Code Editor for app.py

import streamlit as st
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, classification_report
from sklearn.preprocessing import LabelEncoder

st.title('Titanic Survival Prediction')

# Load data
@st.cache_data
def load_data():
    # NOTE: Using corsproxy.io because we're in a WASM environment. If running locally,
    # you can remove the corsproxy.io prefix.
    #url = "https://corsproxy.io/?https://raw.githubusercontent.com/datasciencedojo/datasets/master/titanic.csv"
    url="https://www.kaggle.com/datasets/rahulsah06/titanic?select=train.csv"
    return pd.read_csv(url)

# Load and display raw data
df = load_data()
st.subheader('Raw Data')
st.write(df.head())

# Data preprocessing
def preprocess_data(df):
    # Create a copy of the dataframe
    data = df.copy()
    
    # Drop unnecessary columns
    data = data.drop(['Name', 'Ticket', 'Cabin', 'PassengerId'], axis=1)
    
    # Handle missing values
    data['Age'].fillna(data['Age'].median(), inplace=True)
    data['Embarked'].fillna(data['Embarked'].mode()[0], inplace=True)
    
    # Convert categorical variables
    le = LabelEncoder()
    data['Sex'] = le.fit_transform(data['Sex'])
    data['Embarked'] = le.fit_transform(data['Embarked'])
    
    return data

# Preprocess data
processed_data = preprocess_data(df)

# Split features and target
X = processed_data.drop('Survived', axis=1)
y = processed_data['Survived']

# Split data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Train model
@st.cache_resource
def train_model():
    model = RandomForestClassifier(n_estimators=100, random_state=42)
    model.fit(X_train, y_train)
    return model

model = train_model()

# Make predictions
y_pred = model.predict(X_test)

# Display model performance
st.subheader('Model Performance')
st.write('Accuracy:', accuracy_score(y_test, y_pred))
st.write('Classification Report:')
st.text(classification_report(y_test, y_pred))

# Feature importance
st.subheader('Feature Importance')
feature_importance = pd.DataFrame({
    'feature': X.columns,
    'importance': model.feature_importances_
})
feature_importance = feature_importance.sort_values('importance', ascending=False)
st.bar_chart(feature_importance.set_index('feature'))

# Interactive Prediction
st.subheader('Predict Survival')
col1, col2 = st.columns(2)

with col1:
    pclass = st.selectbox('Passenger Class', [1, 2, 3])
    sex = st.selectbox('Sex', ['male', 'female'])
    age = st.number_input('Age', min_value=0, max_value=100, value=30)
    sibsp = st.number_input('Number of Siblings/Spouses', min_value=0, value=0)

with col2:
    parch = st.number_input('Number of Parents/Children', min_value=0, value=0)
    fare = st.number_input('Fare', min_value=0, value=50)
    embarked = st.selectbox('Embarked', ['C', 'Q', 'S'])

if st.button('Predict'):
    # Prepare input data
    input_data = pd.DataFrame({
        'Pclass': [pclass],
        'Sex': [0 if sex == 'male' else 1],
        'Age': [age],
        'SibSp': [sibsp],
        'Parch': [parch],
        'Fare': [fare],
        'Embarked': [0 if embarked == 'C' else 1 if embarked == 'Q' else 2]
    })
    
    # Make prediction
    prediction = model.predict(input_data)
    probability = model.predict_proba(input_data)
    
    # Display prediction
    st.write('Survival Prediction:', 'Survived' if prediction[0] == 1 else 'Did Not Survive')
    st.write('Survival Probability:', f"{probability[0][1]:.2%}")