tsfresh

tsfresh copied to clipboard

Scalability of feature extraction

8

Thank you for this package! Somewhat related to #356 , as far as I understand currently the input format is a pandas.DataFrame, then data is aggregated by the `date` and...

rth

we could use use that warning in the extract_features method to issue a warning there as well as some features assume uniformly sampled time series as well. If we do...

nils-braun

Signature Transformations

1

Hey, have you ever considered adding signature transformations?

firmai

Future Improvement: The transforms covered in The Great Time Series Classification BakeOff

4

There was an interesting paper last year which compared a bunch of newly published time series classifiers. http://www-bcf.usc.edu/~liu32/milets16/paper/MiLeTS_2016_paper_5.pdf In a wild oversimplification, several of the classifiers simply transform the data...

ClimbsRocks

Efficient rolling window of time series (e.g. while using temporary results)

13

I want to extract features from a rolling window of a table with columns of several timeserieses and do some prediction based on the timeseries in that window. Currently, as...

xgdgsc

Would you consider adding Nelson rules in the pipeline?

4

More of a suggestion/question rather than bug reporting :) I was wondering if you would be interested at adding preprocessing steps such as Time Series validation with [Nelson rules](https://en.wikipedia.org/wiki/Nelson_rules). If...

lovemeblender

beat the Y-1 baseline in Google Stock notebook

2

Hi, first I think this is an awesome project! However, I would like to see a notice on the Google Stock notebook that this is just a technical example but...

lh14576

We already include type annotations for most functions in their docstrings. [mypy](http://mypy-lang.org/) offers a comment syntax for annotating types in Python 2. This would help us ensure that these annotations...

jneuff

calculate_relevance_table() does not work with y in form of numpy.ndarray

1

**The problem**: The function `feature_selection.relevance.calculate_relevance_table()` is supposed to support numpy.ndarray as y argument. This causes an attribute error though because numpy.ndarray does not have the `sort_index` function that is called...

nicolasj92

Too slow. GPU support please

24

Hi, firstly, apologize in advance for using bug report instead of Discussion and feature requests. I posted a request there a while back with no activity. Please add support for...

jarlva