test

recommend_normal.py

@@ -28,8 +28,8 @@ def load_data():
 
 # Load movie data
 movies_data = load_data()
-vectorizer_path = hf_hub_download(repo_id=repo_id, filename="feature_vector.pkl")
-similarity_path = hf_hub_download(repo_id=repo_id, filename="model_similarity.pkl")
+vectorizer_path = hf_hub_download(repo_id=repo_id, filename="feature_vector.pkl", cache_dir=cache_dir)
+similarity_path = hf_hub_download(repo_id=repo_id, filename="model_similarity.pkl", cache_dir=cache_dir)
 def recommend_movies(movie_name):
     # Add the movie to the user's history
     if vectorizer_path and similarity_path:

recommendwithdesc.py

@@ -27,8 +27,8 @@ def load_data():
 
 # Load movie data
 movies_data = load_data()
-model_vectorizer = hf_hub_download(repo_id=repo_id, filename="model_vectorizer.pkl")
-similarity_path = hf_hub_download(repo_id=repo_id, filename="model_similarity.pkl")
+model_vectorizer = hf_hub_download(repo_id=repo_id, filename="model_vectorizer.pkl", cache_dir=cache_dir)
+similarity_path = hf_hub_download(repo_id=repo_id, filename="model_similarity.pkl", cache_dir=cache_dir)
 with open(model_vectorizer, 'rb') as vec_file, open(similarity_path, 'rb') as sim_file:
         vectorizer = pickle.load(vec_file)
         similarity = pickle.load(sim_file)

recommendwithhist.py

@@ -61,8 +61,8 @@ for feature in selected_features:
 
 # Combine features
 combined_features = movies_data['genres'] + ' ' + movies_data['keywords'] + ' ' + movies_data['tagline'] + ' ' + movies_data['cast'] + ' ' + movies_data['director']
-model_vectorizer = hf_hub_download(repo_id=repo_id, filename="model_vectorizer.pkl")
-similarity_path = hf_hub_download(repo_id=repo_id, filename="model_similarity.pkl")
+model_vectorizer = hf_hub_download(repo_id=repo_id, filename="model_vectorizer.pkl", cache_dir=cache_dir)
+similarity_path = hf_hub_download(repo_id=repo_id, filename="model_similarity.pkl", cache_dir=cache_dir)
 # Check if the model (vectorizer and similarity) exists
 if model_vectorizer and similarity_path:
     # Load the vectorizer and similarity matrix