python from dpark import DparkContext dpark_context = DparkContext() file_path = "/path/to/logfile.txt" lines = dpark_context.textFile(file_path) word_count = lines.flatMap(lambda line: line.split(" ")) \ .map(lambda word: (word, 1)) \ .reduceByKey(lambda a, b: a + b) print(word_count.collect())


上一篇:
下一篇:
切换中文