def test_valid_input(self):
expected_result = [
datetime.datetime(2015, 3, 1, 0, 0),
datetime.datetime(2015, 6, 1, 0, 0),
datetime.datetime(2015, 9, 1, 0, 0),
datetime.datetime(2015, 12, 1, 0, 0),
datetime.datetime(2016, 3, 1, 0, 0),
datetime.datetime(2016, 6, 1, 0, 0),
]
chopper = Timechop(
feature_start_time=datetime.datetime(2010, 1, 1, 0, 0),
feature_end_time=datetime.datetime(2017, 1, 1, 0, 0),
label_start_time=datetime.datetime(2015, 1, 1, 0, 0),
label_end_time=datetime.datetime(2017, 1, 1, 0, 0),
model_update_frequency="3 months",
training_as_of_date_frequencies=["1 day"],
test_as_of_date_frequencies=["1 day"],
max_training_histories=["1 year"],
test_durations=["6 months"],
test_label_timespans=["1 months"],
training_label_timespans=["3 days"],
)
# this should throw an exception because last possible label date is after
# end of feature time
result = chopper.calculate_train_test_split_times(
training_label_timespan=convert_str_to_relativedelta("3 days"),
test_duration="6 months",
test_label_timespan=convert_str_to_relativedelta("1 month"),
)
assert result == expected_result
def test_no_valid_label_dates(self):
chopper = Timechop(
feature_start_time=datetime.datetime(2010, 1, 1, 0, 0),
feature_end_time=datetime.datetime(2016, 1, 1, 0, 0),
label_start_time=datetime.datetime(2015, 1, 1, 0, 0),
label_end_time=datetime.datetime(2015, 2, 1, 0, 0),
model_update_frequency="3 months",
training_as_of_date_frequencies=["1 day"],
test_as_of_date_frequencies=["1 day"],
max_training_histories=["1 year"],
test_durations=["6 months"],
test_label_timespans=["1 months"],
training_label_timespans=["3 days"],
)
# this should raise an error because there are no valid label dates in
# the labeling time (label span is longer than labeling time)
with self.assertRaises(ValueError):
chopper.calculate_train_test_split_times(
training_label_timespan=convert_str_to_relativedelta("3 days"),
test_duration="6 months",
test_label_timespan=convert_str_to_relativedelta("1 month"),
)
def test_labels_after_features(self):
chopper = Timechop(
feature_start_time=datetime.datetime(2010, 1, 1, 0, 0),
feature_end_time=datetime.datetime(2016, 1, 1, 0, 0),
label_start_time=datetime.datetime(2015, 1, 1, 0, 0),
label_end_time=datetime.datetime(2017, 1, 1, 0, 0),
model_update_frequency="3 months",
training_as_of_date_frequencies=["1 day"],
test_as_of_date_frequencies=["1 day"],
max_training_histories=["1 year"],
test_durations=["6 months"],
test_label_timespans=["1 months"],
training_label_timespans=["3 days"],
)
# this should throw an exception because last possible label date is after
# end of feature time
with self.assertRaises(ValueError):
chopper.calculate_train_test_split_times(
training_label_timespan=convert_str_to_relativedelta("3 days"),
test_duration="6 months",
test_label_timespan=convert_str_to_relativedelta("1 month"),
)
