evalml.pipelines.TimeSeriesRegressionPipeline

class evalml.pipelines.TimeSeriesRegressionPipeline(component_graph, parameters=None, custom_name=None, custom_hyperparameters=None, random_seed=0)[source]

Pipeline base class for time series regression problems.

Instance attributes

custom_hyperparameters

Custom hyperparameters for the pipeline.

custom_name

Custom name of the pipeline.

default_parameters

The default parameter dictionary for this pipeline.

feature_importance

Importance associated with each feature.

hyperparameters

Returns hyperparameter ranges from all components as a dictionary

linearized_component_graph

this is not guaranteed to be in proper component computation order

model_family

Returns model family of this pipeline template

name

Name of the pipeline.

parameters

Parameter dictionary for this pipeline

problem_type

summary

A short summary of the pipeline structure, describing the list of components used.

Methods:

__init__

Machine learning pipeline for time series regression problems made out of transformers and a classifier.

can_tune_threshold_with_objective

Determine whether the threshold of a binary classification pipeline can be tuned.

clone

Constructs a new pipeline with the same components, parameters, and random state.

compute_estimator_features

Transforms the data by applying all pre-processing components.

create_objectives

describe

Outputs pipeline details including component parameters

fit

Fit a time series regression pipeline.

get_component

Returns component by name

graph

Generate an image representing the pipeline graph

graph_feature_importance

Generate a bar graph of the pipeline’s feature importance

load

Loads pipeline at file path

new

Constructs a new instance of the pipeline with the same component graph but with a different set of parameters.

predict

Make predictions using selected features.

save

Saves pipeline at file path

score

Evaluate model performance on current and additional objectives.

Class Inheritance

Inheritance diagram of TimeSeriesRegressionPipeline