def load_data(self):
classes_count = len(le_.classes_)
# load test data
# x_test = TestDataTask(self.task_core).run()
# train
x_train, y_train = TrainingDataTask(self.task_core).run()
# split
train_idxs, test_idxs = list(StratifiedShuffleSplit(y_train, 1, test_size=self.task_core.cv_ratio,
random_state=self.task_core.n_seed))[0]
x_test = x_train.filter_rows_by_idxs(test_idxs)
y_test = y_train[test_idxs]
x_train = x_train.filter_rows_by_idxs(train_idxs)
y_train = y_train[train_idxs]
# 2014 only for test
x_test, y_test, _, _ = divide_by_has_sessions(x_test, y_test)
print('running prediction model')
probabilities = run_model(x_train, y_train, x_test, classes_count, self.classifier,
self.task_core.n_threads, self.task_core.n_seed,
self.task_core.cache_dir)
print_probabilities(probabilities)
s = score(probabilities, y_test)
return {'Score': s}
def load_data(self):
classes_count = len(le_.classes_)
# load test data
x_test = TestDataTask(self.task_core).run()
# train
x_train, y_train = TrainingDataTask(self.task_core).run()
# perm_idxs = list(np.random.permutation(y_train.shape[0]))
# x_train = x_train.filter_rows(perm_idxs)
# y_train = y_train[perm_idxs]
x_test, x_train = sync_columns_2(x_test, x_train)
probabilities = run_model(x_train, y_train, x_test, classes_count, self.classifier,
self.task_core.n_threads, self.task_core.n_seed,
self.task_core.cache_dir)
print_probabilities(probabilities)
save_submission(x_test.ids_, probabilities, self.task_core.submission_file)