{ "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": 1, "metadata": { "id": "b2c_DuRzIQn9" }, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np\n", "import seaborn as sns\n", "import matplotlib.pyplot as plt\n", "from sklearn.preprocessing import LabelEncoder, StandardScaler\n" ] }, { "cell_type": "code", "source": [ "df = sns.load_dataset('titanic')\n", "# OR load from CSV if downloaded\n", "# df = pd.read_csv('titanic.csv')\n", "df.head()\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 206 }, "id": "e-hUE5nyIRs6", "outputId": "434cda7c-df23-4c09-ddc6-5473ecc9f729" }, "execution_count": 2, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " survived pclass sex age sibsp parch fare embarked class \\\n", "0 0 3 male 22.0 1 0 7.2500 S Third \n", "1 1 1 female 38.0 1 0 71.2833 C First \n", "2 1 3 female 26.0 0 0 7.9250 S Third \n", "3 1 1 female 35.0 1 0 53.1000 S First \n", "4 0 3 male 35.0 0 0 8.0500 S Third \n", "\n", " who adult_male deck embark_town alive alone \n", "0 man True NaN Southampton no False \n", "1 woman False C Cherbourg yes False \n", "2 woman False NaN Southampton yes True \n", "3 woman False C Southampton yes False \n", "4 man True NaN Southampton no True " ], "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", "
survivedpclasssexagesibspparchfareembarkedclasswhoadult_maledeckembark_townalivealone
003male22.0107.2500SThirdmanTrueNaNSouthamptonnoFalse
111female38.01071.2833CFirstwomanFalseCCherbourgyesFalse
213female26.0007.9250SThirdwomanFalseNaNSouthamptonyesTrue
311female35.01053.1000SFirstwomanFalseCSouthamptonyesFalse
403male35.0008.0500SThirdmanTrueNaNSouthamptonnoTrue
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\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\": \"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\": \"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\": \"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\": \"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 \"column\": \"class\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 3,\n \"samples\": [\n \"Third\",\n \"First\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"who\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 3,\n \"samples\": [\n \"man\",\n \"woman\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"adult_male\",\n \"properties\": {\n \"dtype\": \"boolean\",\n \"num_unique_values\": 2,\n \"samples\": [\n false,\n true\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"deck\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 7,\n \"samples\": [\n \"C\",\n \"E\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"embark_town\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 3,\n \"samples\": [\n \"Southampton\",\n \"Cherbourg\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"alive\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 2,\n \"samples\": [\n \"yes\",\n \"no\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"alone\",\n \"properties\": {\n \"dtype\": \"boolean\",\n \"num_unique_values\": 2,\n \"samples\": [\n true,\n false\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" } }, "metadata": {}, "execution_count": 2 } ] }, { "cell_type": "code", "source": [ "print(df.shape)\n", "print(df.info())\n", "print(df.describe())\n", "print(df.isnull().sum())\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "TyUAJtUTITti", "outputId": "33b4bc45-90fb-4ab7-cbee-a7d0480e1eab" }, "execution_count": 3, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "(891, 15)\n", "\n", "RangeIndex: 891 entries, 0 to 890\n", "Data columns (total 15 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 survived 891 non-null int64 \n", " 1 pclass 891 non-null int64 \n", " 2 sex 891 non-null object \n", " 3 age 714 non-null float64 \n", " 4 sibsp 891 non-null int64 \n", " 5 parch 891 non-null int64 \n", " 6 fare 891 non-null float64 \n", " 7 embarked 889 non-null object \n", " 8 class 891 non-null category\n", " 9 who 891 non-null object \n", " 10 adult_male 891 non-null bool \n", " 11 deck 203 non-null category\n", " 12 embark_town 889 non-null object \n", " 13 alive 891 non-null object \n", " 14 alone 891 non-null bool \n", "dtypes: bool(2), category(2), float64(2), int64(4), object(5)\n", "memory usage: 80.7+ KB\n", "None\n", " survived pclass age sibsp parch fare\n", "count 891.000000 891.000000 714.000000 891.000000 891.000000 891.000000\n", "mean 0.383838 2.308642 29.699118 0.523008 0.381594 32.204208\n", "std 0.486592 0.836071 14.526497 1.102743 0.806057 49.693429\n", "min 0.000000 1.000000 0.420000 0.000000 0.000000 0.000000\n", "25% 0.000000 2.000000 20.125000 0.000000 0.000000 7.910400\n", "50% 0.000000 3.000000 28.000000 0.000000 0.000000 14.454200\n", "75% 1.000000 3.000000 38.000000 1.000000 0.000000 31.000000\n", "max 1.000000 3.000000 80.000000 8.000000 6.000000 512.329200\n", "survived 0\n", "pclass 0\n", "sex 0\n", "age 177\n", "sibsp 0\n", "parch 0\n", "fare 0\n", "embarked 2\n", "class 0\n", "who 0\n", "adult_male 0\n", "deck 688\n", "embark_town 2\n", "alive 0\n", "alone 0\n", "dtype: int64\n" ] } ] }, { "cell_type": "code", "source": [ "# Fill missing age with median\n", "df['age'].fillna(df['age'].median(), inplace=True)\n", "\n", "# Fill embarked with mode\n", "df['embarked'].fillna(df['embarked'].mode()[0], inplace=True)\n", "\n", "# Drop columns with too many missing values (like deck)\n", "df.drop(columns=['deck'], inplace=True)\n", "\n", "# Drop rows with any remaining nulls (optional)\n", "df.dropna(inplace=True)\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "ldFjXF4yIVZK", "outputId": "842225f4-6e78-4122-fc1f-14f44775f8d8" }, "execution_count": 4, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ ":2: 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", " df['age'].fillna(df['age'].median(), inplace=True)\n", ":5: 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", " df['embarked'].fillna(df['embarked'].mode()[0], inplace=True)\n" ] } ] }, { "cell_type": "code", "source": [ "label_encoders = {}\n", "categorical_cols = ['sex', 'embarked', 'class', 'who', 'adult_male', 'alone']\n", "\n", "for col in categorical_cols:\n", " le = LabelEncoder()\n", " df[col] = le.fit_transform(df[col])\n", " label_encoders[col] = le\n" ], "metadata": { "id": "r6Z8NhxoIW85" }, "execution_count": 5, "outputs": [] }, { "cell_type": "code", "source": [ "scaler = StandardScaler()\n", "df[['age', 'fare']] = scaler.fit_transform(df[['age', 'fare']])\n" ], "metadata": { "id": "ysVUzJFZJpOx" }, "execution_count": 6, "outputs": [] }, { "cell_type": "code", "source": [ "print(df.head())\n", "print(df.isnull().sum())\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "ORBvQlgsJp4B", "outputId": "08522416-1443-479a-a2ff-1a54ee1cb78c" }, "execution_count": 7, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ " survived pclass sex age sibsp parch fare embarked class \\\n", "0 0 3 1 -0.563674 1 0 -0.500240 2 2 \n", "1 1 1 0 0.669217 1 0 0.788947 0 0 \n", "2 1 3 0 -0.255451 0 0 -0.486650 2 2 \n", "3 1 1 0 0.438050 1 0 0.422861 2 0 \n", "4 0 3 1 0.438050 0 0 -0.484133 2 2 \n", "\n", " who adult_male embark_town alive alone \n", "0 1 1 Southampton no 0 \n", "1 2 0 Cherbourg yes 0 \n", "2 2 0 Southampton yes 1 \n", "3 2 0 Southampton yes 0 \n", "4 1 1 Southampton no 1 \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", "class 0\n", "who 0\n", "adult_male 0\n", "embark_town 0\n", "alive 0\n", "alone 0\n", "dtype: int64\n" ] } ] } ] }