def test_correct_data_is_marked_as_change_point(self):
input_data = [5, 5, 5, 5, 5, 5, 5, 5]
input_data.extend([7, 7, 7, 7, 7, 7, 7, 7])
X_train = pd.Series(input_data, name="ts")
cpd = IidChangePointDetector(confidence=95,
change_history_length=4) << {
'result': 'ts'
}
data = cpd.fit_transform(X_train)
self.assertEqual(data.loc[8, '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([
IidChangePointDetector(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()
###############################################################################
# IidChangePointDetector
import pandas as pd
from nimbusml.timeseries import IidChangePointDetector
# Create a sample series with a change
input_data = [5, 5, 5, 5, 5, 5, 5, 5]
input_data.extend([7, 7, 7, 7, 7, 7, 7, 7])
X_train = pd.Series(input_data, name="ts")
cpd = IidChangePointDetector(confidence=95, change_history_length=4) << {
'result': 'ts'
}
data = cpd.fit_transform(X_train)
print(data)
# ts result.Alert result.Raw Score result.P-Value Score result.Martingale Score
# 0 5 0.0 5.0 5.000000e-01 0.001213
# 1 5 0.0 5.0 5.000000e-01 0.001213
# 2 5 0.0 5.0 5.000000e-01 0.001213
# 3 5 0.0 5.0 5.000000e-01 0.001213
# 4 5 0.0 5.0 5.000000e-01 0.001213
# 5 5 0.0 5.0 5.000000e-01 0.001213
# 6 5 0.0 5.0 5.000000e-01 0.001213
# 7 5 0.0 5.0 5.000000e-01 0.001213
# 8 7 1.0 7.0 1.000000e-08 10298.666376 <-- alert is on, predicted changepoint
# 9 7 0.0 7.0 1.328455e-01 33950.164799
# 10 7 0.0 7.0 2.613750e-01 60866.342063
# 11 7 0.0 7.0 3.776152e-01 78362.038772
'LightGbmRegressor':
LightGbmRegressor(minimum_example_count_per_group=1,
minimum_example_count_per_leaf=1),
'LightGbmRanker':
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']}),
'FromKey': Pipeline([
ToKey(columns=['Sepal_Length']),
FromKey(columns=['Sepal_Length'])
]),
# GlobalContrastRowScaler currently requires a vector input to work
'GlobalContrastRowScaler': Pipeline([
ColumnConcatenator() << {
'concated_columns': [
'Petal_Length',
'Sepal_Width',
'Sepal_Length']},
GlobalContrastRowScaler(columns={'normed_columns': 'concated_columns'})
]),
'Handler': Handler(replace_with='Mean', columns={'NewVals': 'Petal_Length'}),
'IidSpikeDetector': IidSpikeDetector(columns=['Sepal_Length']),
'IidChangePointDetector': IidChangePointDetector(columns=['Sepal_Length']),
'Indicator': Indicator(columns={'Has_Nan': 'Petal_Length'}),
'KMeansPlusPlus': KMeansPlusPlus(n_clusters=3, feature=['Sepal_Width', 'Sepal_Length']),
'LightGbmRanker': LightGbmRanker(feature=['Class', 'dep_day', 'duration'],
label='rank',
group_id='group'),
'Loader': Loader(columns={'ImgPath': 'Path'}),
'LpScaler': Pipeline([
ColumnConcatenator() << {
'concated_columns': [
'Petal_Length',
'Sepal_Width',
'Sepal_Length']},
LpScaler(columns={'normed_columns': 'concated_columns'})
]),
'MutualInformationSelector': Pipeline([
# 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(
[IidChangePointDetector(columns={'t2_cp': 't2'}, change_history_length=4)])
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 0.01 5.000000e-01 1.212573e-03
# 1 0.02 0.02 0.0200 0.0 0.02 4.960106e-01 1.221347e-03
# 2 0.03 0.03 0.0200 0.0 0.03 1.139087e-02 3.672914e-02
# 3 0.03 0.03 0.0250 0.0 0.03 2.058296e-01 8.164447e-02
# 4 0.03 0.03 0.0005 0.0 0.03 2.804577e-01 1.373786e-01
# 5 0.03 0.05 0.0100 1.0 0.05 1.448886e-06 1.315014e+04
# 6 0.05 0.07 0.0500 0.0 0.07 2.616611e-03 4.941587e+04
# 7 0.07 0.09 0.0900 0.0 0.09 3.053187e-02 2.752614e+05
# 8 0.09 99.00 99.0000 0.0 99.00 1.000000e-08 1.389396e+12
# 9 1.10 0.10 0.1000 1.0 0.10 3.778296e-01 1.854344e+07