Skip to content

[SPARK-7036][MLLIB] ALS.train should support DataFrames in PySpark #5619

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

[SPARK-7036][MLLIB] ALS.train should support DataFrames in PySpark #5619

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
36 changes: 26 additions & 10 deletions python/pyspark/mllib/recommendation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@
from pyspark.rdd import RDD
from pyspark.mllib.common import JavaModelWrapper, callMLlibFunc, inherit_doc
from pyspark.mllib.util import JavaLoader, JavaSaveable
from pyspark.sql import DataFrame

__all__ = ['MatrixFactorizationModel', 'ALS', 'Rating']

Expand Down Expand Up @@ -78,18 +79,23 @@ class MatrixFactorizationModel(JavaModelWrapper, JavaSaveable, JavaLoader):
True
>>> model = ALS.train(ratings, 1, nonnegative=True, seed=10)
>>> model.predict(2,2)
>>> model.predict(2, 2)
3.8...
>>> 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=10)
>>> model.predict(2, 2)
3.8...
>>> model = ALS.trainImplicit(ratings, 1, nonnegative=True, seed=10)
>>> model.predict(2,2)
>>> 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)
>>> sameModel.predict(2, 2)
0.4...
>>> sameModel.predictAll(testset).collect()
[Rating(...
Expand Down Expand Up @@ -125,13 +131,20 @@ class ALS(object):

@classmethod
def _prepare(cls, ratings):
assert isinstance(ratings, RDD), "ratings should be RDD"
if isinstance(ratings, RDD):
pass
elif isinstance(ratings, DataFrame):
ratings = ratings.rdd
else:
raise TypeError("Ratings should be represented by either an RDD or a DataFrame, "
"but got %s." % type(ratings))
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

a minor issue: maybe better to use "%s is provided"

first = ratings.first()
if not isinstance(first, Rating):
if isinstance(first, (tuple, list)):
ratings = ratings.map(lambda x: Rating(*x))
else:
raise ValueError("rating should be RDD of Rating or tuple/list")
if isinstance(first, Rating):
pass
elif isinstance(first, (tuple, list)):
ratings = ratings.map(lambda x: Rating(*x))
else:
raise TypeError("Expect a Rating or a tuple/list, but got %s." % type(first))
return ratings

@classmethod
Expand All @@ -152,8 +165,11 @@ def trainImplicit(cls, ratings, rank, iterations=5, lambda_=0.01, blocks=-1, alp
def _test():
import doctest
import pyspark.mllib.recommendation
from pyspark.sql import SQLContext
globs = pyspark.mllib.recommendation.__dict__.copy()
globs['sc'] = SparkContext('local[4]', 'PythonTest')
sc = SparkContext('local[4]', 'PythonTest')
globs['sc'] = sc
globs['sqlContext'] = SQLContext(sc)
(failure_count, test_count) = doctest.testmod(globs=globs, optionflags=doctest.ELLIPSIS)
globs['sc'].stop()
if failure_count:
Expand Down