def test_timeseries(self, tmp_path):
ts_hours = 12
data_len = 120
train_file_name = os.path.join(str(tmp_path), 'train_data.csv')
test_file_name = os.path.join(str(tmp_path), 'test_data.csv')
features = generate_value_cols(['date', 'int'], data_len,
ts_hours * 3600)
labels = [generate_timeseries_labels(features)]
feature_headers = list(map(lambda col: col[0], features))
label_headers = list(map(lambda col: col[0], labels))
# Create the training dataset and save it to a file
columns_train = list(
map(lambda col: col[1:int(len(col) * 3 / 4)], features))
columns_train.extend(
list(map(lambda col: col[1:int(len(col) * 3 / 4)], labels)))
columns_to_file(columns_train,
train_file_name,
headers=[*feature_headers, *label_headers])
# Create the testing dataset and save it to a file
columns_test = list(
map(lambda col: col[int(len(col) * 3 / 4):], features))
columns_to_file(columns_test, test_file_name, headers=feature_headers)
mdb = Predictor(name='test_timeseries')
mdb.learn(from_data=train_file_name,
to_predict=label_headers,
timeseries_settings={
'order_by': [feature_headers[0]],
'window': 3
},
stop_training_in_x_seconds=10,
use_gpu=False,
advanced_args={'force_predict': True})
results = mdb.predict(when_data=test_file_name, use_gpu=False)
for row in results:
expect_columns = [
label_headers[0], label_headers[0] + '_confidence'
]
for col in expect_columns:
assert col in row
models = F.get_models()
model_data = F.get_model_data(models[0]['name'])
assert model_data
def get_models(self, status='any'):
models = F.get_models()
if status != 'any':
models = [x for x in models if x['status'] == status]
for i in range(len(models)):
for k in ['train_end_at', 'updated_at', 'created_at']:
if k in models[i] and models[i][k] is not None:
try:
models[i][k] = parse_datetime(
str(models[i][k]).split('.')[0])
except Exception as e:
models[i][k] = parse_datetime(str(models[i][k]))
return models
def test_multilabel_prediction(self, tmp_path):
train_file_name = os.path.join(str(tmp_path), 'train_data.csv')
test_file_name = os.path.join(str(tmp_path), 'test_data.csv')
data_len = 60
features = generate_value_cols(['int', 'float', 'int', 'float'], data_len)
labels = []
labels.append(generate_log_labels(features))
labels.append(generate_timeseries_labels(features))
feature_headers = list(map(lambda col: col[0], features))
label_headers = list(map(lambda col: col[0], labels))
# Create the training dataset and save it to a file
columns_train = list(
map(lambda col: col[1:int(len(col) * 3 / 4)], features))
columns_train.extend(
list(map(lambda col: col[1:int(len(col) * 3 / 4)], labels)))
columns_to_file(columns_train, train_file_name,
headers=[*feature_headers, *label_headers])
# Create the testing dataset and save it to a file
columns_test = list(
map(lambda col: col[int(len(col) * 3 / 4):], features))
columns_to_file(columns_test, test_file_name,
headers=feature_headers)
mdb = Predictor(name='test_multilabel_prediction')
mdb.learn(
from_data=train_file_name,
to_predict=label_headers,
stop_training_in_x_seconds=1,
use_gpu=False,
advanced_args={'force_predict': True}
)
results = mdb.predict(when_data=test_file_name)
models = F.get_models()
model_data = F.get_model_data(models[0]['name'])
assert model_data
for i in range(len(results)):
row = results[i]
for label in label_headers:
expect_columns = [label, label + '_confidence']
for col in expect_columns:
assert col in row
def get_models(self, status='any'):
models = F.get_models()
if status != 'any':
models = [x for x in models if x['status'] == status]
models = [
x for x in models
if x['status'] != 'training' or parse_datetime(x['created_at']) >
parse_datetime(self.config['mindsdb_last_started_at'])
]
for i in range(len(models)):
for k in ['train_end_at', 'updated_at', 'created_at']:
if k in models[i] and models[i][k] is not None:
try:
models[i][k] = parse_datetime(
str(models[i][k]).split('.')[0])
except Exception:
models[i][k] = parse_datetime(str(models[i][k]))
return models