diff --git a/your-code/pandas_1.ipynb b/your-code/pandas_1.ipynb index 4f428ac..2979a45 100644 --- a/your-code/pandas_1.ipynb +++ b/your-code/pandas_1.ipynb @@ -44,10 +44,34 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "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": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "myseries = pd.Series(lst)\n", + "myseries" + ] }, { "cell_type": "markdown", @@ -60,10 +84,24 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "74.4" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "indexing_third_value = pd.Series(lst)\n", + "indexing_third_value[2]" + ] }, { "cell_type": "markdown", @@ -74,7 +112,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 5, "metadata": {}, "outputs": [], "source": [ @@ -92,10 +130,145 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 6, "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": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "c = pd.DataFrame(b)\n", + "c" + ] }, { "cell_type": "markdown", @@ -106,7 +279,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 7, "metadata": {}, "outputs": [], "source": [ @@ -124,7 +297,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 8, "metadata": {}, "outputs": [], "source": [ @@ -133,10 +306,52 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 9, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Index(['Score_1', 'Score_2', 'Score_3', 'Score_4', 'Score_5'], dtype='object')\n" + ] + } + ], + "source": [ + "# renaming data frame columns\n", + "\n", + "renaming_data = pd.DataFrame(b, columns = colnames)\n", + "print(renaming_data.columns)" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " 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\n" + ] + } + ], + "source": [ + "# we check if it is correct getting the data frame\n", + "\n", + "print(renaming_data)" + ] }, { "cell_type": "markdown", @@ -147,10 +362,122 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 11, "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": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "renaming_data[['Score_1','Score_3', 'Score_5']]" + ] }, { "cell_type": "markdown", @@ -161,10 +488,146 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 12, "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", + "
Score_1Score_2Score_3Score_4Score_5
count10.0000010.0000010.00000010.00000010.000000
mean54.6200050.1100056.95000047.28000063.250000
std25.6489932.1220430.16827831.39344624.562313
min20.600000.100000.1000004.20000026.900000
25%32.9500029.5500043.45000025.05000039.450000
50%55.2500040.7500053.60000036.40000069.000000
75%70.6000072.1500080.92500079.30000085.300000
max96.6000096.4000096.10000088.80000091.800000
\n", + "
" + ], + "text/plain": [ + " Score_1 Score_2 Score_3 Score_4 Score_5\n", + "count 10.00000 10.00000 10.000000 10.000000 10.000000\n", + "mean 54.62000 50.11000 56.950000 47.280000 63.250000\n", + "std 25.64899 32.12204 30.168278 31.393446 24.562313\n", + "min 20.60000 0.10000 0.100000 4.200000 26.900000\n", + "25% 32.95000 29.55000 43.450000 25.050000 39.450000\n", + "50% 55.25000 40.75000 53.600000 36.400000 69.000000\n", + "75% 70.60000 72.15000 80.925000 79.300000 85.300000\n", + "max 96.60000 96.40000 96.100000 88.800000 91.800000" + ] + }, + "execution_count": 12, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "renaming_data.describe() #numerical columns" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "56.95000000000001" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "renaming_data[\"Score_3\"].mean()" + ] }, { "cell_type": "markdown", @@ -175,10 +638,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 14, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "88.8" + ] + }, + "execution_count": 14, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "renaming_data[\"Score_4\"].max()" + ] }, { "cell_type": "markdown", @@ -189,10 +665,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 15, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "40.75" + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "renaming_data[\"Score_2\"].median()" + ] }, { "cell_type": "markdown", @@ -203,7 +692,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 16, "metadata": {}, "outputs": [], "source": [ @@ -224,10 +713,134 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 17, "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": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "product_orders = pd.DataFrame(orders)\n", + "product_orders" + ] }, { "cell_type": "markdown", @@ -238,10 +851,41 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 18, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "2978\n" + ] + } + ], + "source": [ + "total_quantity = product_orders[\"Quantity\"].sum()\n", + "print(total_quantity)" + ] + }, + { + "cell_type": "code", + "execution_count": 19, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "637.0\n" + ] + } + ], + "source": [ + "total_revenue = product_orders[\"Revenue\"].sum()\n", + "print(total_revenue)" + ] }, { "cell_type": "markdown", @@ -252,10 +896,41 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 20, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "11.95\n", + "0.18\n" + ] + } + ], + "source": [ + "most_expensive = product_orders[\"UnitPrice\"].max()\n", + "least_expensive = product_orders[\"UnitPrice\"].min()\n", + "print(most_expensive)\n", + "print(least_expensive)" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "11.77\n" + ] + } + ], + "source": [ + "print(most_expensive - least_expensive)" + ] }, { "cell_type": "markdown", @@ -266,7 +941,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 22, "metadata": {}, "outputs": [], "source": [ @@ -285,10 +960,130 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 23, "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", + "
Serial No.GRE ScoreTOEFL ScoreUniversity RatingSOPLORCGPAResearchChance of Admit
0133711844.54.59.6510.92
1231610433.03.58.0010.72
2332211033.52.58.6710.80
3431410322.03.08.2100.65
4533011554.53.09.3410.90
\n", + "
" + ], + "text/plain": [ + " Serial No. GRE Score TOEFL Score University Rating SOP LOR CGPA \\\n", + "0 1 337 118 4 4.5 4.5 9.65 \n", + "1 2 316 104 3 3.0 3.5 8.00 \n", + "2 3 322 110 3 3.5 2.5 8.67 \n", + "3 4 314 103 2 2.0 3.0 8.21 \n", + "4 5 330 115 5 4.5 3.0 9.34 \n", + "\n", + " Research Chance of Admit \n", + "0 1 0.92 \n", + "1 1 0.72 \n", + "2 1 0.80 \n", + "3 0 0.65 \n", + "4 1 0.90 " + ] + }, + "execution_count": 23, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions.head()" + ] }, { "cell_type": "markdown", @@ -299,10 +1094,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 24, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "False" + ] + }, + "execution_count": 24, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pd.isnull(admissions).values.any()" + ] }, { "cell_type": "markdown", @@ -313,17 +1121,21 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 25, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "admissions.reset_index(inplace=True)" + ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 26, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "admissions.set_index(\"Serial No.\", inplace=True) #you need to add inplace, othewise changes are not saved" + ] }, { "cell_type": "markdown", @@ -334,10 +1146,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 27, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "0" + ] + }, + "execution_count": 27, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions.duplicated(subset=[\"GRE Score\", \"CGPA\"]).sum()" + ] }, { "cell_type": "markdown", @@ -348,10 +1173,232 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 29, "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
indexGRE ScoreTOEFL ScoreUniversity RatingSOPLORCGPAResearchChance of Admit
Serial No.
1033711844.54.59.6510.92
5433011554.53.09.3410.90
111032811244.04.59.1010.78
201932811655.05.09.5010.94
212033411955.04.59.7010.95
..............................
38037932911144.54.09.2310.89
38138032411033.53.59.0410.82
38238132510733.03.59.1110.84
38338233011645.04.59.4510.91
38538433311745.04.09.6610.95
\n", + "

101 rows × 9 columns

\n", + "
" + ], + "text/plain": [ + " index GRE Score TOEFL Score University Rating SOP LOR CGPA \\\n", + "Serial No. \n", + "1 0 337 118 4 4.5 4.5 9.65 \n", + "5 4 330 115 5 4.5 3.0 9.34 \n", + "11 10 328 112 4 4.0 4.5 9.10 \n", + "20 19 328 116 5 5.0 5.0 9.50 \n", + "21 20 334 119 5 5.0 4.5 9.70 \n", + "... ... ... ... ... ... ... ... \n", + "380 379 329 111 4 4.5 4.0 9.23 \n", + "381 380 324 110 3 3.5 3.5 9.04 \n", + "382 381 325 107 3 3.0 3.5 9.11 \n", + "383 382 330 116 4 5.0 4.5 9.45 \n", + "385 384 333 117 4 5.0 4.0 9.66 \n", + "\n", + " Research Chance of Admit \n", + "Serial No. \n", + "1 1 0.92 \n", + "5 1 0.90 \n", + "11 1 0.78 \n", + "20 1 0.94 \n", + "21 1 0.95 \n", + "... ... ... \n", + "380 1 0.89 \n", + "381 1 0.82 \n", + "382 1 0.84 \n", + "383 1 0.91 \n", + "385 1 0.95 \n", + "\n", + "[101 rows x 9 columns]" + ] + }, + "execution_count": 29, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "rslt = admissions[(admissions['CGPA'] > 9) & (admissions['Research'] > 0)]\n", + "rslt" + ] }, { "cell_type": "markdown", @@ -362,17 +1409,370 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 30, "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", + "
indexGRE ScoreTOEFL ScoreUniversity RatingSOPLORCGPAResearchChance of Admit
Serial No.
292833811843.04.59.4010.91
636232711433.03.09.0200.61
14114032611433.03.09.1110.83
21821732411143.03.09.0110.82
38238132510733.03.59.1110.84
\n", + "
" + ], + "text/plain": [ + " index GRE Score TOEFL Score University Rating SOP LOR CGPA \\\n", + "Serial No. \n", + "29 28 338 118 4 3.0 4.5 9.40 \n", + "63 62 327 114 3 3.0 3.0 9.02 \n", + "141 140 326 114 3 3.0 3.0 9.11 \n", + "218 217 324 111 4 3.0 3.0 9.01 \n", + "382 381 325 107 3 3.0 3.5 9.11 \n", + "\n", + " Research Chance of Admit \n", + "Serial No. \n", + "29 1 0.91 \n", + "63 0 0.61 \n", + "141 1 0.83 \n", + "218 1 0.82 \n", + "382 1 0.84 " + ] + }, + "execution_count": 30, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "rslt_4 = admissions[(admissions[\"CGPA\"]> 9) & (admissions[\"SOP\"] < 3.5)]\n", + "rslt_4" + ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 32, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "#find the mean of CHANCE ADMIT\n", + "\n", + "mean_chance = rslt_4['Chance of Admit'].mean()" + ] + }, + { + "cell_type": "code", + "execution_count": 100, + "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", + " \n", + " \n", + " \n", + " \n", + "
Serial No.GRE ScoreTOEFL ScoreUniversity RatingSOPLORCGPAResearchChance of Admit
0133711844.54.59.6510.92
1231610433.03.58.0010.72
2332211033.52.58.6710.80
3431410322.03.08.2100.65
4533011554.53.09.3410.90
..............................
38038132411033.53.59.0410.82
38138232510733.03.59.1110.84
38238333011645.04.59.4510.91
38338431210333.54.08.7800.67
38438533311745.04.09.6610.95
\n", + "

385 rows × 9 columns

\n", + "
" + ], + "text/plain": [ + " Serial No. GRE Score TOEFL Score University Rating SOP LOR CGPA \\\n", + "0 1 337 118 4 4.5 4.5 9.65 \n", + "1 2 316 104 3 3.0 3.5 8.00 \n", + "2 3 322 110 3 3.5 2.5 8.67 \n", + "3 4 314 103 2 2.0 3.0 8.21 \n", + "4 5 330 115 5 4.5 3.0 9.34 \n", + ".. ... ... ... ... ... ... ... \n", + "380 381 324 110 3 3.5 3.5 9.04 \n", + "381 382 325 107 3 3.0 3.5 9.11 \n", + "382 383 330 116 4 5.0 4.5 9.45 \n", + "383 384 312 103 3 3.5 4.0 8.78 \n", + "384 385 333 117 4 5.0 4.0 9.66 \n", + "\n", + " Research Chance of Admit \n", + "0 1 0.92 \n", + "1 1 0.72 \n", + "2 1 0.80 \n", + "3 0 0.65 \n", + "4 1 0.90 \n", + ".. ... ... \n", + "380 1 0.82 \n", + "381 1 0.84 \n", + "382 1 0.91 \n", + "383 0 0.67 \n", + "384 1 0.95 \n", + "\n", + "[385 rows x 9 columns]" + ] + }, + "execution_count": 100, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions" + ] }, { "cell_type": "markdown", @@ -384,38 +1784,506 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 121, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "def new_column(i):\n", + " if i > 100:\n", + " return True\n", + " else:\n", + " return False\n", + " " + ] }, { - "cell_type": "markdown", + "cell_type": "code", + "execution_count": 122, "metadata": {}, + "outputs": [], "source": [ - "Now we create a new column called \"Decision\" and apply to the TOEFL Score column" + "admissions[\"New Column\"] = admissions[\"TOEFL Score\"].apply(new_column)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 123, "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Serial No.GRE ScoreTOEFL ScoreUniversity RatingSOPLORCGPAResearchChance of AdmitNew Column
0133711844.54.59.6510.92True
1231610433.03.58.0010.72True
2332211033.52.58.6710.80True
3431410322.03.08.2100.65True
4533011554.53.09.3410.90True
.................................
38038132411033.53.59.0410.82True
38138232510733.03.59.1110.84True
38238333011645.04.59.4510.91True
38338431210333.54.08.7800.67True
38438533311745.04.09.6610.95True
\n", + "

385 rows × 10 columns

\n", + "
" + ], + "text/plain": [ + " Serial No. GRE Score TOEFL Score University Rating SOP LOR CGPA \\\n", + "0 1 337 118 4 4.5 4.5 9.65 \n", + "1 2 316 104 3 3.0 3.5 8.00 \n", + "2 3 322 110 3 3.5 2.5 8.67 \n", + "3 4 314 103 2 2.0 3.0 8.21 \n", + "4 5 330 115 5 4.5 3.0 9.34 \n", + ".. ... ... ... ... ... ... ... \n", + "380 381 324 110 3 3.5 3.5 9.04 \n", + "381 382 325 107 3 3.0 3.5 9.11 \n", + "382 383 330 116 4 5.0 4.5 9.45 \n", + "383 384 312 103 3 3.5 4.0 8.78 \n", + "384 385 333 117 4 5.0 4.0 9.66 \n", + "\n", + " Research Chance of Admit New Column \n", + "0 1 0.92 True \n", + "1 1 0.72 True \n", + "2 1 0.80 True \n", + "3 0 0.65 True \n", + "4 1 0.90 True \n", + ".. ... ... ... \n", + "380 1 0.82 True \n", + "381 1 0.84 True \n", + "382 1 0.91 True \n", + "383 0 0.67 True \n", + "384 1 0.95 True \n", + "\n", + "[385 rows x 10 columns]" + ] + }, + "execution_count": 123, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Now we create a new column called \"Decision\" and apply to the TOEFL Score column" + ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 124, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "admissions[\"Decision\"] = admissions[\"TOEFL Score\"]" + ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 125, "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Serial No.GRE ScoreTOEFL ScoreUniversity RatingSOPLORCGPAResearchChance of AdmitNew ColumnDecision
0133711844.54.59.6510.92True118
1231610433.03.58.0010.72True104
2332211033.52.58.6710.80True110
3431410322.03.08.2100.65True103
4533011554.53.09.3410.90True115
....................................
38038132411033.53.59.0410.82True110
38138232510733.03.59.1110.84True107
38238333011645.04.59.4510.91True116
38338431210333.54.08.7800.67True103
38438533311745.04.09.6610.95True117
\n", + "

385 rows × 11 columns

\n", + "
" + ], + "text/plain": [ + " Serial No. GRE Score TOEFL Score University Rating SOP LOR CGPA \\\n", + "0 1 337 118 4 4.5 4.5 9.65 \n", + "1 2 316 104 3 3.0 3.5 8.00 \n", + "2 3 322 110 3 3.5 2.5 8.67 \n", + "3 4 314 103 2 2.0 3.0 8.21 \n", + "4 5 330 115 5 4.5 3.0 9.34 \n", + ".. ... ... ... ... ... ... ... \n", + "380 381 324 110 3 3.5 3.5 9.04 \n", + "381 382 325 107 3 3.0 3.5 9.11 \n", + "382 383 330 116 4 5.0 4.5 9.45 \n", + "383 384 312 103 3 3.5 4.0 8.78 \n", + "384 385 333 117 4 5.0 4.0 9.66 \n", + "\n", + " Research Chance of Admit New Column Decision \n", + "0 1 0.92 True 118 \n", + "1 1 0.72 True 104 \n", + "2 1 0.80 True 110 \n", + "3 0 0.65 True 103 \n", + "4 1 0.90 True 115 \n", + ".. ... ... ... ... \n", + "380 1 0.82 True 110 \n", + "381 1 0.84 True 107 \n", + "382 1 0.91 True 116 \n", + "383 0 0.67 True 103 \n", + "384 1 0.95 True 117 \n", + "\n", + "[385 rows x 11 columns]" + ] + }, + "execution_count": 125, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions" + ] }, { "cell_type": "markdown", @@ -427,10 +2295,262 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 127, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "admissions['decision2'] = np.where(admissions['SOP'] > 3, 1, 0)" + ] + }, + { + "cell_type": "code", + "execution_count": 128, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Serial No.GRE ScoreTOEFL ScoreUniversity RatingSOPLORCGPAResearchChance of AdmitNew ColumnDecisiondecision2
0133711844.54.59.6510.92True1181
1231610433.03.58.0010.72True1040
2332211033.52.58.6710.80True1101
3431410322.03.08.2100.65True1030
4533011554.53.09.3410.90True1151
.......................................
38038132411033.53.59.0410.82True1101
38138232510733.03.59.1110.84True1070
38238333011645.04.59.4510.91True1161
38338431210333.54.08.7800.67True1031
38438533311745.04.09.6610.95True1171
\n", + "

385 rows × 12 columns

\n", + "
" + ], + "text/plain": [ + " Serial No. GRE Score TOEFL Score University Rating SOP LOR CGPA \\\n", + "0 1 337 118 4 4.5 4.5 9.65 \n", + "1 2 316 104 3 3.0 3.5 8.00 \n", + "2 3 322 110 3 3.5 2.5 8.67 \n", + "3 4 314 103 2 2.0 3.0 8.21 \n", + "4 5 330 115 5 4.5 3.0 9.34 \n", + ".. ... ... ... ... ... ... ... \n", + "380 381 324 110 3 3.5 3.5 9.04 \n", + "381 382 325 107 3 3.0 3.5 9.11 \n", + "382 383 330 116 4 5.0 4.5 9.45 \n", + "383 384 312 103 3 3.5 4.0 8.78 \n", + "384 385 333 117 4 5.0 4.0 9.66 \n", + "\n", + " Research Chance of Admit New Column Decision decision2 \n", + "0 1 0.92 True 118 1 \n", + "1 1 0.72 True 104 0 \n", + "2 1 0.80 True 110 1 \n", + "3 0 0.65 True 103 0 \n", + "4 1 0.90 True 115 1 \n", + ".. ... ... ... ... ... \n", + "380 1 0.82 True 110 1 \n", + "381 1 0.84 True 107 0 \n", + "382 1 0.91 True 116 1 \n", + "383 0 0.67 True 103 1 \n", + "384 1 0.95 True 117 1 \n", + "\n", + "[385 rows x 12 columns]" + ] + }, + "execution_count": 128, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions" + ] } ], "metadata": { @@ -449,7 +2569,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.10.8" + "version": "3.10.9" }, "toc": { "base_numbering": "",