v0.16.1

IssueID #3922: v0.16.1 - Readded baseline unit tests - Readded large_number_of_peaks removed in v0.9.0 - Readded mean_autocorrelation removed in v0.9.0 - Reverted to original augmented_dickey_fuller that was changed in v0.9.0 - Reverted to original fft_coefficient that was changed in v0.9.0 - Readded mean_abs_change_quantiles that was removed in v0.9.0 - Readded the original time_reversal_asymmetry_statistic that was in use pre v0.9.0 - blue-yonder#198 - Readded original autocorrelation that was removed in v0.9.0 - Disabled partial_autocorrelation added in v0.10.0 - Disabled cid_ce added in v0.11.1 - Disabled fft_aggregated added in v0.11.0 - Disabled Fix agg change made to agg_autocorrelation added in v0.11.1 blue-yonder@a53fb6a - Changed to new value_count and range_count method added in v0.11.1 - Configured settings for pre v0.9.0 features - Hardcoded TSFRESH_BASELINE_VERSION = '0.9.1' in tests - Disabled linear_trend_timewise added in v0.12.0 - Readded tsfresh/examples/test_tsfresh_baseline_dataset.py which was removed in v0.12.0 - Use v0.11.01 value_count and range_count method not as per v0.13.0 - Disabled count_above and count_below features that were added in v0.15.0 - Configured settings for pre v0.9.0 features - Hardcoded TSFRESH_BASELINE_VERSION = '0.16.1' in tests Added: tests/baseline/tsfresh-0.1.2.py2.data.json.features.transposed.csv tests/baseline/tsfresh-0.3.0.py2.data.json.features.transposed.csv tests/baseline/tsfresh-0.3.0.py3.data.json.features.transposed.csv tests/baseline/tsfresh-0.3.1.py2.data.json.features.transposed.csv tests/baseline/tsfresh-0.3.1.py3.data.json.features.transposed.csv tests/baseline/tsfresh-0.4.0.py2.data.json.features.transposed.csv tests/baseline/tsfresh-0.4.0.py3.data.json.features.transposed.csv tests/baseline/tsfresh-0.5.0.py2.data.json.features.transposed.csv tests/baseline/tsfresh-0.5.0.py3.data.json.features.transposed.csv tests/baseline/tsfresh-0.5.1.py3.data.json.features.transposed.csv tests/baseline/tsfresh-0.6.0.py2.data.json.features.transposed.csv tests/baseline/tsfresh-0.6.0.py3.data.json.features.transposed.csv tests/baseline/tsfresh-0.6.1.py3.data.json.features.transposed.csv tests/baseline/tsfresh-0.7.2.py3.data.json.features.transposed.csv tests/baseline/tsfresh-0.8.2.py3.data.json.features.transposed.csv tests/baseline/tsfresh-0.9.1.py3.data.json.features.transposed.csv tests/baseline/tsfresh-0.10.2.py3.data.json.features.transposed.csv tests/baseline/tsfresh-0.11.3.py3.data.json.features.transposed.csv tests/baseline/tsfresh-0.12.1.py3.data.json.features.transposed.csv tests/baseline/tsfresh-0.13.1.py3.data.json.features.transposed.csv tests/baseline/tsfresh-0.14.1.py3.data.json.features.transposed.csv tests/baseline/tsfresh-0.15.2.py3.data.json.features.transposed.csv tests/baseline/tsfresh-0.16.1.py3.data.json.features.transposed.csv tests/baseline/tsfresh_features_test.py Modified: CHANGES.rst README.md tsfresh/feature_extraction/feature_calculators.py tsfresh/feature_extraction/settings.py
earthgecko · Dec 31, 2020 · 7e4f4b3 · 7e4f4b3
1 parent a003983
commit 7e4f4b3
Show file tree

Hide file tree

Showing 29 changed files with 5,742 additions and 66 deletions.
diff --git a/CHANGES.rst b/CHANGES.rst
@@ -4,6 +4,12 @@ Changelog
 
 tsfresh uses `Semantic Versioning <http://semver.org/>`_
 
+Version 0.16.1
+==============
+
+- Disabled count_above and count_below features that were added in v0.15.0
+- Merged previous v0.15.2 changes
+
 Version 0.16.0
 ==============
 
@@ -32,6 +38,11 @@ Version 0.16.0
       But your results will change!
 
 
+Version 0.15.2
+==============
+
+- Disabled new features count_above and count_below
+
 Version 0.15.1
 ==============
 
@@ -50,6 +61,11 @@ Version 0.15.0
     - Add missing distributor keyword (#648)
     - Fix tuple input for cwt (#645)
 
+Version 0.14.1 (2)
+==============
+
+- Merged 0.14.0 changes
+
 Version 0.14.1
 ==============
 
@@ -75,6 +91,10 @@ Version 0.14.0
     - Replace Benjamini-Hochberg implementation with statsmodels implementation (#570)
     - Fix the kernel and the naming of a notebook (#626)
 
+Version 0.13.1
+==============
+
+- Reverted to the v0.11.1 value_count setting
 
 Version 0.13.0
 ==============
@@ -102,6 +122,11 @@ Version 0.13.0
     - Improve performance with Numpy's sum function (#567)
     - Optimize mean_change (fixes issue #542) and correct documentation (#574)
 
+Version 0.12.1
+==============
+
+- Disabled linear_trend_timewise added in v0.12.0
+- Readded tsfresh/examples/test_tsfresh_baseline_dataset.py which was removed in v0.12.0
 
 Version 0.12.0
 ==============
@@ -117,6 +142,12 @@ Version 0.12.0
 - enable the RelevantFeatureAugmenter to be used in cross validated pipelines
 - increased scipy dependency to 1.2.0
 
+Version 0.11.3
+==============
+- Disabled new feature calculators:
+    - fft_aggregated
+    - cid_ce
+- reverted to the original mean_second_derivate_central from mean_second_derivative_central
 
 Version 0.11.2
 ==============

diff --git a/README.md b/README.md
@@ -7,6 +7,21 @@
 [![Binder](https://mybinder.org/badge.svg)](https://mybinder.org/v2/gh/blue-yonder/tsfresh/master?filepath=notebooks)
 [![Downloads](https://pepy.tech/badge/tsfresh)](https://pepy.tech/project/tsfresh)
 
+# MODIFIED FORK
+
+This repository contains a *MODIFIED FORK* of the tsfresh python package for use with Skyline.
+This modified fork maintains the features extracted at v0.4.0 but moves this tsfresh version forward in line with blue-yonder/tsfresh in terms of tsfresh internals and dependencies, etc.
+
+- New features added to blue-yonder/tsfresh are disabled in this version
+- Original methods for features are maintained even if they are changed in blue-yonder/tsfresh
+
+*NOTE*: these branches/versions are tested against the tests/baseline/tsfresh_features_test.py, which was
+removed from blue-yonder/tsfresh in v0.7.0 but has been readded to this fork. These branches/versions are
+only tested via the Skyline build tests, they *are not* tested against the tsfresh tests.  Seeing as this
+fork follows the blue-yonder/tsfresh versions and retrospectively makes backwards compatible changes to the
+settings and feature_calculators.py which work with the Skyline tests.  Therefore these changes are not
+currently backported to the tsfresh tests themselves and the tsfresh tests will fail if run against any
+of theses branches.
 
 # tsfresh
 

diff --git a/tests/baseline/tsfresh-0.1.2.py2.data.json.features.transposed.csv b/tests/baseline/tsfresh-0.1.2.py2.data.json.features.transposed.csv
@@ -0,0 +1,207 @@
+,tsfresh_features_test
+value__symmetry_looking__r_0.65,1.0
+value__mean_abs_change_quantiles__qh_1.0__ql_0.0,46.6949152542
+value__absolute_sum_of_changes,2755.0
+value__augmented_dickey_fuller,-0.804122034203
+value__large_number_of_peaks__n_3,1.0
+value__large_number_of_peaks__n_5,0.0
+value__last_location_of_minimum,0.0333333333333
+value__mean_abs_change_quantiles__qh_0.4__ql_0.0,35.6
+value__mean_abs_change_quantiles__qh_0.4__ql_0.2,12.0
+value__minimum,9856.0
+value__mean_abs_change_quantiles__qh_0.4__ql_0.6,0.0
+value__mean_abs_change_quantiles__qh_0.4__ql_0.8,0.0
+value__maximum,10123.0
+value__value_count__value_-inf,0.0
+value__number_peaks__n_1,21.0
+value__number_peaks__n_3,9.0
+value__longest_strike_above_mean,10.0
+value__number_peaks__n_5,4.0
+value__first_location_of_minimum,0.0166666666667
+value__large_standard_deviation__r_0.25,0.0
+value__large_number_of_peaks__n_1,1.0
+value__count_above_mean,29.0
+value__symmetry_looking__r_0.75,1.0
+value__mean_abs_change,46.6949152542
+value__mean_change,2.38983050847
+value__value_count__value_1,0.0
+value__value_count__value_0,0.0
+value__mean_abs_change_quantiles__qh_0.4__ql_0.4,0.0
+value__mean_autocorrelation,1.1720475294
+value__autocorrelation__lag_5,0.464639525765
+value__median,9981.0
+value__symmetry_looking__r_0.85,1.0
+value__mean_abs_change_quantiles__qh_0.8__ql_0.4,20.0
+value__symmetry_looking__r_0.05,1.0
+value__mean_abs_change_quantiles__qh_0.8__ql_0.6,13.0
+value__value_count__value_inf,0.0
+value__mean_abs_change_quantiles__qh_0.8__ql_0.0,43.0256410256
+value__mean_abs_change_quantiles__qh_0.8__ql_0.2,31.619047619
+value__large_standard_deviation__r_0.45,0.0
+value__mean_abs_change_quantiles__qh_0.8__ql_0.8,0.0
+value__autocorrelation__lag_6,0.512480168514
+value__autocorrelation__lag_7,0.653853495147
+value__autocorrelation__lag_4,0.535012070945
+value__last_location_of_maximum,0.966666666667
+value__autocorrelation__lag_2,0.367658131978
+value__autocorrelation__lag_3,0.411575406169
+value__autocorrelation__lag_0,1.0
+value__autocorrelation__lag_1,0.51547994425
+value__autocorrelation__lag_8,0.360082254297
+value__autocorrelation__lag_9,0.217484000968
+value__variance_larger_than_standard_deviation,1.0
+value__variance,3196.67638889
+value__mean,9986.08333333
+value__mean_abs_change_quantiles__qh_0.6__ql_0.8,0.0
+value__mean_abs_change_quantiles__qh_0.6__ql_0.6,0.0
+value__mean_abs_change_quantiles__qh_0.6__ql_0.4,6.0
+value__mean_abs_change_quantiles__qh_0.6__ql_0.2,23.1818181818
+value__mean_abs_change_quantiles__qh_0.6__ql_0.0,42.25
+value__symmetry_looking__r_0.15,1.0
+value__mean_second_derivate_central,0.706896551724
+value__skewness,-0.135422921254
+value__length,60.0
+value__first_location_of_maximum,0.95
+value__mean_abs_change_quantiles__qh_1.0__ql_0.2,42.4634146341
+value__mean_abs_change_quantiles__qh_1.0__ql_0.4,45.0740740741
+value__mean_abs_change_quantiles__qh_1.0__ql_0.6,41.125
+value__mean_abs_change_quantiles__qh_1.0__ql_0.8,58.3333333333
+value__range_count__max_1__min_-1,0.0
+value__kurtosis,-0.0289015217515
+value__symmetry_looking__r_0.25,1.0
+value__time_reversal_asymmetry_statistic__lag_3,1993963105.11
+value__abs_energy,5983503421.0
+value__time_reversal_asymmetry_statistic__lag_2,1215832201.59
+value__time_reversal_asymmetry_statistic__lag_1,836027272.276
+value__symmetry_looking__r_0.35,1.0
+value__large_standard_deviation__r_0.3,0.0
+value__large_standard_deviation__r_0.2,1.0
+value__large_standard_deviation__r_0.1,1.0
+value__large_standard_deviation__r_0.0,1.0
+value__large_standard_deviation__r_0.4,0.0
+value__large_standard_deviation__r_0.15,1.0
+value__standard_deviation,56.5391580136
+value__binned_entropy__max_bins_10,2.11974362674
+value__large_standard_deviation__r_0.35,0.0
+value__symmetry_looking__r_0.95,1.0
+value__longest_strike_below_mean,9.0
+value__sum_values,599165.0
+value__symmetry_looking__r_0.45,1.0
+value__symmetry_looking__r_0.6,1.0
+value__symmetry_looking__r_0.7,1.0
+value__symmetry_looking__r_0.4,1.0
+value__symmetry_looking__r_0.5,1.0
+value__symmetry_looking__r_0.2,1.0
+value__symmetry_looking__r_0.3,1.0
+value__symmetry_looking__r_0.0,0.0
+value__symmetry_looking__r_0.1,1.0
+value__has_duplicate,1.0
+value__symmetry_looking__r_0.8,1.0
+value__symmetry_looking__r_0.9,1.0
+value__value_count__value_nan,0.0
+value__mean_abs_change_quantiles__qh_0.2__ql_0.8,0.0
+value__large_standard_deviation__r_0.05,1.0
+value__mean_abs_change_quantiles__qh_0.2__ql_0.2,0.0
+value__has_duplicate_max,0.0
+value__mean_abs_change_quantiles__qh_0.2__ql_0.0,29.4
+value__mean_abs_change_quantiles__qh_0.2__ql_0.6,0.0
+value__mean_abs_change_quantiles__qh_0.2__ql_0.4,0.0
+value__number_cwt_peaks__n_5,6.0
+value__number_cwt_peaks__n_1,9.0
+value__has_duplicate_min,0.0
+value__symmetry_looking__r_0.55,1.0
+value__count_below_mean,31.0
+value__quantile__q_0.1,9909.9
+value__quantile__q_0.2,9937.8
+value__quantile__q_0.3,9962.7
+value__quantile__q_0.4,9975.6
+value__quantile__q_0.6,10004.8
+value__quantile__q_0.7,10017.6
+value__quantile__q_0.8,10033.2
+value__quantile__q_0.9,10048.9
+value__ar_coefficient__k_10__coeff_0,904.439185079
+value__ar_coefficient__k_10__coeff_1,0.163578948116
+value__ar_coefficient__k_10__coeff_2,-0.0432470001474
+value__ar_coefficient__k_10__coeff_3,-0.066542370683
+value__ar_coefficient__k_10__coeff_4,0.283685319392
+value__index_mass_quantile__q_0.1,0.116666666667
+value__index_mass_quantile__q_0.2,0.216666666667
+value__index_mass_quantile__q_0.3,0.316666666667
+value__index_mass_quantile__q_0.4,0.416666666667
+value__index_mass_quantile__q_0.6,0.616666666667
+value__index_mass_quantile__q_0.7,0.716666666667
+value__index_mass_quantile__q_0.8,0.816666666667
+value__index_mass_quantile__q_0.9,0.916666666667
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_0__w_2",-40.2658469608
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_1__w_2",5485.74118013
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_2__w_2",7535.02284446
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_3__w_2",6017.19200793
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_4__w_2",3308.43040143
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_5__w_2",1295.74336719
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_6__w_2",336.632431542
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_7__w_2",39.9167672586
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_8__w_2",17.9554856918
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_9__w_2",50.2590300879
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_10__w_2",35.9047024745
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_11__w_2",-24.146023861
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_12__w_2",-61.8871252413
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_13__w_2",-33.6685043252
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_14__w_2",24.2088382102
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_0__w_5",-20.2575971343
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_1__w_5",3771.32544152
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_2__w_5",7120.96092089
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_3__w_5",9670.13169234
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_4__w_5",11207.9294065
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_5__w_5",11696.157551
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_6__w_5",11253.943681
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_7__w_5",10110.8994435
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_8__w_5",8545.47382822
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_9__w_5",6826.23862162
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_10__w_5",5169.35388762
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_11__w_5",3717.9693031
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_12__w_5",2542.01968757
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_13__w_5",1652.10185551
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_14__w_5",1019.57078515
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_0__w_10",836.64197854
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_1__w_10",3543.0796763
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_2__w_10",6167.81421141
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_3__w_10",8634.72484753
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_4__w_10",10876.5237364
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_5__w_10",12835.3989402
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_6__w_10",14466.1094898
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_7__w_10",15737.7224437
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_8__w_10",16639.5484491
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_9__w_10",17169.076641
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_10__w_10",17339.7697657
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_11__w_10",17183.302683
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_12__w_10",16737.7538459
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_13__w_10",16046.1857704
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_14__w_10",15154.9058723
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_0__w_20",18718.9572589
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_1__w_20",20645.6350314
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_2__w_20",22554.4207082
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_3__w_20",24433.795925
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_4__w_20",26275.1871817
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_5__w_20",28065.040621
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_6__w_20",29788.0657403
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_7__w_20",31428.5198149
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_8__w_20",32985.8151195
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_9__w_20",34437.5408409
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_10__w_20",35770.923232
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_11__w_20",36992.8147885
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_12__w_20",38098.1939127
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_13__w_20",39076.9898057
+"value__cwt_coefficients__widths_(2, 5, 10, 20)__coeff_14__w_20",39919.0572501
+value__spkt_welch_density__coeff_2,1843.82117181
+value__spkt_welch_density__coeff_5,2859.9769052
+value__spkt_welch_density__coeff_8,2536.99547001
+value__fft_coefficient__coeff_0,178744.0
+value__fft_coefficient__coeff_1,-0.804510387479
+value__fft_coefficient__coeff_2,-53.1328616833
+value__fft_coefficient__coeff_3,-338.0
+value__fft_coefficient__coeff_4,122.445039355
+value__fft_coefficient__coeff_5,-58.9307961342
+value__fft_coefficient__coeff_6,13.0
+value__fft_coefficient__coeff_7,112.235306522
+value__fft_coefficient__coeff_8,118.187822328
+value__fft_coefficient__coeff_9,-248.0