-401c-967f-5db0b46be715", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -3080,9 +3460,15 @@ }, { "cell_type": "code", - "execution_count": 24, + "execution_count": 26, "id": "8763d003-24b7-43aa-8a0b-19a437e995b3", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -3140,7 +3526,7 @@ "134 2021-12-31 2021 NaN" ] }, - "execution_count": 24, + "execution_count": 26, "metadata": {}, "output_type": "execute_result" } @@ -3153,6 +3539,7 @@ "cell_type": "markdown", "id": "af2bb599-24e4-4395-aea7-e5634bc7e9e3", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -3164,9 +3551,15 @@ }, { "cell_type": "code", - "execution_count": 25, + "execution_count": 27, "id": "2bdd2c3a-4e85-497c-8e49-c0f7c1209917", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -3224,7 +3617,7 @@ "0 2021-05-14 2021 1716561.0" ] }, - "execution_count": 25, + "execution_count": 27, "metadata": {}, "output_type": "execute_result" } @@ -3238,6 +3631,7 @@ "cell_type": "markdown", "id": "7c1c9dfb-fbba-4ba4-a076-29d253eabe5b", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -3253,9 +3647,15 @@ }, { "cell_type": "code", - "execution_count": 26, + "execution_count": 28, "id": "3507eb04-e15a-4d22-9a75-ab998895c563", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -3361,7 +3761,7 @@ "2021 992406.0 1278557.0 1119303.0 825745.0 974221.0 " ] }, - "execution_count": 26, + "execution_count": 28, "metadata": {}, "output_type": "execute_result" } @@ -3378,6 +3778,7 @@ "cell_type": "markdown", "id": "472179dc-8fbe-4ff2-8df5-0c40d4818827", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -3391,6 +3792,7 @@ "cell_type": "markdown", "id": "abee4e0e-26a4-4c6e-a7eb-0bad992ad955", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -3406,9 +3808,15 @@ }, { "cell_type": "code", - "execution_count": 27, + "execution_count": 29, "id": "68607e99-1692-4c48-8579-a43b530dbd75", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -3522,7 +3930,7 @@ "10 2187298.0 1702686.0 974221.0" ] }, - "execution_count": 27, + "execution_count": 29, "metadata": {}, "output_type": "execute_result" } @@ -3535,6 +3943,7 @@ "cell_type": "markdown", "id": "fb294961-c185-47cd-a709-e9a02e2e4924", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -3550,9 +3959,15 @@ }, { "cell_type": "code", - "execution_count": 28, + "execution_count": 30, "id": "7eef15b0-a0a3-42ae-9d60-a829682aeca0", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -3632,7 +4047,7 @@ "2019-12-31 New Year's Eve" ] }, - "execution_count": 28, + "execution_count": 30, "metadata": {}, "output_type": "execute_result" } @@ -3646,6 +4061,7 @@ "cell_type": "markdown", "id": "fc3c6b8b-b7e1-4ac8-a38a-b36ff17bc850", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -3657,9 +4073,13 @@ }, { "cell_type": "code", - "execution_count": 29, + "execution_count": 31, "id": "b738bd1b-0c73-4cb6-9616-236fb3ffb8a2", "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, "tags": [] }, "outputs": [ @@ -3739,7 +4159,7 @@ "859 2019-01-05 2019 1975947.0 NaN" ] }, - "execution_count": 29, + "execution_count": 31, "metadata": {}, "output_type": "execute_result" } @@ -3755,6 +4175,7 @@ "cell_type": "markdown", "id": "ef78ac45-6a52-4719-b531-52ea846f48dd", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -3768,6 +4189,7 @@ "cell_type": "markdown", "id": "00efa48d-b2e3-49c0-bd2a-b073a62f26ab", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -3781,9 +4203,15 @@ }, { "cell_type": "code", - "execution_count": 30, + "execution_count": 32, "id": "16e9a948-55fb-4c7d-af08-67a7c718ff8d", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [], "source": [ "tsa_melted_holiday_travel = tsa_melted_holidays.assign(\n", @@ -3798,6 +4226,7 @@ "cell_type": "markdown", "id": "7228baa8-3fd6-4fcb-a2ef-5ac3f3f566a0", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -3811,6 +4240,7 @@ "cell_type": "markdown", "id": "ecc512de-592b-4a8d-8424-ddb4da991e0c", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -3822,9 +4252,15 @@ }, { "cell_type": "code", - "execution_count": 31, + "execution_count": 33, "id": "8516dbf4-9c4b-4726-9639-d10a39867928", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -3934,7 +4370,7 @@ "869 2019-12-26 2019 2470786.0 Christmas Day" ] }, - "execution_count": 31, + "execution_count": 33, "metadata": {}, "output_type": "execute_result" } @@ -3950,6 +4386,7 @@ "cell_type": "markdown", "id": "63b60c6b-5ab1-41c8-a1ca-3f4640b5894e", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -3969,6 +4406,7 @@ "cell_type": "markdown", "id": "286bf0c8-fd66-472d-8512-60f9da7dfff6", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -3986,6 +4424,7 @@ "cell_type": "markdown", "id": "f5da03b7-84f8-4f7c-b1dd-654910e6b526", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -4000,9 +4439,15 @@ }, { "cell_type": "code", - "execution_count": 32, + "execution_count": 34, "id": "22a43bea-1065-404b-843e-38e22c361867", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -4098,7 +4543,7 @@ "2021 1998871.0 NaN NaN " ] }, - "execution_count": 32, + "execution_count": 34, "metadata": {}, "output_type": "execute_result" } @@ -4114,6 +4559,7 @@ "cell_type": "markdown", "id": "6aacdc27-6ee7-4443-a8bf-2b3e045737e3", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -4127,9 +4573,15 @@ }, { "cell_type": "code", - "execution_count": 33, + "execution_count": 35, "id": "107e005d-8c15-4a26-a13c-b99346783ae6", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -4225,7 +4677,7 @@ "2021 -0.554856 NaN NaN " ] }, - "execution_count": 33, + "execution_count": 35, "metadata": {}, "output_type": "execute_result" } @@ -4241,6 +4693,7 @@ "cell_type": "markdown", "id": "6e9ee5fb-ec4c-487f-8215-51fc1fe93373", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -4254,9 +4707,15 @@ }, { "cell_type": "code", - "execution_count": 34, + "execution_count": 36, "id": "9d2a221e-4a76-4f1b-a159-e9f9d8f09719", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [], "source": [ "pd.set_option('display.float_format', '{:,.0f}'.format)" @@ -4266,6 +4725,7 @@ "cell_type": "markdown", "id": "306104af-223c-4628-b6f9-793f77fa7ae8", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -4279,9 +4739,15 @@ }, { "cell_type": "code", - "execution_count": 35, + "execution_count": 37, "id": "cdae2ea6-45ef-4fb6-8bd7-bd5940883926", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -4384,7 +4850,7 @@ "Total 12,454,836 83,559,966 " ] }, - "execution_count": 35, + "execution_count": 37, "metadata": {}, "output_type": "execute_result" } @@ -4409,6 +4875,7 @@ "cell_type": "markdown", "id": "ce5d1263-e50e-4760-9a9f-de5d476e110e", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -4422,9 +4889,15 @@ }, { "cell_type": "code", - "execution_count": 36, + "execution_count": 38, "id": "17df79b9-6634-4613-8205-047abe035098", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [], "source": [ "pd.reset_option('display.float_format')" @@ -4434,6 +4907,7 @@ "cell_type": "markdown", "id": "8e8e9d4d-2b57-4a8b-9a97-611e521f2c38", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -4447,6 +4921,7 @@ "cell_type": "markdown", "id": "0a368707-1d0c-42af-97c9-83482de776b4", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -4464,6 +4939,7 @@ "cell_type": "markdown", "id": "b9dfbc99-1441-4b6c-bdb8-e61645c67872", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -4477,9 +4953,10 @@ }, { "cell_type": "code", - "execution_count": 37, + "execution_count": 39, "id": "2a91f292-c404-4df5-8eac-4bd02cc7ac8e", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -4580,7 +5057,7 @@ "2009.0 5.0 1492.0 8333.4 1397.25" ] }, - "execution_count": 37, + "execution_count": 39, "metadata": {}, "output_type": "execute_result" } @@ -4601,6 +5078,7 @@ "cell_type": "markdown", "id": "f6ba37d0-a219-42f7-97d4-6275d663c524", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -4615,9 +5093,15 @@ }, { "cell_type": "code", - "execution_count": 38, + "execution_count": 40, "id": "177e3825-4b0f-45f1-a118-9f76bf0a06cb", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -4682,7 +5166,7 @@ "high 323 44 0" ] }, - "execution_count": 38, + "execution_count": 40, "metadata": {}, "output_type": "execute_result" } @@ -4702,6 +5186,7 @@ "cell_type": "markdown", "id": "f8628adb-7101-48ff-8c61-ad785eaa8e7b", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -4715,6 +5200,7 @@ "cell_type": "markdown", "id": "900cb77c-7003-4472-a4b4-f0381cf86a57", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -4728,6 +5214,7 @@ "cell_type": "markdown", "id": "74d93b19-2cd3-4bbf-9a65-834216d04cb0", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -4742,9 +5229,15 @@ }, { "cell_type": "code", - "execution_count": 39, + "execution_count": 41, "id": "6ad5821d-09d2-438d-8abf-7caddc8235a6", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -4850,7 +5343,7 @@ "2021 1409377.75 1743515.0 " ] }, - "execution_count": 39, + "execution_count": 41, "metadata": {}, "output_type": "execute_result" } @@ -4863,6 +5356,7 @@ "cell_type": "markdown", "id": "4c20d991-2579-44f4-b66f-f953ed6b9b8b", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -4876,9 +5370,15 @@ }, { "cell_type": "code", - "execution_count": 40, + "execution_count": 42, "id": "6487feec-cb63-4d88-a9a9-2804940d63cf", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -4944,7 +5444,7 @@ "1 2021-05-13 2021 1743515.0 NaN 1.0" ] }, - "execution_count": 40, + "execution_count": 42, "metadata": {}, "output_type": "execute_result" } @@ -4959,6 +5459,7 @@ "cell_type": "markdown", "id": "82c92d64-7f14-4741-a0b2-f32b8aedc233", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -4972,9 +5473,15 @@ }, { "cell_type": "code", - "execution_count": 41, + "execution_count": 43, "id": "b04bdf3b-8f96-4dd4-a158-3dfa8097f04c", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -5072,7 +5579,7 @@ "2021 1.114347e+06 339479.298658 " ] }, - "execution_count": 41, + "execution_count": 43, "metadata": {}, "output_type": "execute_result" } @@ -5089,6 +5596,7 @@ "cell_type": "markdown", "id": "9e203a6e-b329-44bc-995b-408e1d4e1574", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -5102,6 +5610,7 @@ "cell_type": "markdown", "id": "f9b57329-d84d-4350-8bef-ff6769c78cd7", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -5115,9 +5624,15 @@ }, { "cell_type": "code", - "execution_count": 42, + "execution_count": 44, "id": "07871965-12c3-4f45-855c-cd22c5b57d23", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -5197,7 +5712,7 @@ "2021 9.994355e+05 273573.249680 1 2" ] }, - "execution_count": 42, + "execution_count": 44, "metadata": {}, "output_type": "execute_result" } @@ -5216,6 +5731,7 @@ "cell_type": "markdown", "id": "af031c62-b9c0-48b6-b655-2885a54ead43", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -5233,6 +5749,7 @@ "cell_type": "markdown", "id": "654f2293-838e-4881-bcf1-eb25e782bc24", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -5246,6 +5763,7 @@ "cell_type": "markdown", "id": "5cfe5493-56b3-4ff0-bbda-bc198dd40264", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -5263,6 +5781,7 @@ "cell_type": "markdown", "id": "2c849ba3-739c-4ee1-84b2-44fd5244001a", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -5276,9 +5795,10 @@ }, { "cell_type": "code", - "execution_count": 43, + "execution_count": 45, "id": "e7b7376d-8589-43ca-b16e-ee58a0cc121e", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -5366,7 +5886,7 @@ "Found 60000000.0 " ] }, - "execution_count": 43, + "execution_count": 45, "metadata": {}, "output_type": "execute_result" } @@ -5382,6 +5902,7 @@ "cell_type": "markdown", "id": "ebae6837-e2fe-4cbf-8f0d-68b25a45036a", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -5401,6 +5922,7 @@ "cell_type": "markdown", "id": "6dc6cb90-17db-41f8-a67d-05d5128186be", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -5418,6 +5940,7 @@ "cell_type": "markdown", "id": "8a469a96-9ed3-4256-9fb8-8b7f1871ed63", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -5433,9 +5956,15 @@ }, { "cell_type": "code", - "execution_count": 44, + "execution_count": 46, "id": "faf650aa-1da5-4e4f-ac5f-1a564da22aa1", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [], "source": [ "taxis = taxis.set_index('dropoff').sort_index()" @@ -5445,6 +5974,7 @@ "cell_type": "markdown", "id": "0a424c09-7978-4946-8599-03c5402628e0", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -5456,9 +5986,15 @@ }, { "cell_type": "code", - "execution_count": 45, + "execution_count": 47, "id": "9ffb09d0-876c-40bb-aa85-9980d32c8384", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -5592,7 +6128,7 @@ "2019-10-24 12:42:01 0.2 4.3 0.068301 " ] }, - "execution_count": 45, + "execution_count": 47, "metadata": {}, "output_type": "execute_result" } @@ -5605,6 +6141,7 @@ "cell_type": "markdown", "id": "82511690-b84f-40a0-b3ab-2c8e90cb9c72", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -5616,9 +6153,15 @@ }, { "cell_type": "code", - "execution_count": 46, + "execution_count": 48, "id": "18c9050c-52fd-47de-a628-5c03d07ea108", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -5752,7 +6295,7 @@ "2019-10-24 12:42:01 0.2 4.3 0.068301 " ] }, - "execution_count": 46, + "execution_count": 48, "metadata": {}, "output_type": "execute_result" } @@ -5765,6 +6308,7 @@ "cell_type": "markdown", "id": "112cc144-f809-48bd-87a1-3333fe1921a7", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -5778,6 +6322,7 @@ "cell_type": "markdown", "id": "0550c385-2705-4b5a-9a5b-53284e0402db", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -5791,9 +6336,15 @@ }, { "cell_type": "code", - "execution_count": 47, + "execution_count": 49, "id": "f14b6804-ea6f-43c6-a260-83b576d5de4e", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -5952,7 +6503,7 @@ "2019-10-24 12:42:01 0.200000 4.3 0.068301 " ] }, - "execution_count": 47, + "execution_count": 49, "metadata": {}, "output_type": "execute_result" } @@ -5965,6 +6516,7 @@ "cell_type": "markdown", "id": "9fc39b46-d155-4b53-a32c-3c7eb2f82bab", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -5978,6 +6530,7 @@ "cell_type": "markdown", "id": "1bc7af6d-fbd2-4028-99e3-deac76074f63", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -5989,9 +6542,15 @@ }, { "cell_type": "code", - "execution_count": 48, + "execution_count": 50, "id": "327eae28-526b-4f16-a813-164141a793da", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [], "source": [ "tsa_melted_holiday_travel = tsa_melted_holiday_travel.set_index('date')" @@ -6001,6 +6560,7 @@ "cell_type": "markdown", "id": "24dfd787-ac43-451e-b5e5-5aeeabc0bd22", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -6014,9 +6574,15 @@ }, { "cell_type": "code", - "execution_count": 49, + "execution_count": 51, "id": "2138f995-7db1-4f0f-b7dc-ad11873d4563", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -6154,7 +6720,7 @@ "2020-01-10 2020 2183734.0 NaN 495760.0 -238538.0" ] }, - "execution_count": 49, + "execution_count": 51, "metadata": {}, "output_type": "execute_result" } @@ -6169,7 +6735,13 @@ { "cell_type": "markdown", "id": "c70daf1f-c67c-4f44-8057-1a912aeec044", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "source": [ "*Tip: To perform operations other than subtraction, take a look at the `shift()` method. It also makes it possible to perform operations across columns.*" ] @@ -6178,6 +6750,7 @@ "cell_type": "markdown", "id": "a2157b7e-ccfe-4f35-9e74-a056e4c15882", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -6192,9 +6765,15 @@ }, { "cell_type": "code", - "execution_count": 50, + "execution_count": 52, "id": "6593acbe-6bab-438d-a160-3784f4d3131c", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -6310,7 +6889,7 @@ "2021-03-31 86094635.0 9.566071e+05 280399.809061" ] }, - "execution_count": 50, + "execution_count": 52, "metadata": {}, "output_type": "execute_result" } @@ -6324,6 +6903,7 @@ "cell_type": "markdown", "id": "824a21af-ca5b-46e6-a31c-fb1bd0e8fa32", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -6341,6 +6921,7 @@ "cell_type": "markdown", "id": "80f7db58-1714-4645-87c4-196971cb7aaa", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -6357,6 +6938,7 @@ "cell_type": "markdown", "id": "15b71997-1107-463b-849b-f3969fa6a592", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -6368,9 +6950,15 @@ }, { "cell_type": "code", - "execution_count": 51, + "execution_count": 53, "id": "3dc35819-cc7a-4235-97ed-37ee2351b6ad", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -6508,7 +7096,7 @@ "2020-01-10 2020 2183734.0 NaN 1.972969e+06 2.072344e+06" ] }, - "execution_count": 51, + "execution_count": 53, "metadata": {}, "output_type": "execute_result" } @@ -6526,6 +7114,7 @@ "cell_type": "markdown", "id": "097e50b3-c3d9-4bca-9641-6555b744b431", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -6537,9 +7126,15 @@ }, { "cell_type": "code", - "execution_count": 52, + "execution_count": 54, "id": "71ec5579-1f12-4e5e-8ef6-076811dc715e", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [], "source": [ "import matplotlib_inline\n", @@ -6554,7 +7149,13 @@ { "cell_type": "markdown", "id": "597d978d-9ba3-4012-8b9a-8eb075fc03bd", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "source": [ "*Tip: For most use cases, only the first argument is necessary – we will discuss the second argument in more detail in the next section.*" ] @@ -6563,6 +7164,7 @@ "cell_type": "markdown", "id": "aca1c599-9edd-4fd6-ae9e-6ab99dce776f", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -6574,9 +7176,15 @@ }, { "cell_type": "code", - "execution_count": 53, + "execution_count": 55, "id": "a2b79c72-d7b4-45e4-bc2c-4f990d9bf278", - "metadata": {}, + "metadata": { + "editable": true, + "slideshow": { + "slide_type": "" + }, + "tags": [] + }, "outputs": [ { "data": { @@ -8477,6 +9085,7 @@ "cell_type": "markdown", "id": "c0ddbf35-b1f3-487c-b3f9-dfc017937077", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -8492,6 +9101,7 @@ "cell_type": "markdown", "id": "170454cf-2f3f-4f3b-beae-40479acb2a76", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, @@ -8509,6 +9119,7 @@ "cell_type": "markdown", "id": "34dece95-55f0-4ab2-932f-5a6ae13093f1", "metadata": { + "editable": true, "slideshow": { "slide_type": "subslide" }, @@ -8522,9 +9133,10 @@ }, { "cell_type": "code", - "execution_count": 54, + "execution_count": 56, "id": "eac8caa8-73c0-4dd7-a8ba-eea5b701f8f7", "metadata": { + "editable": true, "slideshow": { "slide_type": "fragment" }, @@ -8615,7 +9227,7 @@ "2019-10-23 19:00:00 98.59 268.00 24.48 25.74" ] }, - "execution_count": 54, + "execution_count": 56, "metadata": {}, "output_type": "execute_result" } @@ -8636,6 +9248,7 @@ "cell_type": "markdown", "id": "71cbab3e-e8f5-48a6-8520-5f9412ff7300", "metadata": { + "editable": true, "slideshow": { "slide_type": "slide" }, diff --git a/slides/utils.py b/slides/utils.py index c13dcf4..041c9c8 100644 --- a/slides/utils.py +++ b/slides/utils.py @@ -2,6 +2,8 @@ import datetime as dt +import pandas as pd + def mpl_svg_config(hashsalt): """Help configure the SVG backend for Matplotlib and make it reproducible.""" @@ -13,3 +15,32 @@ def mpl_svg_config(hashsalt): 'Date': f'(c) 2021-{dt.date.today().year} Stefanie Molin' } } + +def highlight_long_format(df, colors): + """Highlight long format columns in the data.""" + + def get_style(x): + if color := colors.get(x): + return f'background-color: {color}' + return None + + def highlight_column(x): + return [get_style(x.name)] * x.shape[0] + + return df.style\ + .apply_index(lambda x: x.apply(get_style), axis=1)\ + .apply(highlight_column, axis=0) + +def highlight_wide_format(df, colors): + """Highlight wide format columns in the melted data.""" + + def highlight_melt(x): + color = colors[x.year] + return [f"background-color: {color};"] * 2 + + return df.melt(id_vars='date', var_name='year', value_name='travelers')\ + .assign( + date=lambda x: pd.to_datetime(x.year + x.date.dt.strftime('-%m-%d')) + )\ + .sample(5, random_state=1)\ + .style.apply(highlight_melt, subset=['year', 'travelers'], axis=1) From 4ec11eb5090382d5db968c0eb47b5bc210720469 Mon Sep 17 00:00:00 2001 From: Stefanie Molin <24376333+stefmolin@users.noreply.github.com> Date: Sat, 29 Jun 2024 19:49:39 -0400 Subject: [PATCH 14/20] Update slides --- slides/html/workshop.slides.html | 1153 ++++++++++++++++++++++++++++-- 1 file changed, 1091 insertions(+), 62 deletions(-) diff --git a/slides/html/workshop.slides.html b/slides/html/workshop.slides.html index 72f3270..fbae8fb 100644 --- a/slides/html/workshop.slides.html +++ b/slides/html/workshop.slides.html @@ -12820,7 +12820,7 @@

Reshaping data @@ -13067,70 +13067,49 @@

Reshaping dataOut[22]: @@ -13159,7 +13138,7 @@

Reshaping data 
from utils import highlight_wide_format
 
-highlight_wide_format(tsa.head(), colors)
+highlight_wide_format(tsa.head(2), colors)
@@ -13173,55 +13152,61 @@

Reshaping dataOut[23]:
-
diff --git a/slides/utils.py b/slides/utils.py index 041c9c8..ba6875e 100644 --- a/slides/utils.py +++ b/slides/utils.py @@ -42,5 +42,5 @@ def highlight_melt(x): .assign( date=lambda x: pd.to_datetime(x.year + x.date.dt.strftime('-%m-%d')) )\ - .sample(5, random_state=1)\ + .sort_values('date', ascending=False)\ .style.apply(highlight_melt, subset=['year', 'travelers'], axis=1) From 6ad2609a6aab5992e39039c04c33122006ea0d3c Mon Sep 17 00:00:00 2001 From: Stefanie Molin <24376333+stefmolin@users.noreply.github.com> Date: Sun, 30 Jun 2024 11:30:13 -0400 Subject: [PATCH 18/20] Fix version typo in README --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 915003d..04698ed 100644 --- a/README.md +++ b/README.md @@ -41,7 +41,7 @@ You can work through the notebooks locally or in your browser. Pick the installa **Warning**: It is highly recommended that you use your personal laptop for the installation. 0. Install the following, if not already installed: - - Python >= version 3.9 and <= version 3.13 OR install [Anaconda](https://docs.anaconda.com/anaconda/install/)/[Miniconda](https://docs.conda.io/en/latest/miniconda.html). Note that Anaconda/Miniconda is recommended if you are working on a Windows machine and are not very comfortable with the command line. + - Python >= version 3.9 and <= version 3.12 OR install [Anaconda](https://docs.anaconda.com/anaconda/install/)/[Miniconda](https://docs.conda.io/en/latest/miniconda.html). Note that Anaconda/Miniconda is recommended if you are working on a Windows machine and are not very comfortable with the command line. - [Git](https://git-scm.com/book/en/v2/Getting-Started-Installing-Git) 1. Fork this repository: From d3d3c6fa466426d1a25765bfb784a7075c8dae35 Mon Sep 17 00:00:00 2001 From: Stefanie Molin <24376333+stefmolin@users.noreply.github.com> Date: Sun, 30 Jun 2024 11:51:07 -0400 Subject: [PATCH 19/20] Fix typo --- notebooks/2-data_wrangling.ipynb | 2 +- slides/2-data_wrangling.ipynb | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/notebooks/2-data_wrangling.ipynb b/notebooks/2-data_wrangling.ipynb index adbb769..97558ef 100644 --- a/notebooks/2-data_wrangling.ipynb +++ b/notebooks/2-data_wrangling.ipynb @@ -2477,7 +2477,7 @@ "tags": [] }, "source": [ - "Now, we can work on reshaping it into two columns the date and the traveler throughput from 2019 through 2021." + "Now, we can work on reshaping it into two columns: the date and the traveler throughput from 2019 through 2021." ] }, { diff --git a/slides/2-data_wrangling.ipynb b/slides/2-data_wrangling.ipynb index 9e0531f..1cd823d 100644 --- a/slides/2-data_wrangling.ipynb +++ b/slides/2-data_wrangling.ipynb @@ -3005,7 +3005,7 @@ "tags": [] }, "source": [ - "Now, we can work on reshaping it into two columns the date and the traveler throughput from 2019 through 2021." + "Now, we can work on reshaping it into two columns: the date and the traveler throughput from 2019 through 2021." ] }, { From 441a70cfe0f9e6e86bde5c25504aac09b42f6de7 Mon Sep 17 00:00:00 2001 From: Stefanie Molin <24376333+stefmolin@users.noreply.github.com> Date: Sun, 30 Jun 2024 11:53:15 -0400 Subject: [PATCH 20/20] Update slides --- slides/html/workshop.slides.html | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/slides/html/workshop.slides.html b/slides/html/workshop.slides.html index b0efdc5..d5f78d7 100644 --- a/slides/html/workshop.slides.html +++ b/slides/html/workshop.slides.html @@ -13027,7 +13027,7 @@

Reshaping data