def test_look_back_time_equal_modeling_start(self):
# TODO: rework this test since the test label window of 3 months
# cannot be satisfied by the 10 day difference between modeling
# start and end times, so it's not a very realistic case
expected_result = {
'feature_start_time': datetime.datetime(1990, 1, 1, 0, 0),
'label_start_time': datetime.datetime(2010, 1, 1, 0, 0),
'feature_end_time': datetime.datetime(2010, 1, 11, 0, 0),
'label_end_time': datetime.datetime(2010, 1, 11, 0, 0),
'train_matrix': {
'first_as_of_time': datetime.datetime(2010, 1, 1, 0, 0),
'last_as_of_time': datetime.datetime(2010, 1, 5, 0, 0),
'matrix_info_end_time': datetime.datetime(2010, 1, 6, 0, 0),
'as_of_times': [
datetime.datetime(2010, 1, 1, 0, 0),
datetime.datetime(2010, 1, 2, 0, 0),
datetime.datetime(2010, 1, 3, 0, 0),
datetime.datetime(2010, 1, 4, 0, 0),
datetime.datetime(2010, 1, 5, 0, 0)
],
'training_label_timespan': '1 day',
'training_as_of_date_frequency': '1 days',
'max_training_history': '5 days'
},
'test_matrices': [{
'first_as_of_time': datetime.datetime(2010, 1, 6, 0, 0),
'last_as_of_time': datetime.datetime(2010, 1, 9, 0, 0),
'matrix_info_end_time': datetime.datetime(2010, 1, 10, 0, 0),
'as_of_times': [
datetime.datetime(2010, 1, 6, 0, 0),
datetime.datetime(2010, 1, 9, 0, 0)
],
'test_label_timespan': '1 day',
'test_as_of_date_frequency': '3 days',
'test_duration': '5 days'
}]
}
chopper = Timechop(
feature_start_time=datetime.datetime(1990, 1, 1, 0, 0),
feature_end_time=datetime.datetime(2010, 1, 11, 0, 0),
label_start_time=datetime.datetime(2010, 1, 1, 0, 0),
label_end_time=datetime.datetime(2010, 1, 11, 0, 0),
model_update_frequency='5 days',
training_as_of_date_frequencies=['1 days'],
test_as_of_date_frequencies=['3 days'],
max_training_histories=['5 days'],
test_durations=['5 days'],
test_label_timespans=['1 day'],
training_label_timespans=['1 day']
)
result = chopper.generate_matrix_definitions(
train_test_split_time=datetime.datetime(2010, 1, 6, 0, 0),
training_as_of_date_frequency='1 days',
max_training_history='5 days',
test_duration='5 days',
test_label_timespan='1 day',
training_label_timespan='1 day'
)
assert result == expected_result
def test_look_back_time_before_modeling_start(self):
expected_result = {
"feature_start_time": datetime.datetime(1990, 1, 1, 0, 0),
"label_start_time": datetime.datetime(2010, 1, 1, 0, 0),
"feature_end_time": datetime.datetime(2010, 1, 11, 0, 0),
"label_end_time": datetime.datetime(2010, 1, 11, 0, 0),
"train_matrix": {
"first_as_of_time": datetime.datetime(2010, 1, 1, 0, 0),
"last_as_of_time": datetime.datetime(2010, 1, 5, 0, 0),
"matrix_info_end_time": datetime.datetime(2010, 1, 6, 0, 0),
"as_of_times": [
datetime.datetime(2010, 1, 1, 0, 0),
datetime.datetime(2010, 1, 2, 0, 0),
datetime.datetime(2010, 1, 3, 0, 0),
datetime.datetime(2010, 1, 4, 0, 0),
datetime.datetime(2010, 1, 5, 0, 0),
],
"training_label_timespan": "1 day",
"training_as_of_date_frequency": "1 days",
"max_training_history": "10 days",
},
"test_matrices": [
{
"first_as_of_time": datetime.datetime(2010, 1, 6, 0, 0),
"last_as_of_time": datetime.datetime(2010, 1, 9, 0, 0),
"matrix_info_end_time": datetime.datetime(2010, 1, 10, 0, 0),
"as_of_times": [
datetime.datetime(2010, 1, 6, 0, 0),
datetime.datetime(2010, 1, 9, 0, 0),
],
"test_label_timespan": "1 day",
"test_as_of_date_frequency": "3 days",
"test_duration": "5 days",
},
{
"first_as_of_time": datetime.datetime(2010, 1, 6, 0, 0),
"last_as_of_time": datetime.datetime(2010, 1, 6, 0, 0),
"matrix_info_end_time": datetime.datetime(2010, 1, 7, 0, 0),
"as_of_times": [datetime.datetime(2010, 1, 6, 0, 0)],
"test_label_timespan": "1 day",
"test_as_of_date_frequency": "6 days",
"test_duration": "5 days",
},
],
}
chopper = Timechop(
feature_start_time=datetime.datetime(1990, 1, 1, 0, 0),
feature_end_time=datetime.datetime(2010, 1, 11, 0, 0),
label_start_time=datetime.datetime(2010, 1, 1, 0, 0),
label_end_time=datetime.datetime(2010, 1, 11, 0, 0),
model_update_frequency="5 days",
training_as_of_date_frequencies=["1 days"],
test_as_of_date_frequencies=["3 days", "6 days"],
max_training_histories=["10 days"],
test_durations=["5 days"],
test_label_timespans=["1 day"],
training_label_timespans=["1 day"],
)
result = chopper.generate_matrix_definitions(
train_test_split_time=datetime.datetime(2010, 1, 6, 0, 0),
training_as_of_date_frequency="1 days",
max_training_history="10 days",
test_duration="5 days",
test_label_timespan="1 day",
training_label_timespan="1 day",
)
assert result == expected_result
def test_look_back_time_equal_modeling_start(self):
# TODO: rework this test since the test label window of 3 months
# cannot be satisfied by the 10 day difference between modeling
# start and end times, so it's not a very realistic case
expected_result = {
"feature_start_time": datetime.datetime(1990, 1, 1, 0, 0),
"label_start_time": datetime.datetime(2010, 1, 1, 0, 0),
"feature_end_time": datetime.datetime(2010, 1, 11, 0, 0),
"label_end_time": datetime.datetime(2010, 1, 11, 0, 0),
"train_matrix": {
"first_as_of_time": datetime.datetime(2010, 1, 1, 0, 0),
"last_as_of_time": datetime.datetime(2010, 1, 5, 0, 0),
"matrix_info_end_time": datetime.datetime(2010, 1, 6, 0, 0),
"as_of_times": [
datetime.datetime(2010, 1, 1, 0, 0),
datetime.datetime(2010, 1, 2, 0, 0),
datetime.datetime(2010, 1, 3, 0, 0),
datetime.datetime(2010, 1, 4, 0, 0),
datetime.datetime(2010, 1, 5, 0, 0),
],
"training_label_timespan": "1 day",
"training_as_of_date_frequency": "1 days",
"max_training_history": "5 days",
},
"test_matrices": [
{
"first_as_of_time": datetime.datetime(2010, 1, 6, 0, 0),
"last_as_of_time": datetime.datetime(2010, 1, 9, 0, 0),
"matrix_info_end_time": datetime.datetime(2010, 1, 10, 0, 0),
"as_of_times": [
datetime.datetime(2010, 1, 6, 0, 0),
datetime.datetime(2010, 1, 9, 0, 0),
],
"test_label_timespan": "1 day",
"test_as_of_date_frequency": "3 days",
"test_duration": "5 days",
}
],
}
chopper = Timechop(
feature_start_time=datetime.datetime(1990, 1, 1, 0, 0),
feature_end_time=datetime.datetime(2010, 1, 11, 0, 0),
label_start_time=datetime.datetime(2010, 1, 1, 0, 0),
label_end_time=datetime.datetime(2010, 1, 11, 0, 0),
model_update_frequency="5 days",
training_as_of_date_frequencies=["1 days"],
test_as_of_date_frequencies=["3 days"],
max_training_histories=["5 days"],
test_durations=["5 days"],
test_label_timespans=["1 day"],
training_label_timespans=["1 day"],
)
result = chopper.generate_matrix_definitions(
train_test_split_time=datetime.datetime(2010, 1, 6, 0, 0),
training_as_of_date_frequency="1 days",
max_training_history="5 days",
test_duration="5 days",
test_label_timespan="1 day",
training_label_timespan="1 day",
)
assert result == expected_result
def test_look_back_time_before_modeling_start(self):
expected_result = {
'feature_start_time': datetime.datetime(1990, 1, 1, 0, 0),
'label_start_time': datetime.datetime(2010, 1, 1, 0, 0),
'feature_end_time': datetime.datetime(2010, 1, 11, 0, 0),
'label_end_time': datetime.datetime(2010, 1, 11, 0, 0),
'train_matrix': {
'first_as_of_time': datetime.datetime(2010, 1, 1, 0, 0),
'last_as_of_time': datetime.datetime(2010, 1, 5, 0, 0),
'matrix_info_end_time': datetime.datetime(2010, 1, 6, 0, 0),
'as_of_times': [
datetime.datetime(2010, 1, 1, 0, 0),
datetime.datetime(2010, 1, 2, 0, 0),
datetime.datetime(2010, 1, 3, 0, 0),
datetime.datetime(2010, 1, 4, 0, 0),
datetime.datetime(2010, 1, 5, 0, 0)
],
'training_label_timespan': '1 day',
'training_as_of_date_frequency': '1 days',
'max_training_history': '10 days'
},
'test_matrices': [
{
'first_as_of_time': datetime.datetime(2010, 1, 6, 0, 0),
'last_as_of_time': datetime.datetime(2010, 1, 9, 0, 0),
'matrix_info_end_time': datetime.datetime(2010, 1, 10, 0, 0),
'as_of_times': [
datetime.datetime(2010, 1, 6, 0, 0),
datetime.datetime(2010, 1, 9, 0, 0)
],
'test_label_timespan': '1 day',
'test_as_of_date_frequency': '3 days',
'test_duration': '5 days'
},
{
'first_as_of_time': datetime.datetime(2010, 1, 6, 0, 0),
'last_as_of_time': datetime.datetime(2010, 1, 6, 0, 0),
'matrix_info_end_time': datetime.datetime(2010, 1, 7, 0, 0),
'as_of_times': [
datetime.datetime(2010, 1, 6, 0, 0),
],
'test_label_timespan': '1 day',
'test_as_of_date_frequency': '6 days',
'test_duration': '5 days'
}
]
}
chopper = Timechop(
feature_start_time=datetime.datetime(1990, 1, 1, 0, 0),
feature_end_time=datetime.datetime(2010, 1, 11, 0, 0),
label_start_time=datetime.datetime(2010, 1, 1, 0, 0),
label_end_time=datetime.datetime(2010, 1, 11, 0, 0),
model_update_frequency='5 days',
training_as_of_date_frequencies=['1 days'],
test_as_of_date_frequencies=['3 days', '6 days'],
max_training_histories=['10 days'],
test_durations=['5 days'],
test_label_timespans=['1 day'],
training_label_timespans=['1 day']
)
result = chopper.generate_matrix_definitions(
train_test_split_time=datetime.datetime(2010, 1, 6, 0, 0),
training_as_of_date_frequency='1 days',
max_training_history='10 days',
test_duration='5 days',
test_label_timespan='1 day',
training_label_timespan='1 day'
)
assert result == expected_result
