Reorganize the server testing directory (#1705)

server/test/performance/create_test_matrix.py

@@ -0,0 +1,44 @@
+import anndata
+import argparse
+import random
+import scipy
+import numpy as np
+
+
+def main():
+    parser = argparse.ArgumentParser("A command to generate test h5ad files")
+    parser.add_argument("output", help="Name of the output file")
+    parser.add_argument("nobs", type=int, help="Number of observations (rows)")
+    parser.add_argument("nvar", type=int, help="Number of variables (columns)")
+    parser.add_argument("-n", "--nnz-percent", type=float, default=100, help="percent of non-zeros")
+    parser.add_argument("-c", "--col-shift", action="store_true", help="add a random value to each column")
+    parser.add_argument("--seed", type=int, default=None, help="add a random value to each column")
+
+    args = parser.parse_args()
+    create_test_h5ad(args.output, args.nobs, args.nvar, args.nnz_percent, args.col_shift, args.seed)
+
+
+def create_test_h5ad(outfile, nobs, nvar, nnz_percent=100, apply_col_shift=False, seed=None):
+    random.seed(seed)
+    np.random.seed(seed)
+    x = create_X_array(nobs, nvar, nnz_percent, apply_col_shift)
+    obsm = {"X_random": np.random.rand(nobs, 2).astype(np.float32)}
+    adata = anndata.AnnData(x, obsm=obsm)
+    adata.write(outfile)
+
+
+def create_X_array(nobs, nvar, nnz_percent, apply_col_shift):
+    if nnz_percent < 100:
+        array = scipy.sparse.random(nobs, nvar, nnz_percent * 0.01, dtype=np.float32, format="csc")
+    else:
+        array = np.random.rand(nobs, nvar).astype(np.float32)
+
+    if apply_col_shift:
+        col_shift = np.random.rand((nvar))
+        array += col_shift
+
+    return array
+
+
+if __name__ == "__main__":
+    main()

server/test/performance/run_diffexp.py

@@ -0,0 +1,117 @@
+import sys
+import argparse
+import random
+import time
+import numpy as np
+
+import server.compute.diffexp_cxg as diffexp_cxg
+import server.compute.diffexp_generic as diffexp_generic
+
+from server.common.app_config import AppConfig
+from server.data_common.matrix_loader import MatrixDataLoader
+from server.data_cxg.cxg_adaptor import CxgAdaptor
+
+
+def main():
+    parser = argparse.ArgumentParser("A command to test diffexp")
+    parser.add_argument("dataset", help="name of a dataset to load")
+    parser.add_argument("-na", "--numA", type=int, help="number of rows in group A")
+    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(
+        "-a", "--alg", choices=("default", "generic", "cxg"), default="default", help="algorithm to use"
+    )
+    parser.add_argument("-s", "--show", default=False, action="store_true", help="show the results")
+    parser.add_argument(
+        "-n", "--new-selection", default=False, action="store_true", help="change the selection between each trial"
+    )
+    parser.add_argument("--seed", default=1, type=int, help="set the random seed")
+
+    args = parser.parse_args()
+
+    app_config = AppConfig()
+    app_config.update_server_config(single_dataset__datapath=args.dataset)
+    app_config.update_server_config(app__verbose=True)
+    app_config.complete_config()
+
+    loader = MatrixDataLoader(args.dataset)
+    adaptor = loader.open(app_config)
+
+    if args.show:
+        if isinstance(adaptor, CxgAdaptor):
+            adaptor.open_array("X").schema.dump()
+
+    random.seed(args.seed)
+    np.random.seed(args.seed)
+    rows = adaptor.get_shape()[0]
+
+    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 args.numB:
+        filterB = random.sample(range(rows), args.numB)
+    elif args.varB:
+        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):
+        if args.new_selection:
+            if args.numA:
+                filterA = random.sample(range(rows), args.numA)
+            if args.numB:
+                filterB = random.sample(range(rows), args.numB)
+
+        maskA = np.zeros(rows, dtype=bool)
+        maskA[filterA] = True
+        maskB = np.zeros(rows, dtype=bool)
+        maskB[filterB] = True
+
+        t1 = time.time()
+        if args.alg == "default":
+            results = adaptor.compute_diffexp_ttest(maskA, maskB)
+        elif args.alg == "generic":
+            results = diffexp_generic.diffexp_ttest(adaptor, maskA, maskB)
+        elif args.alg == "cxg":
+            if not isinstance(adaptor, CxgAdaptor):
+                print("cxg only works with CxgAdaptor")
+                sys.exit(1)
+            results = diffexp_cxg.diffexp_ttest(adaptor, maskA, maskB)
+
+        t2 = time.time()
+        print("TIME=", t2 - t1)
+
+    if args.show:
+        for res in results:
+            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__":
+    main()