embeddings = embedding_helper(value, model="bow", dictionary=dictionary).get_embedding()
embedded_movie_contents[data_manager.get_index_from_movie_id(movie_id)] = embeddings # array start at 0
np.save('data/embedded_movie_content.npy', embedded_movie_contents)
print("\nEncoding content")
if encoded_movie_path:
print(encoded_movie_path)
encoded_movie_contents = np.load(encoded_movie_path)
else:
print(embedded_movie_contents.shape)
intermediate_size = int(embedded_movie_contents.shape[1])
encoded_size = int(intermediate_size)
ae = AutoEncoder(embedded_movie_contents, validation_perc=0.2, lr=1e-3, intermediate_size=5000, encoded_size=100,
is_enable_bath_norm=True)
ae.train_loop(epochs=60)
encoded_movie_contents = ae.get_encoded_representations()
ae.save_encoder()
ae.save_decoder()
print(encoded_movie_contents.shape)
np.save('data/encoded_movie_contents.npy', encoded_movie_contents)
losses = pd.DataFrame(data=list(zip(ae.train_losses, ae.val_losses)), columns=['train_loss', 'validation_loss'])
losses['epoch'] = (losses.index + 1)
fig, ax = plt.subplots()
ax.plot(losses['epoch'], losses['train_loss'], label='train_loss')
ax.plot(losses['epoch'], losses['validation_loss'], label='validation_loss')
ax.set_ylabel('MSE loss')
ax.set_xlabel('epoch')
ax.set_title('autoencoder loss over time')
embedded_movie_contents[movie_dict_link.get(movieId)] = embeddings
np.save('data/embedded_movie_content.npy', embedded_movie_contents)
print("\nEncoding content")
if encoded_movie_path:
print(os.path.abspath(encoded_movie_path))
encoded_movie_contents = np.load(os.path.abspath(encoded_movie_path))
else:
ae = AutoEncoder(embedded_movie_contents,
validation_perc=0.1,
lr=1e-3,
intermediate_size=5000,
encoded_size=100,
is_enable_bath_norm=True)
ae.train_loop(epochs=15)
encoded_movie_contents = ae.get_encoded_representations()
ae.save_encoder()
ae.save_decoder()
np.save('data/encoded_movie_contents.npy', encoded_movie_contents)
print("\nCalculating similarity score")
if target_movie_id != 0:
cosine_similarity = similarity_helper(encoded_movie_contents)
movie_similarity = cosine_similarity.get_similarity_by_movie(
target_movie_id, movie_dict_link)
movie_name_column = {} # key = movieId, value = title
movie_content_column = {}