Create app.py

app.py

@@ -0,0 +1,101 @@
+import pandas as pd
+import gradio as gr
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+from sklearn.preprocessing import MinMaxScaler
+import difflib
+
+# Load dataset
+data = pd.read_csv('steam.csv', quotechar='"', on_bad_lines='skip', nrows=10000)
+data.fillna('', inplace=True)
+
+# Combine better features
+selected_features = ['genres', 'categories', 'tags']
+for feature in selected_features:
+    if feature not in data.columns:
+        data[feature] = ''
+
+data['combined_features'] = data['genres'] + ' ' + data['categories'] + ' ' + data['tags']
+
+# TF-IDF Vectorizer tuned
+vectorizer = TfidfVectorizer(
+    stop_words='english', 
+    ngram_range=(1, 2),
+    max_features=8000
+)
+feature_vectors = vectorizer.fit_transform(data['combined_features'])
+
+# Normalize positive ratings for re-ranking
+scaler = MinMaxScaler()
+data['positive_ratings_scaled'] = scaler.fit_transform(data[['positive_ratings']])
+
+# Calculate cosine similarity
+game_similarity = cosine_similarity(feature_vectors)
+
+# List of titles
+list_of_all_titles = data['name'].tolist()
+
+def recommend_games(user_game_name_input):
+    find_close_match = difflib.get_close_matches(user_game_name_input, list_of_all_titles, n=1)
+    if not find_close_match:
+        return "No close match found. Please try another game name."
+    
+    closest_match = find_close_match[0]
+    index_of_the_game = data.loc[data['name'] == closest_match].index[0]
+
+    similarity_scores = list(enumerate(game_similarity[index_of_the_game]))
+    
+    # Sort by similarity and positive ratings
+    sorted_similar_games = sorted(
+        similarity_scores, 
+        key=lambda x: (x[1], data.iloc[x[0]]['positive_ratings_scaled']), 
+        reverse=True
+    )
+
+    recommendations = []
+    for i, (index, score) in enumerate(sorted_similar_games[1:21]):  # Skip itself
+        if score < 0.3:
+            continue  # Skip very low similarity
+        game_name = data.iloc[index]['name']
+        recommendations.append(f"{i+1}. {game_name} (Similarity: {score:.2f})")
+        if len(recommendations) >= 10:
+            break
+
+    return "\n".join(recommendations)
+
+# Simulate evaluation Precision@5
+def evaluate_precision(user_game_name_input):
+    find_close_match = difflib.get_close_matches(user_game_name_input, list_of_all_titles, n=1)
+    if not find_close_match:
+        return 0.0
+    
+    closest_match = find_close_match[0]
+    index_of_the_game = data.loc[data['name'] == closest_match].index[0]
+    similarity_scores = list(enumerate(game_similarity[index_of_the_game]))
+    sorted_similar_games = sorted(
+        similarity_scores, 
+        key=lambda x: (x[1], data.iloc[x[0]]['positive_ratings_scaled']), 
+        reverse=True
+    )
+    
+    top_5 = [data.iloc[idx]['genres'] for idx, _ in sorted_similar_games[1:6]]
+    original_genre = data.iloc[index_of_the_game]['genres']
+    hits = sum(1 for genre in top_5 if genre == original_genre)
+    precision_at_5 = hits / 5
+    return round(precision_at_5, 2)
+
+# Gradio App
+def recommend_and_score(user_input):
+    recommendations = recommend_games(user_input)
+    precision = evaluate_precision(user_input)
+    return f"{recommendations}\n\nPrecision@5 (approx): {precision}"
+
+demo = gr.Interface(
+    fn=recommend_and_score,
+    inputs=gr.Textbox(lines=1, placeholder="Enter your favorite game"),
+    outputs="text",
+    title="Steam Game Recommender (Optimized Scikit-Learn Version)",
+    description="Enter a game name and get high-accuracy recommendations! 🚀"
+)
+
+demo.launch()