pyspark二值化（0-1化）

from pyspark.sql import SparkSession
from pyspark.ml.feature import Binarizer

spark = SparkSession\
    .builder\
    .appName("BinarizerExample")\
    .getOrCreate()
continuousDataFrame = spark.createDataFrame([
    (0, 0.5),
    (1, 0.8),
    (2, 0.2)
], ["id", "feature"])
# threshold：设置阈值，大于阈值设置为1，小于等于阈值设置为0
binarizer = Binarizer(threshold=0.5, inputCol="feature", outputCol="binarized_feature")
binarizedDataFrame = binarizer.transform(continuousDataFrame)
print("Binarizer output with Threshold = %f" % binarizer.getThreshold())
binarizedDataFrame.show()