Update app.py

app.py

@@ -3,15 +3,13 @@ import pandas as pd
 import numpy as np
 from sklearn.ensemble import RandomForestRegressor
 import joblib
-import requests
-from io import BytesIO
 
 st.title('Restaurant Revenue Predictor')
-        
+
 # Create input form
 st.write('Enter restaurant details:')
 
-# City selection (changed from City Group)
+# City selection
 city = st.selectbox('City', ['Istanbul', 'Ankara', 'Izmir', 'Other Cities'])
 
 # Adding description for Type
@@ -24,72 +22,61 @@ st.write("""
 """)
 type = st.selectbox('Type', ['FC', 'IL', 'DT', 'MB'])
 
+# Create a simple model for demonstration
 @st.cache_resource
-def load_model():
-    try:
-        # Download the model file from Hugging Face
-        url = "https://huggingface.co/alperugurcan/restaurant_revenue_model/resolve/main/restaurant_revenue_model.joblib"
-        response = requests.get(url)
-        if response.status_code == 200:
-            model_bytes = BytesIO(response.content)
-            model = joblib.load(model_bytes)
-            return model
-        else:
-            st.error(f"Failed to download model: HTTP {response.status_code}")
-            return None
-    except Exception as e:
-        st.error(f"Error loading model: {str(e)}")
-        return None
+def create_model():
+    model = RandomForestRegressor(
+        n_estimators=100,
+        max_depth=10,
+        random_state=42
+    )
+    # Create some sample training data
+    X_train = pd.DataFrame({
+        'City Group_Big Cities': [1, 0, 1, 0],
+        'City Group_Other': [0, 1, 0, 1],
+        'Type_DT': [1, 0, 0, 0],
+        'Type_FC': [0, 1, 0, 0],
+        'Type_IL': [0, 0, 1, 0],
+        'Type_MB': [0, 0, 0, 1],
+        'days': [1000, 800, 600, 400]
+    })
+    y_train = np.array([1500000, 1000000, 800000, 500000])
+    model.fit(X_train, y_train)
+    return model
 
 if st.button('Predict Revenue'):
     # Map city to City Group
     city_group = 'Big Cities' if city in ['Istanbul', 'Ankara', 'Izmir'] else 'Other'
     
-    # Average values for P1-P37
-    avg_values = {
-        'P1': 5.380, 'P2': 3.961, 'P3': 4.372, 'P4': 3.219, 'P5': 2.743,
-        'P6': 4.508, 'P7': 4.064, 'P8': 3.801, 'P9': 3.915, 'P10': 4.116,
-        'P11': 3.049, 'P12': 2.995, 'P13': 4.606, 'P14': 4.275, 'P15': 3.901,
-        'P16': 3.925, 'P17': 4.142, 'P18': 3.664, 'P19': 3.321, 'P20': 4.093,
-        'P21': 3.833, 'P22': 3.667, 'P23': 3.916, 'P24': 4.089, 'P25': 3.743,
-        'P26': 3.464, 'P27': 4.233, 'P28': 3.967, 'P29': 3.813, 'P30': 3.901,
-        'P31': 4.108, 'P32': 3.739, 'P33': 3.438, 'P34': 4.117, 'P35': 3.865,
-        'P36': 3.728, 'P37': 3.896
-    }
-    
-    # Create input dataframe with average values for other features
-    input_data = {
-        'City Group': city_group,
-        'Type': type,
-        'Open.Date': pd.Timestamp('2015-01-01'),  # Default date
-        **avg_values  # Unpack the average values
-    }
-    
-    df = pd.DataFrame([input_data])
-    
-    # Process dates
-    df['date'] = pd.to_datetime(df['Open.Date'])
-    df['day'] = df['date'].dt.day
-    df['month'] = df['date'].dt.month.astype('category')
-    df['year'] = df['date'].dt.year.astype('category')
-    
-    # Calculate days open
-    end_date = pd.to_datetime('2020-08-13')
-    df['days'] = (end_date - df['date']).dt.days
-    
-    # Drop unnecessary columns
-    df = df.drop(['Open.Date', 'date'], axis=1)
-    
-    # Convert categorical variables
-    df = pd.get_dummies(df)
+    # Create input dataframe
+    input_data = pd.DataFrame({
+        'City Group_Big Cities': [1 if city_group == 'Big Cities' else 0],
+        'City Group_Other': [1 if city_group == 'Other' else 0],
+        'Type_DT': [1 if type == 'DT' else 0],
+        'Type_FC': [1 if type == 'FC' else 0],
+        'Type_IL': [1 if type == 'IL' else 0],
+        'Type_MB': [1 if type == 'MB' else 0],
+        'days': [500]  # default value
+    })
     
     try:
-        # Load model
-        model = load_model()
+        # Get model
+        model = create_model()
         
         # Make prediction
-        prediction = model.predict(df)[0]
+        prediction = model.predict(input_data)[0]
+        
+        # Format prediction
+        formatted_prediction = f"${prediction:,.2f}"
+        
+        # Display prediction with additional context
+        st.success(f'Predicted Revenue: {formatted_prediction}')
+        
+        # Add some context about the prediction
+        st.info("""
+        Note: This is a simplified model for demonstration purposes. 
+        The prediction is based on limited training data and should be used as a rough estimate only.
+        """)
         
-        st.success(f'Predicted Revenue: ${prediction:,.2f}')
     except Exception as e:
-        st.error(f"Error loading model or making prediction: {str(e)}")
+        st.error(f"Error making prediction: {str(e)}")