Update app.py

app.py

@@ -1,71 +1,66 @@
 import streamlit as st
 import pandas as pd
-import numpy as np
 from sklearn.linear_model import LinearRegression
-from sklearn.model_selection import train_test_split
-from sklearn.preprocessing import LabelEncoder
+import matplotlib.pyplot as plt
 
-# Streamlit UI
-st.set_page_config(page_title="BigMart Sales Predictor", page_icon="🛒", layout="centered")
-st.title("🛒 BigMart Sales Prediction using Real World Dataset")
-st.markdown("Fill in the product details to get a sales prediction.")
+# Page config
+st.set_page_config(page_title="Crime Rate Prediction", layout="wide")
+st.title("📊 Crime Rate Prediction Based on Past Data")
 
-# Load and preprocess dataset
-@st.cache_data
-def load_data():
-    data = pd.read_csv("Train.csv")  # 👈 Make sure Train.csv is in the same directory
-    # Handle missing values
-    data.fillna(data.mean(numeric_only=True), inplace=True)
-    data.fillna("Unknown", inplace=True)
-    
-    # Encode categorical columns
-    label_enc = LabelEncoder()
-    for col in ['Item_Fat_Content', 'Item_Type', 'Outlet_Identifier', 'Outlet_Size', 'Outlet_Location_Type', 'Outlet_Type']:
-        data[col] = label_enc.fit_transform(data[col])
-    return data
+# Replace this with your actual dataset path
+csv_path = "crime_data.csv"  # Example: "data/crime_data.csv" if inside a folder
 
-df = load_data()
+# Load data
+try:
+    df = pd.read_csv(csv_path)
 
-# Select features and target
-features = ['Item_Weight', 'Item_Visibility', 'Item_MRP']
-target = 'Item_Outlet_Sales'
+    # Display raw data
+    st.subheader("📄 Raw Dataset")
+    st.dataframe(df)
 
-X = df[features]
-y = df[target]
+    # 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()
 
-# Train model
-model = LinearRegression()
-model.fit(X, y)
+    # Rename for easier access
+    data.columns = ['State/UT', '2018', '2019', '2020', '2021']
 
-# Input UI
-product_name = st.text_input("📦 Product Name")
-item_weight = st.number_input("⚖️ Item Weight (kg)", min_value=0.0, step=0.1)
-item_visibility = st.slider("👀 Item Visibility", 0.0, 1.0, 0.05)
-item_mrp = st.number_input("💰 Item MRP", min_value=0.0, step=1.0)
+    # Model training & prediction
+    years = ['2018', '2019', '2020', '2021']
+    future_year = '2022'
 
-# Prediction
-if st.button("Predict Sales"):
-    if not product_name:
-        st.warning("Please enter a product name.")
-    else:
-        user_input = np.array([[item_weight, item_visibility, item_mrp]])
-        predicted_sales = model.predict(user_input)[0]
-        st.success(f"📈 Predicted Sales for '{product_name}': ₹{predicted_sales:,.2f}")
-        
-        # Optional: Download Prediction
-        result_df = pd.DataFrame({
-            "Product Name": [product_name],
-            "Item Weight": [item_weight],
-            "Item Visibility": [item_visibility],
-            "Item MRP": [item_mrp],
-            "Predicted Sales": [predicted_sales]
-        })
+    X = pd.DataFrame({'Year': [2018, 2019, 2020, 2021]})
+    predicted_values = []
 
-        st.download_button("📥 Download Result as CSV", result_df.to_csv(index=False), file_name="prediction.csv", mime="text/csv")
+    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
 
-# Sidebar Info
-st.sidebar.title("📌 About")
-st.sidebar.markdown("""
-This app uses a **real BigMart dataset** from Kaggle and a **Linear Regression model** to predict sales.
-You can customize features or switch to advanced ML models later!
-""")
+    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.")