{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   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\\t Mr. Owen Harris    male  22.0      1   \n",
      "1  Cumings\\t Mrs. John Bradley (Florence Briggs T...  female  38.0      1   \n",
      "2                             Heikkinen\\t Miss Laina  female  26.0      0   \n",
      "3      Futrelle\\t Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n",
      "4                          Allen\\t 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  \n",
      "\n",
      "Missing values in each column:\n",
      "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\n",
      "\n",
      "X shape: (891, 8)\n",
      "y shape: (891,)\n",
      "\n",
      "X_train shape: (712, 8)\n",
      "X_test shape: (179, 8)\n",
      "Accuracy: 0.8156\n"
     ]
    }
   ],
   "source": [
    "# Import necessary libraries\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.metrics import  accuracy_score, confusion_matrix\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "\n",
    "\n",
    "# Load the Titanic dataset\n",
    "# Assuming you have the dataset in your working directory\n",
    "# If not, you can download it from: https://www.kaggle.com/c/titanic/data\n",
    "df = pd.read_csv('titanic.csv')\n",
    "\n",
    "# Display the first few rows to understand the data\n",
    "print(df.head())\n",
    "\n",
    "# Check for missing values\n",
    "print(\"\\nMissing values in each column:\")\n",
    "print(df.isnull().sum())\n",
    "\n",
    "# Basic preprocessing\n",
    "# Fill missing values\n",
    "df['Age'].fillna(df['Age'].mean(), inplace=True)\n",
    "df['Fare'].fillna(df['Fare'].mean(), inplace=True)\n",
    "df['Embarked'].fillna(df['Embarked'].mode()[0], inplace=True)\n",
    "\n",
    "# Drop columns that won't be used as features\n",
    "df = df.drop(['PassengerId', 'Name', 'Ticket', 'Cabin'], axis=1)\n",
    "\n",
    "# Convert categorical variables to numeric\n",
    "df = pd.get_dummies(df, columns=['Sex', 'Embarked'], drop_first=True)\n",
    "\n",
    "# Define features (X) and target (y)\n",
    "X = df.drop('Survived', axis=1)\n",
    "y = df['Survived']\n",
    "\n",
    "# Print shapes to verify\n",
    "print(f\"\\nX shape: {X.shape}\")\n",
    "print(f\"y shape: {y.shape}\")\n",
    "\n",
    "# Split the data into training and testing sets\n",
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    X, y, test_size=0.2, random_state=42)\n",
    "\n",
    "print(f\"\\nX_train shape: {X_train.shape}\")\n",
    "print(f\"X_test shape: {X_test.shape}\")\n",
    "\n",
    "# Scale the features (important for many ML algorithms)\n",
    "scaler = StandardScaler()\n",
    "X_train_scaled = scaler.fit_transform(X_train)\n",
    "X_test_scaled = scaler.transform(X_test)\n",
    "\n",
    "\n",
    "# Now X_train_scaled and y_train are ready for model training\n",
    "# X_test_scaled and y_test are ready for model evaluation\n",
    "sklearn_rf = RandomForestClassifier()\n",
    "sklearn_rf.fit(X_train_scaled, y_train)\n",
    "\n",
    "# Y predictions\n",
    "y_pred = sklearn_rf.predict(X_test_scaled)\n",
    "\n",
    "# Accuracy score of the model\n",
    "accuracy = accuracy_score(y_test, y_pred)\n",
    "print(f\"Accuracy: {accuracy:.4f}\")\n",
    "\n",
    "# Confusion matrix\n",
    "conf_matrix = confusion_matrix(y_test, y_pred)\n",
    "\n",
    "\n",
    "\n",
    "\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}