forecastflowml.ForecastFlowML.train#

ForecastFlowML.train(df, spark=None, local_result=False)[source]#

Train models

Parameters:

  • df (Union[pandas.core.frame.DataFrame, pyspark.sql.dataframe.DataFrame]) – Dataset to fit.

  • spark (Optional[pyspark.sql.session.SparkSession]) – Spark session instance. Only provide when df is a pandas DataFrame.

  • local_result (bool) – Whether to store trained models as attribute. Only provide True in case of the trained models are not expected to overload the driver node.

Return type:

None if df is pandas DataFrame or local_result=True. Otherwise, pyspark DataFrame that includes the trained models.