Update app.py

app.py

@@ -2,25 +2,16 @@ import streamlit as st
 import numpy as np
 import pandas as pd
 import tensorflow as tf
-from sklearn.preprocessing import OneHotEncoder, StandardScaler
+from sklearn.preprocessing import StandardScaler
 import joblib
 
 # Load the trained model
 model = tf.keras.models.load_model('trained_game_price_model.h5')
 
 # Function to preprocess the input data
-def preprocess_input(data, ohe, scaler):
+def preprocess_input(data, scaler):
     # Convert input into DataFrame for processing
-    input_data = pd.DataFrame([data], columns=['genre', 'targetPlatform', 'gamePlays', 'competitorPricing', 'currencyFluctuations'])
-    
-    # Apply OneHotEncoder for categorical features
-    input_data_transformed = ohe.transform(input_data[['genre', 'targetPlatform']])
-    
-    # Ensure numerical features are 2D
-    numerical_features = input_data[['gamePlays', 'competitorPricing', 'currencyFluctuations']].values.reshape(1, -1)
-    
-    # Merge with numerical features
-    input_data = np.hstack((input_data_transformed.toarray(), numerical_features))
+    input_data = pd.DataFrame([data])
     
     # Scale the features
     input_data_scaled = scaler.transform(input_data)
@@ -30,56 +21,84 @@ def preprocess_input(data, ohe, scaler):
 # Function to make a prediction
 def make_prediction(input_data):
     # Preprocess the data for the model
-    input_data_scaled = preprocess_input(input_data, ohe, scaler)
+    input_data_scaled = preprocess_input(input_data, scaler)
     
     # Make prediction
     prediction = model.predict(input_data_scaled)
     
     return prediction[0][0]
 
-# Load pre-trained OneHotEncoder and StandardScaler (assuming you have these saved)
-ohe = joblib.load('ohe.pkl')  # Load the OneHotEncoder
-scaler = joblib.load('scaler.pkl')  # Load the StandardScaler
+# Load pre-trained StandardScaler
+scaler = joblib.load('scaler.pkl')
 
 # Streamlit application
-st.title("Game Price Prediction App")
+st.title("Dynamic Game Price Prediction App")
 
 st.write("""
-### Enter the game details below to predict its price.
+### Enter the game details below to predict its optimal price.
+This model considers actual sales data and market trends for more accurate pricing.
 """)
 
 # Game details form
 with st.form("game_details_form"):
     genre = st.selectbox('Genre', ['Action', 'RPG', 'Puzzle', 'Adventure', 'Simulation', 'Strategy', 'Horror', 'Fighting', 'Sports', 'Racing', 'Casual', 'MOBA', 'Sandbox'])
     target_platform = st.selectbox('Platform', ['PC', 'PlayStation', 'Xbox', 'Mobile', 'Switch', 'Nintendo 3DS', 'VR', 'Web'])
-    game_plays = st.number_input('Number of Game Plays', min_value=0, value=50000)
-    competitor_pricing = st.number_input('Competitor Pricing', min_value=0.0, value=30.0, format="%.2f")
-    currency_fluctuations = st.number_input('Currency Fluctuations', min_value=0.5, max_value=1.5, value=1.0, format="%.2f")
-
+    total_sales = st.number_input('Total Sales (units)', min_value=0, value=10000)
+    initial_price = st.number_input('Initial Price Offering ($)', min_value=0.0, value=29.99, format="%.2f")
+    revenue = total_sales * initial_price
+    st.write(f"Current Revenue: ${revenue:.2f}")
+    
+    avg_market_price = st.number_input('Average Market Price for Similar Games ($)', min_value=0.0, value=24.99, format="%.2f")
+    market_saturation = st.slider('Market Saturation (0-100%)', min_value=0, max_value=100, value=50)
+    user_rating = st.slider('User Rating (0-5 stars)', min_value=0.0, max_value=5.0, value=4.0, step=0.1)
+    
     # Submit button
-    submitted = st.form_submit_button("Predict Price")
+    submitted = st.form_submit_button("Predict Optimal Price")
 
 # Prediction logic
 if submitted:
     # Prepare input data
     input_data = {
         'genre': genre,
-        'targetPlatform': target_platform,
-        'gamePlays': game_plays,
-        'competitorPricing': competitor_pricing,
-        'currencyFluctuations': currency_fluctuations
+        'target_platform': target_platform,
+        'total_sales': total_sales,
+        'initial_price': initial_price,
+        'revenue': revenue,
+        'avg_market_price': avg_market_price,
+        'market_saturation': market_saturation / 100,  # Convert to 0-1 scale
+        'user_rating': user_rating
     }
     
     # Make prediction
     predicted_price = make_prediction(input_data)
     
     # Display results
-    st.write(f"### Predicted Game Price: ${predicted_price:.2f}")
+    st.write(f"### Predicted Optimal Price: ${predicted_price:.2f}")
     
     # Show the input details for reference
     st.write("#### Input Details:")
     st.write(f"- **Genre**: {genre}")
     st.write(f"- **Platform**: {target_platform}")
-    st.write(f"- **Game Plays**: {game_plays}")
-    st.write(f"- **Competitor Pricing**: ${competitor_pricing:.2f}")
-    st.write(f"- **Currency Fluctuations**: {currency_fluctuations}")
+    st.write(f"- **Total Sales**: {total_sales}")
+    st.write(f"- **Initial Price**: ${initial_price:.2f}")
+    st.write(f"- **Current Revenue**: ${revenue:.2f}")
+    st.write(f"- **Avg. Market Price**: ${avg_market_price:.2f}")
+    st.write(f"- **Market Saturation**: {market_saturation}%")
+    st.write(f"- **User Rating**: {user_rating} stars")
+    
+    # Provide some insights
+    price_difference = predicted_price - initial_price
+    if abs(price_difference) < 1:
+        st.write("The predicted optimal price is close to your initial price. Your pricing strategy seems to be aligned with the market.")
+    elif price_difference > 0:
+        st.write(f"The model suggests increasing your price by ${price_difference:.2f}. This might help maximize revenue, but consider the potential impact on sales volume.")
+    else:
+        st.write(f"The model suggests decreasing your price by ${-price_difference:.2f}. This might help increase sales volume and overall revenue.")
+
+    st.write("Remember, this is a prediction based on the provided data. Always consider other factors like marketing strategies, seasonal trends, and your specific game's unique value proposition when making pricing decisions.")
+
+# Add a note about the dynamic nature of the marketplace
+st.write("""
+#### Note on Marketplace Dynamics
+This prediction model takes into account current market trends and your game's performance. As the marketplace is dynamic, it's recommended to periodically reassess your pricing strategy using updated sales data and market information.
+""")