From 21b68a14994907fd5261154fcef7b49d1937fb1c Mon Sep 17 00:00:00 2001 From: ArisGoulas Date: Sun, 16 Apr 2023 19:06:46 +0100 Subject: [PATCH 1/2] lab done --- your-code/main.ipynb | 703 ++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 665 insertions(+), 38 deletions(-) diff --git a/your-code/main.ipynb b/your-code/main.ipynb index 0fc1af6..5b06cfd 100644 --- a/your-code/main.ipynb +++ b/your-code/main.ipynb @@ -18,10 +18,13 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "import numpy as np\n", + "import pandas as pd" + ] }, { "cell_type": "markdown", @@ -32,7 +35,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 6, "metadata": {}, "outputs": [], "source": [ @@ -41,10 +44,34 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 28, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "0 5.7\n", + "1 75.2\n", + "2 74.4\n", + "3 84.0\n", + "4 66.5\n", + "5 66.3\n", + "6 55.8\n", + "7 75.7\n", + "8 29.1\n", + "9 43.7\n", + "dtype: float64" + ] + }, + "execution_count": 28, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "series = pd.Series(lst)\n", + "series" + ] }, { "cell_type": "markdown", @@ -57,10 +84,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 29, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "74.4" + ] + }, + "execution_count": 29, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "series[2]" + ] }, { "cell_type": "markdown", @@ -71,7 +111,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 18, "metadata": {}, "outputs": [], "source": [ @@ -89,10 +129,145 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 32, "metadata": {}, - "outputs": [], - "source": [] + "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", + "
01234
053.195.067.535.078.4
161.340.830.837.887.6
220.673.244.214.691.8
357.40.196.14.269.5
483.620.585.422.835.9
549.069.00.131.889.1
623.340.795.083.826.9
727.626.453.888.868.5
896.696.453.472.450.1
973.739.043.281.634.7
\n", + "
" + ], + "text/plain": [ + " 0 1 2 3 4\n", + "0 53.1 95.0 67.5 35.0 78.4\n", + "1 61.3 40.8 30.8 37.8 87.6\n", + "2 20.6 73.2 44.2 14.6 91.8\n", + "3 57.4 0.1 96.1 4.2 69.5\n", + "4 83.6 20.5 85.4 22.8 35.9\n", + "5 49.0 69.0 0.1 31.8 89.1\n", + "6 23.3 40.7 95.0 83.8 26.9\n", + "7 27.6 26.4 53.8 88.8 68.5\n", + "8 96.6 96.4 53.4 72.4 50.1\n", + "9 73.7 39.0 43.2 81.6 34.7" + ] + }, + "execution_count": 32, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df = pd.DataFrame(b)\n", + "df" + ] }, { "cell_type": "markdown", @@ -103,7 +278,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 23, "metadata": {}, "outputs": [], "source": [ @@ -112,10 +287,145 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 34, "metadata": {}, - "outputs": [], - "source": [] + "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", + "
Score_1Score_2Score_3Score_4Score_5
053.195.067.535.078.4
161.340.830.837.887.6
220.673.244.214.691.8
357.40.196.14.269.5
483.620.585.422.835.9
549.069.00.131.889.1
623.340.795.083.826.9
727.626.453.888.868.5
896.696.453.472.450.1
973.739.043.281.634.7
\n", + "
" + ], + "text/plain": [ + " Score_1 Score_2 Score_3 Score_4 Score_5\n", + "0 53.1 95.0 67.5 35.0 78.4\n", + "1 61.3 40.8 30.8 37.8 87.6\n", + "2 20.6 73.2 44.2 14.6 91.8\n", + "3 57.4 0.1 96.1 4.2 69.5\n", + "4 83.6 20.5 85.4 22.8 35.9\n", + "5 49.0 69.0 0.1 31.8 89.1\n", + "6 23.3 40.7 95.0 83.8 26.9\n", + "7 27.6 26.4 53.8 88.8 68.5\n", + "8 96.6 96.4 53.4 72.4 50.1\n", + "9 73.7 39.0 43.2 81.6 34.7" + ] + }, + "execution_count": 34, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df = pd.DataFrame(b, columns = [colnames])\n", + "df" + ] }, { "cell_type": "markdown", @@ -126,10 +436,122 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 38, "metadata": {}, - "outputs": [], - "source": [] + "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", + "
Score_1Score_3Score_5
053.167.578.4
161.330.887.6
220.644.291.8
357.496.169.5
483.685.435.9
549.00.189.1
623.395.026.9
727.653.868.5
896.653.450.1
973.743.234.7
\n", + "
" + ], + "text/plain": [ + " Score_1 Score_3 Score_5\n", + "0 53.1 67.5 78.4\n", + "1 61.3 30.8 87.6\n", + "2 20.6 44.2 91.8\n", + "3 57.4 96.1 69.5\n", + "4 83.6 85.4 35.9\n", + "5 49.0 0.1 89.1\n", + "6 23.3 95.0 26.9\n", + "7 27.6 53.8 68.5\n", + "8 96.6 53.4 50.1\n", + "9 73.7 43.2 34.7" + ] + }, + "execution_count": 38, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df[[\"Score_1\", \"Score_3\", \"Score_5\"]]" + ] }, { "cell_type": "markdown", @@ -140,10 +562,25 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 43, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "Score_3 56.95\n", + "dtype: float64" + ] + }, + "execution_count": 43, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "Score3_av = df[\"Score_3\"].mean()\n", + "Score3_av" + ] }, { "cell_type": "markdown", @@ -154,10 +591,25 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 45, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "Score_4 36.4\n", + "dtype: float64" + ] + }, + "execution_count": 45, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "Score4_max = df[\"Score_4\"].max()\n", + "Score4_max" + ] }, { "cell_type": "markdown", @@ -168,10 +620,25 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 46, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "Score_2 40.75\n", + "dtype: float64" + ] + }, + "execution_count": 46, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "Score2_med = df[\"Score_2\"].median()\n", + "Score2_med" + ] }, { "cell_type": "markdown", @@ -182,7 +649,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 48, "metadata": {}, "outputs": [], "source": [ @@ -203,10 +670,135 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 78, "metadata": {}, - "outputs": [], - "source": [] + "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", + "
DescriptionQuantityUnitPriceRevenue
0LUNCH BAG APPLE DESIGN11.651.65
1SET OF 60 VINTAGE LEAF CAKE CASES240.5513.20
2RIBBON REEL STRIPES DESIGN11.651.65
3WORLD WAR 2 GLIDERS ASSTD DESIGNS28800.18518.40
4PLAYING CARDS JUBILEE UNION JACK21.252.50
5POPCORN HOLDER70.855.95
6BOX OF VINTAGE ALPHABET BLOCKS111.9511.95
7PARTY BUNTING44.9519.80
8JAZZ HEARTS ADDRESS BOOK100.191.90
9SET OF 4 SANTA PLACE SETTINGS481.2560.00
\n", + "
" + ], + "text/plain": [ + " Description Quantity UnitPrice Revenue\n", + "0 LUNCH BAG APPLE DESIGN 1 1.65 1.65\n", + "1 SET OF 60 VINTAGE LEAF CAKE CASES 24 0.55 13.20\n", + "2 RIBBON REEL STRIPES DESIGN 1 1.65 1.65\n", + "3 WORLD WAR 2 GLIDERS ASSTD DESIGNS 2880 0.18 518.40\n", + "4 PLAYING CARDS JUBILEE UNION JACK 2 1.25 2.50\n", + "5 POPCORN HOLDER 7 0.85 5.95\n", + "6 BOX OF VINTAGE ALPHABET BLOCKS 1 11.95 11.95\n", + "7 PARTY BUNTING 4 4.95 19.80\n", + "8 JAZZ HEARTS ADDRESS BOOK 10 0.19 1.90\n", + "9 SET OF 4 SANTA PLACE SETTINGS 48 1.25 60.00" + ] + }, + "execution_count": 78, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df = pd.DataFrame.from_dict(orders)\n", + "type(df)\n", + "df" + ] }, { "cell_type": "markdown", @@ -217,10 +809,25 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 72, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "2978\n", + "637.0\n" + ] + } + ], + "source": [ + "total_quantity = df[\"Quantity\"].sum()\n", + "print(total_quantity)\n", + "\n", + "revenue = df[\"Revenue\"].sum()\n", + "print(revenue)" + ] }, { "cell_type": "markdown", @@ -229,6 +836,26 @@ "### 12. Obtain the prices of the most expensive and least expensive items ordered and print the difference." ] }, + { + "cell_type": "code", + "execution_count": 79, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "11.77\n" + ] + } + ], + "source": [ + "price_max = df[\"UnitPrice\"].max()\n", + "price_min = df[\"UnitPrice\"].min()\n", + "price_diff = price_max - price_min\n", + "print(price_diff)" + ] + }, { "cell_type": "code", "execution_count": null, @@ -239,7 +866,7 @@ ], "metadata": { "kernelspec": { - "display_name": "Python 3", + "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, @@ -253,7 +880,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.8" + "version": "3.10.9" } }, "nbformat": 4, From 9cef392801adda506092c83b03a4f9ab8734ef5b Mon Sep 17 00:00:00 2001 From: ArisGoulas Date: Thu, 22 Jun 2023 13:33:09 +0100 Subject: [PATCH 2/2] lab revised after bootcamp --- your-code/main.ipynb | 111 +++++++++++++++++++------------------------ 1 file changed, 49 insertions(+), 62 deletions(-) diff --git a/your-code/main.ipynb b/your-code/main.ipynb index 5b06cfd..28953bd 100644 --- a/your-code/main.ipynb +++ b/your-code/main.ipynb @@ -18,7 +18,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 2, "metadata": {}, "outputs": [], "source": [ @@ -35,7 +35,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 3, "metadata": {}, "outputs": [], "source": [ @@ -44,7 +44,7 @@ }, { "cell_type": "code", - "execution_count": 28, + "execution_count": 14, "metadata": {}, "outputs": [ { @@ -63,14 +63,13 @@ "dtype: float64" ] }, - "execution_count": 28, + "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "series = pd.Series(lst)\n", - "series" + "pd.Series(lst)" ] }, { @@ -84,7 +83,7 @@ }, { "cell_type": "code", - "execution_count": 29, + "execution_count": 8, "metadata": {}, "outputs": [ { @@ -93,13 +92,13 @@ "74.4" ] }, - "execution_count": 29, + "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "series[2]" + "pd.Series(lst)[2]" ] }, { @@ -111,7 +110,7 @@ }, { "cell_type": "code", - "execution_count": 18, + "execution_count": 10, "metadata": {}, "outputs": [], "source": [ @@ -129,7 +128,7 @@ }, { "cell_type": "code", - "execution_count": 32, + "execution_count": 33, "metadata": {}, "outputs": [ { @@ -259,14 +258,15 @@ "9 73.7 39.0 43.2 81.6 34.7" ] }, - "execution_count": 32, + "execution_count": 33, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "df = pd.DataFrame(b)\n", - "df" + "# syntax: DataFrame(data=None, index=None, columns=None, dtype=None, copy=None)\n", + "\n", + "pd.DataFrame(data = b)" ] }, { @@ -278,7 +278,7 @@ }, { "cell_type": "code", - "execution_count": 23, + "execution_count": 34, "metadata": {}, "outputs": [], "source": [ @@ -287,7 +287,7 @@ }, { "cell_type": "code", - "execution_count": 34, + "execution_count": 35, "metadata": {}, "outputs": [ { @@ -417,14 +417,14 @@ "9 73.7 39.0 43.2 81.6 34.7" ] }, - "execution_count": 34, + "execution_count": 35, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "df = pd.DataFrame(b, columns = [colnames])\n", - "df" + "df_b = pd.DataFrame(data = b, columns = [colnames]) # could also do pd.Dataframe(b).columns = colnames\n", + "df_b" ] }, { @@ -436,7 +436,7 @@ }, { "cell_type": "code", - "execution_count": 38, + "execution_count": 36, "metadata": {}, "outputs": [ { @@ -544,13 +544,14 @@ "9 73.7 43.2 34.7" ] }, - "execution_count": 38, + "execution_count": 36, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "df[[\"Score_1\", \"Score_3\", \"Score_5\"]]" + "df_b_subset = df_b[[\"Score_1\", \"Score_3\", \"Score_5\"]]\n", + "df_b_subset" ] }, { @@ -562,7 +563,7 @@ }, { "cell_type": "code", - "execution_count": 43, + "execution_count": 37, "metadata": {}, "outputs": [ { @@ -572,14 +573,13 @@ "dtype: float64" ] }, - "execution_count": 43, + "execution_count": 37, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "Score3_av = df[\"Score_3\"].mean()\n", - "Score3_av" + "df_b[\"Score_3\"].mean()" ] }, { @@ -591,24 +591,23 @@ }, { "cell_type": "code", - "execution_count": 45, + "execution_count": 38, "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "Score_4 36.4\n", + "Score_4 88.8\n", "dtype: float64" ] }, - "execution_count": 45, + "execution_count": 38, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "Score4_max = df[\"Score_4\"].max()\n", - "Score4_max" + "df_b[\"Score_4\"].max()" ] }, { @@ -620,7 +619,7 @@ }, { "cell_type": "code", - "execution_count": 46, + "execution_count": 39, "metadata": {}, "outputs": [ { @@ -630,14 +629,13 @@ "dtype: float64" ] }, - "execution_count": 46, + "execution_count": 39, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "Score2_med = df[\"Score_2\"].median()\n", - "Score2_med" + "df_b[\"Score_2\"].median()" ] }, { @@ -649,7 +647,7 @@ }, { "cell_type": "code", - "execution_count": 48, + "execution_count": 42, "metadata": {}, "outputs": [], "source": [ @@ -670,7 +668,7 @@ }, { "cell_type": "code", - "execution_count": 78, + "execution_count": 43, "metadata": {}, "outputs": [ { @@ -789,15 +787,14 @@ "9 SET OF 4 SANTA PLACE SETTINGS 48 1.25 60.00" ] }, - "execution_count": 78, + "execution_count": 43, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "df = pd.DataFrame.from_dict(orders)\n", - "type(df)\n", - "df" + "df_orders = pd.DataFrame(orders)\n", + "df_orders" ] }, { @@ -809,24 +806,13 @@ }, { "cell_type": "code", - "execution_count": 72, + "execution_count": 46, "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "2978\n", - "637.0\n" - ] - } - ], + "outputs": [], "source": [ - "total_quantity = df[\"Quantity\"].sum()\n", - "print(total_quantity)\n", + "total_quantity = df_orders[\"Quantity\"].sum()\n", "\n", - "revenue = df[\"Revenue\"].sum()\n", - "print(revenue)" + "revenue = df_orders[\"Revenue\"].sum()" ] }, { @@ -838,7 +824,7 @@ }, { "cell_type": "code", - "execution_count": 79, + "execution_count": 47, "metadata": {}, "outputs": [ { @@ -850,10 +836,11 @@ } ], "source": [ - "price_max = df[\"UnitPrice\"].max()\n", - "price_min = df[\"UnitPrice\"].min()\n", - "price_diff = price_max - price_min\n", - "print(price_diff)" + "most_expensive = df_orders[\"UnitPrice\"].max()\n", + "\n", + "least_expensive = df_orders[\"UnitPrice\"].min()\n", + "\n", + "print(most_expensive - least_expensive)" ] }, { @@ -880,7 +867,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.10.9" + "version": "3.10.10" } }, "nbformat": 4,