diff --git a/your-code/pandas_1.ipynb b/your-code/pandas_1.ipynb index 4f428ac..e25fbcb 100644 --- a/your-code/pandas_1.ipynb +++ b/your-code/pandas_1.ipynb @@ -44,10 +44,12 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "panda_series = pd.Series([5.7, 75.2, 74.4, 84.0, 66.5, 66.3, 55.8, 75.7, 29.1, 43.7])" + ] }, { "cell_type": "markdown", @@ -60,10 +62,43 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 15, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "74.4" + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "panda_series[2]" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "74.4" + ] + }, + "execution_count": 14, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "panda_series.iloc[2]" + ] }, { "cell_type": "markdown", @@ -74,7 +109,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 16, "metadata": {}, "outputs": [], "source": [ @@ -92,10 +127,145 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 18, "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": 18, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df = pd.DataFrame(b)\n", + "df" + ] }, { "cell_type": "markdown", @@ -106,7 +276,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 19, "metadata": {}, "outputs": [], "source": [ @@ -124,7 +294,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 20, "metadata": {}, "outputs": [], "source": [ @@ -133,10 +303,145 @@ }, { "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", + " \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": 23, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df = pd.DataFrame(b, columns = colnames)\n", + "df" + ] }, { "cell_type": "markdown", @@ -147,10 +452,123 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 24, "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": 24, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df_subset = df[[\"Score_1\", \"Score_3\",\"Score_5\"]]\n", + "df_subset" + ] }, { "cell_type": "markdown", @@ -161,10 +579,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 30, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "56.95000000000001" + ] + }, + "execution_count": 30, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df[\"Score_3\"].mean()" + ] }, { "cell_type": "markdown", @@ -175,10 +606,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 32, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "88.8" + ] + }, + "execution_count": 32, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df[\"Score_4\"].max()" + ] }, { "cell_type": "markdown", @@ -189,10 +633,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 33, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "36.4" + ] + }, + "execution_count": 33, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df[\"Score_4\"].median()" + ] }, { "cell_type": "markdown", @@ -203,7 +660,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 35, "metadata": {}, "outputs": [], "source": [ @@ -224,10 +681,136 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] + "execution_count": 69, + "metadata": { + "scrolled": true + }, + "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": 69, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pd.DataFrame.from_dict(orders)\n", + "df_from_dict" + ] }, { "cell_type": "markdown", @@ -238,10 +821,26 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] + "execution_count": 70, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Total quantity is: 2978\n", + "Total revenue is: 637.0\n" + ] + } + ], + "source": [ + "total_quantity = df_from_dict[\"Quantity\"].sum()\n", + "print(f'Total quantity is: {total_quantity}')\n", + "total_revenue = df_from_dict[\"Revenue\"].sum()\n", + "print(f'Total revenue is: {total_revenue}')" + ] }, { "cell_type": "markdown", @@ -252,10 +851,21 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 72, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "11.77\n" + ] + } + ], + "source": [ + "difference = df_from_dict[\"UnitPrice\"].max() - df_from_dict[\"UnitPrice\"].min()\n", + "print(difference)" + ] }, { "cell_type": "markdown", @@ -266,7 +876,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 73, "metadata": {}, "outputs": [], "source": [ @@ -285,10 +895,130 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 75, "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": 75, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions.head()" + ] }, { "cell_type": "markdown", @@ -299,10 +1029,32 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 77, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "Serial No. 0\n", + "GRE Score 0\n", + "TOEFL Score 0\n", + "University Rating 0\n", + "SOP 0\n", + "LOR 0\n", + "CGPA 0\n", + "Research 0\n", + "Chance of Admit 0\n", + "dtype: int64" + ] + }, + "execution_count": 77, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions.isnull().sum()" + ] }, { "cell_type": "markdown", @@ -313,31 +1065,267 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 79, "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 Admit
Serial No.
1133711844.54.59.6510.92
2231610433.03.58.0010.72
3332211033.52.58.6710.80
4431410322.03.08.2100.65
5533011554.53.09.3410.90
..............................
38138132411033.53.59.0410.82
38238232510733.03.59.1110.84
38338333011645.04.59.4510.91
38438431210333.54.08.7800.67
38538533311745.04.09.6610.95
\n", + "

385 rows × 9 columns

\n", + "
" + ], + "text/plain": [ + " Serial No. GRE Score TOEFL Score University Rating SOP LOR \\\n", + "Serial No. \n", + "1 1 337 118 4 4.5 4.5 \n", + "2 2 316 104 3 3.0 3.5 \n", + "3 3 322 110 3 3.5 2.5 \n", + "4 4 314 103 2 2.0 3.0 \n", + "5 5 330 115 5 4.5 3.0 \n", + "... ... ... ... ... ... ... \n", + "381 381 324 110 3 3.5 3.5 \n", + "382 382 325 107 3 3.0 3.5 \n", + "383 383 330 116 4 5.0 4.5 \n", + "384 384 312 103 3 3.5 4.0 \n", + "385 385 333 117 4 5.0 4.0 \n", + "\n", + " CGPA Research Chance of Admit \n", + "Serial No. \n", + "1 9.65 1 0.92 \n", + "2 8.00 1 0.72 \n", + "3 8.67 1 0.80 \n", + "4 8.21 0 0.65 \n", + "5 9.34 1 0.90 \n", + "... ... ... ... \n", + "381 9.04 1 0.82 \n", + "382 9.11 1 0.84 \n", + "383 9.45 1 0.91 \n", + "384 8.78 0 0.67 \n", + "385 9.66 1 0.95 \n", + "\n", + "[385 rows x 9 columns]" + ] + }, + "execution_count": 79, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions.set_index(\"Serial No.\",drop = False)" + ] }, { - "cell_type": "code", - "execution_count": null, + "cell_type": "markdown", "metadata": {}, - "outputs": [], - "source": [] + "source": [ + "#### Turns out that GRE Score and CGPA also uniquely identify the data. Show this in the cell below." + ] }, { - "cell_type": "markdown", + "cell_type": "code", + "execution_count": 115, "metadata": {}, + "outputs": [], "source": [ - "\"Turns out that GRE Score and CGPA also uniquely identify the data. Show this in the cell below.\"" + "admissions[\"GRE Score and CGPA\"] = admissions[\"GRE Score\"].astype(str) + \" and \" + admissions[\"CGPA\"].astype(str)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 116, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "True" + ] + }, + "execution_count": 116, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions[\"GRE Score and CGPA\"].is_unique" + ] }, { "cell_type": "markdown", @@ -348,31 +1336,190 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 117, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "condition_1 = admissions[\"CGPA\"] > 9" + ] + }, + { + "cell_type": "code", + "execution_count": 118, + "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", + "
Serial No.GRE ScoreTOEFL ScoreUniversity RatingSOPLORCGPAResearchChance of AdmitGRE Score and CGPA
35735833611944.54.09.6210.95336 and 9.62
282933811843.04.59.4010.91338 and 9.4
38038132411033.53.59.0410.82324 and 9.04
434433911954.54.09.7000.89339 and 9.7
202133411955.04.59.7010.95334 and 9.7
\n", + "
" + ], + "text/plain": [ + " Serial No. GRE Score TOEFL Score University Rating SOP LOR CGPA \\\n", + "357 358 336 119 4 4.5 4.0 9.62 \n", + "28 29 338 118 4 3.0 4.5 9.40 \n", + "380 381 324 110 3 3.5 3.5 9.04 \n", + "43 44 339 119 5 4.5 4.0 9.70 \n", + "20 21 334 119 5 5.0 4.5 9.70 \n", + "\n", + " Research Chance of Admit GRE Score and CGPA \n", + "357 1 0.95 336 and 9.62 \n", + "28 1 0.91 338 and 9.4 \n", + "380 1 0.82 324 and 9.04 \n", + "43 0 0.89 339 and 9.7 \n", + "20 1 0.95 334 and 9.7 " + ] + }, + "execution_count": 118, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions[condition_1].sample(5)" + ] }, { "cell_type": "markdown", "metadata": {}, "source": [ - "#### 4 - Now return all the rows where the CGPA is greater than 9 and the SOP score is less than 3.5. Find the mean chance of admit for these applicants." + "### 4 - Now return all the rows where the CGPA is greater than 9 and the SOP score is less than 3.5. Find the mean chance of admit for these applicants." ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 119, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "condition_2 = admissions[\"SOP\"] < 3.5" + ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 124, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "new_admissions = admissions[condition_1 & condition_2]" + ] + }, + { + "cell_type": "code", + "execution_count": 125, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0.8019999999999999" + ] + }, + "execution_count": 125, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "new_admissions[\"Chance of Admit\"].mean()" + ] }, { "cell_type": "markdown", @@ -384,10 +1531,15 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 131, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "def Toefl (TOEFL_Score):\n", + " if TOEFL_Score > 100:\n", + " return True\n", + " return False" + ] }, { "cell_type": "markdown", @@ -398,31 +1550,508 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 135, "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 AdmitGRE Score and CGPADecision
0133711844.54.59.6510.92337 and 9.65True
1231610433.03.58.0010.72316 and 8.0True
2332211033.52.58.6710.80322 and 8.67True
3431410322.03.08.2100.65314 and 8.21True
4533011554.53.09.3410.90330 and 9.34True
....................................
38038132411033.53.59.0410.82324 and 9.04True
38138232510733.03.59.1110.84325 and 9.11True
38238333011645.04.59.4510.91330 and 9.45True
38338431210333.54.08.7800.67312 and 8.78True
38438533311745.04.09.6610.95333 and 9.66True
\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 GRE Score and CGPA Decision \n", + "0 1 0.92 337 and 9.65 True \n", + "1 1 0.72 316 and 8.0 True \n", + "2 1 0.80 322 and 8.67 True \n", + "3 0 0.65 314 and 8.21 True \n", + "4 1 0.90 330 and 9.34 True \n", + ".. ... ... ... ... \n", + "380 1 0.82 324 and 9.04 True \n", + "381 1 0.84 325 and 9.11 True \n", + "382 1 0.91 330 and 9.45 True \n", + "383 0 0.67 312 and 8.78 True \n", + "384 1 0.95 333 and 9.66 True \n", + "\n", + "[385 rows x 11 columns]" + ] + }, + "execution_count": 135, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions[\"Decision\"] = admissions.apply(lambda x: Toefl(x[\"TOEFL Score\"]), axis = 1)\n", + "admissions" + ] }, { - "cell_type": "code", - "execution_count": null, + "cell_type": "markdown", "metadata": {}, - "outputs": [], - "source": [] + "source": [ + "Create a column called `decision2` in the `admissions` dataframe. Assign 1 to this column if the value of `SOP` is greater than 3 and 0 otherwise. \n", + "HINT (use np.where)" + ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 141, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "admissions[\"decision2\"] = np.where(admissions['SOP'] > 3,1,0)" + ] }, { - "cell_type": "markdown", + "cell_type": "code", + "execution_count": 142, "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 AdmitGRE Score and CGPADecisiondecision2
0133711844.54.59.6510.92337 and 9.65True1
1231610433.03.58.0010.72316 and 8.0True0
2332211033.52.58.6710.80322 and 8.67True1
3431410322.03.08.2100.65314 and 8.21True0
4533011554.53.09.3410.90330 and 9.34True1
.......................................
38038132411033.53.59.0410.82324 and 9.04True1
38138232510733.03.59.1110.84325 and 9.11True0
38238333011645.04.59.4510.91330 and 9.45True1
38338431210333.54.08.7800.67312 and 8.78True1
38438533311745.04.09.6610.95333 and 9.66True1
\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 GRE Score and CGPA Decision decision2 \n", + "0 1 0.92 337 and 9.65 True 1 \n", + "1 1 0.72 316 and 8.0 True 0 \n", + "2 1 0.80 322 and 8.67 True 1 \n", + "3 0 0.65 314 and 8.21 True 0 \n", + "4 1 0.90 330 and 9.34 True 1 \n", + ".. ... ... ... ... ... \n", + "380 1 0.82 324 and 9.04 True 1 \n", + "381 1 0.84 325 and 9.11 True 0 \n", + "382 1 0.91 330 and 9.45 True 1 \n", + "383 0 0.67 312 and 8.78 True 1 \n", + "384 1 0.95 333 and 9.66 True 1 \n", + "\n", + "[385 rows x 12 columns]" + ] + }, + "execution_count": 142, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "Create a column called `decision2` in the `admissions` dataframe. Assign 1 to this column if the value of `SOP` is greater than 3 and 0 otherwise. \n", - "HINT (use np.where)" + "admissions" ] }, { @@ -435,9 +2064,9 @@ ], "metadata": { "kernelspec": { - "display_name": "Python 3 (ipykernel)", + "display_name": "ironhack", "language": "python", - "name": "python3" + "name": "ironhack" }, "language_info": { "codemirror_mode": { @@ -449,7 +2078,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.10.8" + "version": "3.11.5" }, "toc": { "base_numbering": "",