Feature Extraction Notebook

import pandas as pd
import numpy as np
import interpreTS as it

# Creating a time series data
data = pd.DataFrame({
    'id': np.repeat(range(100), 100),
    'time': np.tile(range(100), 100),
    'value1': np.random.normal(0, 1, 10000),
    'value2': np.random.normal(20, 10, 10000)
})
# Creating a feature extractor object
extractor = it.FeatureExtractor(id_column='id', sort_column='time')

# Extracting features from data
features = extractor.extract_features(data)
print("\nFeatures from Original Data:")
display(features)

Features from Original Data:

	length_value1	length_value2	mean_value1	mean_value2	variance_value1	variance_value2	stability_value1	stability_value2	entropy_value1	entropy_value2	spikeness_value1	spikeness_value2	seasonality_strength_value1	seasonality_strength_value2
0	100	100	-0.090984	20.984855	0.980715	96.393343	0.945029	0.957836	0.953598	0.936353	-0.171176	0.002747	0.024829	0.000000
1	100	100	-0.041073	19.321699	0.860151	122.939138	0.966346	0.967090	0.965428	0.943508	0.057399	-0.160669	0.000000	0.029677
2	100	100	0.040655	19.561352	1.013766	94.271772	0.959903	0.959041	0.960737	0.971435	0.039584	-0.037157	0.000000	0.000000
3	100	100	0.089580	18.423254	0.919226	105.640273	0.961216	0.961425	0.960473	0.972152	0.162142	-0.209542	0.000000	0.002774
4	100	100	0.043688	20.889307	1.016813	98.086690	0.953565	0.972875	0.976043	0.968271	-0.094232	-0.039167	0.000000	0.014184
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
95	100	100	0.071281	22.267479	0.958148	83.890173	0.941137	0.965725	0.948012	0.917666	-0.313000	-0.285326	0.093162	0.076888
96	100	100	0.180755	18.164891	1.205403	115.013098	0.940937	0.963686	0.965665	0.954352	0.045914	-0.356734	0.000000	0.000000
97	100	100	0.027402	20.088945	1.018580	111.999915	0.948826	0.966604	0.969764	0.979842	-0.325421	-0.167496	0.199431	0.053288
98	100	100	-0.035698	21.318984	0.805854	97.065517	0.959439	0.965456	0.943548	0.956747	-0.008034	-0.280393	0.000000	0.112888
99	100	100	0.174627	21.461813	0.883258	88.348130	0.962152	0.959698	0.966687	0.958974	0.212796	-0.443187	0.038056	0.000000

100 rows × 14 columns