diff options
author | Matei Zaharia <matei@databricks.com> | 2014-04-05 20:52:05 -0700 |
---|---|---|
committer | Matei Zaharia <matei@databricks.com> | 2014-04-05 20:52:05 -0700 |
commit | 0b855167818b9afd2d2aa9f617b9861d77b2425d (patch) | |
tree | c0f4258b8b6ec6ffcdc805a069e77bbfe1cab84f | |
parent | 890d63bd4e16296ac70e151b3754727ea42b583c (diff) | |
download | spark-0b855167818b9afd2d2aa9f617b9861d77b2425d.tar.gz spark-0b855167818b9afd2d2aa9f617b9861d77b2425d.tar.bz2 spark-0b855167818b9afd2d2aa9f617b9861d77b2425d.zip |
SPARK-1421. Make MLlib work on Python 2.6
The reason it wasn't working was passing a bytearray to stream.write(), which is not supported in Python 2.6 but is in 2.7. (This array came from NumPy when we converted data to send it over to Java). Now we just convert those bytearrays to strings of bytes, which preserves nonprintable characters as well.
Author: Matei Zaharia <matei@databricks.com>
Closes #335 from mateiz/mllib-python-2.6 and squashes the following commits:
f26c59f [Matei Zaharia] Update docs to no longer say we need Python 2.7
a84d6af [Matei Zaharia] SPARK-1421. Make MLlib work on Python 2.6
-rw-r--r-- | docs/mllib-guide.md | 3 | ||||
-rw-r--r-- | docs/python-programming-guide.md | 2 | ||||
-rw-r--r-- | python/pyspark/mllib/__init__.py | 6 | ||||
-rw-r--r-- | python/pyspark/serializers.py | 11 |
4 files changed, 13 insertions, 9 deletions
diff --git a/docs/mllib-guide.md b/docs/mllib-guide.md index 203d235bf9..a5e0cc5080 100644 --- a/docs/mllib-guide.md +++ b/docs/mllib-guide.md @@ -38,6 +38,5 @@ depends on native Fortran routines. You may need to install the if it is not already present on your nodes. MLlib will throw a linking error if it cannot detect these libraries automatically. -To use MLlib in Python, you will need [NumPy](http://www.numpy.org) version 1.7 or newer -and Python 2.7. +To use MLlib in Python, you will need [NumPy](http://www.numpy.org) version 1.7 or newer. diff --git a/docs/python-programming-guide.md b/docs/python-programming-guide.md index cbe7d820b4..c2e5327324 100644 --- a/docs/python-programming-guide.md +++ b/docs/python-programming-guide.md @@ -152,7 +152,7 @@ Many of the methods also contain [doctests](http://docs.python.org/2/library/doc # Libraries [MLlib](mllib-guide.html) is also available in PySpark. To use it, you'll need -[NumPy](http://www.numpy.org) version 1.7 or newer, and Python 2.7. The [MLlib guide](mllib-guide.html) contains +[NumPy](http://www.numpy.org) version 1.7 or newer. The [MLlib guide](mllib-guide.html) contains some example applications. # Where to Go from Here diff --git a/python/pyspark/mllib/__init__.py b/python/pyspark/mllib/__init__.py index b420d7a7f2..538ff26ce7 100644 --- a/python/pyspark/mllib/__init__.py +++ b/python/pyspark/mllib/__init__.py @@ -19,11 +19,7 @@ Python bindings for MLlib. """ -# MLlib currently needs Python 2.7+ and NumPy 1.7+, so complain if lower - -import sys -if sys.version_info[0:2] < (2, 7): - raise Exception("MLlib requires Python 2.7+") +# MLlib currently needs and NumPy 1.7+, so complain if lower import numpy if numpy.version.version < '1.7': diff --git a/python/pyspark/serializers.py b/python/pyspark/serializers.py index 4d802924df..b253807974 100644 --- a/python/pyspark/serializers.py +++ b/python/pyspark/serializers.py @@ -64,6 +64,7 @@ import cPickle from itertools import chain, izip, product import marshal import struct +import sys from pyspark import cloudpickle @@ -113,6 +114,11 @@ class FramedSerializer(Serializer): where C{length} is a 32-bit integer and data is C{length} bytes. """ + def __init__(self): + # On Python 2.6, we can't write bytearrays to streams, so we need to convert them + # to strings first. Check if the version number is that old. + self._only_write_strings = sys.version_info[0:2] <= (2, 6) + def dump_stream(self, iterator, stream): for obj in iterator: self._write_with_length(obj, stream) @@ -127,7 +133,10 @@ class FramedSerializer(Serializer): def _write_with_length(self, obj, stream): serialized = self.dumps(obj) write_int(len(serialized), stream) - stream.write(serialized) + if self._only_write_strings: + stream.write(str(serialized)) + else: + stream.write(serialized) def _read_with_length(self, stream): length = read_int(stream) |