def main(ratings_components=300, features_components=300, print_scores=False):
np.random.seed(42)
tf.set_random_seed(1984)
data_path = '../data/goodbooks-10k/'
book_features = get_book_features(get_book_dataframe(data_path))
reduced_item_features, _, _ = reduce_matrix(book_features, n_components=features_components)
goodreads_path = '../data/goodbooks-10k/ratings.csv'
amazon_path = '../data/amazon/ratings_amazon.csv'
spr = get_ratings(goodreads_path, amazon_path, min_amazon_items=6)
n_folds = 5
scores = np.zeros((n_folds, 2))
kf = ColumnwiseKFold(n_folds, random_seed=30)
for i, (X, (user_indices, item_indices)) in enumerate(kf.split(spr)):
_, _, rating_VT = reduce_matrix(X, n_components=ratings_components)
reduced_item_ratings = rating_VT.T
items = get_reduced_joint(reduced_item_ratings, reduced_item_features)
tf.reset_default_graph()
encoder = BookEncoder(user_input_dim=10000, book_input_dim=items.shape[1], user_hidden=150, book_hidden=150)
with tf.Session() as sess:
encoder.initialize(sess)
encoder.train(sess, X, items)
scores[i, :] = encoder.test(sess, spr, X, items, user_indices, item_indices)
if print_scores:
print_evaluation(scores[i, 0], scores[i, 1])
scores = np.mean(scores, axis=0)
if print_scores:
print('{0:d}-Fold Scores:'.format(n_folds))
print_evaluation(scores[0], scores[1])
return scores
def main(ratings_components=100, features_components=100, print_scores=False):
#data_path = '../data/goodbooks-10k/'
data_path = '../../goodbooks-10k/'
book_features = get_book_features(get_book_dataframe(data_path))
reduced_item_features, _, _ = reduce_matrix(
book_features, n_components=features_components)
goodreads_path = data_path + 'ratings.csv'
amazon_path = data_path + 'ratings_amazon.csv'
spr = get_ratings(goodreads_path, amazon_path, min_amazon_items=6)
n_folds = 5
scores = np.zeros((n_folds, 2))
kf = ColumnwiseKFold(n_folds, random_seed=30)
for i, (X, (user_incides, item_indices)) in enumerate(kf.split(spr)):
_, _, rating_VT = reduce_matrix(X, n_components=ratings_components)
reduced_item_ratings = rating_VT.T
items = get_reduced_joint(reduced_item_ratings, reduced_item_features)
sim = (cosine_similarity(items) + 1) / 2
scores[i, :] = evaluate(spr, X, sim, user_incides, item_indices)
if print_scores:
print_evaluation(scores[i, 0], scores[i, 1])
scores = np.mean(scores, axis=0)
if print_scores:
print('{0:d}-Fold Scores:')
print_evaluation(scores[0], scores[1])
return scores
def get_user_vector(user_input):
try:
q = np.load('../.tmp/user_'+user_input+'.npy')
print('found user_vector...')
return q
except:
# Set this to where you save and load all data
data_path = '../../goodbooks-10k/'
# Get dataframe from books
books = get_book_dataframe(data_path)
mapper = get_mapper(data_path + 'books.csv')
# make an array for myself
q = np.zeros((10000), dtype = np.int)
# username = secret.USERNAME
api_key = secret.API_KEY
if not user_input.isdigit():
user_id = get_id_from_username(user_input, api_key)
else:
user_id = user_input
if user_id is None:
return None
page = 1
while True:
response = requests.get('https://www.goodreads.com/review/list/?v=2&id='+user_id+'&shelf=read&format=xml&key='+api_key+'&per_page=200&page=' + str(page))
tree = ElementTree.fromstring(response.content)
reviews = tree.find('reviews')
for review in reviews:
goodreads_book_id = str(review.find('book').find('id').text)
if goodreads_book_id in mapper:
book_id = int(mapper[goodreads_book_id])
rating = int(review.find('rating').text)
q[book_id-1] = float(rating)
page += 1
print(len(reviews))
if len(reviews) < 1:
break
for i in range(len(q)):
if q[i] != 0:
title = books.iloc[i]['title']
print("%s --> %s" % (q[i], title))
# Turn 1-5 rating scale into negative - positive scale
ratings_mapper = {0:0, 1:-2, 2:-1, 3:1, 4:2, 5:3}
for i in range(len(q)):
q[i] = ratings_mapper[q[i]]
print('saving user_vector...')
np.save('../.tmp/user_'+user_input, q)
return q
def main():
""" Sample program to verify the code.
This method will load in the book features, do some preprocessing,
and use SVD to reduce it to 100 dimensions. It will then output
the top 10 singular values.
"""
# Set this to where you save and load all data
# data_path = '../data/goodbooks-10k/'
data_path = '../../goodbooks-10k/'
df = get_book_dataframe(data_path)
fv = get_book_features(df)
U, S, VT = reduce_matrix(fv, 100, random_state = 42)
print(S[:10])
def main():
"""
Sample program to verify the code.
This method will load and join ratings
"""
# Set this to where you save and load all data
# data_path = '../data/goodbooks-10k/'
data_path = '../../goodbooks-10k/'
goodreads_path = data_path + 'ratings.csv'
amazon_path = data_path + 'ratings_amazon.csv'
ratings = get_ratings(goodreads_path, amazon_path)
book_features = get_book_features(get_book_dataframe(data_path))
joint = get_joint(ratings.T, book_features, 30, 30)
print(joint.shape)