titanic.py

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler, LabelEncoder
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, classification_report

url = 'https://github.com/hrishikesh2005/codsoft-task/raw/71f801ac6364b48f160f34355495306104399a42/Titanic-Dataset.csv'
data = pd.read_csv(url)

print("First few rows of the dataset:")
print(data.head())

data = data.drop(columns=['Name', 'Ticket', 'Cabin'])

data['Age'].fillna(data['Age'].median(), inplace=True)  
data['Embarked'].fillna(data['Embarked'].mode()[0], inplace=True)  

label_encoder = LabelEncoder()
data['Sex'] = label_encoder.fit_transform(data['Sex'])
data['Embarked'] = label_encoder.fit_transform(data['Embarked'])

X = data.drop('Survived', axis=1) 
y = data['Survived']             

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

model = RandomForestClassifier(n_estimators=100, random_state=42)
model.fit(X_train, y_train)

y_pred = model.predict(X_test)

accuracy = accuracy_score(y_test, y_pred)
print(f'Accuracy: {accuracy * 100:.2f}%')
print("Classification Report:")
print(classification_report(y_test, y_pred))