📅  最后修改于: 2022-03-11 14:59:53.540000             🧑  作者: Mango
print(spark.version)
2.4.3
# fit model
cvModel = cv_grid.fit(train_df)
# save best model to specified path
mPath = "/path/to/model/folder"
cvModel.bestModel.write().overwrite().save(mPath)
# read pickled model via pipeline api
from pyspark.ml.pipeline import PipelineModel
persistedModel = PipelineModel.load(mPath)
# predict
predictionsDF = persistedModel.transform(test_df)