https://github.com/predict-idlab/tsflex - v0.4.1

What's Changed

• :recycle: improve QOL with mypy by @jvdd in https://github.com/predict-idlab/tsflex/pull/120
• :arrow_up: update pycatch22 by @jvdd in https://github.com/predict-idlab/tsflex/pull/122
• Update dependencies by @jvdd in https://github.com/predict-idlab/tsflex/pull/123
• Update deps ctd. by @jvdd in https://github.com/predict-idlab/tsflex/pull/124
• :bug: check for None before setting n_jobs to nb logical CPUs by @jvdd in https://github.com/predict-idlab/tsflex/pull/126
• :pray: not writeable strided for vectorized by @jvdd in https://github.com/predict-idlab/tsflex/pull/128
• :arrow_up: update dependencies by @jvdd in https://github.com/predict-idlab/tsflex/pull/130

Full Changelog: https://github.com/predict-idlab/tsflex/compare/v0.4.0...v0.4.1

- Python
Published by jonasvdd over 1 year ago

https://github.com/predict-idlab/tsflex - v0.4.0

New features

Now you can utilize the FeatureCollection.calculate method to compute feature based on group ids.

Specifically, 2 arguments wre atted to this FeatureCollection.calculate method:

• group_by_all: creates groups that contains all rows corresponding to the group value
  • Note that this is +/- identical as passing df.groupby(groupbyall) as data to the .calculate method -> (which is now also a valid input for the data argument)
  • group_by_consecutive: creates groups that contain consecutive rows for the group value

Note: Both grouped feature extraction approaches ignore NaNs in the group_by column.

Curious? :Look at our verbose example notebook - grouping feature extraction

What's Changed

• 🎍 improving loggers as described in #66 by @jonasvdd in https://github.com/predict-idlab/tsflex/pull/73
• :broom: some necessary maintenance by @jvdd in https://github.com/predict-idlab/tsflex/pull/80
• :wood: log % duration + output_names for FeatureCollection by @jvdd in https://github.com/predict-idlab/tsflex/pull/83
• :sparkles: validate integration with antropy by @jvdd in https://github.com/predict-idlab/tsflex/pull/88
• :tada: validate nolds integration by @jvdd in https://github.com/predict-idlab/tsflex/pull/94
• 〰️ remove isort and use ruff instead by @jvdd in https://github.com/predict-idlab/tsflex/pull/99
• :arrow_up: support Python 3.11 by @jvdd in https://github.com/predict-idlab/tsflex/pull/87
• :tada: validate pyentrp integration by @jvdd in https://github.com/predict-idlab/tsflex/pull/95
• :bug: support functools.partial by @jvdd in https://github.com/predict-idlab/tsflex/pull/104
• 👷 build: create codeql.yml by @NielsPraet in https://github.com/predict-idlab/tsflex/pull/106
• Build/codspeed setup by @NielsPraet in https://github.com/predict-idlab/tsflex/pull/107
• :arrow_up: update antropy dependency + disable py 3.7 tests by @jvdd in https://github.com/predict-idlab/tsflex/pull/108
• :arrow_up: update dependencies by @jvdd in https://github.com/predict-idlab/tsflex/pull/111
• ✨ feat: Feature extraction with an identifier by @NielsPraet in https://github.com/predict-idlab/tsflex/pull/109
• :arrow_up: soften pandas lock by @jvdd in https://github.com/predict-idlab/tsflex/pull/115
• :rocket: Python 3.12 support by @jvdd in https://github.com/predict-idlab/tsflex/pull/116

New Contributors

• @NielsPraet made their first contribution in https://github.com/predict-idlab/tsflex/pull/106

Full Changelog: https://github.com/predict-idlab/tsflex/compare/v0.3.0...v0.4.0

- Python
Published by jonasvdd almost 2 years ago

https://github.com/predict-idlab/tsflex - tsflex v0.3.0

What's Changed

• :goalnet: update makerobust by @jvdd in https://github.com/predict-idlab/tsflex/pull/45
• :art: Update examples by @jvdd in https://github.com/predict-idlab/tsflex/pull/46
• 💨 series_pipeline insert & append is more compose-like by @jonasvdd in https://github.com/predict-idlab/tsflex/pull/47
• :pushpin: Update dependencies by @jvdd in https://github.com/predict-idlab/tsflex/pull/48
• :seenoevil: minor bug fix in make_robust by @jvdd in https://github.com/predict-idlab/tsflex/pull/52
• :ambulance: Fix windows bug by @jvdd in https://github.com/predict-idlab/tsflex/pull/53
• :ambulance: update critical depencies by @jvdd in https://github.com/predict-idlab/tsflex/pull/55
• :sparkles: vectorized feature function support by @jvdd in https://github.com/predict-idlab/tsflex/pull/58
• [MRG] Remove deprecated closed argument in pd.daterange by @jeroenboeye in https://github.com/predict-idlab/tsflex/pull/64
• :bug: fix bug with bound_method + :sparkles: new integrations by @jvdd in https://github.com/predict-idlab/tsflex/pull/62
• :recycle: improve output indexing by @jvdd in https://github.com/predict-idlab/tsflex/pull/68
• :crayon: improve the make_robust docs by @jonasvdd in https://github.com/predict-idlab/tsflex/pull/72
• :sparkles: decouple stride + support setpoints by @jvdd in https://github.com/predict-idlab/tsflex/pull/74
• :recycle: refactor indexing + :scissors: decouple stride & window + :sparkles: support segment idxs by @jvdd in https://github.com/predict-idlab/tsflex/pull/71

Major changes

Updates on the output indexing

:scissors: Decoupling of stride & window from FeatureDescriptors

• Both argments are now optional.
• The stride can now also be a list of stride values

:sparkles: Support segment indexes

• Users can now add their start & end segment indexes to the FeatureCollection.calculate method - allowing even more flexible feature extraction :wink:

Full Changelog: https://github.com/predict-idlab/tsflex/compare/v0.2.3...v0.3

---

_{DISCLAIMER: this release was already published some months ago (11 Oct, 2022) on pypi.
Our apologies for the late tag + release on GitHub.}

- Python
Published by jvdd almost 3 years ago

https://github.com/predict-idlab/tsflex - tsflex v0.2.3

❗ See also: tsflex v0.2.2 which is even more 🔥 than this one

New features

💚 Next to the tsfresh integrations, tsflex's feature extraction now fully integrates with seglearn and tsfel ⬇️

```python from seglearn.featurefunctions import basefeatures from tsfel.featureextraction import getfeaturesbydomain

from tsflex.features import FeatureCollection, MultipleFeatureDescriptors from tsflex.features.integrations import seglearnfeaturedictwrapper, tsfelfeaturedictwrapper from tsflex.utils.data import loadempaticadata

Load sequence-indexed data (in this case a time-index)

dftmp, dfacc = loadempaticadata(['tmp', 'acc'])

Construct your feature extraction configuration & extract features

fc = FeatureCollection( MultipleFeatureDescriptors( functions=[ *seglearnfeaturedictwrapper(basefeatures()), *tsfelfeaturedictwrapper(getfeaturesbydomain('statistical')), ], seriesnames=["TMP", "ACCx", "ACC_y"], windows=["5min", "15min"], strides="5min" ) )

fc.calculate(data=[dftmp, dfacc], return_df=True) ```

Changes

🎉 The FeatureCollection.calculcate it's feauture-DataFrame output now has a determenistic column order see - #40

- Python
Published by jonasvdd over 4 years ago

https://github.com/predict-idlab/tsflex - tsflex v0.2.2

New features

• 🔥 Now also supports feature-extraction on numeric-index data (and thus not only time-based data)
• 💚 Seamless integration with tsfresh, check out the example below: ```python from tsfresh.feature_extraction import MinimalFCParameters; import scipy.stats as ss

from tsflex.features import FeatureCollection, MultipleFeatureDescriptors from tsflex.features.integrations import tsfreshsettingswrapper from tsflex.utils.data import loadempaticadata

Load sequence-indexed data (in this case a time-index)

dftmp, dfacc = loadempaticadata(['tmp', 'acc'])

Construct your feature extraction configuration & extract features

fc = FeatureCollection( MultipleFeatureDescriptors( functions=tsfreshsettingswrapper(MinimalFCParameters()) + [ss.skew], seriesnames=["TMP", "ACCx", "ACC_y"], windows=["5min", "15min"], strides="5min" ) )

fc.calculate(data=[dftmp, dfacc], return_df=True) ``` * ⚡ Optimized strided-rolling feature-extraction, see the newly generated benchmark ⬇️

• Added FeatureCollection.reduce() which comes in really handy when feature selection is performed in your machine-learning pipeline
• 🐻 chunk_data() now also supports DataFrame-dicts as input, which can be more convenient when having DataFrames with a lot of columns for which you want to specify the sample-frequencies.
• 🌻 SeriesPipeline is now more compose-like as it now accepts SeriesPipeline instances

Changes

• 🧵 Changed pathos ➡️ multiprocess as multiprocessing back-end
• 🔧 Moved the bound_method argument to FeatureCollection.calculate()
• 📝 Rewrote strided-rolling back-end in a more OO manner (introduced the segmenter module), which complies with our roadmap of providing more segmenting functionality

- Python
Published by jonasvdd over 4 years ago