Spaces:
Runtime error
Runtime error
| import pickle | |
| import pandas as pd | |
| import numpy as np | |
| from sklearn.preprocessing import LabelEncoder | |
| from sklearn.feature_extraction.text import TfidfVectorizer | |
| from sklearn.metrics.pairwise import cosine_similarity | |
| from tensorflow.keras.models import load_model | |
| import streamlit as st | |
| # Load datasets | |
| books = pd.read_csv("./dataset/books.csv") | |
| ratings = pd.read_csv("./dataset/ratings.csv") | |
| # Preprocess data | |
| user_encoder = LabelEncoder() | |
| book_encoder = LabelEncoder() | |
| ratings["user_id"] = ratings["user_id"].astype(str) | |
| ratings["user_id"] = user_encoder.fit_transform(ratings["user_id"]) | |
| ratings["book_id"] = book_encoder.fit_transform(ratings["book_id"]) | |
| # Load TF-IDF models | |
| with open("tfidf_model_authors.pkl", "rb") as f: | |
| tfidf_model_authors = pickle.load(f) | |
| with open("tfidf_model_titles.pkl", "rb") as f: | |
| tfidf_model_titles = pickle.load(f) | |
| # Load collaborative filtering model | |
| model_cf = load_model("recommendation_model.keras") | |
| # Content-Based Recommendation | |
| def content_based_recommendation( | |
| query, books, tfidf_model_authors, tfidf_model_titles, num_recommendations=10 | |
| ): | |
| # Transform book author, title, and description into TF-IDF vectors | |
| query_author_tfidf = tfidf_model_authors.transform([query]) | |
| query_title_tfidf = tfidf_model_titles.transform([query]) | |
| # Compute cosine similarity for authors and titles separately | |
| similarity_scores_authors = cosine_similarity( | |
| query_author_tfidf, tfidf_model_authors.transform(books["authors"]) | |
| ) | |
| similarity_scores_titles = cosine_similarity( | |
| query_title_tfidf, tfidf_model_titles.transform(books["original_title"]) | |
| ) | |
| # Combine similarity scores for authors and titles | |
| similarity_scores_combined = ( | |
| similarity_scores_authors + similarity_scores_titles | |
| ) / 2 | |
| # Get indices of recommended books | |
| recommended_indices = np.argsort(similarity_scores_combined.flatten())[ | |
| -num_recommendations: | |
| ][::-1] | |
| # Get recommended books | |
| recommended_books = books.iloc[recommended_indices] | |
| return recommended_books | |
| # Collaborative Recommendation | |
| def collaborative_recommendation(user_id, model_cf, ratings, num_recommendations=10): | |
| # Get unrated books for the user | |
| unrated_books = ratings[ | |
| ~ratings["book_id"].isin(ratings[ratings["user_id"] == user_id]["book_id"]) | |
| ]["book_id"].unique() | |
| # Predict ratings for unrated books | |
| predictions = model_cf.predict( | |
| [np.full_like(unrated_books, user_id), unrated_books] | |
| ).flatten() | |
| # Get top indices based on predictions | |
| top_indices = np.argsort(predictions)[-num_recommendations:][::-1] | |
| # Get recommended books | |
| recommended_books = books.iloc[top_indices][["original_title", "authors"]] | |
| return recommended_books | |
| # Hybrid Recommendation | |
| def hybrid_recommendation( | |
| user_id, | |
| query, | |
| model_cf, | |
| books, | |
| ratings, | |
| tfidf_model_authors, | |
| tfidf_model_titles, | |
| num_recommendations=10, | |
| ): | |
| content_based_rec = content_based_recommendation( | |
| query, | |
| books, | |
| tfidf_model_authors, | |
| tfidf_model_titles, | |
| num_recommendations=num_recommendations, | |
| ) | |
| collaborative_rec = collaborative_recommendation( | |
| user_id, model_cf, ratings, num_recommendations=num_recommendations | |
| ) | |
| # Combine recommendations from different approaches | |
| hybrid_rec = pd.concat([content_based_rec, collaborative_rec]).drop_duplicates( | |
| subset="book_id", keep="first" | |
| ) | |
| return hybrid_rec | |
| # Streamlit App | |
| st.title("Book Recommendation System") | |
| # Sidebar for user input | |
| user_input = st.text_input("Enter book name or author:", "") | |
| # Get recommendations on button click | |
| if st.button("Get Recommendations"): | |
| st.write("Content-Based Recommendation:") | |
| content_based_rec = content_based_recommendation( | |
| user_input, books, tfidf_model_authors, tfidf_model_titles | |
| ) | |
| st.write(content_based_rec) | |
| # Example user ID for collaborative recommendation | |
| USER_ID = 0 | |
| st.write("Collaborative Recommendation:") | |
| collaborative_rec = collaborative_recommendation(USER_ID, model_cf, ratings) | |
| st.write(collaborative_rec) | |
| st.write("Hybrid Recommendation:") | |
| hybrid_rec = hybrid_recommendation( | |
| USER_ID, | |
| user_input, | |
| model_cf, | |
| books, | |
| ratings, | |
| tfidf_model_authors, | |
| tfidf_model_titles, | |
| ) | |
| st.write(hybrid_rec) | |