CODEWITHSUNDEEP
pythonpandassklearn-pandas
Cnerb
Cnerb

Reputation: 171

Using tsfresh on a simple pandas data frame

I'm trying to extract features (tsfresh.extract_features) on a simple pandas dataframe that I made up. Every time I run and print features I simply get every calculated feature as either 0 or NaN. I've tried reading the documentation quite a bit, but can't seem to wrap my head around it.

Here's the code: 

d = {'one':pd.Series(np.random.randn(10)),
     'two':pd.Series(np.random.randn(10))}
df = pd.DataFrame(d)
print(df)
#
features = extract_features(df, column_id='one')
print(features)

Any help is appreciated.

Thanks

Upvotes: 2

Views: 5677

Answers (1)

MaxBenChrist
MaxBenChrist

Reputation: 547

The problem is that your time series are only one value long, most feature calculators will return a NaN for one valued time series.

You can try it with longer time series.

Have a look at the notebooks here https://github.com/blue-yonder/tsfresh/tree/master/notebooks

Upvotes: 1

Related Questions