Python Spark 统计文本文件数据频率

from pyspark.sql import SparkSession

spark = SparkSession.builder.getOrCreate() lines = spark.read.text('data01.txt').rdd res = lines.map(lambda x: x.value.split(',')).map(lambda x: (x[0], 1)) result = res.reduceByKey(lambda x, y: x + y) result.collect()