fork/cellxgene
1
0
Fork 0
mirror of https://github.com/chanzuckerberg/cellxgene.git synced 2026-10-08 21:28:12 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update run_diffexp.py (#1494)

Browse Source 
You can now select labels within groups instead of random rows.
This commit is contained in:
bmccandless
2020-05-26 16:06:33 -07:00
committed by GitHub
parent 51758a0be9
commit 030eea1898
1 changed files with 43 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
server/test/run_diffexp.py
+43 -12
View File
@@ -15,8 +15,10 @@ from server.data_cxg.cxg_adaptor import CxgAdaptor
def main(): def main():
parser = argparse.ArgumentParser("A command to test diffexp") parser = argparse.ArgumentParser("A command to test diffexp")
parser.add_argument("dataset", help="name of a dataset to load") parser.add_argument("dataset", help="name of a dataset to load")
parser.add_argument("-na", "--numA", type=int, required=True, help="number of rows in group A") parser.add_argument("-na", "--numA", type=int, help="number of rows in group A")
parser.add_argument("-nb", "--numB", type=int, required=True, help="number of rows in group B") parser.add_argument("-nb", "--numB", type=int, help="number of rows in group B")
parser.add_argument("-va", "--varA", help="obs variable:value to use for group A")
parser.add_argument("-vb", "--varB", help="obs variable:value to use for group B")
parser.add_argument("-t", "--trials", default=1, type=int, help="number of trials") parser.add_argument("-t", "--trials", default=1, type=int, help="number of trials")
parser.add_argument( parser.add_argument(
"-a", "--alg", choices=("default", "generic", "cxg"), default="default", help="algorithm to use" "-a", "--alg", choices=("default", "generic", "cxg"), default="default", help="algorithm to use"
@@ -41,22 +43,34 @@ def main():
if isinstance(adaptor, CxgAdaptor): if isinstance(adaptor, CxgAdaptor):
adaptor.open_array("X").schema.dump() adaptor.open_array("X").schema.dump()
numA = args.numA random.seed(args.seed)
numB = args.numB np.random.seed(args.seed)
rows = adaptor.get_shape()[0] rows = adaptor.get_shape()[0]
random.seed(args.seed) if args.numA:
filterA = random.sample(range(rows), args.numA)
elif args.varA:
vname, vval = args.varA.split(":")
filterA = get_filter_from_obs(adaptor, vname, vval)
else:
print("must supply numA or varA")
sys.exit(1)
if not args.new_selection: if args.numB:
samples = random.sample(range(rows), numA + numB) filterB = random.sample(range(rows), args.numB)
filterA = samples[:numA] elif args.varB:
filterB = samples[numA:] vname, vval = args.varB.split(":")
filterB = get_filter_from_obs(adaptor, vname, vval)
else:
print("must supply numB or varB")
sys.exit(1)
for i in range(args.trials): for i in range(args.trials):
if args.new_selection: if args.new_selection:
samples = random.sample(range(rows), numA + numB) if args.numA:
filterA = samples[:numA] filterA = random.sample(range(rows), args.numA)
filterB = samples[numA:] if args.numB:
filterB = random.sample(range(rows), args.numB)
maskA = np.zeros(rows, dtype=bool) maskA = np.zeros(rows, dtype=bool)
maskA[filterA] = True maskA[filterA] = True
@@ -82,5 +96,22 @@ def main():
print(res) print(res)
def get_filter_from_obs(adaptor, obsname, obsval):
attrs = adaptor.get_obs_columns()
if obsname not in attrs:
print(f"Unknown obs attr {obsname}: expected on of {attrs}")
sys.exit(1)
obsvals = adaptor.query_obs_array(obsname)[:]
obsval = type(obsvals[0])(obsval)
vfilter = np.where(obsvals == obsval)[0]
if len(vfilter) == 0:
u = np.unique(obsvals)
print(f"Unknown value in variable {obsname}:{obsval}: expected one of {list(u)}")
sys.exit(1)
return vfilter
if __name__ == "__main__": if __name__ == "__main__":
main() main()