{ "cells": [ { "cell_type": "code", "execution_count": 2, "id": "6bcdf33e-15dd-4ebe-b5eb-91388c99e8d8", "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", "
PassengerIdSurvivedPclassNameSexAgeSibSpParchTicketFareCabinEmbarked
0103Braund, Mr. Owen Harrismale22.010A/5 211717.2500NaNS
1211Cumings, Mrs. John Bradley (Florence Briggs Th...female38.010PC 1759971.2833C85C
2313Heikkinen, Miss. Lainafemale26.000STON/O2. 31012827.9250NaNS
3411Futrelle, Mrs. Jacques Heath (Lily May Peel)female35.01011380353.1000C123S
4503Allen, Mr. William Henrymale35.0003734508.0500NaNS
\n", "
" ], "text/plain": [ " PassengerId Survived Pclass \\\n", "0 1 0 3 \n", "1 2 1 1 \n", "2 3 1 3 \n", "3 4 1 1 \n", "4 5 0 3 \n", "\n", " Name Sex Age SibSp \\\n", "0 Braund, Mr. Owen Harris male 22.0 1 \n", "1 Cumings, Mrs. John Bradley (Florence Briggs Th... female 38.0 1 \n", "2 Heikkinen, Miss. Laina female 26.0 0 \n", "3 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35.0 1 \n", "4 Allen, Mr. William Henry male 35.0 0 \n", "\n", " Parch Ticket Fare Cabin Embarked \n", "0 0 A/5 21171 7.2500 NaN S \n", "1 0 PC 17599 71.2833 C85 C \n", "2 0 STON/O2. 3101282 7.9250 NaN S \n", "3 0 113803 53.1000 C123 S \n", "4 0 373450 8.0500 NaN S " ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import pandas as pd\n", "import numpy as np\n", "\n", "df = pd.read_csv('Titanic-Dataset.csv')\n", "df.head()" ] }, { "cell_type": "code", "execution_count": 4, "id": "fd9366a7-3ad6-4b86-88dc-19d294eff8db", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "PassengerId int64\n", "Survived int64\n", "Pclass int64\n", "Name object\n", "Sex object\n", "Age float64\n", "SibSp int64\n", "Parch int64\n", "Ticket object\n", "Fare float64\n", "Cabin object\n", "Embarked object\n", "dtype: object" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.dtypes" ] }, { "cell_type": "code", "execution_count": 6, "id": "319358d9-9466-49d0-a438-fe28e99792b4", "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", "
PassengerIdSurvivedPclassAgeSibSpParchFare
count891.000000891.000000891.000000714.000000891.000000891.000000891.000000
mean446.0000000.3838382.30864229.6991180.5230080.38159432.204208
std257.3538420.4865920.83607114.5264971.1027430.80605749.693429
min1.0000000.0000001.0000000.4200000.0000000.0000000.000000
25%223.5000000.0000002.00000020.1250000.0000000.0000007.910400
50%446.0000000.0000003.00000028.0000000.0000000.00000014.454200
75%668.5000001.0000003.00000038.0000001.0000000.00000031.000000
max891.0000001.0000003.00000080.0000008.0000006.000000512.329200
\n", "
" ], "text/plain": [ " PassengerId Survived Pclass Age SibSp \\\n", "count 891.000000 891.000000 891.000000 714.000000 891.000000 \n", "mean 446.000000 0.383838 2.308642 29.699118 0.523008 \n", "std 257.353842 0.486592 0.836071 14.526497 1.102743 \n", "min 1.000000 0.000000 1.000000 0.420000 0.000000 \n", "25% 223.500000 0.000000 2.000000 20.125000 0.000000 \n", "50% 446.000000 0.000000 3.000000 28.000000 0.000000 \n", "75% 668.500000 1.000000 3.000000 38.000000 1.000000 \n", "max 891.000000 1.000000 3.000000 80.000000 8.000000 \n", "\n", " Parch Fare \n", "count 891.000000 891.000000 \n", "mean 0.381594 32.204208 \n", "std 0.806057 49.693429 \n", "min 0.000000 0.000000 \n", "25% 0.000000 7.910400 \n", "50% 0.000000 14.454200 \n", "75% 0.000000 31.000000 \n", "max 6.000000 512.329200 " ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.describe()" ] }, { "cell_type": "code", "execution_count": 8, "id": "b115d5be-9837-4e2b-86fc-eb0cccf6780f", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "PassengerId 0\n", "Survived 0\n", "Pclass 0\n", "Name 0\n", "Sex 0\n", "Age 177\n", "SibSp 0\n", "Parch 0\n", "Ticket 0\n", "Fare 0\n", "Cabin 687\n", "Embarked 2\n", "dtype: int64" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.isnull().sum()" ] }, { "cell_type": "code", "execution_count": 10, "id": "e36730f2-f8a9-4740-944c-a6577e87eee4", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Columns dropped: ['Cabin']\n", "Remaining columns: Index(['PassengerId', 'Survived', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp',\n", " 'Parch', 'Ticket', 'Fare', 'Embarked'],\n", " dtype='object')\n" ] } ], "source": [ "missing_percentage = df.isnull().mean() * 100\n", "threshold = 30 \n", "columns_to_drop = missing_percentage[missing_percentage > threshold].index\n", "df = df.drop(columns=columns_to_drop)\n", "print(f\"Columns dropped: {list(columns_to_drop)}\")\n", "print(f\"Remaining columns: {df.columns}\")" ] }, { "cell_type": "code", "execution_count": 12, "id": "0fe00447-edd1-429f-8608-e8da39e90c0b", "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", "
PassengerIdSurvivedPclassNameSexAgeSibSpParchTicketFareEmbarked
0103108122.0105237.25002
1211190038.01059671.28330
2313353026.0006697.92502
3411272035.0104953.10002
450315135.0004728.05002
\n", "
" ], "text/plain": [ " PassengerId Survived Pclass Name Sex Age SibSp Parch Ticket \\\n", "0 1 0 3 108 1 22.0 1 0 523 \n", "1 2 1 1 190 0 38.0 1 0 596 \n", "2 3 1 3 353 0 26.0 0 0 669 \n", "3 4 1 1 272 0 35.0 1 0 49 \n", "4 5 0 3 15 1 35.0 0 0 472 \n", "\n", " Fare Embarked \n", "0 7.2500 2 \n", "1 71.2833 0 \n", "2 7.9250 2 \n", "3 53.1000 2 \n", "4 8.0500 2 " ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from sklearn.preprocessing import LabelEncoder\n", "label_encoder = LabelEncoder()\n", "for column in df.select_dtypes(include=['object']).columns:\n", " df[column] = label_encoder.fit_transform(df[column])\n", " \n", "df.head()" ] }, { "cell_type": "code", "execution_count": 14, "id": "212af8da-1564-4eef-b15c-fa6e1c249319", "metadata": {}, "outputs": [], "source": [ "for column in df.select_dtypes(include=['float64']).columns:\n", " mean_value = df[column].mean()\n", " df[column] = df[column].fillna(mean_value) " ] }, { "cell_type": "code", "execution_count": 16, "id": "37649f20-df67-4c39-8331-11fdec710802", "metadata": {}, "outputs": [], "source": [ "for column in df.select_dtypes(include=['object']).columns:\n", " mean_value = df[column].mode()[0]\n", " df[column] = df[column].fillna(mean_value) " ] }, { "cell_type": "code", "execution_count": 18, "id": "f0f4db1b-4d04-448d-b48e-33e14b0c2387", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "PassengerId 0\n", "Survived 0\n", "Pclass 0\n", "Name 0\n", "Sex 0\n", "Age 0\n", "SibSp 0\n", "Parch 0\n", "Ticket 0\n", "Fare 0\n", "Embarked 0\n", "dtype: int64" ] }, "execution_count": 18, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.isnull().sum()" ] }, { "cell_type": "code", "execution_count": 20, "id": "ccaf9013-aa1f-451e-b136-740c6c7c4ca0", "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", "
PassengerIdSurvivedPclassNameSexAgeSibSpParchTicketFareEmbarked
0103108122.000000105237.25002
1211190038.0000001059671.28330
2313353026.000000006697.92502
3411272035.000000104953.10002
450315135.000000004728.05002
....................................
88688702548127.0000000010113.00002
88788811303019.000000001430.00002
88888903413029.6991181267523.45002
8898901181126.00000000830.00000
89089103220132.000000004667.75001
\n", "

891 rows × 11 columns

\n", "
" ], "text/plain": [ " PassengerId Survived Pclass Name Sex Age SibSp Parch \\\n", "0 1 0 3 108 1 22.000000 1 0 \n", "1 2 1 1 190 0 38.000000 1 0 \n", "2 3 1 3 353 0 26.000000 0 0 \n", "3 4 1 1 272 0 35.000000 1 0 \n", "4 5 0 3 15 1 35.000000 0 0 \n", ".. ... ... ... ... ... ... ... ... \n", "886 887 0 2 548 1 27.000000 0 0 \n", "887 888 1 1 303 0 19.000000 0 0 \n", "888 889 0 3 413 0 29.699118 1 2 \n", "889 890 1 1 81 1 26.000000 0 0 \n", "890 891 0 3 220 1 32.000000 0 0 \n", "\n", " Ticket Fare Embarked \n", "0 523 7.2500 2 \n", "1 596 71.2833 0 \n", "2 669 7.9250 2 \n", "3 49 53.1000 2 \n", "4 472 8.0500 2 \n", ".. ... ... ... \n", "886 101 13.0000 2 \n", "887 14 30.0000 2 \n", "888 675 23.4500 2 \n", "889 8 30.0000 0 \n", "890 466 7.7500 1 \n", "\n", "[891 rows x 11 columns]" ] }, "execution_count": 20, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df" ] }, { "cell_type": "code", "execution_count": 104, "id": "9fb1188f-9611-48c4-af98-ed16cb8a0275", "metadata": {}, "outputs": [], "source": [ "def replace_outliers_with_nan(column):\n", " Q1 = column.quantile(0.25)\n", " Q3 = column.quantile(0.75)\n", " IQR = Q3 - Q1\n", " lower_bound = Q1 - 1.5 * IQR\n", " upper_bound = Q3 + 1.5 * IQR\n", " return column.where((column >= lower_bound) & (column <= upper_bound), np.nan)\n", "\n", "\n", "df.fillna(df.median(), inplace=True)" ] }, { "cell_type": "code", "execution_count": 22, "id": "2ae54858-ce44-48f0-8491-64a33cbcca61", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Sum of null values in each column:\n", "PassengerId 0\n", "Survived 0\n", "Pclass 0\n", "Name 0\n", "Sex 0\n", "Age 0\n", "SibSp 0\n", "Parch 0\n", "Ticket 0\n", "Fare 0\n", "Embarked 0\n", "dtype: int64\n" ] } ], "source": [ "null_counts = df.isnull().sum()\n", "print(\"Sum of null values in each column:\")\n", "print(null_counts)" ] }, { "cell_type": "code", "execution_count": 26, "id": "11a7d8f4-7730-493f-8ebf-36f9b53e3322", "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", "
PassengerIdSurvivedPclassNameSexAgeSibSpParchTicketFareEmbarked
0103108122.000000105237.25002
1211190038.0000001059671.28330
2313353026.000000006697.92502
3411272035.000000104953.10002
450315135.000000004728.05002
....................................
88688702548127.0000000010113.00002
88788811303019.000000001430.00002
88888903413029.6991181267523.45002
8898901181126.00000000830.00000
89089103220132.000000004667.75001
\n", "

891 rows × 11 columns

\n", "
" ], "text/plain": [ " PassengerId Survived Pclass Name Sex Age SibSp Parch \\\n", "0 1 0 3 108 1 22.000000 1 0 \n", "1 2 1 1 190 0 38.000000 1 0 \n", "2 3 1 3 353 0 26.000000 0 0 \n", "3 4 1 1 272 0 35.000000 1 0 \n", "4 5 0 3 15 1 35.000000 0 0 \n", ".. ... ... ... ... ... ... ... ... \n", "886 887 0 2 548 1 27.000000 0 0 \n", "887 888 1 1 303 0 19.000000 0 0 \n", "888 889 0 3 413 0 29.699118 1 2 \n", "889 890 1 1 81 1 26.000000 0 0 \n", "890 891 0 3 220 1 32.000000 0 0 \n", "\n", " Ticket Fare Embarked \n", "0 523 7.2500 2 \n", "1 596 71.2833 0 \n", "2 669 7.9250 2 \n", "3 49 53.1000 2 \n", "4 472 8.0500 2 \n", ".. ... ... ... \n", "886 101 13.0000 2 \n", "887 14 30.0000 2 \n", "888 675 23.4500 2 \n", "889 8 30.0000 0 \n", "890 466 7.7500 1 \n", "\n", "[891 rows x 11 columns]" ] }, "execution_count": 26, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df" ] }, { "cell_type": "code", "execution_count": null, "id": "87104063-b689-4748-99f5-69e665432254", "metadata": {}, "outputs": [], "source": [ "import matplotlib.pyplot as plt\n", "import seaborn as sns\n", "\n", "plt.figure(figsize=(8, 6))\n", "sns.scatterplot(x='Age', y='Survived', data=df, hue='classification', palette='Set2')\n", "plt.title('Age vs Survived')\n", "plt.xlabel('Age')\n", "plt.ylabel('Survived')\n", "plt.show()" ] } ], "metadata": { "kernelspec": { "display_name": "Python [conda env:First]", "language": "python", "name": "conda-env-First-py" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.12.9" } }, "nbformat": 4, "nbformat_minor": 5 }