TSPipeline


TSPipeline

A pipeline for time series forecasting.

from zoo.zouwu.autots.forecast import TSPipeline

Note:

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

Methods

fit

This is usually for incremental fitting, and doesn't involve AutoML.

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

Arguments

predict

predict(input_df) 

Arguments

evaluate

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

Arguments


Load and Save a TSPipeline can be used in below way.

 from zoo.zouwu.autots.forecast import TSPipeline
 loaded_ppl = TSPipeline.load(file)
 # ... do sth. e.g. incremental fitting
 loaded_ppl.save(another_file)

load

load is a static method.

load(pipeline_file)

Arguments

save

save(pipeline_file)

Arguments