Update app.py

app.py

@@ -17,7 +17,7 @@ st.set_page_config(page_title="Dynamic Game Pricing App", layout="wide")
 @st.cache_data
 def load_data():
     if os.path.exists('game_data.csv'):
-        return pd.read_csv('game_data.csv')
+        df = pd.read_csv('game_data.csv')
     else:
         # Sample dataset
         data = {
@@ -32,7 +32,11 @@ def load_data():
         }
         df = pd.DataFrame(data)
         df.to_csv('game_data.csv', index=False)
-        return df
+    
+    # Print column names for debugging
+    st.sidebar.write("Available columns:", df.columns.tolist())
+    
+    return df
 
 # Load data
 df = load_data()
@@ -49,15 +53,22 @@ if page == "Data Explorer":
     
     st.subheader("Data Visualization")
     fig, ax = plt.subplots(1, 2, figsize=(15, 5))
-    ax[0].scatter(df['competitor_price'], df['suggested_price'])
-    ax[0].set_xlabel('Competitor Price')
-    ax[0].set_ylabel('Suggested Price')
-    ax[0].set_title('Competitor Price vs Suggested Price')
     
-    ax[1].scatter(df['demand_index'], df['suggested_price'])
-    ax[1].set_xlabel('Demand Index')
-    ax[1].set_ylabel('Suggested Price')
-    ax[1].set_title('Demand Index vs Suggested Price')
+    # 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'])
+        ax[0].set_xlabel(price_col[0])
+        ax[0].set_ylabel('Suggested Price')
+        ax[0].set_title(f'{price_col[0]} vs Suggested Price')
+    
+    if demand_col and 'suggested_price' in df.columns:
+        ax[1].scatter(df[demand_col[0]], df['suggested_price'])
+        ax[1].set_xlabel(demand_col[0])
+        ax[1].set_ylabel('Suggested Price')
+        ax[1].set_title(f'{demand_col[0]} vs Suggested Price')
     
     st.pyplot(fig)
 
@@ -65,15 +76,20 @@ elif page == "Model Training":
     st.title("Model Training")
     
     # Data preprocessing
-    le_genre = LabelEncoder()
-    df['genre_encoded'] = le_genre.fit_transform(df['genre'])
+    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']
     
-    le_region = LabelEncoder()
-    df['region_encoded'] = le_region.fit_transform(df['region'])
+    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')
     
-    features = ['genre_encoded', 'region_encoded', 'release_year', 'demand_index', 'competitor_price', 'past_sales']
-    X = df[features]
-    y = df['suggested_price']
+    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)
@@ -107,11 +123,11 @@ elif page == "Model Training":
         ax.legend()
         st.pyplot(fig)
         
-        # Save model and scaler
+        # Save model and preprocessing objects
         model.save('dynamic_pricing_model.h5')
         joblib.dump(scaler, 'scaler.pkl')
-        joblib.dump(le_genre, 'le_genre.pkl')
-        joblib.dump(le_region, 'le_region.pkl')
+        joblib.dump(encoders, 'encoders.pkl')
+        joblib.dump(feature_cols, 'feature_cols.pkl')
         
         st.info("Model and preprocessing objects saved.")
 
@@ -122,28 +138,30 @@ elif page == "Price Prediction":
     if os.path.exists('dynamic_pricing_model.h5'):
         model = load_model('dynamic_pricing_model.h5')
         scaler = joblib.load('scaler.pkl')
-        le_genre = joblib.load('le_genre.pkl')
-        le_region = joblib.load('le_region.pkl')
+        encoders = joblib.load('encoders.pkl')
+        feature_cols = joblib.load('feature_cols.pkl')
         
         # User input
-        genre = st.selectbox("Select Genre", le_genre.classes_)
-        region = st.selectbox("Select Region", le_region.classes_)
-        release_year = st.slider("Release Year", 2018, 2024, 2022)
-        demand_index = st.slider("Demand Index", 0.1, 1.0, 0.5)
-        competitor_price = st.slider("Competitor Price", 20.0, 60.0, 40.0)
-        past_sales = st.slider("Past Sales", 100, 1000, 500)
+        input_data = {}
+        for col in feature_cols:
+            if col.endswith('_encoded'):
+                original_col = col[:-8]  # Remove '_encoded' suffix
+                if original_col in encoders:
+                    value = st.selectbox(f"Select {original_col}", encoders[original_col].classes_)
+                    input_data[col] = encoders[original_col].transform([value])[0]
+            else:
+                if 'year' in col.lower():
+                    input_data[col] = st.slider(f"{col}", 2018, 2024, 2022)
+                elif 'price' in col.lower():
+                    input_data[col] = st.slider(f"{col}", 20.0, 60.0, 40.0)
+                elif 'sales' in col.lower():
+                    input_data[col] = st.slider(f"{col}", 100, 1000, 500)
+                else:
+                    input_data[col] = st.slider(f"{col}", 0.1, 1.0, 0.5)
         
         # Prepare input for prediction
-        input_data = np.array([[
-            le_genre.transform([genre])[0],
-            le_region.transform([region])[0],
-            release_year,
-            demand_index,
-            competitor_price,
-            past_sales
-        ]])
-        
-        input_scaled = scaler.transform(input_data)
+        input_df = pd.DataFrame([input_data])
+        input_scaled = scaler.transform(input_df)
         
         # Make prediction
         if st.button("Predict Price"):