Update app.py

app.py

@@ -1,25 +1,28 @@
 import streamlit as st
 import pandas as pd
 import numpy as np
+from sklearn.metrics.pairwise import cosine_similarity
 
 books = pd.read_csv("books.csv")
 books["Book-Title"] = books["Book-Title"] + " by " + books["Book-Author"]
 weighted_similarity = np.load("weighted_similarity.npy")
 
+
 def recommend_books(input_books, top_n=5):
     recommended_books_set = set()
-    vector_sum = np.zeros_like(weighted_similarity[0])
+    book_vectors = []
     for book_title in input_books:
         if book_title in books['Book-Title'].values:
             book_index = books[books['Book-Title'] == book_title].index[0]
-            vector_sum += weighted_similarity[book_index]
-
-    vector_sum /= np.linalg.norm(vector_sum)
-    similarities = np.dot(weighted_similarity, vector_sum)
-    top_books_indices = similarities.argsort()[-top_n:][::-1]
+            book_vectors.append(weighted_similarity[book_index])
+    # Sum the vectors
+    summed_vector = np.sum(book_vectors, axis=0)
+    # Calculate cosine similarity
+    cosine_sim = cosine_similarity(summed_vector.reshape(1, -1), weighted_similarity)
+    # Get top book indices
+    top_books_indices = cosine_sim.argsort()[0][-top_n - 1:-1][::-1]
     recommended_books_set.update(books.loc[top_books_indices, 'Book-Title'])
-
-    recommended_books_list = list(recommended_books_set)
+    recommended_books_list = list(recommended_books_set)[:top_n]
     return recommended_books_list