本文整理匯總了Python中pyspark.mllib.recommendation.ALS.train方法的典型用法代碼示例。如果您正苦於以下問題：Python ALS.train方法的具體用法？Python ALS.train怎麽用？Python ALS.train使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類pyspark.mllib.recommendation.ALS的用法示例。
在下文中一共展示了ALS.train方法的2個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。
示例1: main
# 需要導入模塊: from pyspark.mllib.recommendation import ALS [as 別名]
# 或者: from pyspark.mllib.recommendation.ALS import train [as 別名]
def main():
movies = movies_original.map(parse_movies).cache()
ratings = ratings_original.map(parse_ratings).cache()
user_ratings = user_ratings_original.map(parse_user_ratings).filter(lambda x: x is not None).cache().coalesce(1)
user_ratings_list = user_ratings.collect()
standard_user_ratings = register_user_movies(user_ratings_list, movies).cache()
user_r = standard_user_ratings.map(lambda (m_id, m, rating): Rating(40000, int(m_id), float(rating)))
u_movies = standard_user_ratings.map(lambda (m_id, m, rating): (m_id, m)).collect()
r = ratings.map(lambda l: Rating(int(l[0]), int(l[1]), float(l[2])))
r = r.union(user_r)
rank = 7
numIterations = 10
model = ALS.train(r, rank, numIterations)
testdata = sc.parallelize(list(set(movies.collect())-set(u_movies))).map(lambda x: (40000, int(x[0])))
predictions = model.predictAll(testdata).map(lambda x: (x[1], x[2])) # movie_id, score
results = movies.map(lambda (movie_id, m): (int(movie_id), m)).join(predictions)
outdata = results.map(lambda x: (x[0], x[1][0], x[1][1])).sortBy(lambda l: l[2], ascending=False)
outdata.saveAsTextFile(output) 示例2: main
# 需要導入模塊: from pyspark.mllib.recommendation import ALS [as 別名]
# 或者: from pyspark.mllib.recommendation.ALS import train [as 別名]
def main():
training_data = sc.textFile(training_inputs)
testing_data = sc.textFile(testing_inputs)
training_ratings = training_data.map(get_tuple).cache()
testing_ratings = testing_data.map(get_tuple).cache()
testing_all = testing_ratings.map(lambda (uid, mid, rating): (uid, mid)).cache()
ratings = testing_ratings.map(to_Rating)
ranks = [2, 4, 8, 16, 32, 64, 128, 256]
reg_params = [0.1, 0.01]
for i in range(len(reg_params)):
RMSES = []
for rank in ranks:
model = ALS.train(training_ratings, rank=rank, lambda_=reg_params[i], seed=10)
predictions = model.predictAll(testing_all).map(lambda r: ((r[0], r[1]), r[2]))
ratesAndPreds = ratings.map(lambda r: ((r[0], r[1]), r[2])).join(predictions)
MSE = ratesAndPreds.map(lambda r: (r[1][0] - r[1][1])**2).mean()
RMSE = math.sqrt(MSE)
RMSES.append(RMSE)
plt.plot(range(len(ranks)), RMSES, label=str(reg_params[i]))
plt.xticks(range(len(ranks)), ranks, size='small')
plt.legend()
plt.show()