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

adds ability to specify ordered or not on fromrdd #333

Merged
merged 1 commit into from
Jun 15, 2016
Merged

adds ability to specify ordered or not on fromrdd #333

Show file tree
Hide file tree
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
7 changes: 5 additions & 2 deletions thunder/images/readers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
spark = check_spark()


def fromrdd(rdd, dims=None, nrecords=None, dtype=None, labels=None):
def fromrdd(rdd, dims=None, nrecords=None, dtype=None, labels=None, ordered=False):
"""
Load images from a Spark RDD.

Expand All @@ -31,6 +31,9 @@ def fromrdd(rdd, dims=None, nrecords=None, dtype=None, labels=None):

labels : array, optional, default = None
Labels for records. If provided, should be one-dimensional.

ordered : boolean, optional, default = False
Whether or not the rdd is ordered by key
"""
from .images import Images
from bolt.spark.array import BoltArraySpark
Expand All @@ -49,7 +52,7 @@ def process_keys(record):
k = (k,)
return k, v

values = BoltArraySpark(rdd.map(process_keys), shape=(nrecords,) + tuple(dims), dtype=dtype, split=1)
values = BoltArraySpark(rdd.map(process_keys), shape=(nrecords,) + tuple(dims), dtype=dtype, split=1, ordered=ordered)
return Images(values, labels=labels)

def fromarray(values, labels=None, npartitions=None, engine=None):
Expand Down
7 changes: 5 additions & 2 deletions thunder/series/readers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@
spark = check_spark()


def fromrdd(rdd, nrecords=None, shape=None, index=None, labels=None, dtype=None):
def fromrdd(rdd, nrecords=None, shape=None, index=None, labels=None, dtype=None, ordered=False):
"""
Load series data from a Spark RDD.

Expand All @@ -37,6 +37,9 @@ def fromrdd(rdd, nrecords=None, shape=None, index=None, labels=None, dtype=None)

dtype : string, default = None
Data numerical type (if provided will avoid check)

ordered : boolean, optional, default = False
Whether or not the rdd is ordered by key
"""
from .series import Series
from bolt.spark.array import BoltArraySpark
Expand Down Expand Up @@ -65,7 +68,7 @@ def process_keys(record):
k = (k,)
return k, v

values = BoltArraySpark(rdd.map(process_keys), shape=shape, dtype=dtype, split=len(shape)-1)
values = BoltArraySpark(rdd.map(process_keys), shape=shape, dtype=dtype, split=len(shape)-1, ordered=ordered)
return Series(values, index=index, labels=labels)

def fromarray(values, index=None, labels=None, npartitions=None, engine=None):
Expand Down