app.py

import pandas as pd
import numpy as np
import gradio as gr
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder

# Load dataset
df = pd.read_csv("titanic.csv")
expected_cols = ["Pclass", "Sex", "Age", "SibSp", "Parch", "Fare", "Survived"]
available_cols = [col for col in expected_cols if col in df.columns]
df = df[available_cols].dropna()


# Encode 'Sex'
df["Sex"] = LabelEncoder().fit_transform(df["Sex"])  # male=1, female=0

# Features & target
X = df.drop("Survived", axis=1)
y = df["Survived"]

# Train model
model = RandomForestClassifier(n_estimators=100, random_state=42)
model.fit(X, y)

# Prediction function
def predict_survival(pclass, sex, age, fare):
    sex_encoded = 1 if sex == "male" else 0
    input_data = np.array([[pclass, sex_encoded, age, fare]])
    prediction = model.predict(input_data)[0]
    return "✅ Survived" if prediction == 1 else "❌ Did not survive"

# Gradio interface
iface = gr.Interface(
    fn=predict_survival,
    inputs=[
        gr.Dropdown([1, 2, 3], label="Passenger Class"),
        gr.Radio(["male", "female"], label="Sex"),
        gr.Slider(0, 80, step=1, label="Age"),
        gr.Slider(0, 500, step=1, label="Fare"),
    ],
    outputs="text",
    title="🚢 Titanic Survival Predictor",
    description="Enter passenger details to predict their survival on the Titanic."
)

if __name__ == "__main__":
    iface.launch()