zoo.automl.pipeline package

Submodules

zoo.automl.pipeline.abstract module

class zoo.automl.pipeline.abstract.Pipeline

Bases: abc.ABC

The pipeline object which is used to store the series of transformation of features and model

evaluate(input_df, metric=None)

evaluate the pipeline :param input_df: input data frame :param metric: the evaluation metric :return:

predict(input_df)

predict using the pipeline :param input_df: input data frame :return: the prediction result

save(file)

save the pipeline to a file :param file: the pipeline file :return: a pipeline object

zoo.automl.pipeline.time_sequence module

class zoo.automl.pipeline.time_sequence.TimeSequencePipeline(feature_transformers=None, model=None, config=None, name=None)

Bases: zoo.automl.pipeline.abstract.Pipeline

config_save(config_file=None)

save all configs to file. :param config_file: :return:

describe()

evaluate(input_df, metrics=['mse'], multioutput='raw_values')

evaluate the pipeline :param input_df: :param metrics: subset of [‘mean_squared_error’, ‘r_square’, ‘sMAPE’] :param multioutput: string in [‘raw_values’, ‘uniform_average’] ‘raw_values’ : Returns a full set of errors in case of multioutput input. ‘uniform_average’ : Errors of all outputs are averaged with uniform weight. :return:

fit(input_df, validation_df=None, mc=False, epoch_num=20)

fit_with_fixed_configs(input_df, validation_df=None, mc=False, **user_configs)

Fit pipeline with fixed configs. The model will be trained from initialization with the hyper-parameter specified in configs. The configs contain both identity configs (Eg. “future_seq_len”, “dt_col”, “target_col”, “metric”) and automl tunable configs (Eg. “past_seq_len”, “batch_size”). We recommend calling get_default_configs to see the name and default values of configs you you can specify. :param input_df: one data frame or a list of data frames :param validation_df: one data frame or a list of data frames :param user_configs: you can overwrite or add more configs with user_configs. Eg. “epochs” :return:

get_default_configs()

predict(input_df)

predict test data with the pipeline fitted :param input_df: :return:

predict_with_uncertainty(input_df, n_iter=100)

save(ppl_file=None)

save pipeline to file, contains feature transformer, model, trial config. :param ppl_file: :return:

zoo.automl.pipeline.time_sequence.load_ts_pipeline(file)

zoo.automl.pipeline.time_sequence.load_xgboost_pipeline(file, model_type='regressor')

Module contents