{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [] }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" } }, "cells": [ { "cell_type": "code", "execution_count": 2, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 536 }, "id": "FEn31ru7v4DW", "outputId": "0378e78a-3b9a-4994-c15a-91b431b0bf05" }, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "RangeIndex: 891 entries, 0 to 890\n", "Data columns (total 12 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 PassengerId 891 non-null int64 \n", " 1 Survived 891 non-null int64 \n", " 2 Pclass 891 non-null int64 \n", " 3 Name 891 non-null object \n", " 4 Sex 891 non-null object \n", " 5 Age 714 non-null float64\n", " 6 SibSp 891 non-null int64 \n", " 7 Parch 891 non-null int64 \n", " 8 Ticket 891 non-null object \n", " 9 Fare 891 non-null float64\n", " 10 Cabin 204 non-null object \n", " 11 Embarked 889 non-null object \n", "dtypes: float64(2), int64(5), object(5)\n", "memory usage: 83.7+ KB\n" ] }, { "output_type": "execute_result", "data": { "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 " ], "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", "
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", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", "
\n" ], "application/vnd.google.colaboratory.intrinsic+json": { "type": "dataframe", "variable_name": "df", "summary": "{\n \"name\": \"df\",\n \"rows\": 891,\n \"fields\": [\n {\n \"column\": \"PassengerId\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 257,\n \"min\": 1,\n \"max\": 891,\n \"num_unique_values\": 891,\n \"samples\": [\n 710,\n 440,\n 841\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Survived\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0,\n \"min\": 0,\n \"max\": 1,\n \"num_unique_values\": 2,\n \"samples\": [\n 1,\n 0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Pclass\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0,\n \"min\": 1,\n \"max\": 3,\n \"num_unique_values\": 3,\n \"samples\": [\n 3,\n 1\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Name\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 891,\n \"samples\": [\n \"Moubarek, Master. Halim Gonios (\\\"William George\\\")\",\n \"Kvillner, Mr. Johan Henrik Johannesson\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Sex\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 2,\n \"samples\": [\n \"female\",\n \"male\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Age\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 14.526497332334044,\n \"min\": 0.42,\n \"max\": 80.0,\n \"num_unique_values\": 88,\n \"samples\": [\n 0.75,\n 22.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"SibSp\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1,\n \"min\": 0,\n \"max\": 8,\n \"num_unique_values\": 7,\n \"samples\": [\n 1,\n 0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Parch\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0,\n \"min\": 0,\n \"max\": 6,\n \"num_unique_values\": 7,\n \"samples\": [\n 0,\n 1\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Ticket\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 681,\n \"samples\": [\n \"11774\",\n \"248740\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Fare\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 49.693428597180905,\n \"min\": 0.0,\n \"max\": 512.3292,\n \"num_unique_values\": 248,\n \"samples\": [\n 11.2417,\n 51.8625\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Cabin\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 147,\n \"samples\": [\n \"D45\",\n \"B49\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Embarked\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 3,\n \"samples\": [\n \"S\",\n \"C\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" } }, "metadata": {}, "execution_count": 2 } ], "source": [ "import pandas as pd\n", "import numpy as np\n", "\n", "df = pd.read_csv('Titanic-Dataset.csv')\n", "df.info()\n", "df.head()" ] }, { "cell_type": "code", "source": [ "df.duplicated()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 459 }, "id": "5Esiejdqv7eA", "outputId": "5efe735a-2508-407e-91c8-4c5457dab90e" }, "execution_count": 3, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "0 False\n", "1 False\n", "2 False\n", "3 False\n", "4 False\n", " ... \n", "886 False\n", "887 False\n", "888 False\n", "889 False\n", "890 False\n", "Length: 891, dtype: bool" ], "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", "
0
0False
1False
2False
3False
4False
......
886False
887False
888False
889False
890False
\n", "

891 rows × 1 columns

\n", "

" ] }, "metadata": {}, "execution_count": 3 } ] }, { "cell_type": "code", "source": [ "cat_col = [col for col in df.columns if df[col].dtype == 'object']\n", "num_col = [col for col in df.columns if df[col].dtype != 'object']\n", "\n", "print('Categorical columns:', cat_col)\n", "print('Numerical columns:', num_col)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "MaRt3w5iwFtj", "outputId": "6c6b68f2-7310-4ce0-c102-2cb47a0bc6f0" }, "execution_count": 4, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Categorical columns: ['Name', 'Sex', 'Ticket', 'Cabin', 'Embarked']\n", "Numerical columns: ['PassengerId', 'Survived', 'Pclass', 'Age', 'SibSp', 'Parch', 'Fare']\n" ] } ] }, { "cell_type": "code", "source": [ "df[cat_col].nunique()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 241 }, "id": "h2Sa2xrTwILF", "outputId": "a95af263-f2f6-4418-f003-0b7fdd8170b1" }, "execution_count": 5, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "Name 891\n", "Sex 2\n", "Ticket 681\n", "Cabin 147\n", "Embarked 3\n", "dtype: int64" ], "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", "
0
Name891
Sex2
Ticket681
Cabin147
Embarked3
\n", "

" ] }, "metadata": {}, "execution_count": 5 } ] }, { "cell_type": "code", "source": [ "round((df.isnull().sum() / df.shape[0]) * 100, 2)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 461 }, "id": "EaTSawwqwTng", "outputId": "4d777061-df3b-46af-bacc-d18aa7600640" }, "execution_count": 6, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "PassengerId 0.00\n", "Survived 0.00\n", "Pclass 0.00\n", "Name 0.00\n", "Sex 0.00\n", "Age 19.87\n", "SibSp 0.00\n", "Parch 0.00\n", "Ticket 0.00\n", "Fare 0.00\n", "Cabin 77.10\n", "Embarked 0.22\n", "dtype: float64" ], "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", "
0
PassengerId0.00
Survived0.00
Pclass0.00
Name0.00
Sex0.00
Age19.87
SibSp0.00
Parch0.00
Ticket0.00
Fare0.00
Cabin77.10
Embarked0.22
\n", "

" ] }, "metadata": {}, "execution_count": 6 } ] }, { "cell_type": "code", "source": [ "df1 = df.drop(columns=['Name', 'Ticket', 'Cabin'])\n", "df1.dropna(subset=['Embarked'], inplace=True)\n", "df1['Age'].fillna(df1['Age'].mean(), inplace=True)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "TILaFimHwWXX", "outputId": "6cd5ba81-44b9-4dfc-be4c-d225b9a559c9" }, "execution_count": 7, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "/tmp/ipykernel_16628/56642916.py:3: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n", "The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n", "\n", "For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n", "\n", "\n", " df1['Age'].fillna(df1['Age'].mean(), inplace=True)\n" ] } ] }, { "cell_type": "code", "source": [ "import matplotlib.pyplot as plt\n", "\n", "plt.boxplot(df1['Age'], vert=False)\n", "plt.ylabel('Variable')\n", "plt.xlabel('Age')\n", "plt.title('Box Plot')\n", "plt.show()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 472 }, "id": "li-YKa2OwYkH", "outputId": "15db72ff-af3a-4383-d52a-cb39b0cd7d0d" }, "execution_count": 9, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "
" ], "image/png": "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\n" }, "metadata": {} } ] }, { "cell_type": "code", "source": [ "mean = df1['Age'].mean()\n", "std = df1['Age'].std()\n", "\n", "lower_bound = mean - 2 * std\n", "upper_bound = mean + 2 * std\n", "\n", "df2 = df1[(df1['Age'] >= lower_bound) & (df1['Age'] <= upper_bound)]" ], "metadata": { "id": "pqJdtTDJwbJi" }, "execution_count": 10, "outputs": [] }, { "cell_type": "code", "source": [ "df3 = df2.fillna(df2['Age'].mean())\n", "df3.isnull().sum()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 367 }, "id": "jA0KKGA6weAN", "outputId": "c519d6b6-8919-4458-fab8-a04f6003f349" }, "execution_count": 11, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "PassengerId 0\n", "Survived 0\n", "Pclass 0\n", "Sex 0\n", "Age 0\n", "SibSp 0\n", "Parch 0\n", "Fare 0\n", "Embarked 0\n", "dtype: int64" ], "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", "
0
PassengerId0
Survived0
Pclass0
Sex0
Age0
SibSp0
Parch0
Fare0
Embarked0
\n", "

" ] }, "metadata": {}, "execution_count": 11 } ] }, { "cell_type": "code", "source": [ "mean = df3['Age'].mean()\n", "std = df3['Age'].std()\n", "\n", "lower_bound = mean - 2 * std\n", "upper_bound = mean + 2 * std\n", "\n", "print('Lower Bound :', lower_bound)\n", "print('Upper Bound :', upper_bound)\n", "\n", "df4 = df3[(df3['Age'] >= lower_bound) & (df3['Age'] <= upper_bound)]" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "AQLNS5sswh_2", "outputId": "4eec0c6e-04aa-4e96-e9c3-8d66754dd0af" }, "execution_count": 12, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Lower Bound : 8.978989004171481\n", "Upper Bound : 49.30395961288911\n" ] } ] }, { "cell_type": "code", "source": [ "X = df3[['Pclass','Sex','Age', 'SibSp','Parch','Fare','Embarked']]\n", "Y = df3['Survived']" ], "metadata": { "id": "snfwzijuwkUl" }, "execution_count": 13, "outputs": [] }, { "cell_type": "code", "source": [ "from sklearn.preprocessing import MinMaxScaler\n", "\n", "scaler = MinMaxScaler(feature_range=(0, 1))\n", "\n", "num_col_ = [col for col in X.columns if X[col].dtype != 'object']\n", "x1 = X\n", "x1[num_col_] = scaler.fit_transform(x1[num_col_])\n", "x1.head()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 311 }, "id": "zWu-nH0Awmia", "outputId": "68300264-e918-448f-a59a-f01724fdfd4e" }, "execution_count": 14, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "/tmp/ipykernel_16628/1761829158.py:7: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " x1[num_col_] = scaler.fit_transform(x1[num_col_])\n" ] }, { "output_type": "execute_result", "data": { "text/plain": [ " Pclass Sex Age SibSp Parch Fare Embarked\n", "0 1.0 male 0.349515 0.125 0.0 0.014151 S\n", "1 0.0 female 0.660194 0.125 0.0 0.139136 C\n", "2 1.0 female 0.427184 0.000 0.0 0.015469 S\n", "3 0.0 female 0.601942 0.125 0.0 0.103644 S\n", "4 1.0 male 0.601942 0.000 0.0 0.015713 S" ], "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", "
PclassSexAgeSibSpParchFareEmbarked
01.0male0.3495150.1250.00.014151S
10.0female0.6601940.1250.00.139136C
21.0female0.4271840.0000.00.015469S
30.0female0.6019420.1250.00.103644S
41.0male0.6019420.0000.00.015713S
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", "
\n" ], "application/vnd.google.colaboratory.intrinsic+json": { "type": "dataframe", "variable_name": "x1", "summary": "{\n \"name\": \"x1\",\n \"rows\": 821,\n \"fields\": [\n {\n \"column\": \"Pclass\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.4126456502459271,\n \"min\": 0.0,\n \"max\": 1.0,\n \"num_unique_values\": 3,\n \"samples\": [\n 1.0,\n 0.0,\n 0.5\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Sex\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 2,\n \"samples\": [\n \"female\",\n \"male\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Age\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.19575228450833776,\n \"min\": 0.0,\n \"max\": 1.0,\n \"num_unique_values\": 65,\n \"samples\": [\n 0.7184466019417476,\n 0.9514563106796117\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"SibSp\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.13533793431975993,\n \"min\": 0.0,\n \"max\": 1.0,\n \"num_unique_values\": 7,\n \"samples\": [\n 0.125,\n 0.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Parch\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.13255263703557738,\n \"min\": 0.0,\n \"max\": 1.0,\n \"num_unique_values\": 7,\n \"samples\": [\n 0.0,\n 0.3333333333333333\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Fare\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.09769338561795964,\n \"min\": 0.0,\n \"max\": 1.0,\n \"num_unique_values\": 239,\n \"samples\": [\n 0.05410739813385612,\n 0.10122885832000206\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Embarked\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 3,\n \"samples\": [\n \"S\",\n \"C\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" } }, "metadata": {}, "execution_count": 14 } ] }, { "cell_type": "code", "source": [], "metadata": { "id": "cyaFh5gxwoce" }, "execution_count": null, "outputs": [] } ] }