Skip to content
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

Jump to bottom

SPARK-1428: MLlib should convert non-float64 NumPy arrays to float64 instead of complaining #356

Closed
wants to merge 1 commit into from
+14 −4
Closed

SPARK-1428: MLlib should convert non-float64 NumPy arrays to float64 instead of complaining #356

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
18 changes: 14 additions & 4 deletions python/pyspark/mllib/_common.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,8 +15,9 @@
# limitations under the License.
#

from numpy import ndarray, copyto, float64, int64, int32, ones, array_equal, array, dot, shape
from numpy import ndarray, copyto, float64, int64, int32, ones, array_equal, array, dot, shape, complex, issubdtype
from pyspark import SparkContext, RDD
import numpy as np

from pyspark.serializers import Serializer
import struct
Expand Down Expand Up @@ -47,13 +48,22 @@ def _deserialize_byte_array(shape, ba, offset):
return ar.copy()

def _serialize_double_vector(v):
"""Serialize a double vector into a mutually understood format."""
"""Serialize a double vector into a mutually understood format.
>>> x = array([1,2,3])
>>> y = _deserialize_double_vector(_serialize_double_vector(x))
>>> array_equal(y, array([1.0, 2.0, 3.0]))
True
"""
if type(v) != ndarray:
raise TypeError("_serialize_double_vector called on a %s; "
"wanted ndarray" % type(v))
"""complex is only datatype that can't be converted to float64"""
if issubdtype(v.dtype, complex):
raise TypeError("_serialize_double_vector called on a %s; "
"wanted ndarray" % type(v))
if v.dtype != float64:
raise TypeError("_serialize_double_vector called on an ndarray of %s; "
"wanted ndarray of float64" % v.dtype)
v = v.astype(float64)
if v.ndim != 1:
raise TypeError("_serialize_double_vector called on a %ddarray; "
"wanted a 1darray" % v.ndim)
Expand Down