diff options
author | Davies Liu <davies@databricks.com> | 2015-04-16 16:20:57 -0700 |
---|---|---|
committer | Josh Rosen <joshrosen@databricks.com> | 2015-04-16 16:20:57 -0700 |
commit | 04e44b37cc04f62fbf9e08c7076349e0a4d12ea8 (patch) | |
tree | b6429253955210445ddc37faa4d5166ea25a91e2 /python/pyspark/mllib/stat/_statistics.py | |
parent | 55f553a979db925aa0c3559f7e80b99d2bf3feb4 (diff) | |
download | spark-04e44b37cc04f62fbf9e08c7076349e0a4d12ea8.tar.gz spark-04e44b37cc04f62fbf9e08c7076349e0a4d12ea8.tar.bz2 spark-04e44b37cc04f62fbf9e08c7076349e0a4d12ea8.zip |
[SPARK-4897] [PySpark] Python 3 support
This PR update PySpark to support Python 3 (tested with 3.4).
Known issue: unpickle array from Pyrolite is broken in Python 3, those tests are skipped.
TODO: ec2/spark-ec2.py is not fully tested with python3.
Author: Davies Liu <davies@databricks.com>
Author: twneale <twneale@gmail.com>
Author: Josh Rosen <joshrosen@databricks.com>
Closes #5173 from davies/python3 and squashes the following commits:
d7d6323 [Davies Liu] fix tests
6c52a98 [Davies Liu] fix mllib test
99e334f [Davies Liu] update timeout
b716610 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
cafd5ec [Davies Liu] adddress comments from @mengxr
bf225d7 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
179fc8d [Davies Liu] tuning flaky tests
8c8b957 [Davies Liu] fix ResourceWarning in Python 3
5c57c95 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
4006829 [Davies Liu] fix test
2fc0066 [Davies Liu] add python3 path
71535e9 [Davies Liu] fix xrange and divide
5a55ab4 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
125f12c [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
ed498c8 [Davies Liu] fix compatibility with python 3
820e649 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
e8ce8c9 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
ad7c374 [Davies Liu] fix mllib test and warning
ef1fc2f [Davies Liu] fix tests
4eee14a [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
20112ff [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
59bb492 [Davies Liu] fix tests
1da268c [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
ca0fdd3 [Davies Liu] fix code style
9563a15 [Davies Liu] add imap back for python 2
0b1ec04 [Davies Liu] make python examples work with Python 3
d2fd566 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
a716d34 [Davies Liu] test with python 3.4
f1700e8 [Davies Liu] fix test in python3
671b1db [Davies Liu] fix test in python3
692ff47 [Davies Liu] fix flaky test
7b9699f [Davies Liu] invalidate import cache for Python 3.3+
9c58497 [Davies Liu] fix kill worker
309bfbf [Davies Liu] keep compatibility
5707476 [Davies Liu] cleanup, fix hash of string in 3.3+
8662d5b [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3
f53e1f0 [Davies Liu] fix tests
70b6b73 [Davies Liu] compile ec2/spark_ec2.py in python 3
a39167e [Davies Liu] support customize class in __main__
814c77b [Davies Liu] run unittests with python 3
7f4476e [Davies Liu] mllib tests passed
d737924 [Davies Liu] pass ml tests
375ea17 [Davies Liu] SQL tests pass
6cc42a9 [Davies Liu] rename
431a8de [Davies Liu] streaming tests pass
78901a7 [Davies Liu] fix hash of serializer in Python 3
24b2f2e [Davies Liu] pass all RDD tests
35f48fe [Davies Liu] run future again
1eebac2 [Davies Liu] fix conflict in ec2/spark_ec2.py
6e3c21d [Davies Liu] make cloudpickle work with Python3
2fb2db3 [Josh Rosen] Guard more changes behind sys.version; still doesn't run
1aa5e8f [twneale] Turned out `pickle.DictionaryType is dict` == True, so swapped it out
7354371 [twneale] buffer --> memoryview I'm not super sure if this a valid change, but the 2.7 docs recommend using memoryview over buffer where possible, so hoping it'll work.
b69ccdf [twneale] Uses the pure python pickle._Pickler instead of c-extension _pickle.Pickler. It appears pyspark 2.7 uses the pure python pickler as well, so this shouldn't degrade pickling performance (?).
f40d925 [twneale] xrange --> range
e104215 [twneale] Replaces 2.7 types.InstsanceType with 3.4 `object`....could be horribly wrong depending on how types.InstanceType is used elsewhere in the package--see http://bugs.python.org/issue8206
79de9d0 [twneale] Replaces python2.7 `file` with 3.4 _io.TextIOWrapper
2adb42d [Josh Rosen] Fix up some import differences between Python 2 and 3
854be27 [Josh Rosen] Run `futurize` on Python code:
7c5b4ce [Josh Rosen] Remove Python 3 check in shell.py.
Diffstat (limited to 'python/pyspark/mllib/stat/_statistics.py')
-rw-r--r-- | python/pyspark/mllib/stat/_statistics.py | 25 |
1 files changed, 13 insertions, 12 deletions
diff --git a/python/pyspark/mllib/stat/_statistics.py b/python/pyspark/mllib/stat/_statistics.py index 1d83e9d483..b475be4b4d 100644 --- a/python/pyspark/mllib/stat/_statistics.py +++ b/python/pyspark/mllib/stat/_statistics.py @@ -15,7 +15,7 @@ # limitations under the License. # -from pyspark import RDD +from pyspark.rdd import RDD, ignore_unicode_prefix from pyspark.mllib.common import callMLlibFunc, JavaModelWrapper from pyspark.mllib.linalg import Matrix, _convert_to_vector from pyspark.mllib.regression import LabeledPoint @@ -38,7 +38,7 @@ class MultivariateStatisticalSummary(JavaModelWrapper): return self.call("variance").toArray() def count(self): - return self.call("count") + return int(self.call("count")) def numNonzeros(self): return self.call("numNonzeros").toArray() @@ -78,7 +78,7 @@ class Statistics(object): >>> cStats.variance() array([ 4., 13., 0., 25.]) >>> cStats.count() - 3L + 3 >>> cStats.numNonzeros() array([ 3., 2., 0., 3.]) >>> cStats.max() @@ -124,20 +124,20 @@ class Statistics(object): >>> rdd = sc.parallelize([Vectors.dense([1, 0, 0, -2]), Vectors.dense([4, 5, 0, 3]), ... Vectors.dense([6, 7, 0, 8]), Vectors.dense([9, 0, 0, 1])]) >>> pearsonCorr = Statistics.corr(rdd) - >>> print str(pearsonCorr).replace('nan', 'NaN') + >>> print(str(pearsonCorr).replace('nan', 'NaN')) [[ 1. 0.05564149 NaN 0.40047142] [ 0.05564149 1. NaN 0.91359586] [ NaN NaN 1. NaN] [ 0.40047142 0.91359586 NaN 1. ]] >>> spearmanCorr = Statistics.corr(rdd, method="spearman") - >>> print str(spearmanCorr).replace('nan', 'NaN') + >>> print(str(spearmanCorr).replace('nan', 'NaN')) [[ 1. 0.10540926 NaN 0.4 ] [ 0.10540926 1. NaN 0.9486833 ] [ NaN NaN 1. NaN] [ 0.4 0.9486833 NaN 1. ]] >>> try: ... Statistics.corr(rdd, "spearman") - ... print "Method name as second argument without 'method=' shouldn't be allowed." + ... print("Method name as second argument without 'method=' shouldn't be allowed.") ... except TypeError: ... pass """ @@ -153,6 +153,7 @@ class Statistics(object): return callMLlibFunc("corr", x.map(float), y.map(float), method) @staticmethod + @ignore_unicode_prefix def chiSqTest(observed, expected=None): """ .. note:: Experimental @@ -188,11 +189,11 @@ class Statistics(object): >>> from pyspark.mllib.linalg import Vectors, Matrices >>> observed = Vectors.dense([4, 6, 5]) >>> pearson = Statistics.chiSqTest(observed) - >>> print pearson.statistic + >>> print(pearson.statistic) 0.4 >>> pearson.degreesOfFreedom 2 - >>> print round(pearson.pValue, 4) + >>> print(round(pearson.pValue, 4)) 0.8187 >>> pearson.method u'pearson' @@ -202,12 +203,12 @@ class Statistics(object): >>> observed = Vectors.dense([21, 38, 43, 80]) >>> expected = Vectors.dense([3, 5, 7, 20]) >>> pearson = Statistics.chiSqTest(observed, expected) - >>> print round(pearson.pValue, 4) + >>> print(round(pearson.pValue, 4)) 0.0027 >>> data = [40.0, 24.0, 29.0, 56.0, 32.0, 42.0, 31.0, 10.0, 0.0, 30.0, 15.0, 12.0] >>> chi = Statistics.chiSqTest(Matrices.dense(3, 4, data)) - >>> print round(chi.statistic, 4) + >>> print(round(chi.statistic, 4)) 21.9958 >>> data = [LabeledPoint(0.0, Vectors.dense([0.5, 10.0])), @@ -218,9 +219,9 @@ class Statistics(object): ... LabeledPoint(1.0, Vectors.dense([3.5, 40.0])),] >>> rdd = sc.parallelize(data, 4) >>> chi = Statistics.chiSqTest(rdd) - >>> print chi[0].statistic + >>> print(chi[0].statistic) 0.75 - >>> print chi[1].statistic + >>> print(chi[1].statistic) 1.5 """ if isinstance(observed, RDD): |