def test_correct_data_is_marked_as_change_point(self):
seasonality_size = 5
seasonal_data = np.arange(seasonality_size)
data = np.tile(seasonal_data, 3)
data = np.append(data, [0, 100, 200, 300, 400]) # change distribution
X_train = pd.Series(data, name="ts")
training_seasons = 3
training_size = seasonality_size * training_seasons
cpd = SsaChangePointDetector(confidence=95,
change_history_length=8,
training_window_size=training_size,
seasonal_window_size=seasonality_size + 1) << {'result': 'ts'}
cpd.fit(X_train, verbose=1)
data = cpd.transform(X_train)
self.assertEqual(data.loc[16, 'result.Alert'], 1.0)
data = data.loc[data['result.Alert'] == 1.0]
self.assertEqual(len(data), 1)
def test_multiple_user_specified_columns_is_not_allowed(self):
path = get_dataset('timeseries').as_filepath()
data = FileDataStream.read_csv(path)
try:
pipeline = Pipeline([
SsaChangePointDetector(columns=['t2', 't3'], change_history_length=5)
])
pipeline.fit_transform(data)
except RuntimeError as e:
self.assertTrue('Only one column is allowed' in str(e))
return
self.fail()
LightGbmRanker(minimum_example_count_per_group=1,
minimum_example_count_per_leaf=1),
'NGramFeaturizer':
NGramFeaturizer(word_feature_extractor=n_gram()),
'SkipFilter':
SkipFilter(count=5),
'TakeFilter':
TakeFilter(count=100000),
'IidSpikeDetector':
IidSpikeDetector(columns=['F0']),
'IidChangePointDetector':
IidChangePointDetector(columns=['F0']),
'SsaSpikeDetector':
SsaSpikeDetector(columns=['F0'], seasonal_window_size=2),
'SsaChangePointDetector':
SsaChangePointDetector(columns=['F0'], seasonal_window_size=2),
'SsaForecaster':
SsaForecaster(columns=['F0'],
window_size=2,
series_length=5,
train_size=5,
horizon=1),
'TensorFlowScorer':
TensorFlowScorer(model_location=os.path.join(this, '..', 'nimbusml',
'examples',
'frozen_saved_model.pb'),
columns={'c': ['a', 'b']}),
}
MULTI_OUTPUT_EX = [
'FastLinearClassifier', 'FastLinearRegressor',
'PcaAnomalyDetector': PcaAnomalyDetector(rank=3),
'PcaTransformer': PcaTransformer(rank=2),
'PixelExtractor': Pipeline([
Loader(columns={'ImgPath': 'Path'}),
PixelExtractor(columns={'ImgPixels': 'ImgPath'}),
]),
'PrefixColumnConcatenator': PrefixColumnConcatenator(columns={'Features': 'Sepal_'}),
'Resizer': Pipeline([
Loader(columns={'ImgPath': 'Path'}),
Resizer(image_width=227, image_height=227,
columns={'ImgResize': 'ImgPath'})
]),
'SkipFilter': SkipFilter(count=5),
'SsaSpikeDetector': SsaSpikeDetector(columns=['Sepal_Length'],
seasonal_window_size=2),
'SsaChangePointDetector': SsaChangePointDetector(columns=['Sepal_Length'],
seasonal_window_size=2),
'SsaForecaster': SsaForecaster(columns=['Sepal_Length'],
window_size=2,
series_length=5,
train_size=5,
horizon=1),
'RangeFilter': RangeFilter(min=5.0, max=5.1, columns=['Sepal_Length']),
'TakeFilter': TakeFilter(count=100),
'TensorFlowScorer': TensorFlowScorer(
model_location=os.path.join(
script_dir,
'..',
'nimbusml',
'examples',
'frozen_saved_model.pb'),
columns={'c': ['a', 'b']}),
# 10 0
# 11 1
# 12 2
# 13 3
# 14 4
# 15 0
# 16 100
# 17 200
# 18 300
# 19 400
training_seasons = 3
training_size = seasonality_size * training_seasons
cpd = SsaChangePointDetector(confidence=95,
change_history_length=8,
training_window_size=training_size,
seasonal_window_size=seasonality_size + 1) << {'result': 'ts'}
cpd.fit(X_train, verbose=1)
data = cpd.transform(X_train)
print(data)
# ts result.Alert result.Raw Score result.P-Value Score result.Martingale Score
# 0 0 0.0 -2.531824 5.000000e-01 1.470334e-06
# 1 1 0.0 -0.008832 5.818072e-03 8.094459e-05
# 2 2 0.0 0.763040 1.374071e-01 2.588526e-04
# 3 3 0.0 0.693811 2.797713e-01 4.365186e-04
# 4 4 0.0 1.442079 1.838294e-01 1.074242e-03
# 5 0 0.0 -1.844414 1.707238e-01 2.825599e-03
# 6 1 0.0 0.219578 4.364025e-01 3.193633e-03
# data input (as a FileDataStream)
path = get_dataset('timeseries').as_filepath()
data = FileDataStream.read_csv(path)
print(data.head())
# t1 t2 t3
# 0 0.01 0.01 0.0100
# 1 0.02 0.02 0.0200
# 2 0.03 0.03 0.0200
# 3 0.03 0.03 0.0250
# 4 0.03 0.03 0.0005
# define the training pipeline
pipeline = Pipeline([
SsaChangePointDetector(columns={'t2_cp': 't2'},
change_history_length=4,
training_window_size=8,
seasonal_window_size=3)
])
result = pipeline.fit_transform(data)
print(result)
# t1 t2 t3 t2_cp.Alert t2_cp.Raw Score t2_cp.P-Value Score t2_cp.Martingale Score
# 0 0.01 0.01 0.0100 0.0 -0.111334 5.000000e-01 0.001213
# 1 0.02 0.02 0.0200 0.0 -0.076755 4.862075e-01 0.001243
# 2 0.03 0.03 0.0200 0.0 -0.034871 3.856320e-03 0.099119
# 3 0.03 0.03 0.0250 0.0 -0.012559 8.617091e-02 0.482400
# 4 0.03 0.03 0.0005 0.0 -0.015723 2.252377e-01 0.988788
# 5 0.03 0.05 0.0100 0.0 -0.001133 1.767711e-01 2.457946
# 6 0.05 0.07 0.0500 0.0 0.006265 9.170460e-02 0.141898
# 7 0.07 0.09 0.0900 0.0 0.002383 2.701134e-01 0.050747