def test_seq_ml_reader(self):
test_n_sample = 10
test_batch_size = 2
test_n_feat = 30
test_sub_group = 3
data = generate_simulation_sequence_data(n_sample=test_n_sample,
n_feat=test_n_feat,
task='binaryclass')()
seq_ds = seq_ml_reader.DatasetReader(
data,
sub_group=test_sub_group,
data_type='aggregation',
task_type='binaryclass').get_data()
assert np.shape(seq_ds['X'])[0] == test_n_sample
assert np.shape(seq_ds['X'])[1] == test_n_feat * test_sub_group
assert np.shape(seq_ds['Y'])[0] == test_n_sample
assert np.shape(seq_ds['Y'])[1] == 1
test_n_sample = 10
test_batch_size = 2
test_n_feat = 30
test_sub_group = 3
test_n_class = 3
data = generate_simulation_sequence_data(n_sample=test_n_sample,
n_feat=test_n_feat,
task='multiclass',
n_class=test_n_class)()
seq_ds = seq_ml_reader.DatasetReader(
data,
sub_group=test_sub_group,
data_type='aggregation',
task_type='multiclass').get_data()
assert np.shape(seq_ds['X'])[0] == test_n_sample
assert np.shape(seq_ds['X'])[1] == test_n_feat * test_sub_group
assert np.shape(seq_ds['Y'])[0] == test_n_sample
assert np.shape(seq_ds['Y'])[1] == 1
test_n_sample = 10
test_batch_size = 2
test_n_feat = 30
test_sub_group = 3
test_n_class = 3
data = generate_simulation_sequence_data(n_sample=test_n_sample,
n_feat=test_n_feat,
task='multilabel',
n_class=test_n_class)()
seq_ds = seq_ml_reader.DatasetReader(
data,
sub_group=test_sub_group,
data_type='aggregation',
task_type='multilabel').get_data()
assert np.shape(seq_ds['X'])[0] == test_n_sample
assert np.shape(seq_ds['X'])[1] == test_n_feat * test_sub_group
assert np.shape(seq_ds['Y'])[0] == test_n_sample
assert np.shape(seq_ds['Y'])[1] == test_n_class
def fit(self, data_dict, X=None, y=None, assign_task_type=None):
"""
Parameters
----------
train_data : {
'x':list[episode_file_path],
'y':list[label],
'l':list[seq_len],
'feat_n': n of feature space,
'label_n': n of label space
}
The input train samples dict.
valid_data : {
'x':list[episode_file_path],
'y':list[label],
'l':list[seq_len],
'feat_n': n of feature space,
'label_n': n of label space
}
The input valid samples dict.
Returns
-------
self : object
Fitted estimator.
"""
self.task_type = assign_task_type
if data_dict != None:
self._data_check([data_dict])
data = ml_reader.DatasetReader(
data_dict, task_type=self.task_type).get_data()
_X = np.array(data['X'])
_y = np.array(data['Y'])
elif X != None and y != None:
self._data_check([{'X': X, 'Y': Y}])
_X = X
_y = Y
else:
raise Exception('fill in correct data for model train')
print(np.shape(_X), np.shape(_y))
self._build_model()
self.predictor.fit(_X, _y)
model_path = os.path.join(self.checkout_dir, 'best.model')
joblib.dump(self.predictor, model_path)
def inference(self, data_dict, X=None, y=None):
"""
Parameters
----------
test_data : {
'x':list[episode_file_path],
'y':list[label],
'l':list[seq_len],
'feat_n': n of feature space,
'label_n': n of label space
}
The input test samples dict.
"""
if data_dict != None:
self._data_check([data_dict])
data = ml_reader.DatasetReader(
data_dict, task_type=self.task_type).get_data()
_X = data['X']
_y = data['Y']
elif X != None and y != None:
self._data_check({'X': X, 'Y': y})
_X = X
_y = y
else:
raise Exception('fill in correct data for model inference')
if self.task_type in ['binaryclass', 'regression']:
real_v = _y.reshape(-1, 1)
prob_v = self.predictor.predict_proba(_X)[:, 1].reshape(-1, 1)
elif self.task_type in ['multiclass']:
real_v = np.array(_y)
prob_v = self.predictor.predict_proba(_X).reshape(
-1,
np.shape(real_v)[1])
elif self.task_type in ['multilabel']:
real_v = np.array(_y)
prob_v = []
_prob_v = self.predictor.predict_proba(_X)
for each_class in _prob_v:
if len(each_class) == 1:
each_class = np.array([each_class])
prob_v.append(each_class[:, 1:2])
prob_v = np.concatenate(prob_v, 1)
pickle.dump(prob_v, open(os.path.join(self.result_dir, 'hat_y'), 'wb'))
pickle.dump(real_v, open(os.path.join(self.result_dir, 'y'), 'wb'))