module timeseries.base

Inheritance diagram of mlinsights.timeseries.base

Short summary

module mlinsights.timeseries.base

Base class for timeseries.

source on GitHub

Classes

class

truncated documentation

BaseReciprocalTimeSeriesTransformer

Base for all timeseries preprocessing automatically applied within a predictor.

BaseTimeSeries

Base class to build a predictor on timeseries. The class computes one or several predictions at each time, between …

TimeSeriesRegressorMixin

Addition to sklearn.base.RegressorMixin.

Properties

property

truncated documentation

_repr_html_

HTML representation of estimator. This is redundant with the logic of _repr_mimebundle_. The latter should …

_repr_html_

HTML representation of estimator. This is redundant with the logic of _repr_mimebundle_. The latter should …

Methods

method

truncated documentation

__init__

__init__

_applies_preprocessing

Applies the preprocessing to the series.

_applies_preprocessing_inv

Applies the preprocessing to the series.

_base_fit_predict

Trains the preprocessing and returns the modified X, y, sample_weight.

_fit_preprocessing

Applies the preprocessing. X, y, sample_weight.

fit

Stores the first values.

get_fct_inv

Returns the reverse tranform.

has_preprocessing

Tells if there is one preprocessing.

score

Scores the prediction using ts_mape()

transform

Transforms both X and y. Returns X and y, returns sample_weight as well if not None. The …

Documentation

Base class for timeseries.

source on GitHub

class mlinsights.timeseries.base.BaseReciprocalTimeSeriesTransformer(context_length=0)[source]

Bases: mlinsights.mlmodel.sklearn_transform_inv.BaseReciprocalTransformer

Base for all timeseries preprocessing automatically applied within a predictor.

source on GitHub

Parameters

context_length – number of previous observations to build or rebuild the observations

source on GitHub

__init__(context_length=0)[source]
Parameters

context_length – number of previous observations to build or rebuild the observations

source on GitHub

fit(X, y, sample_weight=None)[source]

Stores the first values.

source on GitHub

get_fct_inv()[source]

Returns the reverse tranform.

source on GitHub

transform(X, y, sample_weight=None, context=None)[source]

Transforms both X and y. Returns X and y, returns sample_weight as well if not None. The context is used when the y series stored in the predictor is not related to the y series given to the transform method.

source on GitHub

class mlinsights.timeseries.base.BaseTimeSeries(past=1, delay1=1, delay2=2, use_all_past=False, preprocessing=None)[source]

Bases: sklearn.base.BaseEstimator

Base class to build a predictor on timeseries. The class computes one or several predictions at each time, between delay1 and delay2. It computes: \hat{Y_{t+d} = f(Y_{t-1}, ..., Y_{t-p})} with d in [delay1, delay2[ and 1 \leqslant p \leqslant past.

source on GitHub

Parameters
  • past – values to use to predict

  • delay1 – the model computes the first prediction for time=t + delay1

  • delay2 – the model computes the last prediction for time=t + delay2 excluded

  • use_all_past – use all past features, not only the timeseries

  • preprocessing – preprocessing to apply before predicting, only the timeseries itselves, it can be a difference, it must be of type BaseReciprocalTimeSeriesTransformer

source on GitHub

__init__(past=1, delay1=1, delay2=2, use_all_past=False, preprocessing=None)[source]
Parameters
  • past – values to use to predict

  • delay1 – the model computes the first prediction for time=t + delay1

  • delay2 – the model computes the last prediction for time=t + delay2 excluded

  • use_all_past – use all past features, not only the timeseries

  • preprocessing – preprocessing to apply before predicting, only the timeseries itselves, it can be a difference, it must be of type BaseReciprocalTimeSeriesTransformer

source on GitHub

_applies_preprocessing(X, y, sample_weight)[source]

Applies the preprocessing to the series.

source on GitHub

_applies_preprocessing_inv(X, y, sample_weight)[source]

Applies the preprocessing to the series.

source on GitHub

_base_fit_predict(X, y, sample_weight=None)[source]

Trains the preprocessing and returns the modified X, y, sample_weight.

Parameters
  • X – output of X may be empty (None)

  • y – timeseries (one single vector), array [n_obs]

  • sample_weight – weights None or array [n_obs]

Returns

X, y, sample_weight

The y series is moved by self.delay1 in the past.

source on GitHub

_fit_preprocessing(X, y, sample_weight=None)[source]

Applies the preprocessing. X, y, sample_weight.

Parameters
  • X – output of X may be empty (None)

  • y – timeseries (one single vector), array [n_obs]

  • sample_weight – weights None or array [n_obs]

Returns

X, y, sample_weight

source on GitHub

has_preprocessing()[source]

Tells if there is one preprocessing.

source on GitHub

class mlinsights.timeseries.base.TimeSeriesRegressorMixin[source]

Bases: sklearn.base.RegressorMixin

Addition to sklearn.base.RegressorMixin.

source on GitHub

score(X, y, sample_weight=None)[source]

Scores the prediction using ts_mape

Parameters
  • X – features

  • y – expected values

  • sample_weight – sample weight

Returns

see ts_mape

source on GitHub