Update app.py

app.py

@@ -1,71 +1,48 @@
 import streamlit as st
 import pandas as pd
-from sklearn.linear_model import LinearRegression
-import matplotlib.pyplot as plt
+import joblib
+import re
+import string
 
 # Page configuration
-st.set_page_config(page_title="Crime Rate Predictor", layout="centered")
-st.title("🔮 Crime Rate Prediction for Indian States/UTs")
-
-# CSV path (Hosted online)
-csv_path = "https://huggingface.co/spaces/MLDeveloper/crime_rate_predicition/resolve/main/RS_Session_255_AS_116.1%20(2).csv"
-
-try:
-    # Load and preprocess data
-    df = pd.read_csv(csv_path)
-    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']
-    for col in ['2018', '2019', '2020', '2021']:
-        data[col] = pd.to_numeric(data[col], errors='coerce').fillna(0).astype(int)
-
-    # --- User Inputs ---
-    st.subheader("📝 Enter Details to Predict Future Crime Rates")
-    
-    # Dropdown for State selection
-    state_input = st.selectbox("Select State/UT", sorted(data['State/UT'].unique()))
-    
-    # Slider for year selection
-    year_input = st.slider("Select Starting Year", 2022, 2026, 2022)
-
-    if state_input:
-        if state_input in data['State/UT'].values:
-            selected_row = data[data['State/UT'] == state_input].iloc[0]
-            X_train = pd.DataFrame({'Year': [2018, 2019, 2020, 2021]})
-            y_train = selected_row[['2018', '2019', '2020', '2021']].values
-
-            # Train model and predict
-            model = LinearRegression()
-            model.fit(X_train, y_train)
-
-            future_years = list(range(year_input, 2028))
-            predictions = model.predict(pd.DataFrame({'Year': future_years}))
-
-            result_df = pd.DataFrame({
-                'Year': future_years,
-                'Predicted Crime Cases': [max(0, int(pred)) for pred in predictions]
-            })
-
-            # Show predictions
-            st.subheader(f"📈 Predicted Crime Rate for {state_input} ({year_input} to 2027)")
-            st.dataframe(result_df, use_container_width=True)
-
-            # Plot
-            fig, ax = plt.subplots()
-            ax.plot(result_df['Year'], result_df['Predicted Crime Cases'], marker='o', linestyle='--', color='orangered')
-            ax.set_xlabel("Year")
-            ax.set_ylabel("Predicted Crime Cases")
-            ax.set_title(f"{state_input} Crime Rate Prediction")
-            st.pyplot(fig)
-        else:
-            st.warning("⚠️ Please enter a valid State/UT name from the dataset.")
+st.set_page_config(page_title="SMS Spam Detector", layout="centered")
+st.title("📩 SMS Spam Detection App")
+st.markdown("🔍 Enter a message below to check if it's **Spam** or **Not Spam (Ham)**")
+
+# --- Load Model and Vectorizer ---
+model = joblib.load("model/spam_model.pkl")           # Make sure path is correct
+vectorizer = joblib.load("model/tfidf_vectorizer.pkl")  # Adjust as per your folder
+
+# --- Text Cleaning Function ---
+def clean_text(text):
+    text = text.lower()
+    text = re.sub(r"http\S+|www\S+|https\S+", '', text, flags=re.MULTILINE)
+    text = re.sub(r'\@w+|\#','', text)
+    text = re.sub(r'[^\w\s]', '', text)
+    text = re.sub(r'\d+', '', text)
+    text = text.translate(str.maketrans('', '', string.punctuation))
+    return text.strip()
+
+# --- Prediction Function ---
+def predict_spam(message):
+    cleaned = clean_text(message)
+    vector = vectorizer.transform([cleaned])
+    prediction = model.predict(vector)
+    return "Spam" if prediction[0] == 1 else "Not Spam"
+
+# --- Input Section ---
+user_input = st.text_area("✉️ Enter your SMS message here:")
+
+if st.button("Check Message"):
+    if user_input.strip() == "":
+        st.warning("⚠️ Please enter a valid message.")
     else:
-        st.info("👈 Please enter a State/UT name to begin prediction.")
+        result = predict_spam(user_input)
+        if result == "Spam":
+            st.error("🚫 This message is classified as **SPAM**.")
+        else:
+            st.success("✅ This message is classified as **NOT SPAM (HAM)**.")
 
-except FileNotFoundError:
-    st.error(f"❌ File not found at path: {csv_path}. Please check the path.")
+# Footer
+st.markdown("---")
+st.markdown("🔒 **Note**: This is a demo model and not intended for production use without proper testing.")