def example():
"""simple test and performance measure
"""
# reviews = movielens_extractor.get_ml_1m_dataset()
reviews = movielens_extractor.get_ml_100K_dataset()
ratings = movielens_extractor.reviews_to_numpy_matrix(reviews)
# suffle_data
np.random.seed(0)
np.set_printoptions(precision=16)
# print(NormalRandom.generate_matrix(1, 10))
# np.random.shuffle(ratings)
# split data to training & validation
train_pct = 0.9
train_size = int(train_pct * len(ratings))
train = ratings[:train_size]
validation = ratings[train_size:]
# params
num_features = 10
bmf_model = BayesianMatrixFactorization()
start_time = time.clock()
bmf_model.load(ratings, train, validation)
end_time = time.clock()
print("time spent = %.3f" % (end_time - start_time))
return bmf_model
def generate_report_ml100k():
reviews = movielens_extractor.get_ml_100K_dataset()
file_name = '/Users/fpena/UCC/Thesis/projects/yelp/notebooks/dataset_analysis_report_ml100k.ipynb'
load_reviews_code =\
'from tripadvisor.fourcity import movielens_extractor\n' +\
'reviews = movielens_extractor.get_ml_100K_dataset()'
dataset_name = 'MovieLens 100k'
ReviewsDatasetAnalyzerReport.generate_report(
reviews, dataset_name, file_name, load_reviews_code)
def test():
R = [
# [5, 3, 0, 1],
# [4, 0, 0, 1],
# [1, 1, 0, 5],
# [1, 0, 0, 4],
# [0, 1, 5, 4],
[5., 7., 5., 7., 0.],
[5., 7., 5., 7., 9.],
[5., 7., 5., 7., 9.],
[6., 6., 6., 6., 5.],
[6., 6., 6., 6., 5.]
]
my_reviews = movielens_extractor.clean_reviews(movielens_extractor.get_ml_100K_dataset())
R = create_matrix(my_reviews).todense()
R = np.array(R)
N = len(R)
M = len(R[0])
K = 2
P = np.random.rand(N, K)
Q = np.random.rand(M, K)
# P.fill(0.1)
# Q.fill(0.1)
nP, nQ = matrix_factorization(R, P, Q, K)
# print(nP)
# print(nQ)
predicted = np.dot(nP[0], nQ[4])
# predicted = np.dot(nP[0, :], nQ[4, :])
# print('Predicted', predicted)
# my_reviews = movielens_extractor.get_ml_100K_dataset()
# my_reviews = movielens_extractor.clean_reviews(movielens_extractor.get_ml_100K_dataset())
# sgd = StochasticGradientDescent(2)
# sgd.load(reviews_matrix_5)
# print(build_user_index_map(test_reviews))
# print(build_item_index_map(test_reviews))
#
# print(create_matrix(test_reviews))
# print(create_matrix(test_reviews).todense())
# print(create_matrix(test_reviews).nonzero())
#
# print(create_matrix(reviews_matrix_5))
# print(create_matrix(reviews_matrix_5).todense())
# print(create_matrix(reviews_matrix_5).nonzero())
# print(sgd.predict(4, 0))
# start_time = time.time()
# test()
# end_time = time.time() - start_time
# print('Total time', end_time)
__author__ = 'fpena'
start_time = time.time()
# main()
# file_path = '/Users/fpena/tmp/filtered_reviews_multi.json'
# file_path = '/Users/fpena/tmp/filtered_reviews_multi_new.json'
# file_path = '/Users/fpena/tmp/filtered_reviews_multi_non_sparse_shuffled.json'
# file_path = '/Users/fpena/UCC/Thesis/datasets/TripHotelReviewXml/all_reviews.json'
file_path = '/Users/fpena/UCC/Thesis/datasets/TripHotelReviewXml/cleaned_reviews.json'
# reviews = ETLUtils.load_json_file(file_path)
# reviews = movielens_extractor.clean_reviews(movielens_extractor.get_ml_100K_dataset())
# reviews = extractor.pre_process_reviews()
reviews = movielens_extractor.get_ml_100K_dataset()
# shuffle(reviews)
# ETLUtils.save_json_file('/Users/fpena/tmp/filtered_reviews_multi_non_sparse_shuffled.json', reviews)
# print(reviews[0])
# print(reviews[1])
# print(reviews[2])
# print(reviews[10])
# print(reviews[100])
#
# for review in reviews:
# print(review)
my_recommender_list = [
# SingleCF(),
from etl.reviews_dataset_analyzer import ReviewsDatasetAnalyzer
from tripadvisor.fourcity.recommender_evaluator import evaluate_recommenders
__author__ = 'fpena'
start_time = time.time()
# main()
# file_path = '/Users/fpena/tmp/filtered_reviews_multi.json'
# file_path = '/Users/fpena/tmp/filtered_reviews_multi_new.json'
# file_path = '/Users/fpena/tmp/filtered_reviews_multi_non_sparse_shuffled.json'
# file_path = '/Users/fpena/UCC/Thesis/datasets/TripHotelReviewXml/all_reviews.json'
file_path = '/Users/fpena/UCC/Thesis/datasets/TripHotelReviewXml/cleaned_reviews.json'
# reviews = ETLUtils.load_json_file(file_path)
# reviews = movielens_extractor.clean_reviews(movielens_extractor.get_ml_100K_dataset())
# reviews = extractor.pre_process_reviews()
reviews = movielens_extractor.get_ml_100K_dataset()
# shuffle(reviews)
# ETLUtils.save_json_file('/Users/fpena/tmp/filtered_reviews_multi_non_sparse_shuffled.json', reviews)
# print(reviews[0])
# print(reviews[1])
# print(reviews[2])
# print(reviews[10])
# print(reviews[100])
#
# for review in reviews:
# print(review)
my_recommender_list = [
# SingleCF(),
# AdjustedWeightedSumRecommender(SingleSimilarityMatrixBuilder('euclidean')),
