Note
Click here to download the full example code
Simple FeatureRepMix ExampleΒΆ
This example demonstrates how to use the FeatureRepMix on segmented data.
Although not shown here, FeatureRepMix can be used with Pype in place of FeatureRep. See API documentation for an example.
Out:
After segmentation:
X: [[[ 0. 1. 2. 3.]
[ 4. 5. 6. 7.]
[ 8. 9. 10. 11.]]]
y: [0.]
After column-wise feature extraction:
a_min_0 b_min_1 c_min_2 c_min_3 d_max_0 d_max_1 e_max_2 e_max_3
0 0.0 1.0 2.0 3.0 8.0 9.0 10.0 11.0
# Author: Matthias Gazzari
# License: BSD
from seglearn.transform import Segment, FeatureRep, FeatureRepMix
from seglearn.feature_functions import minimum, maximum
from seglearn.base import TS_Data
import numpy as np
import pandas as pd
# Single multivariate time series with 3 samples of 4 variables
X = [np.array([[0, 1, 2, 3], [4, 5, 6, 7], [8, 9, 10, 11]])]
# Time series target
y = [np.array([True, False, False])]
segment = Segment(width=3, overlap=1)
X, y, _ = segment.fit_transform(X, y)
print('After segmentation:')
print("X:", X)
print("y: ", y)
union = FeatureRepMix([
('a', FeatureRep(features={'min': minimum}), 0),
('b', FeatureRep(features={'min': minimum}), 1),
('c', FeatureRep(features={'min': minimum}), [2, 3]),
('d', FeatureRep(features={'max': maximum}), slice(0, 2)),
('e', FeatureRep(features={'max': maximum}), [False, False, True, True]),
])
X = union.fit_transform(X, y)
print('After column-wise feature extraction:')
df = pd.DataFrame(data=X, columns=union.f_labels)
print(df)
Total running time of the script: ( 0 minutes 1.887 seconds)