Update app.py

app.py

@@ -1,24 +1,23 @@
 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 = "https://huggingface.co/spaces/MLDeveloper/crime_rate_predicition/resolve/main/RS_Session_255_AS_116.1%20(2).csv"  # Example: "data/crime_data.csv" if inside a folder
+# CSV path (Make sure this file is uploaded in Streamlit cloud if deployed)
+csv_path = "crime_data.csv"
 
-# Load data
 try:
+    # Load the dataset
     df = pd.read_csv(csv_path)
 
-    # Display raw data
     st.subheader("📄 Raw Dataset")
     st.dataframe(df)
 
-    # Extract the relevant columns
+    # Preprocess
     data = df[[
         'State/UT',
         'Number of Cases Registered - 2018-19',
@@ -26,41 +25,45 @@ try:
         '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'
+    # 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)
 
-    X = pd.DataFrame({'Year': [2018, 2019, 2020, 2021]})
-    predicted_values = []
+    # 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
 
-    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
+    model = LinearRegression()
+    model.fit(X_train, y_train)
 
-    data['Predicted 2022'] = predicted_values
+    future_years = list(range(start_year, 2028))
+    predictions = model.predict(pd.DataFrame({'Year': future_years}))
 
-    # Display result
-    st.subheader("📈 Predicted Crime Rate for 2022")
-    st.dataframe(data[['State/UT', 'Predicted 2022']].sort_values(by='Predicted 2022', ascending=False))
+    # Prepare result DataFrame
+    result_df = pd.DataFrame({
+        'Year': future_years,
+        'Predicted Crime Cases': [max(0, int(pred)) for pred in predictions]
+    })
 
-    # Plot top 10 states
-    st.subheader("🔝 Top 10 States by Predicted Crime Rate")
-    top10 = data.sort_values(by='Predicted 2022', ascending=False).head(10)
+    st.subheader(f"📈 Predicted Crime Rate in {selected_state} ({start_year}–2027)")
+    st.dataframe(result_df)
 
-    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)
+    # 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.")