booking_file = '../../data/booking.csv'
users_file = '../../data/user.csv'
rating_thresholds = []
true_objects_indexes = [0, 1, 2, 3, 4, 5]
false_objects_indexes = [6, 7, 8, 9]
file_names = os.listdir(data_directory)
ids_vector = [int(name.split('-')[0]) for name in file_names]
categories_vector = [name.split('-')[1] for name in file_names]
ratings_vector = [int(name.split('.')[0].split('-')[2]) for name in file_names]
name_vector = [data_directory + name for name in file_names]
ratings_matrix, images_indexes_for_id, ids_indexes, users_matrix = load_data(
data_directory, booking_file, users_file, rating_thresholds)
features, new_ratings_vector, new_categories_vector, new_ids_vector, new_paths_vector, text_indexes = divide_texts(
name_vector, ratings_vector, categories_vector, ids_vector, n=10)
ratings_vector = new_ratings_vector
ids_vector = new_ids_vector
scores_auc = []
scores_rmse = []
for i in range(10):
cv_results_file = '../results/cv-generated-data-r-10-n-04-z-rf-' + str(
i) + '.csv'
selection = BasicFactorization(show_selection_results=False,
selection_algorithm='rf')
selection.transform(ids=ids_vector,
features=features,
ratings=ratings_vector,
users_ratings=ratings_matrix,
def transform(self, results_file='', short_texts_length=15):
"""
Classify texts for each provider and save predictions
:param results_file: path to previously computed predictions
:param short_texts_length: length of short texts for different objects
"""
if path.exists(results_file):
self.load_results(results_file)
return
file_names = os.listdir(self.data_directory)
paths = [self.data_directory + '/' + name for name in file_names]
ids_vector = [name.split('-')[0] for name in file_names]
categories_vector = [name.split('-')[1] for name in file_names]
ratings_vector = [
int(name.split('-')[2].split('.')[0]) for name in file_names
]
#features = texts_to_vectors(paths)
features, ratings_vector, categories_vector, ids_vector, paths = divide_texts(
paths,
ratings_vector,
categories_vector,
ids_vector,
n=short_texts_length)
# Feature Agglomeration
if self.feature_agglomeration:
agglomeration = cluster.FeatureAgglomeration(n_clusters=5)
agglomeration.fit(features)
features_reduced = agglomeration.transform(features)
features = features_reduced
self.unique_ratings = sorted(list(set(ratings_vector)))
unique_ids = list(set(ids_vector))
# Object selection
if self.selection == 'none':
selected_features = features
selected_ids_vector = ids_vector
selected_ratings_vector = ratings_vector
elif self.selection == 'kmeans':
selected_features, selected_ids_vector, selected_ratings_vector = self.selection_kmeans(
ids_vector, ratings_vector, features)
elif self.selection == 'random':
selected_features, selected_ids_vector, selected_ratings_vector = self.selection_random(
ids_vector, ratings_vector, features)
elif self.selection == 'silhouette':
selected_features, selected_ids_vector, selected_ratings_vector = self.selection_silhouette(
ids_vector, ratings_vector, features, categories_vector)
true_ratings_object = {}
predicted_ratings_object = {}
predicted_ratings_vector = []
true_ratings_vector = []
paths_object = {}
ids_object = {}
if self.algorithm == 'knn':
model = KNeighborsClassifier(n_neighbors=3)
elif self.algorithm == 'lr':
model = linear_model.Lasso(alpha=0.1)
else:
model = RandomForestClassifier()
for current_id in unique_ids:
# Images for current_id to test set and other images to train set
test_indexes = []
train_indexes = []
for index, img_id in enumerate(ids_vector):
if img_id == current_id:
test_indexes.append(index)
for index, img_id in enumerate(selected_ids_vector):
if img_id != current_id:
train_indexes.append(index)
train_X = selected_features[train_indexes, :]
test_X = features[test_indexes, :]
train_y = [selected_ratings_vector[j] for j in train_indexes]
test_y = [ratings_vector[j] for j in test_indexes]
if len(test_y) == 0:
continue
model.fit(train_X, train_y)
predictions = model.predict(test_X)
# Save to object
predicted_ratings_object[current_id] = predictions
true_ratings_object[current_id] = test_y
paths_object[current_id] = [
paths[test_index] for test_index in test_indexes
]
ids_object[current_id] = [
ids_vector[test_index] for test_index in test_indexes
]
# Save to vector
predicted_ratings_vector.extend(predictions)
true_ratings_vector.extend(test_y)
# Save to class properties
self.predicted_ratings_object = predicted_ratings_object
self.true_ratings_object = true_ratings_object
self.predicted_ratings_vector = predicted_ratings_vector
self.true_ratings_vector = true_ratings_vector
self.paths_object = paths_object
self.ids_object = ids_object
# Save predictions to a file
self.save_results(results_file)