def divide_dataset(self):
tp = ReadFile(self.dataset, space_type=self.space_type)
tp.triple_information()
random.shuffle(tp.triple_dataset)
# Get the number of interactions that each partition should have.
partition_size = int(float(tp.number_interactions) / float(self.n_folds))
list_folds = list()
last = -1
for p in xrange(self.n_folds):
initial = 1 + last
final = (p + 1) * partition_size
list_folds.append(tp.triple_dataset[initial:final])
last = final
for fold in xrange(self.n_folds):
train_set = list()
for fold_train in xrange(self.n_folds):
if fold_train != fold:
train_set += list_folds[fold_train]
train_set.sort()
list_folds[fold].sort()
self.dict_folds[fold] = {'train': train_set, 'test': list_folds[fold]}
def treat_interactions(self):
for num, interaction_file in enumerate(self.list_train_files):
interaction = ReadFile(interaction_file, space_type=self.space_type)
interaction.triple_information()
self.individual_datasets.append(interaction.triple_dataset)
self.final_dataset += interaction.triple_dataset
self.dict_item, self.dict_not_item, self.list_users, self.list_items, \
self.dict_index = return_list_info(self.final_dataset)
self.list_users = list(self.list_users)
self.list_items = list(self.list_items)
def treat_interactions(self):
for num, interaction_file in enumerate(self.list_train_files):
interaction = ReadFile(interaction_file, space_type=self.space_type)
interaction.triple_information()
self.individual_datasets.append(interaction.triple_dataset)
self.final_dataset += interaction.triple_dataset
if num + 1 == len(self.list_train_files):
for triple in interaction.triple_dataset:
self.dict_item_tag[triple[0]] = self.dict_item_tag.get(triple[0], 0) + 1
self.dict_item_tag[triple[1]] = self.dict_item_tag.get(triple[1], 0) + 1
self.dict_item, self.dict_not_item, self.list_users, self.list_items, \
self.dict_index = return_list_info(self.final_dataset)
self.list_users = list(self.list_users)
self.list_items = list(self.list_items)