SeasonalityTransformer

class hcrystalball.feature_extraction.SeasonalityTransformer(auto=True, freq=None, week_day=None, monthly=None, quarterly=None, yearly=None, weekly=None, month_start=False, month_end=False, quarter_start=False, quarter_end=False, year_start=False, year_end=False)[source]

Bases: sklearn.base.BaseEstimator, sklearn.base.TransformerMixin

Generate seasonal feature columns using one-hot encoding.

Parameters

  • auto (bool) – Automatically generate week_day, monthly, quarterly, yearly, weekly if it makes sense given the data frequency

  • freq (str) – Frequency of data

  • week_day (bool) – Whether to add day name as a feature

  • monthly (bool) – Whether to add month as a feature

  • quarterly (bool) – Whether to add quarter as a feature

  • yearly (bool) – Whether to add year as a feature

  • weekly (bool) – Whether to add week number as a feature

Raises

  • ValueError – Error is raised if freq is not in [‘D’, ‘W’, ‘M’,’Q’, ‘Y’, None]

  • ValueError – Error is raised if freq is not provided when using auto=True

Methods Summary

fit(X, y)

Set fit columns to None

fit_transform(X[, y])

Fit to data, then transform it.

get_feature_names()

Provide handle to get column names for created data

get_params([deep])

Get parameters for this estimator.

set_params(**params)

Set the parameters of this estimator.

transform(X)

Create seasonal columns from datetime index

Methods Documentation

fit(X, y)[source]

Set fit columns to None

Parameters
Returns

self

Return type

SeasonalityTransformer

fit_transform(X, y=None, **fit_params)

Fit to data, then transform it.

Fits transformer to X and y with optional parameters fit_params and returns a transformed version of X.

Parameters

  • X (array-like of shape (n_samples, n_features)) – Input samples.

  • y (array-like of shape (n_samples,) or (n_samples, n_outputs), default=None) – Target values (None for unsupervised transformations).

  • **fit_params (dict) – Additional fit parameters.

Returns

X_new – Transformed array.

Return type

ndarray array of shape (n_samples, n_features_new)

get_feature_names()[source]

Provide handle to get column names for created data

Returns

Name of the generated feature vectors when the transformer is fitted.

Return type

list

get_params(deep=True)

Get parameters for this estimator.

Parameters

deep (bool, default=True) – If True, will return the parameters for this estimator and contained subobjects that are estimators.

Returns

params – Parameter names mapped to their values.

Return type

dict

set_params(**params)

Set the parameters of this estimator.

The method works on simple estimators as well as on nested objects (such as Pipeline). The latter have parameters of the form <component>__<parameter> so that it’s possible to update each component of a nested object.

Parameters

**params (dict) – Estimator parameters.

Returns

self – Estimator instance.

Return type

estimator instance

transform(X)[source]

Create seasonal columns from datetime index

Parameters

X (pandas.DataFrame) – Input features.

Returns

Contains the generated feature vector(s)

Return type

pandas.DataFrame