diff --git a/your-code/pandas_1.ipynb b/your-code/pandas_1.ipynb index 4f428ac..71ce2cf 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": [ + "my_series = pd.Series(lst)\n" + ] }, { "cell_type": "markdown", @@ -60,10 +62,23 @@ }, { "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": [ + "my_series[2]\n" + ] }, { "cell_type": "markdown", @@ -74,7 +89,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 5, "metadata": {}, "outputs": [], "source": [ @@ -92,10 +107,145 @@ }, { "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": [ + "df = pd.DataFrame(b)\n", + "df" + ] }, { "cell_type": "markdown", @@ -106,7 +256,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 7, "metadata": {}, "outputs": [], "source": [ @@ -124,19 +274,154 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 8, "metadata": {}, "outputs": [], "source": [ - "colnames = ['Score_1', 'Score_2', 'Score_3', 'Score_4', 'Score_5']" + "colnames = ['Score_1', 'Score_2', 'Score_3', 'Score_4', 'Score_5']\n" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 9, "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": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.columns = colnames\n", + "df" + ] }, { "cell_type": "markdown", @@ -147,10 +432,12 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 10, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "df_sub = df[[\"Score_1\", \"Score_3\", \"Score_5\"]]\n" + ] }, { "cell_type": "markdown", @@ -161,10 +448,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 11, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "56.95000000000001" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df[\"Score_3\"].mean()\n" + ] }, { "cell_type": "markdown", @@ -175,10 +475,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 12, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "88.8" + ] + }, + "execution_count": 12, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df[\"Score_4\"].max()\n" + ] }, { "cell_type": "markdown", @@ -189,10 +502,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 13, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "40.75" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df[\"Score_2\"].median()\n" + ] }, { "cell_type": "markdown", @@ -203,7 +529,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 14, "metadata": {}, "outputs": [], "source": [ @@ -224,10 +550,134 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 15, "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": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "orders_df = pd.DataFrame(orders)\n", + "orders_df\n" + ] }, { "cell_type": "markdown", @@ -238,10 +688,25 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 16, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "637.0" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "orders_df.Quantity.sum()\n", + "\n", + "orders_df.Revenue.sum()\n" + ] }, { "cell_type": "markdown", @@ -252,10 +717,20 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 17, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "11.77\n" + ] + } + ], + "source": [ + "print (orders_df.UnitPrice.max() - orders_df.UnitPrice.min())\n" + ] }, { "cell_type": "markdown", @@ -266,7 +741,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 18, "metadata": {}, "outputs": [], "source": [ @@ -285,10 +760,130 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 19, "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": 19, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions.head()\n" + ] }, { "cell_type": "markdown", @@ -299,10 +894,32 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 20, "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": 20, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions.isna().sum()\n" + ] }, { "cell_type": "markdown", @@ -313,31 +930,695 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 42, "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": 42, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions.set_index(\"Serial No.\", drop = False)\n", + "\n" + ] }, { - "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": 43, "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", + "
Serial No.GRE ScoreTOEFL ScoreUniversity RatingSOPLORCGPAResearchChance of Admit
CGPA
9.65133711844.54.59.6510.92
8.00231610433.03.58.0010.72
8.67332211033.52.58.6710.80
8.21431410322.03.08.2100.65
9.34533011554.53.09.3410.90
..............................
9.0438132411033.53.59.0410.82
9.1138232510733.03.59.1110.84
9.4538333011645.04.59.4510.91
8.7838431210333.54.08.7800.67
9.6638533311745.04.09.6610.95
\n", + "

385 rows × 9 columns

\n", + "
" + ], + "text/plain": [ + " Serial No. GRE Score TOEFL Score University Rating SOP LOR CGPA \\\n", + "CGPA \n", + "9.65 1 337 118 4 4.5 4.5 9.65 \n", + "8.00 2 316 104 3 3.0 3.5 8.00 \n", + "8.67 3 322 110 3 3.5 2.5 8.67 \n", + "8.21 4 314 103 2 2.0 3.0 8.21 \n", + "9.34 5 330 115 5 4.5 3.0 9.34 \n", + "... ... ... ... ... ... ... ... \n", + "9.04 381 324 110 3 3.5 3.5 9.04 \n", + "9.11 382 325 107 3 3.0 3.5 9.11 \n", + "9.45 383 330 116 4 5.0 4.5 9.45 \n", + "8.78 384 312 103 3 3.5 4.0 8.78 \n", + "9.66 385 333 117 4 5.0 4.0 9.66 \n", + "\n", + " Research Chance of Admit \n", + "CGPA \n", + "9.65 1 0.92 \n", + "8.00 1 0.72 \n", + "8.67 1 0.80 \n", + "8.21 0 0.65 \n", + "9.34 1 0.90 \n", + "... ... ... \n", + "9.04 1 0.82 \n", + "9.11 1 0.84 \n", + "9.45 1 0.91 \n", + "8.78 0 0.67 \n", + "9.66 1 0.95 \n", + "\n", + "[385 rows x 9 columns]" + ] + }, + "execution_count": 43, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "\"Turns out that GRE Score and CGPA also uniquely identify the data. Show this in the cell below.\"" + "admissions.set_index(\"CGPA\", drop = False)\n" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 44, "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
GRE Score
337133711844.54.59.6510.92
316231610433.03.58.0010.72
322332211033.52.58.6710.80
314431410322.03.08.2100.65
330533011554.53.09.3410.90
..............................
32438132411033.53.59.0410.82
32538232510733.03.59.1110.84
33038333011645.04.59.4510.91
31238431210333.54.08.7800.67
33338533311745.04.09.6610.95
\n", + "

385 rows × 9 columns

\n", + "
" + ], + "text/plain": [ + " Serial No. GRE Score TOEFL Score University Rating SOP LOR \\\n", + "GRE Score \n", + "337 1 337 118 4 4.5 4.5 \n", + "316 2 316 104 3 3.0 3.5 \n", + "322 3 322 110 3 3.5 2.5 \n", + "314 4 314 103 2 2.0 3.0 \n", + "330 5 330 115 5 4.5 3.0 \n", + "... ... ... ... ... ... ... \n", + "324 381 324 110 3 3.5 3.5 \n", + "325 382 325 107 3 3.0 3.5 \n", + "330 383 330 116 4 5.0 4.5 \n", + "312 384 312 103 3 3.5 4.0 \n", + "333 385 333 117 4 5.0 4.0 \n", + "\n", + " CGPA Research Chance of Admit \n", + "GRE Score \n", + "337 9.65 1 0.92 \n", + "316 8.00 1 0.72 \n", + "322 8.67 1 0.80 \n", + "314 8.21 0 0.65 \n", + "330 9.34 1 0.90 \n", + "... ... ... ... \n", + "324 9.04 1 0.82 \n", + "325 9.11 1 0.84 \n", + "330 9.45 1 0.91 \n", + "312 8.78 0 0.67 \n", + "333 9.66 1 0.95 \n", + "\n", + "[385 rows x 9 columns]" + ] + }, + "execution_count": 44, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions.set_index(\"GRE Score\", drop = False)\n" + ] }, { "cell_type": "markdown", @@ -348,10 +1629,220 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 45, "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", + "
Serial No.GRE ScoreTOEFL ScoreUniversity RatingSOPLORCGPAResearchChance of Admit
0133711844.54.59.6510.92
4533011554.53.09.3410.90
101132811244.04.59.1010.78
192032811655.05.09.5010.94
202133411955.04.59.7010.95
..............................
37938032911144.54.09.2310.89
38038132411033.53.59.0410.82
38138232510733.03.59.1110.84
38238333011645.04.59.4510.91
38438533311745.04.09.6610.95
\n", + "

101 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", + "4 5 330 115 5 4.5 3.0 9.34 \n", + "10 11 328 112 4 4.0 4.5 9.10 \n", + "19 20 328 116 5 5.0 5.0 9.50 \n", + "20 21 334 119 5 5.0 4.5 9.70 \n", + ".. ... ... ... ... ... ... ... \n", + "379 380 329 111 4 4.5 4.0 9.23 \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", + "384 385 333 117 4 5.0 4.0 9.66 \n", + "\n", + " Research Chance of Admit \n", + "0 1 0.92 \n", + "4 1 0.90 \n", + "10 1 0.78 \n", + "19 1 0.94 \n", + "20 1 0.95 \n", + ".. ... ... \n", + "379 1 0.89 \n", + "380 1 0.82 \n", + "381 1 0.84 \n", + "382 1 0.91 \n", + "384 1 0.95 \n", + "\n", + "[101 rows x 9 columns]" + ] + }, + "execution_count": 45, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "con_cgpa = admissions.CGPA > 9\n", + "con_res = admissions.Research == 1 \n", + "\n", + "admissions[con_cgpa & con_res]\n" + ] }, { "cell_type": "markdown", @@ -362,17 +1853,25 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, + "execution_count": 46, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "0.8019999999999999" + ] + }, + "execution_count": 46, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "chance = admissions[con_cgpa & (admissions.SOP < 3.5)]\n", + "\n", + "chance[\"Chance of Admit\"].mean()\n" + ] }, { "cell_type": "markdown", @@ -384,10 +1883,293 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 77, "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \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 AdmitTOEFL > 100
18418533611854.55.09.5310.94True
10710830110733.53.58.3410.62True
19219334012054.54.59.9110.97True
20520633011655.04.59.3610.93True
29229332110933.53.58.8010.74True
16917032911944.54.59.1610.90True
616232511243.53.58.9200.55True
20220333812045.05.09.6610.95True
697031410844.54.09.0410.84True
91032711144.04.59.0010.84True
33433531310132.53.08.0400.62True
23123232511433.53.09.0410.76True
54553009913.02.06.8010.36False
24824931210433.54.08.0900.71True
73743019923.02.08.2200.64False
\n", + "
" + ], + "text/plain": [ + " Serial No. GRE Score TOEFL Score University Rating SOP LOR CGPA \\\n", + "184 185 336 118 5 4.5 5.0 9.53 \n", + "107 108 301 107 3 3.5 3.5 8.34 \n", + "192 193 340 120 5 4.5 4.5 9.91 \n", + "205 206 330 116 5 5.0 4.5 9.36 \n", + "292 293 321 109 3 3.5 3.5 8.80 \n", + "169 170 329 119 4 4.5 4.5 9.16 \n", + "61 62 325 112 4 3.5 3.5 8.92 \n", + "202 203 338 120 4 5.0 5.0 9.66 \n", + "69 70 314 108 4 4.5 4.0 9.04 \n", + "9 10 327 111 4 4.0 4.5 9.00 \n", + "334 335 313 101 3 2.5 3.0 8.04 \n", + "231 232 325 114 3 3.5 3.0 9.04 \n", + "54 55 300 99 1 3.0 2.0 6.80 \n", + "248 249 312 104 3 3.5 4.0 8.09 \n", + "73 74 301 99 2 3.0 2.0 8.22 \n", + "\n", + " Research Chance of Admit TOEFL > 100 \n", + "184 1 0.94 True \n", + "107 1 0.62 True \n", + "192 1 0.97 True \n", + "205 1 0.93 True \n", + "292 1 0.74 True \n", + "169 1 0.90 True \n", + "61 0 0.55 True \n", + "202 1 0.95 True \n", + "69 1 0.84 True \n", + "9 1 0.84 True \n", + "334 0 0.62 True \n", + "231 1 0.76 True \n", + "54 1 0.36 False \n", + "248 0 0.71 True \n", + "73 0 0.64 False " + ] + }, + "execution_count": 77, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "def toefl_calc(x): \n", + " if x > 100: \n", + " return True \n", + " else: \n", + " return False \n", + " \n", + "admissions[\"TOEFL > 100\"] = admissions[\"TOEFL Score\"].apply(toefl_calc) \n", + "admissions.sample(15)\n" + ] }, { "cell_type": "markdown", @@ -398,46 +2180,315 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 89, "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", + "
Serial No.GRE ScoreTOEFL ScoreUniversity RatingSOPLORCGPAResearchChance of AdmitDecisiondecision2
14314433411444.04.09.4310.93True1
30830931410722.54.08.2700.72True0
14814931210933.03.08.6900.77True0
2332211033.52.58.6710.80True1
282933811843.04.59.4010.91True0
\n", + "
" + ], + "text/plain": [ + " Serial No. GRE Score TOEFL Score University Rating SOP LOR CGPA \\\n", + "143 144 334 114 4 4.0 4.0 9.43 \n", + "308 309 314 107 2 2.5 4.0 8.27 \n", + "148 149 312 109 3 3.0 3.0 8.69 \n", + "2 3 322 110 3 3.5 2.5 8.67 \n", + "28 29 338 118 4 3.0 4.5 9.40 \n", + "\n", + " Research Chance of Admit Decision decision2 \n", + "143 1 0.93 True 1 \n", + "308 0 0.72 True 0 \n", + "148 0 0.77 True 0 \n", + "2 1 0.80 True 1 \n", + "28 1 0.91 True 0 " + ] + }, + "execution_count": 89, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions.rename(columns = {\"TOEFL > 100\" : \"Decision\"}, inplace = True) \n", + "admissions.sample(5)\n" + ] }, { - "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": 82, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "import numpy as np \n" + ] }, { - "cell_type": "markdown", + "cell_type": "code", + "execution_count": 85, "metadata": {}, + "outputs": [], "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[\"decision2\"] = np.where(admissions[\"SOP\"] > 3, 1, 0)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 88, "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", + "
Serial No.GRE ScoreTOEFL ScoreUniversity RatingSOPLORCGPAResearchChance of AdmitDecisiondecision2
12812933311354.04.09.2810.89True1
404132611354.54.09.4010.91True1
21922031910633.52.58.3310.74True1
28628730511233.03.58.6500.71True0
13013131610021.53.08.1610.71False0
\n", + "
" + ], + "text/plain": [ + " Serial No. GRE Score TOEFL Score University Rating SOP LOR CGPA \\\n", + "128 129 333 113 5 4.0 4.0 9.28 \n", + "40 41 326 113 5 4.5 4.0 9.40 \n", + "219 220 319 106 3 3.5 2.5 8.33 \n", + "286 287 305 112 3 3.0 3.5 8.65 \n", + "130 131 316 100 2 1.5 3.0 8.16 \n", + "\n", + " Research Chance of Admit Decision decision2 \n", + "128 1 0.89 True 1 \n", + "40 1 0.91 True 1 \n", + "219 1 0.74 True 1 \n", + "286 0 0.71 True 0 \n", + "130 1 0.71 False 0 " + ] + }, + "execution_count": 88, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions.sample(5)" + ] } ], "metadata": { "kernelspec": { - "display_name": "Python 3 (ipykernel)", + "display_name": "ironhack", "language": "python", - "name": "python3" + "name": "ironhack" }, "language_info": { "codemirror_mode": { @@ -449,7 +2500,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.10.8" + "version": "3.11.5" }, "toc": { "base_numbering": "",