def test_ExpectedNumInstanceSampler(): N = 6 train_length = 2 pred_length = 1 ds = make_dataset(N, train_length) t = transform.Chain(trans=[ transform.InstanceSplitter( target_field=FieldName.TARGET, is_pad_field=FieldName.IS_PAD, start_field=FieldName.START, forecast_start_field=FieldName.FORECAST_START, train_sampler=transform.ExpectedNumInstanceSampler( num_instances=4), past_length=train_length, future_length=pred_length, pick_incomplete=True, ) ]) scale_hist = ScaleHistogram() repetition = 2 for i in range(repetition): for data in t(iter(ds), is_train=True): target_values = data["past_target"] # for simplicity, discard values that are zeros to avoid confusion with padding target_values = target_values[target_values > 0] scale_hist.add(target_values) expected_values = {i: 2**i * repetition for i in range(1, N)} assert expected_values == scale_hist.bin_counts
def test_Transformation(): train_length = 100 ds = ListDataset( [{"start": "2012-01-01", "target": [0.2] * train_length}], freq="1D" ) pred_length = 10 t = transform.Chain( trans=[ transform.AddTimeFeatures( start_field=FieldName.START, target_field=FieldName.TARGET, output_field="time_feat", time_features=[ time_feature.DayOfWeek(), time_feature.DayOfMonth(), time_feature.MonthOfYear(), ], pred_length=pred_length, ), transform.AddAgeFeature( target_field=FieldName.TARGET, output_field="age", pred_length=pred_length, log_scale=True, ), transform.AddObservedValuesIndicator( target_field=FieldName.TARGET, output_field="observed_values" ), transform.VstackFeatures( output_field="dynamic_feat", input_fields=["age", "time_feat"], drop_inputs=True, ), transform.InstanceSplitter( target_field=FieldName.TARGET, is_pad_field=FieldName.IS_PAD, start_field=FieldName.START, forecast_start_field=FieldName.FORECAST_START, train_sampler=transform.ExpectedNumInstanceSampler( num_instances=4 ), past_length=train_length, future_length=pred_length, time_series_fields=["dynamic_feat", "observed_values"], ), ] ) for u in t(iter(ds), is_train=True): print(u)
def test_BucketInstanceSampler(): N = 6 train_length = 2 pred_length = 1 ds = make_dataset(N, train_length) dataset_stats = calculate_dataset_statistics(ds) t = transform.Chain( trans=[ transform.InstanceSplitter( target_field=FieldName.TARGET, is_pad_field=FieldName.IS_PAD, start_field=FieldName.START, forecast_start_field=FieldName.FORECAST_START, train_sampler=transform.BucketInstanceSampler( dataset_stats.scale_histogram ), past_length=train_length, future_length=pred_length, pick_incomplete=True, ) ] ) scale_hist = ScaleHistogram() repetition = 200 for i in range(repetition): for data in t(iter(ds), is_train=True): target_values = data["past_target"] # for simplicity, discard values that are zeros to avoid confusion with padding target_values = target_values[target_values > 0] scale_hist.add(target_values) expected_values = {i: repetition for i in range(1, N)} found_values = scale_hist.bin_counts for i in range(1, N): assert abs( expected_values[i] - found_values[i] < expected_values[i] * 0.3 )
def test_target_dim_indicator(): target = np.array([0, 2, 3, 10]).tolist() multi_dim_target = np.array([target, target, target, target]) dataset = ListDataset( data_iter=[{"start": "2012-01-01", "target": multi_dim_target}], freq="1D", one_dim_target=False, ) t = transform.Chain( trans=[ transform.TargetDimIndicator( target_field=FieldName.TARGET, field_name="target_dimensions" ) ] ) for data_entry in t(dataset, is_train=True): assert (data_entry["target_dimensions"] == np.array([0, 1, 2, 3])).all()
def test_cdf_to_gaussian_transformation(): def make_test_data(): target = np.array([ 0, 0, 0, 0, 10, 10, 20, 20, 30, 30, 40, 50, 59, 60, 60, 70, 80, 90, 100, ]).tolist() np.random.shuffle(target) multi_dim_target = np.array([target, target]).transpose() past_is_pad = np.array([[0] * len(target)]).transpose() past_observed_target = np.array([[1] * len(target), [1] * len(target)]).transpose() ds = ListDataset( # Mimic output from InstanceSplitter data_iter=[{ "start": "2012-01-01", "target": multi_dim_target, "past_target": multi_dim_target, "future_target": multi_dim_target, "past_is_pad": past_is_pad, f"past_{FieldName.OBSERVED_VALUES}": past_observed_target, }], freq="1D", one_dim_target=False, ) return ds def make_fake_output(u: DataEntry): fake_output = np.expand_dims(np.expand_dims(u["past_target_cdf"], axis=0), axis=0) return fake_output ds = make_test_data() t = transform.Chain(trans=[ transform.CDFtoGaussianTransform( target_field=FieldName.TARGET, observed_values_field=FieldName.OBSERVED_VALUES, max_context_length=20, target_dim=2, ) ]) for u in t(iter(ds), is_train=False): fake_output = make_fake_output(u) # Fake transformation chain output u["past_target_sorted"] = torch.tensor( np.expand_dims(u["past_target_sorted"], axis=0)) u["slopes"] = torch.tensor(np.expand_dims(u["slopes"], axis=0)) u["intercepts"] = torch.tensor(np.expand_dims(u["intercepts"], axis=0)) back_transformed = transform.cdf_to_gaussian_forward_transform( u, fake_output) # Get any sample/batch (slopes[i][:, d]they are all the same) back_transformed = back_transformed[0][0] original_target = u["target"] # Original target and back-transformed target should be the same assert np.allclose(original_target, back_transformed)
def test_multi_dim_transformation(is_train): train_length = 10 first_dim: list = list(np.arange(1, 11, 1)) first_dim[-1] = "NaN" second_dim: list = list(np.arange(11, 21, 1)) second_dim[0] = "NaN" ds = ListDataset( data_iter=[{ "start": "2012-01-01", "target": [first_dim, second_dim] }], freq="1D", one_dim_target=False, ) pred_length = 2 # Looks weird - but this is necessary to assert the nan entries correctly. first_dim[-1] = np.nan second_dim[0] = np.nan t = transform.Chain(trans=[ transform.AddTimeFeatures( start_field=FieldName.START, target_field=FieldName.TARGET, output_field="time_feat", time_features=[ time_feature.DayOfWeek(), time_feature.DayOfMonth(), time_feature.MonthOfYear(), ], pred_length=pred_length, ), transform.AddAgeFeature( target_field=FieldName.TARGET, output_field="age", pred_length=pred_length, log_scale=True, ), transform.AddObservedValuesIndicator( target_field=FieldName.TARGET, output_field="observed_values", convert_nans=False, ), transform.VstackFeatures( output_field="dynamic_feat", input_fields=["age", "time_feat"], drop_inputs=True, ), transform.InstanceSplitter( target_field=FieldName.TARGET, is_pad_field=FieldName.IS_PAD, start_field=FieldName.START, forecast_start_field=FieldName.FORECAST_START, train_sampler=transform.ExpectedNumInstanceSampler( num_instances=4), past_length=train_length, future_length=pred_length, time_series_fields=["dynamic_feat", "observed_values"], time_first=False, ), ]) if is_train: for u in t(iter(ds), is_train=True): assert_shape(u["past_target"], (2, 10)) assert_shape(u["past_dynamic_feat"], (4, 10)) assert_shape(u["past_observed_values"], (2, 10)) assert_shape(u["future_target"], (2, 2)) assert_padded_array( u["past_observed_values"], np.array([[1.0] * 9 + [0.0], [0.0] + [1.0] * 9]), u["past_is_pad"], ) assert_padded_array( u["past_target"], np.array([first_dim, second_dim]), u["past_is_pad"], ) else: for u in t(iter(ds), is_train=False): assert_shape(u["past_target"], (2, 10)) assert_shape(u["past_dynamic_feat"], (4, 10)) assert_shape(u["past_observed_values"], (2, 10)) assert_shape(u["future_target"], (2, 0)) assert_padded_array( u["past_observed_values"], np.array([[1.0] * 9 + [0.0], [0.0] + [1.0] * 9]), u["past_is_pad"], ) assert_padded_array( u["past_target"], np.array([first_dim, second_dim]), u["past_is_pad"], )