spark算子简单案例 - Python

第1关：WordCount - 词频统计

# -*- coding: UTF-8 -*-
from pyspark import SparkContext
 
if __name__ == "__main__":
 
    """
        需求：对本地文件系统URI为：/root/wordcount.txt 的内容进行词频统计
    """
    # ********** Begin **********#
 
    sc = SparkContext("local","pySpark")
    rdd = sc.textFile("/root/wordcount.txt")
    values = rdd.flatMap(lambda x:str(x).split(" ")).map(lambda x:(x,1)).reduceByKey(lambda x,y:x+y).sortBy(lambda x:tuple(x)[1],False)
    print(values.collect())
 
    # ********** End **********#

第2关：Friend Recommendation - 好友推荐

# -*- coding: UTF-8 -*-
from pyspark import SparkContext
 
def word_couple(word1, word2):
    if hash(word1) > hash(word2):
        return word1 + '_' + word2
    return word2 + '_' + word1
 
def relations(items):
    result = []
    for i in range(1, len(items)):
        result.append((word_couple(items[0], items[i]), 0))
        for j in range(i+1, len(items)):
            result.append((word_couple(items[i], items[j]), 1))
    return result
 
def fun2(x):
    values = tuple(x[1])
    return ((x[0], 0) if min(values)==0 else (x[0], sum(values)))
 
if __name__ == "__main__":
    """
        需求：对本地文件系统URI为：/root/friend.txt 的数据统计间接好友的数量
    """
    # ********** Begin **********#
    sc = SparkContext("local", "friend recommendation")
    src = sc.textFile("/root/friend.txt").map(lambda x:x.strip().encode('utf-8').split(" "))
    rdd = src.flatMap(relations).reduceByKey(lambda x,y:0 if x==0 or y==0 else x+y).filter(lambda x:x[1]>0)
    print(rdd.collect())
 
    # ********** End **********#