Update app.py

app.py

@@ -9,10 +9,8 @@ from sklearn.feature_extraction.text import TfidfVectorizer
 # Initialize Flask
 app = Flask(__name__)
 
-# Dummy Data for testing - replace this with actual data loading in production
+# Dataset is loaded for preprocessing
 df = pd.read_csv("ecommerce_dataset_updated.csv")
-
-# Clean and process data as in your previous code
 df['Category'] = df['Category'].str.replace('&', ' and ')
 df['Purchase_Date'] = pd.to_datetime(df['Purchase_Date'], format='%d-%m-%Y')
 df.dropna(inplace=True)
@@ -30,13 +28,13 @@ interaction_matrix = df.pivot_table(
 user_similarity = cosine_similarity(interaction_matrix)
 user_similarity_df = pd.DataFrame(user_similarity, index=interaction_matrix.index, columns=interaction_matrix.index)
 
-# TF-IDF on categories
+# TF-IDF vectors on categories
 tfidf = TfidfVectorizer(stop_words='english')
 tfidf_matrix = tfidf.fit_transform(df['Category'])
 product_similarity = cosine_similarity(tfidf_matrix, tfidf_matrix)
 product_similarity_df = pd.DataFrame(product_similarity, index=df['Product_ID'], columns=df['Product_ID'])
 
-# Collaborative Filtering Recommendation Function
+# Collaborative Filtering Recommendation Function(Method-1)
 def recommend_collaborative(user_id, top_n=5):
     user_idx = interaction_matrix.index.get_loc(user_id)
     sim_scores = user_similarity_df.iloc[user_idx]
@@ -45,7 +43,7 @@ def recommend_collaborative(user_id, top_n=5):
     recommended_products = interaction_matrix.columns[product_indices]
     return recommended_products.tolist()
 
-# Content-Based Recommendation Function
+# Content-Based Recommendation Function(Method-2)
 def recommend_content_based(product_id, top_n=5):
     sim_scores = product_similarity_df.loc[product_id].sort_values(ascending=False)
     recommended_products = sim_scores.index[1:top_n+1]  # Exclude the product itself