def main():
# Get args
args = build_parser().parse_args(sys.argv[1:])
setup_logger.setup(verbose=args.verbose)
# Read the input gct
in_gct = parse.parse(args.in_gct_path)
# Read in each of the command line arguments
rid = _read_arg(args.rid)
cid = _read_arg(args.cid)
exclude_rid = _read_arg(args.exclude_rid)
exclude_cid = _read_arg(args.exclude_cid)
# Slice the gct
out_gct = sg.slice_gctoo(in_gct,
rid=rid,
cid=cid,
exclude_rid=exclude_rid,
exclude_cid=exclude_cid)
assert out_gct.data_df.size > 0, "Slicing yielded an empty gct!"
# Write the output gct
if args.use_gctx:
wgx.write(out_gct, args.out_name)
else:
wg.write(out_gct,
args.out_name,
data_null="NaN",
metadata_null="NA",
filler_null="NA")
def main():
# get args
args = build_parser().parse_args(sys.argv[1:])
setup_logger.setup(verbose=args.verbose)
logger.debug("args: {}".format(args))
concat_main(args)
def main():
# get args
args = build_parser().parse_args(sys.argv[1:])
setup_logger.setup(verbose=args.verbose)
logger.debug("args: {}".format(args))
# Get files directly
if args.input_filepaths is not None:
files = args.input_filepaths
# Or find them
else:
files = get_file_list(args.file_wildcard)
# No files found
if len(files) == 0:
msg = "No files were found. args.file_wildcard: {}".format(
args.file_wildcard)
logger.error(msg)
raise Exception(msg)
# Only 1 file found
if len(files) == 1:
logger.warning(
"Only 1 file found. No concatenation needs to be done, exiting")
return
# More than 1 file found
else:
# Parse each file and append to a list
gctoos = []
for f in files:
gctoos.append(parse(f))
# Create concatenated gctoo object
if args.concat_direction == "horiz":
out_gctoo = hstack(gctoos, args.remove_all_metadata_fields,
args.error_report_output_file,
args.fields_to_remove, args.reset_ids)
elif args.concat_direction == "vert":
out_gctoo = vstack(gctoos, args.remove_all_metadata_fields,
args.error_report_output_file,
args.fields_to_remove, args.reset_ids)
# Write out_gctoo to file
logger.info("Writing to output file args.out_name: {}".format(
args.out_name))
if args.out_type == "gctx":
write_gctx.write(out_gctoo, args.out_name)
elif args.out_type == "gct":
write_gct.write(out_gctoo,
args.out_name,
filler_null=args.filler_null,
metadata_null=args.metadata_null,
data_null=args.data_null)
def main():
args = build_parser().parse_args(sys.argv[1:])
setup_logger.setup(verbose=args.verbose)
in_gctoo = parse_gctx.parse(args.filename, convert_neg_666=False)
if args.output_filepath == None:
out_name = str.split(in_gctoo.src, "/")[-1].split(".")[0]
else:
out_name = args.output_filepath
write_gct.write(in_gctoo, out_name)
def main():
args = build_parser().parse_args(sys.argv[1:])
setup_logger.setup(verbose=args.verbose)
in_gctoo = parse_gctx.parse(args.filename, convert_neg_666=False)
if args.output_filepath == None:
basename = os.path.basename(args.filename)
out_name = ".".join(basename.split(".")[:-1])
else:
out_name = args.output_filepath
write_gct.write(in_gctoo, out_name)
x = numpy.random.rand(x_shape[0], x_shape[1]) * numpy.random.randint(1, multiplier_max_functional_tests, size=1)
logger.debug("x:\n{}".format(x))
y_other_shape = numpy.random.randint(1, max_dimension_functional_tests, size=1)[0]
y_shape = (x_shape[0], y_other_shape)
logger.debug("y_shape: {}".format(y_shape))
y = numpy.random.rand(y_shape[0], y_shape[1]) * numpy.random.randint(1, multiplier_max_functional_tests, size=1)
logger.debug("y:\n{}".format(y))
combined = numpy.hstack([x, y])
raw_ex = numpy.corrcoef(combined, rowvar=False)
logger.debug("raw_ex.shape: {}".format(raw_ex.shape))
ex = raw_ex[:x.shape[1], -y.shape[1]:]
logger.debug("ex:\n{}".format(ex))
logger.debug("ex.shape: {}".format(ex.shape))
r = fast_corr.nan_fast_corr(x, y)
logger.debug("r:\n{}".format(r))
logger.debug("r.shape: {}".format(r.shape))
self.assertTrue(numpy.allclose(ex, r))
if __name__ == "__main__":
setup_logger.setup(verbose=True)
unittest.main()
def calculate_total_sample_offsets(offset_mat):
abs_total_offset = abs(offset_mat).apply(np.sum)
return abs_total_offset
def plot_pep(data_df, es, fit_params, pep_name, pep_y_offset, degree=None):
plt.figure()
plt.scatter(es,
data_df.loc[pep_name, :])
plt.ylabel("Quant Value")
plt.xlabel("Enrichment Score")
if degree is not None:
x = np.linspace(np.min(es), 1, 101)
plt.plot(x,
make_y(x,
fit_params.loc[pep_name, degree],
pep_y_offset))
plt.title(pep_name)
return plt
if __name__ == "__main__":
args = build_parser().parse_args(sys.argv[1:])
setup_logger.setup(verbose=args.verbose)
logger.debug("args: {}".format(args))
continuous_renormalization(args)
def main():
args = build_parser().parse_args(sys.argv[1:])
setup_logger.setup(verbose=args.verbose)
gct2gctx_main(args)
(data_df, row_df,
col_df) = GCToo.multi_index_df_to_component_dfs(mi_df)
self.assertTrue(col_df.equals(e_col_metadata_df))
self.assertTrue(row_df.equals(e_row_metadata_df))
self.assertTrue(data_df.equals(e_data_df))
# edge case: if the index (or column) of the multi-index has only one
# level, it becomes a regular index
mi_df_index_plain = pd.MultiIndex.from_arrays([["D", "E"]],
names=["rid"])
mi_df2 = pd.DataFrame([[1, 3, 5], [7, 11, 13]],
index=mi_df_index_plain,
columns=mi_df_columns)
# row df should be empty
e_row_df2 = pd.DataFrame(index=["D", "E"])
(data_df2, row_df2,
col_df2) = GCToo.multi_index_df_to_component_dfs(mi_df2)
self.assertTrue(row_df2.equals(e_row_df2))
self.assertTrue(col_df2.equals(e_col_metadata_df))
self.assertTrue(data_df2.equals(e_data_df))
if __name__ == "__main__":
setup_GCToo_logger.setup(verbose=True)
unittest.main()
def main():
# Get args
args = build_parser().parse_args(sys.argv[1:])
setup_logger.setup(verbose=args.verbose)
subset_main(args)
