电影数据:pyspark 协同过滤矩阵分解ALS

需要注意代码里long(p[3])改成float
ratingsRDD = parts.map(lambda p: Row(userId=int(p[0]), movieId=int(p[1]), rating=float(p[2]), timestamp=float(p[3])))代码：

from pyspark import SparkContext, SparkConf
from pyspark.sql import SparkSession
from pyspark.ml.evaluation import RegressionEvaluator
from pyspark.ml.recommendation import ALS
from pyspark.sql import Row
import os
os.environ["PYSPARK_PYTHON"]="/Users/lonng/opt/anaconda3/python.app/Contents/MacOS/python"


spark = SparkSession\
        .builder\
        .appName("ALSExample")\
        .getOrCreate()

# $example on$
lines = spark.read.text("./sample_movielens_ratings.txt").rdd

parts = lines.map(lambda row: row.value.split("::"))
ratingsRDD = parts.map(lambda p: Row(userId=int(p[0]), movieId=int(p[1]),
                                     rating=float(p[2]), timestamp=float(p[3])))
ratings = spark.createDataFrame(