pyspark-Collaborative 过滤

参考地址：

1、http://spark.apache.org/docs/latest/ml-guide.html

2、https://github.com/apache/spark/tree/v2.2.0

3、http://spark.apache.org/docs/latest/ml-collaborative-filtering.html

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

lines = spark.read.text("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=long(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)