app.py

import streamlit as st
import pandas as pd
from sklearn.linear_model import LinearRegression
import matplotlib.pyplot as plt

# Page config
st.set_page_config(page_title="Crime Rate Prediction", layout="wide")
st.title("📊 Crime Rate Prediction Based on Past Data")

# CSV path (Make sure this file is uploaded in Streamlit cloud if deployed)
csv_path = "crime_data.csv"

try:
    # Load the dataset
    df = pd.read_csv(csv_path)

    st.subheader("📄 Raw Dataset")
    st.dataframe(df)

    # Preprocess
    data = df[[
        'State/UT',
        'Number of Cases Registered - 2018-19',
        'Number of Cases Registered - 2019-20',
        'Number of Cases Registered - 2020-21',
        'Number of Cases Registered - 2021-22 (up to 31.10.2021)'
    ]].copy()
    data.columns = ['State/UT', '2018', '2019', '2020', '2021']

    # Convert string numbers to integers (if needed)
    for col in ['2018', '2019', '2020', '2021']:
        data[col] = pd.to_numeric(data[col], errors='coerce').fillna(0).astype(int)

    # Sidebar for user input
    st.sidebar.header("🔍 Predict Future Crime")
    selected_state = st.sidebar.selectbox("Select a State/UT", data['State/UT'].unique())
    start_year = st.sidebar.slider("Select starting year for prediction", 2022, 2026, 2022)

    # Perform prediction for selected state
    selected_row = data[data['State/UT'] == selected_state].iloc[0]
    years = [2018, 2019, 2020, 2021]
    X_train = pd.DataFrame({'Year': years})
    y_train = selected_row[['2018', '2019', '2020', '2021']].values

    model = LinearRegression()
    model.fit(X_train, y_train)

    future_years = list(range(start_year, 2028))
    predictions = model.predict(pd.DataFrame({'Year': future_years}))

    # Prepare result DataFrame
    result_df = pd.DataFrame({
        'Year': future_years,
        'Predicted Crime Cases': [max(0, int(pred)) for pred in predictions]
    })

    st.subheader(f"📈 Predicted Crime Rate in {selected_state} ({start_year}–2027)")
    st.dataframe(result_df)

    # Plotting
    fig2, ax2 = plt.subplots()
    ax2.plot(result_df['Year'], result_df['Predicted Crime Cases'], marker='o', linestyle='--', color='teal')
    ax2.set_xlabel("Year")
    ax2.set_ylabel("Predicted Crime Cases")
    ax2.set_title(f"Crime Trend Prediction for {selected_state}")
    st.pyplot(fig2)

except FileNotFoundError:
    st.error(f"❌ File not found at path: {csv_path}. Please check the path.")