diff --git a/eda/esmm/Model_pipline/dist_predict.py b/eda/esmm/Model_pipline/dist_predict.py index 48ab727054b92c0505abae3ee5bcc8e85a4fa596..37c5ece0fe4e3d5e287c9fc19964e8f436ac3a3d 100644 --- a/eda/esmm/Model_pipline/dist_predict.py +++ b/eda/esmm/Model_pipline/dist_predict.py @@ -187,8 +187,8 @@ if __name__ == "__main__": # df = spark.read.format("tfrecords").load(path+"nearby/part-r-00000") # df.show() - name = spark.createDataFrame([1,2,3,4,5],5) - test = name.map(lambda x: test_map()) + name = spark.createDataFrame([1,2,3,4,5]) + test = name.repartition(5).map(lambda x: test_map()) test.show() b = time.time()