pyspark wordcount按值排序

from pyspark import SparkContext

# 创建SparkContext对象
sc = SparkContext("local", "WordCount")

# 读取文本文件
lines = sc.textFile("path/to/textfile.txt")

# 切分每行为单词
words = lines.flatMap(lambda line: line.split(" "))

# 映射每个单词为(单词, 1)的键值对
word_counts = words.map(lambda word: (word, 1))

# 按键值对中的键进行分组并求和
word_counts = word_counts.reduceByKey(lambda a, b: a + b)

# 按值进行排序
sorted_word_counts = word_counts.sortBy(lambda x: x[1], ascending=False)

# 打印排序后的结果
for word, count in sorted_word_counts.collect():
    print(f"{word}: {count}")

# 停止SparkContext对象
sc.stop()