diff --git a/your-code/pandas_1.ipynb b/your-code/pandas_1.ipynb index 4f428ac..5725464 100644 --- a/your-code/pandas_1.ipynb +++ b/your-code/pandas_1.ipynb @@ -18,7 +18,7 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 100, "metadata": {}, "outputs": [], "source": [ @@ -35,7 +35,7 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 56, "metadata": {}, "outputs": [], "source": [ @@ -44,10 +44,12 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 57, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "a = pd.Series(lst)" + ] }, { "cell_type": "markdown", @@ -60,10 +62,24 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 105, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "74.4" + ] + }, + "execution_count": 105, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s = pd.Series(a)\n", + "s[2]" + ] }, { "cell_type": "markdown", @@ -74,7 +90,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 106, "metadata": {}, "outputs": [], "source": [ @@ -92,10 +108,12 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 123, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "df = pd.DataFrame(b)" + ] }, { "cell_type": "markdown", @@ -106,7 +124,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 98, "metadata": {}, "outputs": [], "source": [ @@ -124,7 +142,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 66, "metadata": {}, "outputs": [], "source": [ @@ -133,10 +151,153 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 132, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "df.rename({0:\"Score_1\", 1:\"Score_2\", 2:\"Score_3\", 3:\"Score_4\", 4:\"Score_5\"}, axis=1, inplace=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 133, + "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", + "
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": 133, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df" + ] }, { "cell_type": "markdown", @@ -147,10 +308,123 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 136, "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": 136, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df_scores = df[[\"Score_1\", \"Score_3\", \"Score_5\"]]\n", + "df_scores" + ] }, { "cell_type": "markdown", @@ -161,10 +435,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 94, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "56.95000000000001" + ] + }, + "execution_count": 94, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "mean_value = raw['Score_3'].mean()" + ] }, { "cell_type": "markdown", @@ -175,10 +462,12 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 92, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "max_value = raw['Score_4'].max()" + ] }, { "cell_type": "markdown", @@ -189,10 +478,12 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 93, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "median_values = raw['Score_2'].median()" + ] }, { "cell_type": "markdown", @@ -203,7 +494,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 144, "metadata": {}, "outputs": [], "source": [ @@ -224,10 +515,134 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 145, "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": 145, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "product_orders = pd.DataFrame(orders)\n", + "product_orders" + ] }, { "cell_type": "markdown", @@ -238,10 +653,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 152, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "The total quantity is: 2978 and the total revenue is: 637.0\n" + ] + } + ], + "source": [ + "total_quantity = product_orders[\"Quantity\"].sum()\n", + "total_revenue = product_orders[\"Revenue\"].sum()\n", + "\n", + "print(f\"The total quantity is: {total_quantity} and the total revenue is: {total_revenue}\")" + ] }, { "cell_type": "markdown", @@ -252,10 +680,40 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 156, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "The most expensive price is: 11.95 and the least expensive proice is: 0.18\n" + ] + } + ], + "source": [ + "most_espensive = product_orders['UnitPrice'].max()\n", + "least_expensive = product_orders['UnitPrice'].min()\n", + "\n", + "print(f\"The most expensive price is: {most_espensive} and the least expensive proice is: {least_expensive}\")" + ] + }, + { + "cell_type": "code", + "execution_count": 157, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "11.77\n" + ] + } + ], + "source": [ + "print(most_espensive - least_expensive)" + ] }, { "cell_type": "markdown", @@ -266,7 +724,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 158, "metadata": {}, "outputs": [], "source": [ @@ -285,10 +743,130 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 160, "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": 160, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions.head()" + ] }, { "cell_type": "markdown", @@ -299,10 +877,217 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 161, "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
0FalseFalseFalseFalseFalseFalseFalseFalseFalse
1FalseFalseFalseFalseFalseFalseFalseFalseFalse
2FalseFalseFalseFalseFalseFalseFalseFalseFalse
3FalseFalseFalseFalseFalseFalseFalseFalseFalse
4FalseFalseFalseFalseFalseFalseFalseFalseFalse
..............................
380FalseFalseFalseFalseFalseFalseFalseFalseFalse
381FalseFalseFalseFalseFalseFalseFalseFalseFalse
382FalseFalseFalseFalseFalseFalseFalseFalseFalse
383FalseFalseFalseFalseFalseFalseFalseFalseFalse
384FalseFalseFalseFalseFalseFalseFalseFalseFalse
\n", + "

385 rows × 9 columns

\n", + "
" + ], + "text/plain": [ + " Serial No. GRE Score TOEFL Score University Rating SOP LOR \\\n", + "0 False False False False False False \n", + "1 False False False False False False \n", + "2 False False False False False False \n", + "3 False False False False False False \n", + "4 False False False False False False \n", + ".. ... ... ... ... ... ... \n", + "380 False False False False False False \n", + "381 False False False False False False \n", + "382 False False False False False False \n", + "383 False False False False False False \n", + "384 False False False False False False \n", + "\n", + " CGPA Research Chance of Admit \n", + "0 False False False \n", + "1 False False False \n", + "2 False False False \n", + "3 False False False \n", + "4 False False False \n", + ".. ... ... ... \n", + "380 False False False \n", + "381 False False False \n", + "382 False False False \n", + "383 False False False \n", + "384 False False False \n", + "\n", + "[385 rows x 9 columns]" + ] + }, + "execution_count": 161, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pd.isnull(admissions)" + ] }, { "cell_type": "markdown", @@ -313,17 +1098,25 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 164, "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "ename": "KeyError", + "evalue": "\"None of ['Serial No.'] are in the columns\"", + "output_type": "error", + "traceback": [ + "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[1;31mKeyError\u001b[0m Traceback (most recent call last)", + "\u001b[1;32m~\\AppData\\Local\\Temp\\ipykernel_17520\\3039814691.py\u001b[0m in \u001b[0;36m?\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0madmissions\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mset_index\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"Serial No.\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minplace\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mTrue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", + "\u001b[1;32m~\\miniconda3\\envs\\ironhack\\Lib\\site-packages\\pandas\\core\\frame.py\u001b[0m in \u001b[0;36m?\u001b[1;34m(self, keys, drop, append, inplace, verify_integrity)\u001b[0m\n\u001b[0;32m 5869\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mfound\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5870\u001b[0m \u001b[0mmissing\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mcol\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5871\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5872\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mmissing\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 5873\u001b[1;33m \u001b[1;32mraise\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34mf\"None of {missing} are in the columns\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 5874\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5875\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0minplace\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5876\u001b[0m \u001b[0mframe\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;31mKeyError\u001b[0m: \"None of ['Serial No.'] are in the columns\"" + ] + } + ], + "source": [ + "admissions.set_index(\"Serial No.\", inplace=True)" + ] }, { "cell_type": "markdown", @@ -334,10 +1127,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 169, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "0" + ] + }, + "execution_count": 169, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions.duplicated(subset=[\"GRE Score\", \"CGPA\"]).sum()" + ] }, { "cell_type": "markdown", @@ -348,10 +1154,138 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 176, "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": 176, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "condition_1 = admissions[\"CGPA\"] > 9\n", + "admissions[condition_1].head()" + ] }, { "cell_type": "markdown", @@ -362,17 +1296,32 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 189, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "condition_2 = admissions[\"SOP\"] < 3.5" + ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 190, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "0.7313235294117648" + ] + }, + "execution_count": 190, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions[condition_1 | condition_2][\"Chance of Admit\"].mean()" + ] }, { "cell_type": "markdown", @@ -384,10 +1333,15 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 194, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "def TOELF(x):\n", + " return True if x > 100 else False\n", + "\n", + "admissions[\"TOELF\"] = admissions[\"TOEFL Score\"].apply(TOELF)" + ] }, { "cell_type": "markdown", @@ -398,39 +1352,39 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 196, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "admissions.rename(columns = {\"TOELF\": \"Decision\"}, inplace=True)" + ] }, { - "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": 198, "metadata": {}, "outputs": [], - "source": [] - }, - { - "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)" + "def sop(x):\n", + " return 1 if x > 3 else 0" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 200, "metadata": {}, "outputs": [], - "source": [] + "source": [ + "admissions[\"Decision2\"] = admissions[\"SOP\"].apply(sop)" + ] } ], "metadata": { @@ -449,7 +1403,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.10.8" + "version": "3.11.5" }, "toc": { "base_numbering": "",