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")

# Replace this with your actual dataset path
csv_path = "crime_data.csv"  # Example: "data/crime_data.csv" if inside a folder

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

    # Display raw data
    st.subheader("📄 Raw Dataset")
    st.dataframe(df)

    # Extract the relevant columns
    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()

    # Rename for easier access
    data.columns = ['State/UT', '2018', '2019', '2020', '2021']

    # Model training & prediction
    years = ['2018', '2019', '2020', '2021']
    future_year = '2022'

    X = pd.DataFrame({'Year': [2018, 2019, 2020, 2021]})
    predicted_values = []

    for i, row in data.iterrows():
        y = row[years].values
        model = LinearRegression()
        model.fit(X, y)
        pred = model.predict([[2022]])[0]
        predicted_values.append(max(0, int(pred)))  # Avoid negatives

    data['Predicted 2022'] = predicted_values

    # Display result
    st.subheader("📈 Predicted Crime Rate for 2022")
    st.dataframe(data[['State/UT', 'Predicted 2022']].sort_values(by='Predicted 2022', ascending=False))

    # Plot top 10 states
    st.subheader("🔝 Top 10 States by Predicted Crime Rate")
    top10 = data.sort_values(by='Predicted 2022', ascending=False).head(10)

    fig, ax = plt.subplots()
    ax.barh(top10['State/UT'], top10['Predicted 2022'], color='salmon')
    ax.set_xlabel("Predicted Cases")
    ax.set_ylabel("State/UT")
    ax.invert_yaxis()
    ax.set_title("Top 10 States with Highest Predicted Crime Rate (2022)")
    st.pyplot(fig)

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