Update app.py

app.py

@@ -9,7 +9,7 @@ import numpy as np
 def load_data():
     try:
         # For Hugging Face Spaces deployment, you might need to adjust this path
-        data = pd.read_csv('games_march2025_cleaned.csv', nrows=88899, on_bad_lines='skip', engine='python')
+        data = pd.read_csv('games_march2025_cleaned.csv', nrows=20000, on_bad_lines='skip', engine='python')
         return data
     except Exception as e:
         print(f"Error loading data: {e}")
@@ -51,7 +51,8 @@ def get_recommendations(game_name, data, feature_vectors):
 
     result_html = ""
 
-    for i, (index, score) in enumerate(sorted_similar_games[1:10], 1):
+    for i, game in enumerate(sorted_similar_games[1:10], 1):
+        index = game[0]
         name = data.loc[index, 'name']
         about = data.loc[index, 'short_description'] or "No description available"
         image_url = data.loc[index, 'header_image'] or ""
@@ -65,19 +66,22 @@ def get_recommendations(game_name, data, feature_vectors):
             platforms.append("Linux")
         platforms_str = ", ".join(platforms) or "Unknown"
 
+        metacritic = data.loc[index, 'metacritic_score']
         price = data.loc[index, 'price']
         pos = data.loc[index, 'positive']
         neg = data.loc[index, 'negative']
         total_reviews = pos + neg
         pos_ratio = f"{(pos / total_reviews * 100):.1f}%" if total_reviews > 0 else "N/A"
 
+        # Combine into HTML
         result_html += f"""
         <div style="display:flex; align-items:flex-start; margin-bottom:20px;">
             <img src="{image_url}" style="width:150px; height:auto; margin-right:15px; border-radius:8px;">
             <div>
-                <h3>{i}. {name} <small>(Similarity: {score:.2f})</small></h3>
+                <h3>{i}. {name}</h3>
                 <p><b>Platforms:</b> {platforms_str}</p>
                 <p><b>Price:</b> ${price}</p>
+                <p><b>Metacritic Score:</b> {metacritic if pd.notnull(metacritic) else "N/A"}</p>
                 <p><b>Positive Reviews:</b> {pos_ratio}</p>
                 <p>{about}</p>
             </div>
@@ -87,29 +91,20 @@ def get_recommendations(game_name, data, feature_vectors):
 
     return result_html
 
+
 # Gradio interface function
-def recommend_games(game_name, max_age, max_price, min_pos_neg_ratio):
+def recommend_games(game_name, max_age, max_price, min_metacritic):
     data = load_data()
     if data is None:
         return "Failed to load data. Please check the data file."
-
-    # Fill NA values to avoid division errors
-    data['positive'] = data['positive'].fillna(0)
-    data['negative'] = data['negative'].fillna(0)
-
-    # Calculate the positive-to-negative ratio (avoid division by zero)
-    data['pos_neg_ratio'] = data.apply(
-        lambda row: (row['positive'] / row['negative']) if row['negative'] > 0 else row['positive'],
-        axis=1
-    )
-
-    # Apply filters
+    
+    # Apply filters BEFORE feature preparation
     data = data[
         (data['required_age'] <= max_age) &
         (data['price'] <= max_price) &
-        (data['pos_neg_ratio'] >= min_pos_neg_ratio)
+        ((data['metacritic_score'].fillna(0) >= min_metacritic) | data['metacritic_score'].isna())
     ].reset_index(drop=True)
-
+    
     if data.empty:
         return "No games found matching your filter criteria."
 
@@ -119,51 +114,32 @@ def recommend_games(game_name, max_age, max_price, min_pos_neg_ratio):
     return recommendations_html
 
 
-    
-    # Format the output for Gradio
-    result_texts = []
-    result_images = []
-    
-    for result, image_url in recommendations:
-        result_texts.append(result)
-        if image_url and str(image_url) != 'nan':
-            result_images.append(image_url)
-        else:
-            # Use a placeholder image if no image URL is available
-            result_images.append(None)
-    
-    # Create a gallery of results
-    results_html = ""
-    for i, (text, img) in enumerate(zip(result_texts, result_images)):
-        results_html += text
-    
-    return results_html, result_images
-
 # Create the Gradio interface
 with gr.Blocks(title="Steam Game Recommender") as demo:
-    gr.Markdown("# 🎮 Steam Game Recommender")
-    gr.Markdown("Enter a game you like and adjust filters to get the best matches.")
+    gr.Markdown("Steam Game Recommender")
+    gr.Markdown("Enter a game you like and customize filters to get similar suggestions.")
 
     with gr.Row():
-        input_text = gr.Textbox(label="🎯 Favorite Game")
+        input_text = gr.Textbox(label="Favorite Game")
     
     with gr.Row():
         max_age_slider = gr.Slider(0, 21, value=17, label="Max Age Rating (Avoid Adult Games)")
         max_price_slider = gr.Slider(0.0, 100.0, value=60.0, step=0.5, label="Maximum Price ($)")
-        min_pos_neg_slider = gr.Slider(0.0, 10.0, value=2.0, step=0.1, label="Min Positive:Negative Ratio")
+        min_metacritic_slider = gr.Slider(0, 100, value=50, step=1, label="Minimum Metacritic Score")
 
     with gr.Row():
-        submit_btn = gr.Button("🔍 Get Recommendations")
+        submit_btn = gr.Button("Get Recommendations")
 
     with gr.Row():
-        output_text = gr.Markdown(label="🧠 Recommendations")
+        output_text = gr.Markdown(label="Recommendations")
 
     submit_btn.click(
         fn=recommend_games,
-        inputs=[input_text, max_age_slider, max_price_slider, min_pos_neg_slider],
+        inputs=[input_text, max_age_slider, max_price_slider, min_metacritic_slider],
         outputs=output_text
     )
 
+
 # Launch the app
 if __name__ == "__main__":
     demo.launch()