titanic_classification.py

# -*- coding: utf-8 -*-
"""Titanic Classification.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1cN8i2h8tqsCy4no_MFIGl1A8uUkGgQLi
"""

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score

# Load the dataset
url = "https://raw.githubusercontent.com/datasciencedojo/datasets/master/titanic.csv"
data = pd.read_csv(url)

# Fill missing values
data['Age'].fillna(data['Age'].mean(), inplace=True)
data['Embarked'].fillna(data['Embarked'].mode()[0], inplace=True)

# Encode categorical variables
data = pd.get_dummies(data)

# Split the data into training and testing sets
X = data.drop('Survived', axis=1)
y = data['Survived']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Create a Random Forest Classifier
clf = RandomForestClassifier(n_estimators=100, random_state=42)

# Train the classifier on the training data
clf.fit(X_train, y_train)

# Predict whether a person will be saved
pred = clf.predict(X_test)

# Calculate the accuracy of the classifier
accuracy = accuracy_score(y_test, pred)
print("Accuracy:", accuracy)