zoo.zouwu.autots package

Submodules

zoo.zouwu.autots.forecast module

class zoo.zouwu.autots.forecast.AutoTSTrainer(horizon=1, dt_col='datetime', target_col='value', extra_features_col=None)

Bases: object

The Automated Time Series Forecast Trainer

fit(train_df, validation_df=None, metric='mse', recipe: zoo.automl.config.recipe.Recipe = <zoo.automl.config.recipe.SmokeRecipe object>, uncertainty: bool = False, distributed: bool = False, hdfs_url=None)

Fit a time series forecasting pipeline w/ automl :param train_df: the input dataframe (as pandas.dataframe) :param validation_df: the validation dataframe (as pandas.dataframe) :param recipe: the configuration of searching :param metric: the evaluation metric to optimize :param uncertainty: whether to enable uncertainty calculation (will output an uncertainty sigma) :param hdfs_url: the hdfs_url to use for storing trail and intermediate results :param distributed: whether to enable distributed training :return a TSPipeline

class zoo.zouwu.autots.forecast.TSPipeline

Bases: object

A pipeline for time series forecasting.

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

evaluate the results :param input_df: the input dataframe :param metrics: the evaluation metrics :param multioutput: output mode of multiple output, whether to aggregate :return: the evaluation results

fit(input_df, validation_df=None, uncertainty: bool = False, epochs=1, **user_config)

Incremental Fitting

Parameters:

• input_df – the input dataframe
• validation_df – the validation dataframe
• uncertainty – whether to calculate uncertainty
• epochs – number of epochs to train
• user_config – user configurations

Returns:

static load(pipeline_file)

load pipeline from a file :param pipeline_file: the pipeline file :return: a TSPipeline object

predict(input_df)

predict the result :param input_df: the input dataframe :return: the forecast results

save(pipeline_file)

save the pipeline to a file :param pipeline_file: the file path :return:

Module contents