Update app.py

app.py

@@ -41,6 +41,11 @@ def load_data():
 # Load data
 df = load_data()
 
+# Identify price and demand columns
+price_col = [col for col in df.columns if 'price' in col.lower() and col != 'suggested_price']
+demand_col = [col for col in df.columns if 'demand' in col.lower()]
+target_col = 'suggested_price' if 'suggested_price' in df.columns else (price_col[0] if price_col else None)
+
 # Sidebar for navigation
 page = st.sidebar.selectbox("Choose a page", ["Data Explorer", "Model Training", "Price Prediction"])
 
@@ -54,82 +59,82 @@ if page == "Data Explorer":
     st.subheader("Data Visualization")
     fig, ax = plt.subplots(1, 2, figsize=(15, 5))
     
-    # Use column names dynamically
-    price_col = [col for col in df.columns if 'price' in col.lower()]
-    demand_col = [col for col in df.columns if 'demand' in col.lower()]
-    
-    if price_col and 'suggested_price' in df.columns:
-        ax[0].scatter(df[price_col[0]], df['suggested_price'])
+    if price_col and target_col:
+        ax[0].scatter(df[price_col[0]], df[target_col])
         ax[0].set_xlabel(price_col[0])
-        ax[0].set_ylabel('Suggested Price')
-        ax[0].set_title(f'{price_col[0]} vs Suggested Price')
+        ax[0].set_ylabel(target_col)
+        ax[0].set_title(f'{price_col[0]} vs {target_col}')
     
-    if demand_col and 'suggested_price' in df.columns:
-        ax[1].scatter(df[demand_col[0]], df['suggested_price'])
+    if demand_col and target_col:
+        ax[1].scatter(df[demand_col[0]], df[target_col])
         ax[1].set_xlabel(demand_col[0])
-        ax[1].set_ylabel('Suggested Price')
-        ax[1].set_title(f'{demand_col[0]} vs Suggested Price')
+        ax[1].set_ylabel(target_col)
+        ax[1].set_title(f'{demand_col[0]} vs {target_col}')
     
     st.pyplot(fig)
 
 elif page == "Model Training":
     st.title("Model Training")
     
-    # Data preprocessing
-    categorical_cols = df.select_dtypes(include=['object']).columns
-    numeric_cols = df.select_dtypes(include=['int64', 'float64']).columns
-    
-    # Remove 'suggested_price' from features if it exists
-    feature_cols = [col for col in numeric_cols if col != 'suggested_price']
-    
-    encoders = {}
-    for col in categorical_cols:
-        encoders[col] = LabelEncoder()
-        df[f'{col}_encoded'] = encoders[col].fit_transform(df[col])
-        feature_cols.append(f'{col}_encoded')
-    
-    X = df[feature_cols]
-    y = df['suggested_price'] if 'suggested_price' in df.columns else df[price_col[0]]
-    
-    scaler = StandardScaler()
-    X_scaled = scaler.fit_transform(X)
-    
-    # Split the data
-    X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)
-    
-    # Model architecture
-    model = Sequential([
-        Dense(64, activation='relu', input_shape=(X_train.shape[1],)),
-        Dense(32, activation='relu'),
-        Dense(16, activation='relu'),
-        Dense(1)
-    ])
-    
-    model.compile(optimizer='adam', loss='mean_squared_error', metrics=['mae'])
-    
-    # Training
-    if st.button("Train Model"):
-        with st.spinner("Training in progress..."):
-            history = model.fit(X_train, y_train, validation_split=0.2, epochs=100, batch_size=32, verbose=0)
+    if not target_col:
+        st.error("No suitable target column (suggested_price or another price column) found in the dataset.")
+    else:
+        # Data preprocessing
+        categorical_cols = df.select_dtypes(include=['object']).columns
+        numeric_cols = df.select_dtypes(include=['int64', 'float64']).columns
+        
+        # Remove target column from features if it exists
+        feature_cols = [col for col in numeric_cols if col != target_col]
+        
+        encoders = {}
+        for col in categorical_cols:
+            encoders[col] = LabelEncoder()
+            df[f'{col}_encoded'] = encoders[col].fit_transform(df[col])
+            feature_cols.append(f'{col}_encoded')
+        
+        X = df[feature_cols]
+        y = df[target_col]
+        
+        scaler = StandardScaler()
+        X_scaled = scaler.fit_transform(X)
         
-        st.success("Model trained successfully!")
+        # Split the data
+        X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)
         
-        # Plot training history
-        fig, ax = plt.subplots(figsize=(10, 5))
-        ax.plot(history.history['loss'], label='Training Loss')
-        ax.plot(history.history['val_loss'], label='Validation Loss')
-        ax.set_xlabel('Epoch')
-        ax.set_ylabel('Loss')
-        ax.legend()
-        st.pyplot(fig)
+        # Model architecture
+        model = Sequential([
+            Dense(64, activation='relu', input_shape=(X_train.shape[1],)),
+            Dense(32, activation='relu'),
+            Dense(16, activation='relu'),
+            Dense(1)
+        ])
         
-        # Save model and preprocessing objects
-        model.save('dynamic_pricing_model.h5')
-        joblib.dump(scaler, 'scaler.pkl')
-        joblib.dump(encoders, 'encoders.pkl')
-        joblib.dump(feature_cols, 'feature_cols.pkl')
+        model.compile(optimizer='adam', loss='mean_squared_error', metrics=['mae'])
         
-        st.info("Model and preprocessing objects saved.")
+        # Training
+        if st.button("Train Model"):
+            with st.spinner("Training in progress..."):
+                history = model.fit(X_train, y_train, validation_split=0.2, epochs=100, batch_size=32, verbose=0)
+            
+            st.success("Model trained successfully!")
+            
+            # Plot training history
+            fig, ax = plt.subplots(figsize=(10, 5))
+            ax.plot(history.history['loss'], label='Training Loss')
+            ax.plot(history.history['val_loss'], label='Validation Loss')
+            ax.set_xlabel('Epoch')
+            ax.set_ylabel('Loss')
+            ax.legend()
+            st.pyplot(fig)
+            
+            # Save model and preprocessing objects
+            model.save('dynamic_pricing_model.h5')
+            joblib.dump(scaler, 'scaler.pkl')
+            joblib.dump(encoders, 'encoders.pkl')
+            joblib.dump(feature_cols, 'feature_cols.pkl')
+            joblib.dump(target_col, 'target_col.pkl')
+            
+            st.info("Model and preprocessing objects saved.")
 
 elif page == "Price Prediction":
     st.title("Price Prediction")
@@ -140,6 +145,7 @@ elif page == "Price Prediction":
         scaler = joblib.load('scaler.pkl')
         encoders = joblib.load('encoders.pkl')
         feature_cols = joblib.load('feature_cols.pkl')
+        target_col = joblib.load('target_col.pkl')
         
         # User input
         input_data = {}
@@ -166,7 +172,7 @@ elif page == "Price Prediction":
         # Make prediction
         if st.button("Predict Price"):
             predicted_price = model.predict(input_scaled)[0][0]
-            st.success(f"Predicted Price: ${predicted_price:.2f}")
+            st.success(f"Predicted {target_col}: ${predicted_price:.2f}")
     else:
         st.warning("Please train the model first!")