Skip to content

Option to only dump random walks to disk and skip training #5

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

Open
viveksck wants to merge 6 commits into
base: master
Choose a base branch
from
Open

Option to only dump random walks to disk and skip training #5

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
0c8c894
Fixed setup.py to install all dependencies. However unfortunately the…
Jan 26, 2015
d3d7ab9
Moving to gensim 0.10.1 as 0.10.2 fails to install via easy install
Jan 26, 2015
743f7a4
Merge remote-tracking branch 'upstream/master'
viveksck May 5, 2016
77c6996
Option to only walk.
viveksck May 5, 2016
ba764e0
Merging requirements.txt from original branch.
viveksck May 5, 2016
e44bdc2
Merging requirements.txt from original branch.
viveksck May 5, 2016
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
12 changes: 12 additions & 0 deletions deepwalk/__main__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,6 +71,11 @@ def process(args):
print("Walking...")
walks = graph.build_deepwalk_corpus(G, num_paths=args.number_walks,
path_length=args.walk_length, alpha=0, rand=random.Random(args.seed))

# If we are only asked to write walks to disk do that and buzz off.
if args.only_walk:
return

print("Training...")
model = Word2Vec(walks, size=args.representation_size, window=args.window_size, min_count=0, workers=args.workers)
else:
Expand All @@ -82,6 +87,10 @@ def process(args):
path_length=args.walk_length, alpha=0, rand=random.Random(args.seed),
num_workers=args.workers)

# If we are only asked to write walks to disk do that and buzz off.
if args.only_walk:
return

print("Counting vertex frequency...")
if not args.vertex_freq_degree:
vertex_counts = serialized_walks.count_textfiles(walk_files, args.workers)
Expand Down Expand Up @@ -149,6 +158,9 @@ def main():
parser.add_argument('--workers', default=1, type=int,
help='Number of parallel processes.')

parser.add_argument('--only-walk', dest="only_walk", action="store_true", default=False,
help='Dont train. Only walk.')


args = parser.parse_args()
numeric_level = getattr(logging, args.log.upper(), None)
Expand Down