def transform(self, ids, features, ratings, users_ratings, users, cv_results_file, images_indexes, true_objects_indexes, false_objects_indexes, paths, use_user_data=True, z_score=False):
"""
Calculates latent matrices and saves ratings predictions
:param ids: vector of ids, rows indexes corresponding to features and ratings indexes
:param features: matrix of features/objects as rows
:param ratings: vector of average ratings
:param users_ratings: matrix of all users ratings for experiences, rows indexes corresponding to users indexes
:param users: matrix of additional data for users
:param cv_results_file: ile for saving cv scores
"""
if self.selection_algorithm != 'random':
preselection = Preselection(true_objects_indexes, false_objects_indexes, self.selection_algorithm)
ids, features, ratings = preselection.transform(paths, ids, ratings, features)
self.ids = ids
self.features = features
self.ratings = ratings
self.users_ratings = users_ratings
self.users = users
self.unique_ratings = list(set(ratings))
self.unique_ids = list(set(self.ids))
self.z_score = z_score
self.save_objects_for_ids()
self.save_ids_to_i()
selected_objects_i_for_ids = self.object_selection()
self.save_data_for_factorization(selected_objects_i_for_ids)
self.factorization(cv_results_file, use_user_data)
def main():
# Preselection example
# Parameters
data_directory = '../data/generated-data-r-2-n-6-4'
features_path = '../data/features-generated-data-r-2-n-6-4'
results_file = '/results-preselection/generated-data-r-2-n-6-4.csv'
#true_objects_indexes = [0, 1, 2, 3, 4, 5, 6, 7]
#false_objects_indexes = [8, 9]
true_objects_indexes = [0, 1, 2, 3, 4, 5]
false_objects_indexes = [6, 7, 8, 9]
preselection = Preselection(data_directory, features_path, true_objects_indexes, false_objects_indexes)
preselection.transform(results_file=results_file)
#preselection.evaluate()
exit()
# Texts example
# Parameters
data_directory = '../data/data-real-r-3-text'
results_file = '/results-text/all_knn.csv'
classification = ClassificationText(data_directory, algorithm='knn', feature_agglomeration=False, selection='none')
classification.transform(results_file=results_file)
classification.evaluate()
exit()
# Images example
# Parameters
data_directory = '../data/data-real-r-3'
features_path = '../data/features-data-real-r-3'
results_file = '/results/kmeans_knn.csv'
classification = Classification(data_directory, features_path, algorithm='knn', feature_agglomeration=False,
selection='kmeans')
classification.transform(results_file=results_file)
classification.evaluate()