def test_simple_forecast(self):
seasonality_size = 5
seasonal_data = np.arange(seasonality_size)
data = np.tile(seasonal_data, 3)
X_train = pd.Series(data, name="ts")
training_seasons = 3
training_size = seasonality_size * training_seasons
forecaster = SsaForecaster(series_length=8,
train_size=training_size,
window_size=seasonality_size + 1,
horizon=2) << {
'fc': 'ts'
}
forecaster.fit(X_train, verbose=1)
data = forecaster.transform(X_train)
self.assertEqual(round(data.loc[0, 'fc.0']), 1.0)
self.assertEqual(round(data.loc[0, 'fc.1']), 2.0)
self.assertEqual(len(data['fc.0']), 15)
def get_uni_standard_trained_on_entire_data_ssa_pipeline():
return Pipeline([
SsaForecaster(series_length=6,
train_size=20,
window_size=3,
horizon=1,
columns={'T (degC)_fc': 'T (degC)'})
])
def test_multiple_user_specified_columns_is_not_allowed(self):
path = get_dataset('timeseries').as_filepath()
data = FileDataStream.read_csv(path)
try:
pipeline = Pipeline([
SsaForecaster(series_length=8,
train_size=15,
window_size=5,
horizon=2,
columns=['t2', 't3'])
])
pipeline.fit_transform(data)
except RuntimeError as e:
self.assertTrue('Only one column is allowed' in str(e))
return
self.fail()
'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',
'LogisticRegressionClassifier', 'FastTreesRegressor',
'FastForestRegressor', 'FastTreesTweedieRegressor',
'OneClassSvmAnomalyDetector', 'NaiveBayesClassifier',
'GamBinaryClassifier', 'GamRegressor', 'OnlineGradientDescentRegressor',
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']}),
'ToKey': ToKey(columns={'edu_1': 'education_str'}),
'TypeConverter': TypeConverter(columns=['group'], result_type='R4'),
'WordTokenizer': WordTokenizer(char_array_term_separators=[" "]) << {'wt': 'SentimentText'}
# 5 0
# 6 1
# 7 2
# 8 3
# 9 4
# 10 0
# 11 1
# 12 100
# 13 110
# 14 120
training_seasons = 3
training_size = seasonality_size * training_seasons
forecaster = SsaForecaster(series_length=8,
train_size=training_size,
window_size=seasonality_size + 1,
horizon=4) << {
'fc': 'ts'
}
forecaster.fit(X_train, verbose=1)
data = forecaster.transform(x_test)
pd.set_option('display.float_format', lambda x: '%.2f' % x)
print(data)
# The fc.x columns are the forecasts
# given the input in the ts column.
#
# ts fc.0 fc.1 fc.2 fc.3
# 0 0 1.00 2.00 3.00 4.00
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([
SsaForecaster(series_length=6,
train_size=8,
window_size=3,
horizon=2,
columns={'t2_fc': 't2'})
])
result = pipeline.fit_transform(data)
pd.set_option('display.float_format', lambda x: '%.2f' % x)
print(result)
# Output
#
# t1 t2 t3 t2_fc.0 t2_fc.1
# 0 0.01 0.01 0.01 0.10 0.12
# 1 0.02 0.02 0.02 0.06 0.08
# 2 0.03 0.03 0.02 0.04 0.05