Transformer
PaddingTransformer
Padding panel of unequal length time series to equal, fixed length.
Pads the input dataset to either a optional fixed length (longer than the longest series). Or finds the max length series across all series and dimensions and pads to that with zeroes.
Quickstart
python
from sktime.transformations.padder import PaddingTransformer
estimator = PaddingTransformer(pad_length=None, fill_value=0)Tags
Capabilities
- Multivariate
- Unequal-length series
- Equalizes series length: Supported
- Inverse transform: Not supported
- Missing values: Not supported
- Removes missing values: Not supported
Properties
- Input typescitype:transform-input
- Series
- Output typescitype:transform-output
- Series
- Label typescitype:transform-labels
- None
- Fit is emptyfit_is_empty
- No
- Keeps the time indextransform-returns-same-time-index
- No
- Requires Xrequires_X
- Yes
- Requires yrequires_y
- No
- X and y need the same indexX-y-must-have-same-index
- No
Parameters(1)
- pad_lengthint, optional (default=None) length to pad the series too.
- if None, will find the longest sequence and use instead.
Examples
>>> import pandas as pd
>>> from sktime.transformations.padder import PaddingTransformer
>>>
>>> # Create a sample nested DataFrame with unequal length time series
>>> data = {
... 'feature1': [
... pd. Series ([1, 2, 3 ]), pd. Series ([4, 5 ]), pd. Series ([6, 7, 8, 9 ])
... ],
... 'feature2': [
... pd. Series ([10, 11 ]), pd. Series ([12, 13, 14 ]), pd. Series ([15 ])
... ]
... }
>>> X = pd. DataFrame (data)
>>>
>>> # Initialize the PaddingTransformer
>>> padder = PaddingTransformer ()
>>>
>>> # Fit the transformer to the data
>>> padder. fit (X) PaddingTransformer()
>>>
>>> # Transform the data
>>> Xt = padder. transform (X)
>>>
>>> # Display the transformed data
>>> # print(Xt)