From 4aecc1e7700ea1d9dad9ef652d5f1c2c566681c1 Mon Sep 17 00:00:00 2001 From: Nuno Silva Date: Sat, 5 Aug 2023 23:59:12 +0100 Subject: [PATCH] Lab Done --- your-code/main.ipynb | 1358 ++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 1299 insertions(+), 59 deletions(-) diff --git a/your-code/main.ipynb b/your-code/main.ipynb index e196ddb..23c8b19 100755 --- a/your-code/main.ipynb +++ b/your-code/main.ipynb @@ -11,11 +11,14 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "metadata": {}, "outputs": [], "source": [ - "# your code here" + "# your code here\n", + "\n", + "import pandas as pd\n", + "import numpy as np" ] }, { @@ -27,11 +30,13 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "metadata": {}, "outputs": [], "source": [ - "# your code here" + "# your code here\n", + "\n", + "path = \"apple_store.csv\"" ] }, { @@ -45,11 +50,13 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "metadata": {}, "outputs": [], "source": [ - "# your code here" + "# your code here\n", + "\n", + "data = pd.read_csv(path)" ] }, { @@ -63,11 +70,137 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "metadata": {}, - "outputs": [], + "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", + "
idtrack_namesize_bytespricerating_count_totrating_count_veruser_ratinguser_rating_verprime_genre
0281656475PAC-MAN Premium1007882243.9921292264.04.5Games
1281796108Evernote - stay organized1585786880.00161065264.03.5Productivity
2281940292WeatherBug - Local Weather, Radar, Maps, Alerts1005240320.0018858328223.54.5Weather
3282614216eBay: Best App to Buy, Sell, Save! Online Shop...1285120000.002622416494.04.5Shopping
4282935706Bible927744000.0098592053204.55.0Reference
\n", + "
" + ], + "text/plain": [ + " id track_name size_bytes \\\n", + "0 281656475 PAC-MAN Premium 100788224 \n", + "1 281796108 Evernote - stay organized 158578688 \n", + "2 281940292 WeatherBug - Local Weather, Radar, Maps, Alerts 100524032 \n", + "3 282614216 eBay: Best App to Buy, Sell, Save! Online Shop... 128512000 \n", + "4 282935706 Bible 92774400 \n", + "\n", + " price rating_count_tot rating_count_ver user_rating user_rating_ver \\\n", + "0 3.99 21292 26 4.0 4.5 \n", + "1 0.00 161065 26 4.0 3.5 \n", + "2 0.00 188583 2822 3.5 4.5 \n", + "3 0.00 262241 649 4.0 4.5 \n", + "4 0.00 985920 5320 4.5 5.0 \n", + "\n", + " prime_genre \n", + "0 Games \n", + "1 Productivity \n", + "2 Weather \n", + "3 Shopping \n", + "4 Reference " + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# your code here" + "# your code here\n", + "data.head()" ] }, { @@ -79,11 +212,36 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 7, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "RangeIndex: 7197 entries, 0 to 7196\n", + "Data columns (total 9 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 id 7197 non-null int64 \n", + " 1 track_name 7197 non-null object \n", + " 2 size_bytes 7197 non-null int64 \n", + " 3 price 7197 non-null float64\n", + " 4 rating_count_tot 7197 non-null int64 \n", + " 5 rating_count_ver 7197 non-null int64 \n", + " 6 user_rating 7197 non-null float64\n", + " 7 user_rating_ver 7197 non-null float64\n", + " 8 prime_genre 7197 non-null object \n", + "dtypes: float64(3), int64(4), object(2)\n", + "memory usage: 506.2+ KB\n" + ] + } + ], "source": [ - "# your code here" + "# your code here\n", + "\n", + "data.info()" ] }, { @@ -95,11 +253,24 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 9, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "9" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# your code here" + "# your code here\n", + "\n", + "data.shape[1]" ] }, { @@ -111,11 +282,26 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 10, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "Index(['id', 'track_name', 'size_bytes', 'price', 'rating_count_tot',\n", + " 'rating_count_ver', 'user_rating', 'user_rating_ver', 'prime_genre'],\n", + " dtype='object')" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# your code here" + "# your code here\n", + "\n", + "data.columns" ] }, { @@ -129,11 +315,44 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 16, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "7197" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# your code here\n", + "\n", + "data.shape[0]" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "7197" + ] + }, + "execution_count": 18, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# your code here" + "data['track_name'].count()" ] }, { @@ -147,11 +366,13 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 20, "metadata": {}, "outputs": [], "source": [ - "# your code here" + "# your code here\n", + "\n", + "user_rating = data['user_rating']" ] }, { @@ -165,11 +386,56 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 21, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "3.526955675976101" + ] + }, + "execution_count": 21, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# your code here\n", + "\n", + "user_rating.mean()" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0 4.0\n", + "1 4.0\n", + "2 3.5\n", + "3 4.0\n", + "4 4.5\n", + " ... \n", + "7192 4.5\n", + "7193 4.5\n", + "7194 4.5\n", + "7195 4.5\n", + "7196 5.0\n", + "Name: user_rating, Length: 7197, dtype: float64" + ] + }, + "execution_count": 28, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# your code here" + "user_rating\n", + "\n" ] }, { @@ -185,11 +451,37 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 30, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "0 4.0\n", + "1 4.0\n", + "3 4.0\n", + "4 4.5\n", + "5 4.0\n", + " ... \n", + "7192 4.5\n", + "7193 4.5\n", + "7194 4.5\n", + "7195 4.5\n", + "7196 5.0\n", + "Name: user_rating, Length: 4781, dtype: float64" + ] + }, + "execution_count": 30, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# your code here" + "# your code here\n", + "\n", + "user_rating_high= user_rating[user_rating >= 4]\n", + "\n", + "user_rating_high" ] }, { @@ -201,11 +493,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 31, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "4781" + ] + }, + "execution_count": 31, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# your code here" + "# your code here\n", + "len(user_rating_high)" ] }, { @@ -219,11 +523,13 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 32, "metadata": {}, "outputs": [], "source": [ - "# your code here" + "# your code here\n", + "\n", + "genres = data['prime_genre']" ] }, { @@ -235,11 +541,44 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 34, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "23" + ] + }, + "execution_count": 34, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# your code here\n", + "\n", + "len(genres.value_counts())" + ] + }, + { + "cell_type": "code", + "execution_count": 36, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "23" + ] + }, + "execution_count": 36, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# your code here" + "len(genres.unique())" ] }, { @@ -260,11 +599,27 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 39, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "Games 3862\n", + "Entertainment 535\n", + "Education 453\n", + "Name: prime_genre, dtype: int64" + ] + }, + "execution_count": 39, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# your code here" + "top3 = genres.value_counts()\n", + "\n", + "top3.head(3)" ] }, { @@ -305,11 +660,275 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 42, "metadata": {}, - "outputs": [], + "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", + " \n", + " \n", + " \n", + " \n", + "
idtrack_namesize_bytespricerating_count_totrating_count_veruser_ratinguser_rating_verprime_genre
1281796108Evernote - stay organized1585786880.0161065264.03.5Productivity
2281940292WeatherBug - Local Weather, Radar, Maps, Alerts1005240320.018858328223.54.5Weather
3282614216eBay: Best App to Buy, Sell, Save! Online Shop...1285120000.02622416494.04.5Shopping
4282935706Bible927744000.098592053204.55.0Reference
6283646709PayPal - Send and request money safely2277959680.01194878794.04.5Finance
..............................
71881186384912Demolition Derby Virtual Reality (VR) Racing1687746560.018184.04.0Games
71921187617475Kubik1266442240.0142754.54.5Games
71931187682390VR Roller-Coaster1207603200.030304.54.5Games
71951187838770VR Roller Coaster World - Virtual Reality972359680.085324.54.5Games
71961188375727Escape the Sweet Shop Series908984320.0335.05.0Games
\n", + "

4056 rows × 9 columns

\n", + "
" + ], + "text/plain": [ + " id track_name \\\n", + "1 281796108 Evernote - stay organized \n", + "2 281940292 WeatherBug - Local Weather, Radar, Maps, Alerts \n", + "3 282614216 eBay: Best App to Buy, Sell, Save! Online Shop... \n", + "4 282935706 Bible \n", + "6 283646709 PayPal - Send and request money safely \n", + "... ... ... \n", + "7188 1186384912 Demolition Derby Virtual Reality (VR) Racing \n", + "7192 1187617475 Kubik \n", + "7193 1187682390 VR Roller-Coaster \n", + "7195 1187838770 VR Roller Coaster World - Virtual Reality \n", + "7196 1188375727 Escape the Sweet Shop Series \n", + "\n", + " size_bytes price rating_count_tot rating_count_ver user_rating \\\n", + "1 158578688 0.0 161065 26 4.0 \n", + "2 100524032 0.0 188583 2822 3.5 \n", + "3 128512000 0.0 262241 649 4.0 \n", + "4 92774400 0.0 985920 5320 4.5 \n", + "6 227795968 0.0 119487 879 4.0 \n", + "... ... ... ... ... ... \n", + "7188 168774656 0.0 18 18 4.0 \n", + "7192 126644224 0.0 142 75 4.5 \n", + "7193 120760320 0.0 30 30 4.5 \n", + "7195 97235968 0.0 85 32 4.5 \n", + "7196 90898432 0.0 3 3 5.0 \n", + "\n", + " user_rating_ver prime_genre \n", + "1 3.5 Productivity \n", + "2 4.5 Weather \n", + "3 4.5 Shopping \n", + "4 5.0 Reference \n", + "6 4.5 Finance \n", + "... ... ... \n", + "7188 4.0 Games \n", + "7192 4.5 Games \n", + "7193 4.5 Games \n", + "7195 4.5 Games \n", + "7196 5.0 Games \n", + "\n", + "[4056 rows x 9 columns]" + ] + }, + "execution_count": 42, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# your code here\n", + "\n", + "free_apps = data[data['price'] == 0]\n", + "free_apps" + ] + }, + { + "cell_type": "code", + "execution_count": 44, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Games 2257\n", + "Entertainment 334\n", + "Photo & Video 167\n", + "Social Networking 143\n", + "Education 132\n", + "Shopping 121\n", + "Utilities 109\n", + "Lifestyle 94\n", + "Finance 84\n", + "Sports 79\n", + "Health & Fitness 76\n", + "Music 67\n", + "Book 66\n", + "Productivity 62\n", + "News 58\n", + "Travel 56\n", + "Food & Drink 43\n", + "Weather 31\n", + "Business 20\n", + "Reference 20\n", + "Navigation 20\n", + "Catalogs 9\n", + "Medical 8\n", + "Name: prime_genre, dtype: int64" + ] + }, + "execution_count": 44, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# your code here" + "free_apps['prime_genre'].value_counts()" ] }, { @@ -352,11 +971,46 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 45, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Shopping 0.991803\n", + "Catalogs 0.900000\n", + "Social Networking 0.856287\n", + "Finance 0.807692\n", + "News 0.773333\n", + "Sports 0.692982\n", + "Travel 0.691358\n", + "Food & Drink 0.682540\n", + "Lifestyle 0.652778\n", + "Entertainment 0.624299\n", + "Book 0.589286\n", + "Games 0.584412\n", + "Music 0.485507\n", + "Photo & Video 0.478510\n", + "Utilities 0.439516\n", + "Navigation 0.434783\n", + "Weather 0.430556\n", + "Health & Fitness 0.422222\n", + "Business 0.350877\n", + "Productivity 0.348315\n", + "Medical 0.347826\n", + "Reference 0.312500\n", + "Education 0.291391\n", + "Name: prime_genre, dtype: float64\n" + ] + } + ], "source": [ - "# your code here" + "# your code here\n", + "\n", + "proportion_free_apps = (data[data['price'] == 0.00]['prime_genre'].value_counts() / data['prime_genre'].value_counts()).sort_values(ascending=False)\n", + "\n", + "print(proportion_free_apps)" ] }, { @@ -397,11 +1051,193 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 59, "metadata": {}, - "outputs": [], + "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", + "
prime_genreaverage_price
10Medical8.776087
1Business5.116316
16Reference4.836875
11Music4.835435
15Productivity4.330562
12Navigation4.124783
3Education4.028234
8Health & Fitness1.916444
0Book1.790536
21Utilities1.647621
22Weather1.605417
6Food & Drink1.552381
14Photo & Video1.473295
7Games1.432923
20Travel1.120370
19Sports0.953070
4Entertainment0.889701
9Lifestyle0.885417
2Catalogs0.799000
13News0.517733
5Finance0.421154
18Social Networking0.339880
17Shopping0.016311
\n", + "
" + ], + "text/plain": [ + " prime_genre average_price\n", + "10 Medical 8.776087\n", + "1 Business 5.116316\n", + "16 Reference 4.836875\n", + "11 Music 4.835435\n", + "15 Productivity 4.330562\n", + "12 Navigation 4.124783\n", + "3 Education 4.028234\n", + "8 Health & Fitness 1.916444\n", + "0 Book 1.790536\n", + "21 Utilities 1.647621\n", + "22 Weather 1.605417\n", + "6 Food & Drink 1.552381\n", + "14 Photo & Video 1.473295\n", + "7 Games 1.432923\n", + "20 Travel 1.120370\n", + "19 Sports 0.953070\n", + "4 Entertainment 0.889701\n", + "9 Lifestyle 0.885417\n", + "2 Catalogs 0.799000\n", + "13 News 0.517733\n", + "5 Finance 0.421154\n", + "18 Social Networking 0.339880\n", + "17 Shopping 0.016311" + ] + }, + "execution_count": 59, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# your code here" + "average_price = data.groupby('prime_genre')['price'].mean().reset_index()\n", + "average_price = average_price.rename(columns={'price': 'average_price'})\n", + "average_price = average_price.sort_values(by='average_price',ascending=False)\n", + "\n", + "\n", + "average_price" ] }, { @@ -417,7 +1253,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 60, "metadata": {}, "outputs": [], "source": [ @@ -438,11 +1274,148 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 61, "metadata": {}, - "outputs": [], + "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", + "
Noyearmonthdayhourpm2.5DEWPTEMPPREScbwdIwsIsIr
012010110NaN-21-11.01021.0NW1.7900
122010111NaN-21-12.01020.0NW4.9200
232010112NaN-21-11.01019.0NW6.7100
342010113NaN-21-14.01019.0NW9.8400
452010114NaN-20-12.01018.0NW12.9700
\n", + "
" + ], + "text/plain": [ + " No year month day hour pm2.5 DEWP TEMP PRES cbwd Iws Is Ir\n", + "0 1 2010 1 1 0 NaN -21 -11.0 1021.0 NW 1.79 0 0\n", + "1 2 2010 1 1 1 NaN -21 -12.0 1020.0 NW 4.92 0 0\n", + "2 3 2010 1 1 2 NaN -21 -11.0 1019.0 NW 6.71 0 0\n", + "3 4 2010 1 1 3 NaN -21 -14.0 1019.0 NW 9.84 0 0\n", + "4 5 2010 1 1 4 NaN -20 -12.0 1018.0 NW 12.97 0 0" + ] + }, + "execution_count": 61, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:" + "# Your code here:\n", + "\n", + "pm25.head()" ] }, { @@ -454,11 +1427,12 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 62, "metadata": {}, "outputs": [], "source": [ "def hourly(x):\n", + " return x/24\n", " '''\n", " Input: A numerical value\n", " Output: The value divided by 24\n", @@ -481,11 +1455,272 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 64, "metadata": {}, - "outputs": [], + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Noyearmonthdayhourpm2.5DEWPTEMPPREScbwdIwsIsIr
012010110NaN-21-11.01021.0NW0.0745830.00.0
122010111NaN-21-12.01020.0NW0.2050000.00.0
232010112NaN-21-11.01019.0NW0.2795830.00.0
342010113NaN-21-14.01019.0NW0.4100000.00.0
452010114NaN-20-12.01018.0NW0.5404170.00.0
..........................................
438194382020141231198.0-23-2.01034.0NW9.6654170.00.0
4382043821201412312010.0-22-3.01034.0NW9.9075000.00.0
4382143822201412312110.0-22-3.01034.0NW10.1125000.00.0
438224382320141231228.0-22-4.01034.0NW10.2800000.00.0
4382343824201412312312.0-21-3.01034.0NW10.4104170.00.0
\n", + "

43824 rows × 13 columns

\n", + "
" + ], + "text/plain": [ + " No year month day hour pm2.5 DEWP TEMP PRES cbwd \\\n", + "0 1 2010 1 1 0 NaN -21 -11.0 1021.0 NW \n", + "1 2 2010 1 1 1 NaN -21 -12.0 1020.0 NW \n", + "2 3 2010 1 1 2 NaN -21 -11.0 1019.0 NW \n", + "3 4 2010 1 1 3 NaN -21 -14.0 1019.0 NW \n", + "4 5 2010 1 1 4 NaN -20 -12.0 1018.0 NW \n", + "... ... ... ... ... ... ... ... ... ... ... \n", + "43819 43820 2014 12 31 19 8.0 -23 -2.0 1034.0 NW \n", + "43820 43821 2014 12 31 20 10.0 -22 -3.0 1034.0 NW \n", + "43821 43822 2014 12 31 21 10.0 -22 -3.0 1034.0 NW \n", + "43822 43823 2014 12 31 22 8.0 -22 -4.0 1034.0 NW \n", + "43823 43824 2014 12 31 23 12.0 -21 -3.0 1034.0 NW \n", + "\n", + " Iws Is Ir \n", + "0 0.074583 0.0 0.0 \n", + "1 0.205000 0.0 0.0 \n", + "2 0.279583 0.0 0.0 \n", + "3 0.410000 0.0 0.0 \n", + "4 0.540417 0.0 0.0 \n", + "... ... ... ... \n", + "43819 9.665417 0.0 0.0 \n", + "43820 9.907500 0.0 0.0 \n", + "43821 10.112500 0.0 0.0 \n", + "43822 10.280000 0.0 0.0 \n", + "43823 10.410417 0.0 0.0 \n", + "\n", + "[43824 rows x 13 columns]" + ] + }, + "execution_count": 64, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Your code here:" + "# Your code here:\n", + "\n", + "pm25_hourly = pm25.copy()\n", + "\n", + "pm25_hourly[\"Iws\"] = pm25_hourly[\"Iws\"].apply(hourly)\n", + "pm25_hourly[\"Is\"] = pm25_hourly[\"Is\"].apply(hourly)\n", + "pm25_hourly[\"Ir\"] = pm25_hourly[\"Ir\"].apply(hourly)\n", + "\n", + "pm25_hourly" ] }, { @@ -499,11 +1734,16 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 65, "metadata": {}, "outputs": [], "source": [ "def sample_sd(x):\n", + "\n", + " numb_elements = x.count()\n", + " std_x = np.std(x, ddof=1)\n", + "\n", + " return std_x/numb_elements\n", " '''\n", " Input: A Pandas series of values\n", " Output: the standard deviation divided by the number of elements in the series\n", @@ -533,7 +1773,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.8" + "version": "3.10.11" } }, "nbformat": 4,