From 49f1a820372d1cba41f3f00d07eb5728f2ed6705 Mon Sep 17 00:00:00 2001
From: Imran Rashid <irashid@cloudera.com>
Date: Fri, 6 Nov 2015 20:06:24 +0000
Subject: [SPARK-10116][CORE] XORShiftRandom.hashSeed is random in high bits

https://issues.apache.org/jira/browse/SPARK-10116

This is really trivial, just happened to notice it -- if `XORShiftRandom.hashSeed` is really supposed to have random bits throughout (as the comment implies), it needs to do something for the conversion to `long`.

mengxr mkolod

Author: Imran Rashid <irashid@cloudera.com>

Closes #8314 from squito/SPARK-10116.
---
 python/pyspark/ml/feature.py           | 20 ++++++++++----------
 python/pyspark/ml/recommendation.py    |  6 +++---
 python/pyspark/mllib/recommendation.py |  4 ++--
 python/pyspark/sql/dataframe.py        |  6 +++---
 4 files changed, 18 insertions(+), 18 deletions(-)

(limited to 'python')

diff --git a/python/pyspark/ml/feature.py b/python/pyspark/ml/feature.py
index c7b6dd926c..b02d41b52a 100644
--- a/python/pyspark/ml/feature.py
+++ b/python/pyspark/ml/feature.py
@@ -1788,21 +1788,21 @@ class Word2Vec(JavaEstimator, HasStepSize, HasMaxIter, HasSeed, HasInputCol, Has
     +----+--------------------+
     |word|              vector|
     +----+--------------------+
-    |   a|[-0.3511952459812...|
-    |   b|[0.29077222943305...|
-    |   c|[0.02315592765808...|
+    |   a|[0.09461779892444...|
+    |   b|[1.15474212169647...|
+    |   c|[-0.3794820010662...|
     +----+--------------------+
     ...
     >>> model.findSynonyms("a", 2).show()
-    +----+-------------------+
-    |word|         similarity|
-    +----+-------------------+
-    |   b|0.29255685145799626|
-    |   c|-0.5414068302988307|
-    +----+-------------------+
+    +----+--------------------+
+    |word|          similarity|
+    +----+--------------------+
+    |   b| 0.16782984556103436|
+    |   c|-0.46761559092107646|
+    +----+--------------------+
     ...
     >>> model.transform(doc).head().model
-    DenseVector([-0.0422, -0.5138, -0.2546, 0.6885, 0.276])
+    DenseVector([0.5524, -0.4995, -0.3599, 0.0241, 0.3461])
 
     .. versionadded:: 1.4.0
     """
diff --git a/python/pyspark/ml/recommendation.py b/python/pyspark/ml/recommendation.py
index ec5748a1cf..b44c66f73c 100644
--- a/python/pyspark/ml/recommendation.py
+++ b/python/pyspark/ml/recommendation.py
@@ -76,11 +76,11 @@ class ALS(JavaEstimator, HasCheckpointInterval, HasMaxIter, HasPredictionCol, Ha
     >>> test = sqlContext.createDataFrame([(0, 2), (1, 0), (2, 0)], ["user", "item"])
     >>> predictions = sorted(model.transform(test).collect(), key=lambda r: r[0])
     >>> predictions[0]
-    Row(user=0, item=2, prediction=0.39...)
+    Row(user=0, item=2, prediction=-0.13807615637779236)
     >>> predictions[1]
-    Row(user=1, item=0, prediction=3.19...)
+    Row(user=1, item=0, prediction=2.6258413791656494)
     >>> predictions[2]
-    Row(user=2, item=0, prediction=-1.15...)
+    Row(user=2, item=0, prediction=-1.5018409490585327)
 
     .. versionadded:: 1.4.0
     """
diff --git a/python/pyspark/mllib/recommendation.py b/python/pyspark/mllib/recommendation.py
index b9442b0d16..93e47a797f 100644
--- a/python/pyspark/mllib/recommendation.py
+++ b/python/pyspark/mllib/recommendation.py
@@ -101,12 +101,12 @@ class MatrixFactorizationModel(JavaModelWrapper, JavaSaveable, JavaLoader):
 
     >>> model = ALS.train(ratings, 1, nonnegative=True, seed=10)
     >>> model.predict(2, 2)
-    3.8...
+    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=10)
     >>> model.predict(2, 2)
-    3.8...
+    3.73...
 
     >>> model = ALS.trainImplicit(ratings, 1, nonnegative=True, seed=10)
     >>> model.predict(2, 2)
diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py
index 3baff81477..765a4511b6 100644
--- a/python/pyspark/sql/dataframe.py
+++ b/python/pyspark/sql/dataframe.py
@@ -436,7 +436,7 @@ class DataFrame(object):
         """Returns a sampled subset of this :class:`DataFrame`.
 
         >>> df.sample(False, 0.5, 42).count()
-        1
+        2
         """
         assert fraction >= 0.0, "Negative fraction value: %s" % fraction
         seed = seed if seed is not None else random.randint(0, sys.maxsize)
@@ -463,8 +463,8 @@ class DataFrame(object):
         +---+-----+
         |key|count|
         +---+-----+
-        |  0|    3|
-        |  1|    8|
+        |  0|    5|
+        |  1|    9|
         +---+-----+
 
         """
-- 
cgit v1.2.3