src/streamlit_app.py

import streamlit as st
from sklearn.datasets import load_diabetes
from sklearn.ensemble import RandomForestRegressor
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error, r2_score
import pandas as pd
import matplotlib.pyplot as plt


# Title
st.title("Diabetes Prediction using Random Forest")

# Load dataset
data = load_diabetes()
X = pd.DataFrame(data.data, columns=data.feature_names)
y = pd.Series(data.target, name="Disease Progression")

# Show data
if st.checkbox("Show raw data"):
    st.subheader("Raw Data")
    st.write(X.head())

# Train-test split slider
test_size = st.slider("Test Size (%)", 10, 50, 20)
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=test_size / 100, random_state=42
)

# Hyperparameters
n_estimators = st.slider("Number of Trees (n_estimators)", 10, 200, 100)
max_depth = st.slider("Max Depth", 1, 30, 10)

# Train model button
if st.button("Train Model"):
    model = RandomForestRegressor(n_estimators=n_estimators, max_depth=max_depth, random_state=42)
    model.fit(X_train, y_train)
    y_pred = model.predict(X_test)

    mse = mean_squared_error(y_test, y_pred)
    r2 = r2_score(y_test, y_pred)

    st.subheader("Evaluation Metrics")
    st.write(f"Mean Squared Error: {mse:.2f}")
    st.write(f"R² Score: {r2:.2f}")

    # Plot actual vs predicted
    fig, ax = plt.subplots()
    ax.scatter(y_test, y_pred, alpha=0.7)
    ax.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], "r--")
    ax.set_xlabel("Actual")
    ax.set_ylabel("Predicted")
    ax.set_title("Actual vs Predicted")
    st.pyplot(fig)