python使用spark实现推荐系统_Spark ALS推荐系统简单例子(python)

# -*- coding: utf-8 -*-

# spark-submit movie_rec.py

from pyspark import SparkConf, SparkContext

from pyspark.mllib.recommendation import ALS, Rating

# 获取所有movie名称和id对应集合

def movie_dict(file):

dict = {}

with open(file) as f:

for line in f:

arr= line.split('|')

movie_id = int(arr[0])

movie_name = str(arr[1])

dict[movie_id] = movie_name

return dict

# 转换用户评分数据格式

def get_rating(str):

arr = str.split('\t')

user_id = int(arr[0])

movie_id = int(arr[1])

user_rating = float(arr[2])

return Rating(user_id, movie_id, user_rating)

conf = SparkConf().setMaster('local').setAppName('MovieRec').set("spark.executor.memory", "512m")

sc = SparkContext(conf=conf)

#加载数据