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

Update mica_mds.py #28

Merged
merged 1 commit into from
Oct 1, 2024
Merged

Update mica_mds.py #28

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
42 changes: 27 additions & 15 deletions MICA/mica_mds.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@
import numpy as np
import pandas as pd
import pathlib
import ast
from sklearn.cluster import KMeans
from MICA.lib import transform as trans
from MICA.lib import mutual_info as mi
Expand Down Expand Up @@ -45,6 +46,16 @@ def main():
mica_mds(args)


def parse_k(value):
try:
return [int(value)]
except ValueError:
try:
return ast.literal_eval(value)
except:
raise argparse.ArgumentTypeError(f"Invalid value for -k: {value}")


def add_mds_arguments(parser):
parser.add_argument('-dm', '--dr-method', metavar='STR', default='MDS', required=False,
help='Transformation method used for dimension reduction '
Expand All @@ -56,7 +67,7 @@ def add_mds_arguments(parser):

# parser.add_argument('-nc', '--num-clusters', metavar='INT', nargs='+', required=False, default=0, type=int,
# help='Number of clusters to be specified in kmeans')
parser.add_argument('-nck', '--num-clusters-k', metavar='INT', default=4, required=False, type=int,
parser.add_argument('-nck', '--num-clusters-k', metavar='INT or List of INT', default=[4], required=False, type=parse_k,
help='Number of clusters to be specified in kmeans')
parser.add_argument('-le', '--louvain-enable', metavar='INT', required=False, default=0, help='enable knn-louvain clustering or not(0)', type=int)
parser.add_argument('-nn', '--num-neighbors', metavar='INT', required=False, default=20, type=int,
Expand Down Expand Up @@ -140,20 +151,21 @@ def mica_mds(args):
logging.info('(cells, genes): {}'.format(frame.shape))

if not args.louvain_enable:
logging.info('Performing Kmeans clustering for # of {}...'.format(args.num_clusters_k))
kms = KMeans(n_clusters=args.num_clusters_k)
kms.fit(mi_mds)
partition = pd.DataFrame(data=[i + 1 for i in list(kms.labels_)], index=frame.index, columns=["label"])

agg_embed = vs.visual_embed(partition, mi_mds,
args.output_dir,
suffix=args.num_clusters_k,
visual_method=args.visual_method,
num_works=args.num_workers,
min_dist=args.min_dist)
end = time.time()
runtime = end - start
logging.info('Done. Runtime: {} seconds'.format(runtime))
for k in args.num_clusters_k:
logging.info('Performing Kmeans clustering for # of {}...'.format(k))
kms = KMeans(n_clusters=k)
kms.fit(mi_mds)
partition = pd.DataFrame(data=[i + 1 for i in list(kms.labels_)], index=frame.index, columns=["label"])

agg_embed = vs.visual_embed(partition, mi_mds,
args.output_dir,
suffix=k,
visual_method=args.visual_method,
num_works=args.num_workers,
min_dist=args.min_dist)
end = time.time()
runtime = end - start
logging.info('Done. Runtime: {} seconds'.format(runtime))

else:
logging.info('Performing KNN clustering ...')
Expand Down