diff --git a/your-code/pandas_1.ipynb b/your-code/pandas_1.ipynb index 4f428ac..f0b270d 100644 --- a/your-code/pandas_1.ipynb +++ b/your-code/pandas_1.ipynb @@ -44,10 +44,34 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "0 5.7\n", + "1 75.2\n", + "2 74.4\n", + "3 84.0\n", + "4 66.5\n", + "5 66.3\n", + "6 55.8\n", + "7 75.7\n", + "8 29.1\n", + "9 43.7\n", + "dtype: float64" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "serie = pd.Series(lst)\n", + "serie" + ] }, { "cell_type": "markdown", @@ -60,10 +84,20 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "84.0\n" + ] + } + ], + "source": [ + "print(serie[3])" + ] }, { "cell_type": "markdown", @@ -74,7 +108,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 5, "metadata": {}, "outputs": [], "source": [ @@ -92,10 +126,145 @@ }, { "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 +275,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 7, "metadata": {}, "outputs": [], "source": [ @@ -124,7 +293,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 8, "metadata": {}, "outputs": [], "source": [ @@ -133,10 +302,145 @@ }, { "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 +451,123 @@ }, { "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", + "
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": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "subset = df[[\"Score_1\", \"Score_2\", \"Score_3\"]]\n", + "subset" + ] }, { "cell_type": "markdown", @@ -161,10 +578,27 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 11, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "56.95" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import statistics as stats\n", + "\n", + "# mean_score_3 = sum(df[\"Score_3\"]) / len(df[\"Score_3\"])\n", + "mean_score_3 = stats.mean(df[\"Score_3\"])\n", + "round(mean_score_3, 2)" + ] }, { "cell_type": "markdown", @@ -175,10 +609,24 @@ }, { "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": [ + "max_score_4 = max(df[\"Score_4\"])\n", + "max_score_4" + ] }, { "cell_type": "markdown", @@ -189,10 +637,25 @@ }, { "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": [ + "import statistics as stats\n", + "median_score_2 = stats.median(df[\"Score_2\"])\n", + "median_score_2" + ] }, { "cell_type": "markdown", @@ -203,7 +666,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 14, "metadata": {}, "outputs": [], "source": [ @@ -224,10 +687,134 @@ }, { "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" + ] }, { "cell_type": "markdown", @@ -238,10 +825,22 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 16, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "The total quantity orderes is 2978 and its revenue is 637.0\n" + ] + } + ], + "source": [ + "total_quantity = sum(orders_df[\"Quantity\"])\n", + "total_revenue = sum(orders_df[\"Revenue\"])\n", + "print(f\"The total quantity orderes is {total_quantity} and its revenue is {total_revenue}\")" + ] }, { "cell_type": "markdown", @@ -252,10 +851,22 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 17, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "The difference between the most an least expensive items is 11.77\n" + ] + } + ], + "source": [ + "max_price = max(orders_df[\"UnitPrice\"])\n", + "least_price = min(orders_df[\"UnitPrice\"])\n", + "print(f\"The difference between the most an least expensive items is {max_price - least_price}\")" + ] }, { "cell_type": "markdown", @@ -266,7 +877,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 34, "metadata": {}, "outputs": [], "source": [ @@ -285,10 +896,130 @@ }, { "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()" + ] }, { "cell_type": "markdown", @@ -299,10 +1030,45 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 20, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Nulls in dataset:\n", + "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\n", + "\n", + "NaNs in dataset:\n", + "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\n" + ] + } + ], + "source": [ + "print(\"Nulls in dataset:\")\n", + "print(admissions.isnull().sum())\n", + "print(\"\\nNaNs in dataset:\")\n", + "print(admissions.isna().sum())" + ] }, { "cell_type": "markdown", @@ -313,17 +1079,231 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, + "execution_count": 35, "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": 35, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions.set_index(['Serial No.'], inplace=False, drop=False)" + ] }, { "cell_type": "markdown", @@ -334,10 +1314,131 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 55, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "49\n", + "168\n" + ] + }, + { + "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", + "
GRE ScoreCGPA
03379.65
13168.00
23228.67
33148.21
43309.34
.........
3803249.04
3813259.11
3823309.45
3833128.78
3843339.66
\n", + "

385 rows × 2 columns

\n", + "
" + ], + "text/plain": [ + " GRE Score CGPA\n", + "0 337 9.65\n", + "1 316 8.00\n", + "2 322 8.67\n", + "3 314 8.21\n", + "4 330 9.34\n", + ".. ... ...\n", + "380 324 9.04\n", + "381 325 9.11\n", + "382 330 9.45\n", + "383 312 8.78\n", + "384 333 9.66\n", + "\n", + "[385 rows x 2 columns]" + ] + }, + "execution_count": 55, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "print(admissions['GRE Score'].nunique())\n", + "print(admissions['CGPA'].nunique())\n", + "subset_ = admissions[['GRE Score', 'CGPA']]\n", + "subset_\n" + ] }, { "cell_type": "markdown", @@ -348,10 +1449,218 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 37, "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": 37, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "subset_1 = admissions[(admissions['CGPA'] > 9) & (admissions['Research'] == 1)]\n", + "subset_1" + ] }, { "cell_type": "markdown", @@ -362,17 +1671,149 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 38, "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
282933811843.04.59.4010.91
626332711433.03.09.0200.61
14014132611433.03.09.1110.83
21721832411143.03.09.0110.82
38138232510733.03.59.1110.84
\n", + "
" + ], + "text/plain": [ + " Serial No. GRE Score TOEFL Score University Rating SOP LOR CGPA \\\n", + "28 29 338 118 4 3.0 4.5 9.40 \n", + "62 63 327 114 3 3.0 3.0 9.02 \n", + "140 141 326 114 3 3.0 3.0 9.11 \n", + "217 218 324 111 4 3.0 3.0 9.01 \n", + "381 382 325 107 3 3.0 3.5 9.11 \n", + "\n", + " Research Chance of Admit \n", + "28 1 0.91 \n", + "62 0 0.61 \n", + "140 1 0.83 \n", + "217 1 0.82 \n", + "381 1 0.84 " + ] + }, + "execution_count": 38, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "subset_2 = admissions[(admissions['CGPA'] > 9) & (admissions['SOP'] < 3.5)]\n", + "subset_2" + ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 39, "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "The mean chance od admit is 0.802\n" + ] + } + ], + "source": [ + "mean_chance = stats.mean(subset_2['Chance of Admit'])\n", + "print(f\"The mean chance od admit is {round(mean_chance, 3)}\")" + ] }, { "cell_type": "markdown", @@ -384,10 +1825,233 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 40, "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 Admitgreater_TOEFL
0133711844.54.59.6510.92True
1231610433.03.58.0010.72True
2332211033.52.58.6710.80True
3431410322.03.08.2100.65True
4533011554.53.09.3410.90True
.................................
38038132411033.53.59.0410.82True
38138232510733.03.59.1110.84True
38238333011645.04.59.4510.91True
38338431210333.54.08.7800.67True
38438533311745.04.09.6610.95True
\n", + "

385 rows × 10 columns

\n", + "
" + ], + "text/plain": [ + " Serial No. GRE Score TOEFL Score University Rating SOP LOR CGPA \\\n", + "0 1 337 118 4 4.5 4.5 9.65 \n", + "1 2 316 104 3 3.0 3.5 8.00 \n", + "2 3 322 110 3 3.5 2.5 8.67 \n", + "3 4 314 103 2 2.0 3.0 8.21 \n", + "4 5 330 115 5 4.5 3.0 9.34 \n", + ".. ... ... ... ... ... ... ... \n", + "380 381 324 110 3 3.5 3.5 9.04 \n", + "381 382 325 107 3 3.0 3.5 9.11 \n", + "382 383 330 116 4 5.0 4.5 9.45 \n", + "383 384 312 103 3 3.5 4.0 8.78 \n", + "384 385 333 117 4 5.0 4.0 9.66 \n", + "\n", + " Research Chance of Admit greater_TOEFL \n", + "0 1 0.92 True \n", + "1 1 0.72 True \n", + "2 1 0.80 True \n", + "3 0 0.65 True \n", + "4 1 0.90 True \n", + ".. ... ... ... \n", + "380 1 0.82 True \n", + "381 1 0.84 True \n", + "382 1 0.91 True \n", + "383 0 0.67 True \n", + "384 1 0.95 True \n", + "\n", + "[385 rows x 10 columns]" + ] + }, + "execution_count": 40, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "def evaluate_TOEFL(value):\n", + " return True if value > 100 else False\n", + "\n", + "admissions['greater_TOEFL'] = admissions['TOEFL Score'].apply(evaluate_TOEFL)\n", + "admissions" + ] }, { "cell_type": "markdown", @@ -398,24 +2062,230 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, + "execution_count": 41, "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": null, - "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 AdmitDecision
0133711844.54.59.6510.92True
1231610433.03.58.0010.72True
2332211033.52.58.6710.80True
3431410322.03.08.2100.65True
4533011554.53.09.3410.90True
.................................
38038132411033.53.59.0410.82True
38138232510733.03.59.1110.84True
38238333011645.04.59.4510.91True
38338431210333.54.08.7800.67True
38438533311745.04.09.6610.95True
\n", + "

385 rows × 10 columns

\n", + "
" + ], + "text/plain": [ + " Serial No. GRE Score TOEFL Score University Rating SOP LOR CGPA \\\n", + "0 1 337 118 4 4.5 4.5 9.65 \n", + "1 2 316 104 3 3.0 3.5 8.00 \n", + "2 3 322 110 3 3.5 2.5 8.67 \n", + "3 4 314 103 2 2.0 3.0 8.21 \n", + "4 5 330 115 5 4.5 3.0 9.34 \n", + ".. ... ... ... ... ... ... ... \n", + "380 381 324 110 3 3.5 3.5 9.04 \n", + "381 382 325 107 3 3.0 3.5 9.11 \n", + "382 383 330 116 4 5.0 4.5 9.45 \n", + "383 384 312 103 3 3.5 4.0 8.78 \n", + "384 385 333 117 4 5.0 4.0 9.66 \n", + "\n", + " Research Chance of Admit Decision \n", + "0 1 0.92 True \n", + "1 1 0.72 True \n", + "2 1 0.80 True \n", + "3 0 0.65 True \n", + "4 1 0.90 True \n", + ".. ... ... ... \n", + "380 1 0.82 True \n", + "381 1 0.84 True \n", + "382 1 0.91 True \n", + "383 0 0.67 True \n", + "384 1 0.95 True \n", + "\n", + "[385 rows x 10 columns]" + ] + }, + "execution_count": 41, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "admissions = admissions.rename({\"greater_TOEFL\":\"Decision\"}, axis=1)\n", + "admissions" + ] }, { "cell_type": "markdown", @@ -427,10 +2297,243 @@ }, { "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Serial No.GRE ScoreTOEFL ScoreUniversity RatingSOPLORCGPAResearchChance of AdmitDecisiondecision2
0133711844.54.59.6510.92True1
1231610433.03.58.0010.72True0
2332211033.52.58.6710.80True1
3431410322.03.08.2100.65True0
4533011554.53.09.3410.90True1
....................................
38038132411033.53.59.0410.82True1
38138232510733.03.59.1110.84True0
38238333011645.04.59.4510.91True1
38338431210333.54.08.7800.67True1
38438533311745.04.09.6610.95True1
\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 Decision decision2 \n", + "0 1 0.92 True 1 \n", + "1 1 0.72 True 0 \n", + "2 1 0.80 True 1 \n", + "3 0 0.65 True 0 \n", + "4 1 0.90 True 1 \n", + ".. ... ... ... ... \n", + "380 1 0.82 True 1 \n", + "381 1 0.84 True 0 \n", + "382 1 0.91 True 1 \n", + "383 0 0.67 True 1 \n", + "384 1 0.95 True 1 \n", + "\n", + "[385 rows x 11 columns]" + ] + }, + "execution_count": 42, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import numpy as np\n", + "admissions['decision2'] = np.where(admissions['SOP'] > 3, 1, 0)\n", + "admissions" + ] } ], "metadata": { @@ -449,7 +2552,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.10.8" + "version": "3.11.5" }, "toc": { "base_numbering": "",