AutoTSTrainer


AutoTSTrainer

Zouwu AutoTSTrainer is used to train a TSPipeline for forecasting using AutoML.

It is built upon Analytics Zoo AutoML module (refer to AutoML ProgrammingGuide and AutoML APIGuide for details), which uses Ray Tune for hyper parameter tuning and runs on Analytics Zoo RayOnSpark.

Methods

__init__

from zoo.zouwu.autots.forecast import AutoTSTrainer

trainer = AutoTSTrainer(dt_col="datetime",
                         target_col="value"
                         horizon=1,
                         extra_features_col=None)

fit

python fit(train_df, validation_df=None, metric="mse", recipe: Recipe = SmokeRecipe(), uncertainty: bool = False, distributed: bool = False, hdfs_url=None validation_df)

Note:

train_df and validation_df are data frames. An exmaple data frame looks like below.

datetime value extra_feature_1 extra_feature_2
2019-06-06 1.2 1 2
2019-06-07 2.3 0 2