evalml.pipelines.components.ARIMARegressor

class evalml.pipelines.components.ARIMARegressor(date_index=None, trend='n', p=1, d=0, q=0, random_seed=0, **kwargs)[source]

Autoregressive Integrated Moving Average Model. The three parameters (p, d, q) are the AR order, the degree of differencing, and the MA order. More information here: https://www.statsmodels.org/devel/generated/statsmodels.tsa.arima_model.ARIMA.html

name = 'ARIMA Regressor'
model_family = 'ARIMA'
supported_problem_types = [<ProblemTypes.TIME_SERIES_REGRESSION: 'time series regression'>]
hyperparameter_ranges = {'d': Integer(low=0, high=10, prior='uniform', transform='identity'), 'p': Integer(low=0, high=10, prior='uniform', transform='identity'), 'q': Integer(low=0, high=10, prior='uniform', transform='identity')}
default_parameters = {'d': 0, 'order': (1, 0, 0), 'p': 1, 'q': 0, 'trend': 'n'}
predict_uses_y = False

Instance attributes

feature_importance

Returns array of 0’s with a length of 1 as feature_importance is not defined for ARIMA regressor.

needs_fitting

parameters

Returns the parameters which were used to initialize the component

Methods:

__init__

param date_column

Specifies the name of the column in X that provides the datetime objects. Defaults to None.

clone

Constructs a new component with the same parameters and random state.

describe

Describe a component and its parameters

fit

Fits component to data

load

Loads component at file path

predict

Make predictions using selected features.

predict_proba

Make probability estimates for labels.

save

Saves component at file path

Class Inheritance

Inheritance diagram of ARIMARegressor