pyspark 协同过滤

from pyspark.ml.evaluation import RegressionEvaluator
from pyspark.ml.recommendation import ALS
from pyspark.sql import Row

from pyspark.sql import SparkSession
spark= SparkSession\
                .builder \
                .appName("dataFrame") \
                .getOrCreate()

lines = spark.read.text("/home/luogan/lg/softinstall/spark-2.3.0-bin-hadoop2.7/data/mllib/als/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(ratingsRDD)
(training, test) = ratings.randomSplit([0.8, 0.2])

# Build the recommendation model using ALS on the training data
# Note we set cold start strategy to 'drop' to ensure we don't get NaN evaluation metrics
als = ALS(maxIter=5, regParam=0.01, userCol="userId", itemCol="movieId", ratingCol="rating",
          coldStartStrategy="drop")
model = als.fit(training)

# Evaluate the model by computing the RMSE on the test data
predictions = model.transform(test)
evaluator = RegressionEvaluator(metricName="rmse", labelCol="rating",
                                predictionCol="prediction")
rmse = evaluator.evaluate(predictions)
print("Root-mean-square error = " + str(rmse))

# Generate top 10 movie recommendations for each user
userRecs = model.recommendForAllUsers(10)
# Generate top 10 user recommendations for each movie
movieRecs = model.recommendForAllItems(10)

# Generate top 10 movie recommendations for a specified set of users
users = ratings.select(als.getUserCol()).distinct().limit(3)
userSubsetRecs = model.recommendForUserSubset(users, 10)
# Generate top 10 user recommendations for a specified set of movies
movies = ratings.select(als.getItemCol()).distinct().limit(3)
movieSubSetRecs = model.recommendForItemSubset(movies, 10)

Root-mean-square error = 1.8381124226830996