Python pyspark MatrixFactorizationModel用法及代码示例

>>> r1 = (1, 1, 1.0)
>>> r2 = (1, 2, 2.0)
>>> r3 = (2, 1, 2.0)
>>> ratings = sc.parallelize([r1, r2, r3])
>>> model = ALS.trainImplicit(ratings, 1, seed=10)
>>> model.predict(2, 2)
0.4...

>>> testset = sc.parallelize([(1, 2), (1, 1)])
>>> model = ALS.train(ratings, 2, seed=0)
>>> model.predictAll(testset).collect()
[Rating(user=1, product=1, rating=1.0...), Rating(user=1, product=2, rating=1.9...)]

>>> model = ALS.train(ratings, 4, seed=10)
>>> model.userFeatures().collect()
[(1, array('d', [...])), (2, array('d', [...]))]

>>> model.recommendUsers(1, 2)
[Rating(user=2, product=1, rating=1.9...), Rating(user=1, product=1, rating=1.0...)]
>>> model.recommendProducts(1, 2)
[Rating(user=1, product=2, rating=1.9...), Rating(user=1, product=1, rating=1.0...)]
>>> model.rank
4

>>> first_user = model.userFeatures().take(1)[0]
>>> latents = first_user[1]
>>> len(latents)
4

>>> model.productFeatures().collect()
[(1, array('d', [...])), (2, array('d', [...]))]

>>> first_product = model.productFeatures().take(1)[0]
>>> latents = first_product[1]
>>> len(latents)
4

>>> products_for_users = model.recommendProductsForUsers(1).collect()
>>> len(products_for_users)
2
>>> products_for_users[0]
(1, (Rating(user=1, product=2, rating=...),))

>>> users_for_products = model.recommendUsersForProducts(1).collect()
>>> len(users_for_products)
2
>>> users_for_products[0]
(1, (Rating(user=2, product=1, rating=...),))

>>> model = ALS.train(ratings, 1, nonnegative=True, seed=123456789)
>>> model.predict(2, 2)
3.73...

>>> df = sqlContext.createDataFrame([Rating(1, 1, 1.0), Rating(1, 2, 2.0), Rating(2, 1, 2.0)])
>>> model = ALS.train(df, 1, nonnegative=True, seed=123456789)
>>> model.predict(2, 2)
3.73...

>>> model = ALS.trainImplicit(ratings, 1, nonnegative=True, seed=123456789)
>>> model.predict(2, 2)
0.4...

>>> import os, tempfile
>>> path = tempfile.mkdtemp()
>>> model.save(sc, path)
>>> sameModel = MatrixFactorizationModel.load(sc, path)
>>> sameModel.predict(2, 2)
0.4...
>>> sameModel.predictAll(testset).collect()
[Rating(...
>>> from shutil import rmtree
>>> try:
...     rmtree(path)
... except OSError:
...     pass