simpleml.models.base_model module

class simpleml.models.base_model.AbstractModel(has_external_files=True, external_model_kwargs={}, params={}, **kwargs)

Bases: simpleml.persistables.base_persistable.Persistable, simpleml.persistables.saving.AllSaveMixin

Abstract Base class for all Model objects. Defines the required parameters for versioning and all other metadata can be stored in the arbitrary metadata field

params: model parameter metadata for easy insight into hyperparameters across trainings feature_metadata: metadata insight into resulting features and importances

add_pipeline(pipeline)

Setter method for pipeline used

assert_fitted(msg='')

Helper method to raise an error if model isn’t fit

assert_pipeline(msg='')

Helper method to raise an error if pipeline isn’t present and configured

external_model

All model objects are going to require some filebase persisted object

Wrapper around whatever underlying class is desired (eg sklearn or keras)

feature_metadata = Column(None, JSONB(astext_type=Text()), table=None, default=ColumnDefault({}))

fit(**kwargs)

Pass through method to external model after running through pipeline

fit_predict(**kwargs)

Wrapper for fit and predict methods

fitted

get_feature_metadata(**kwargs)

Abstract method for each model to define

Should return a dict of feature information (importance, coefficients…)

get_labels(dataset_split=None)

Wrapper method to return labels from dataset

get_params(**kwargs)

Pass through method to external model

load(**kwargs)

Extend main load routine to load relationship class

object_type = 'MODEL'

params = Column(None, JSONB(astext_type=Text()), table=None, default=ColumnDefault({}))

predict(X, **kwargs)

Pass through method to external model after running through pipeline

save(**kwargs)

Extend parent function with a few additional save routines

1. save params
2. save feature metadata

score(X, y=None, **kwargs)

Pass through method to external model

set_params(**params)

Pass through method to external model

transform(*args, **kwargs)

Run input through pipeline

class simpleml.models.base_model.Model(has_external_files=True, external_model_kwargs={}, params={}, **kwargs)

Bases: simpleml.models.base_model.AbstractModel

Base class for all Model objects. Defines the required parameters for versioning and all other metadata can be stored in the arbitrary metadata field

pipeline_id: foreign key relation to the pipeline used to transform input to the model

(training is also dependent on originating dataset but scoring only needs access to the pipeline)

author

created_timestamp

feature_metadata

filepaths

has_external_files

hash_

id

metadata_

modified_timestamp

name

params

pipeline

pipeline_id

project

registered_name

version

version_description