mizarlabs.transformers.technical package

Submodules

mizarlabs.transformers.technical.factory module

mizarlabs.transformers.technical.macd module

mizarlabs.transformers.technical.moving_average module

class mizarlabs.transformers.technical.moving_average.ExponentialWeightedMovingAverageDifference(fast: int, slow: int, column_name: str, normalised: bool = True)[source]

Bases: object

fit(X, y=None, **fit_params)[source]
transform(X: pandas.core.frame.DataFrame) → numpy.ndarray[source]
class mizarlabs.transformers.technical.moving_average.MovingAverageCrossOver(fast: int, slow: int, column_name: str, fill_between_crossovers: bool = False)[source]

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

Moving average crossover transformer

It transform the input data to a 1 when the the fast moving average goes above the slow moving average and -1 when the slow moving average goes above the fast moving average. When fill_between_crossovers is true, then the transfromation will be equal to 1 when the fast moving average is above the slow one and -1 viceversa.

The transformer is specified by the fast and slow moving average number of bars.

Parameters

  • fast (int) – number of bars to use for the moving average of the fast moving average

  • slow (int) – number of bars to use for the moving average of the slow moving average

  • column_name (str) – The name of the column in input that will be used for the transformation.

  • fill_between_crossovers (bool) – whether or not to fill the crossover value untill the next crossover.

fit(X, y=None, **fit_params)[source]
transform(X: pandas.core.frame.DataFrame)[source]
class mizarlabs.transformers.technical.moving_average.MovingAverageCrossOverPredictor(fast: int, slow: int, column_name: str, fill_between_crossovers: bool = False)[source]

Bases: mizarlabs.transformers.technical.moving_average.MovingAverageCrossOver

classes_ = [-1.0, 0.0, 1.0]
n_classes_ = 3
predict(X: pandas.core.frame.DataFrame)[source]
predict_proba(X: pandas.core.frame.DataFrame)[source]

mizarlabs.transformers.technical.volume module

class mizarlabs.transformers.technical.volume.BuySellImbalance(fast: int, slow: int, volume_type: str)[source]

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

allowed_volume_types = ['quote', 'base']
fit(X, y=None, **fit_params)[source]
transform(X: pandas.core.frame.DataFrame) → numpy.ndarray[source]

Module contents