From f93741e9b0b7bdc9a62684f33b25fb58998a0d93 Mon Sep 17 00:00:00 2001 From: "patricia.saez" Date: Wed, 18 Oct 2023 17:09:32 +0200 Subject: [PATCH] Patricia S. all donegit add pandas_1.ipynb --- your-code/pandas_1.ipynb | 2005 ++++++++++++++++++++++++++++++++++++-- 1 file changed, 1927 insertions(+), 78 deletions(-) diff --git a/your-code/pandas_1.ipynb b/your-code/pandas_1.ipynb index 4f428ac..696d671 100644 --- a/your-code/pandas_1.ipynb +++ b/your-code/pandas_1.ipynb @@ -44,10 +44,39 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "p_s =pd.Series(lst)" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "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\n" + ] + } + ], + "source": [ + "print(p_s)" + ] }, { "cell_type": "markdown", @@ -60,10 +89,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "74.4" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "p_s[2]" + ] }, { "cell_type": "markdown", @@ -74,7 +116,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 6, "metadata": {}, "outputs": [], "source": [ @@ -92,10 +134,145 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 7, "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": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pf = pd.DataFrame(b)\n", + "pf" + ] }, { "cell_type": "markdown", @@ -106,7 +283,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 8, "metadata": {}, "outputs": [], "source": [ @@ -124,7 +301,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 9, "metadata": {}, "outputs": [], "source": [ @@ -133,10 +310,145 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 10, "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": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pf.columns=colnames\n", + "pf" + ] }, { "cell_type": "markdown", @@ -147,10 +459,123 @@ }, { "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_2Score_3
053.195.067.5
161.340.830.8
220.673.244.2
357.40.196.1
483.620.585.4
549.069.00.1
623.340.795.0
727.626.453.8
896.696.453.4
973.739.043.2
\n", + "
" + ], + "text/plain": [ + " Score_1 Score_2 Score_3\n", + "0 53.1 95.0 67.5\n", + "1 61.3 40.8 30.8\n", + "2 20.6 73.2 44.2\n", + "3 57.4 0.1 96.1\n", + "4 83.6 20.5 85.4\n", + "5 49.0 69.0 0.1\n", + "6 23.3 40.7 95.0\n", + "7 27.6 26.4 53.8\n", + "8 96.6 96.4 53.4\n", + "9 73.7 39.0 43.2" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pf_subset_135=pf[['Score_1','Score_2','Score_3']]\n", + "pf_subset_135" + ] }, { "cell_type": "markdown", @@ -161,10 +586,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 12, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "56.95000000000001" + ] + }, + "execution_count": 12, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pf.Score_3.mean()" + ] }, { "cell_type": "markdown", @@ -175,10 +613,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 13, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "88.8" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pf.Score_4.max()" + ] }, { "cell_type": "markdown", @@ -189,10 +640,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 14, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "40.75" + ] + }, + "execution_count": 14, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pf.Score_2.median()" + ] }, { "cell_type": "markdown", @@ -203,7 +667,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 15, "metadata": {}, "outputs": [], "source": [ @@ -224,10 +688,134 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 16, "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": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df_products=pd.DataFrame(orders)\n", + "df_products" + ] }, { "cell_type": "markdown", @@ -238,10 +826,20 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 17, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "the total quantity ordered is: 2978 and the total amount of Revenue: 637.0\n" + ] + } + ], + "source": [ + "print(\"the total quantity ordered is: \", df_products[\"Quantity\"].sum(), \"and the total amount of Revenue: \",df_products[\"Revenue\"].sum())" + ] }, { "cell_type": "markdown", @@ -252,10 +850,29 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] + "execution_count": 18, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "the price of the most expensive is: 11.95\n", + "the price of the less expensive is: 0.18\n", + "the difference between both is : 11.77\n" + ] + } + ], + "source": [ + "most_expensive = df_products['UnitPrice'].max()\n", + "less_expensive = df_products['UnitPrice'].min()\n", + "dif = most_expensive - less_expensive\n", + "print (\"the price of the most expensive is: \", most_expensive)\n", + "print (\"the price of the less expensive is: \", less_expensive)\n", + "print (\"the difference between both is : \", dif)" + ] }, { "cell_type": "markdown", @@ -266,7 +883,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 19, "metadata": {}, "outputs": [], "source": [ @@ -285,10 +902,130 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 20, "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": 20, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions.head()" + ] }, { "cell_type": "markdown", @@ -299,10 +1036,32 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 21, "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": 21, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions.isnull().sum()" + ] }, { "cell_type": "markdown", @@ -313,17 +1072,347 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 22, "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": 22, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions.head()" + ] }, { "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
GRE ScoreTOEFL ScoreUniversity RatingSOPLORCGPAResearchChance of Admit
Serial No.
133711844.54.59.6510.92
231610433.03.58.0010.72
332211033.52.58.6710.80
431410322.03.08.2100.65
533011554.53.09.3410.90
...........................
38132411033.53.59.0410.82
38232510733.03.59.1110.84
38333011645.04.59.4510.91
38431210333.54.08.7800.67
38533311745.04.09.6610.95
\n", + "

385 rows × 8 columns

\n", + "
" + ], + "text/plain": [ + " GRE Score TOEFL Score University Rating SOP LOR CGPA \\\n", + "Serial No. \n", + "1 337 118 4 4.5 4.5 9.65 \n", + "2 316 104 3 3.0 3.5 8.00 \n", + "3 322 110 3 3.5 2.5 8.67 \n", + "4 314 103 2 2.0 3.0 8.21 \n", + "5 330 115 5 4.5 3.0 9.34 \n", + "... ... ... ... ... ... ... \n", + "381 324 110 3 3.5 3.5 9.04 \n", + "382 325 107 3 3.0 3.5 9.11 \n", + "383 330 116 4 5.0 4.5 9.45 \n", + "384 312 103 3 3.5 4.0 8.78 \n", + "385 333 117 4 5.0 4.0 9.66 \n", + "\n", + " Research Chance of Admit \n", + "Serial No. \n", + "1 1 0.92 \n", + "2 1 0.72 \n", + "3 1 0.80 \n", + "4 0 0.65 \n", + "5 1 0.90 \n", + "... ... ... \n", + "381 1 0.82 \n", + "382 1 0.84 \n", + "383 1 0.91 \n", + "384 0 0.67 \n", + "385 1 0.95 \n", + "\n", + "[385 rows x 8 columns]" + ] + }, + "execution_count": 23, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#df.set_index(\"year\", inplace=False)\n", + "admissions.set_index(\"Serial No.\", inplace = True)\n", + "admissions" + ] }, { "cell_type": "markdown", @@ -334,10 +1423,25 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 36, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "0" + ] + }, + "execution_count": 36, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions.duplicated(subset =['GRE Score', 'CGPA']).sum()\n", + "# as when checking for dupplicate rows just using the two columns GRE Score and CGPA the sum of the booleans is 0 this\n", + "# means that all are faulse => the combination of these two column leads to unique values for each row" + ] }, { "cell_type": "markdown", @@ -348,10 +1452,140 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 46, "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", + "
GRE ScoreTOEFL ScoreUniversity RatingSOPLORCGPAResearchChance of Admit
Serial No.
133711844.54.59.6510.92
533011554.53.09.3410.90
1132811244.04.59.1010.78
2032811655.05.09.5010.94
2133411955.04.59.7010.95
\n", + "
" + ], + "text/plain": [ + " GRE Score TOEFL Score University Rating SOP LOR CGPA \\\n", + "Serial No. \n", + "1 337 118 4 4.5 4.5 9.65 \n", + "5 330 115 5 4.5 3.0 9.34 \n", + "11 328 112 4 4.0 4.5 9.10 \n", + "20 328 116 5 5.0 5.0 9.50 \n", + "21 334 119 5 5.0 4.5 9.70 \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 " + ] + }, + "execution_count": 46, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "cond_1 = admissions['CGPA'] > 9\n", + "cond_2 = admissions['Research'] > 0\n", + "test_answer = admissions[cond_1 & cond_2]\n", + "test_answer.head()" + ] }, { "cell_type": "markdown", @@ -362,17 +1596,160 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 51, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "The mean chance of admit for these applicants is; 0.8019999999999999\n" + ] + } + ], + "source": [ + "cond_1 = admissions['CGPA'] > 9\n", + "cond_3 = admissions['SOP'] < 3.5\n", + "CGPA_9_SOP_35= admissions[cond_1 & cond_3]\n", + "mean_CGPA_9_SOP_35 = CGPA_9_SOP_35['Chance of Admit'].mean()\n", + "print('The mean chance of admit for these applicants is; ', mean_CGPA_9_SOP_35)" + ] }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] + "execution_count": 48, + "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", + "
GRE ScoreTOEFL ScoreUniversity RatingSOPLORCGPAResearchChance of Admit
Serial No.
2933811843.04.59.4010.91
6332711433.03.09.0200.61
14132611433.03.09.1110.83
21832411143.03.09.0110.82
38232510733.03.59.1110.84
\n", + "
" + ], + "text/plain": [ + " GRE Score TOEFL Score University Rating SOP LOR CGPA \\\n", + "Serial No. \n", + "29 338 118 4 3.0 4.5 9.40 \n", + "63 327 114 3 3.0 3.0 9.02 \n", + "141 326 114 3 3.0 3.0 9.11 \n", + "218 324 111 4 3.0 3.0 9.01 \n", + "382 325 107 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": 48, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "CGPA_9_SOP_35" + ] }, { "cell_type": "markdown", @@ -384,10 +1761,16 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 52, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "def tofle_crieteria (tofle):\n", + " if tofle > 100:\n", + " return True\n", + " else:\n", + " return False" + ] }, { "cell_type": "markdown", @@ -398,31 +1781,497 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 53, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "admissions['Decision'] = admissions ['TOEFL Score'].apply(tofle_crieteria)" + ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 55, "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", + "
GRE ScoreTOEFL ScoreUniversity RatingSOPLORCGPAResearchChance of AdmitDecision
Serial No.
133711844.54.59.6510.92True
231610433.03.58.0010.72True
332211033.52.58.6710.80True
431410322.03.08.2100.65True
533011554.53.09.3410.90True
..............................
38132411033.53.59.0410.82True
38232510733.03.59.1110.84True
38333011645.04.59.4510.91True
38431210333.54.08.7800.67True
38533311745.04.09.6610.95True
\n", + "

385 rows × 9 columns

\n", + "
" + ], + "text/plain": [ + " GRE Score TOEFL Score University Rating SOP LOR CGPA \\\n", + "Serial No. \n", + "1 337 118 4 4.5 4.5 9.65 \n", + "2 316 104 3 3.0 3.5 8.00 \n", + "3 322 110 3 3.5 2.5 8.67 \n", + "4 314 103 2 2.0 3.0 8.21 \n", + "5 330 115 5 4.5 3.0 9.34 \n", + "... ... ... ... ... ... ... \n", + "381 324 110 3 3.5 3.5 9.04 \n", + "382 325 107 3 3.0 3.5 9.11 \n", + "383 330 116 4 5.0 4.5 9.45 \n", + "384 312 103 3 3.5 4.0 8.78 \n", + "385 333 117 4 5.0 4.0 9.66 \n", + "\n", + " Research Chance of Admit Decision \n", + "Serial No. \n", + "1 1 0.92 True \n", + "2 1 0.72 True \n", + "3 1 0.80 True \n", + "4 0 0.65 True \n", + "5 1 0.90 True \n", + "... ... ... ... \n", + "381 1 0.82 True \n", + "382 1 0.84 True \n", + "383 1 0.91 True \n", + "384 0 0.67 True \n", + "385 1 0.95 True \n", + "\n", + "[385 rows x 9 columns]" + ] + }, + "execution_count": 55, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "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": 56, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "admissions['decision2'] = admissions['SOP'].apply(lambda x: 1 if x >3 else 0)" + ] }, { - "cell_type": "markdown", + "cell_type": "code", + "execution_count": 57, "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", + "
GRE ScoreTOEFL ScoreUniversity RatingSOPLORCGPAResearchChance of AdmitDecisiondecision2
Serial No.
133711844.54.59.6510.92True1
231610433.03.58.0010.72True0
332211033.52.58.6710.80True1
431410322.03.08.2100.65True0
533011554.53.09.3410.90True1
.................................
38132411033.53.59.0410.82True1
38232510733.03.59.1110.84True0
38333011645.04.59.4510.91True1
38431210333.54.08.7800.67True1
38533311745.04.09.6610.95True1
\n", + "

385 rows × 10 columns

\n", + "
" + ], + "text/plain": [ + " GRE Score TOEFL Score University Rating SOP LOR CGPA \\\n", + "Serial No. \n", + "1 337 118 4 4.5 4.5 9.65 \n", + "2 316 104 3 3.0 3.5 8.00 \n", + "3 322 110 3 3.5 2.5 8.67 \n", + "4 314 103 2 2.0 3.0 8.21 \n", + "5 330 115 5 4.5 3.0 9.34 \n", + "... ... ... ... ... ... ... \n", + "381 324 110 3 3.5 3.5 9.04 \n", + "382 325 107 3 3.0 3.5 9.11 \n", + "383 330 116 4 5.0 4.5 9.45 \n", + "384 312 103 3 3.5 4.0 8.78 \n", + "385 333 117 4 5.0 4.0 9.66 \n", + "\n", + " Research Chance of Admit Decision decision2 \n", + "Serial No. \n", + "1 1 0.92 True 1 \n", + "2 1 0.72 True 0 \n", + "3 1 0.80 True 1 \n", + "4 0 0.65 True 0 \n", + "5 1 0.90 True 1 \n", + "... ... ... ... ... \n", + "381 1 0.82 True 1 \n", + "382 1 0.84 True 0 \n", + "383 1 0.91 True 1 \n", + "384 0 0.67 True 1 \n", + "385 1 0.95 True 1 \n", + "\n", + "[385 rows x 10 columns]" + ] + }, + "execution_count": 57, + "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 +2284,9 @@ ], "metadata": { "kernelspec": { - "display_name": "Python 3 (ipykernel)", + "display_name": "ironhack", "language": "python", - "name": "python3" + "name": "ironhack" }, "language_info": { "codemirror_mode": { @@ -449,7 +2298,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.10.8" + "version": "3.11.5" }, "toc": { "base_numbering": "",