def main():
# get args
args = build_parser().parse_args(sys.argv[1:])
setup_logger.setup(verbose=args.verbose)
# 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.parse(f))
# Create concatenated gctoo object
if args.concat_direction == "horiz":
out_gctoo = hstack(gctoos, args.fields_to_remove, args.reset_ids)
elif args.concat_direction == "vert":
out_gctoo = vstack(gctoos, 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)
(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()
"""
import logging
import setup_GCToo_logger as setup_logger
import os
import numpy as np
import pandas as pd
import h5py
import GCToo
__author__ = "Oana Enache"
__email__ = "*****@*****.**"
#instantiate logger
logger = logging.getLogger(setup_logger.LOGGER_NAME)
# when not in debug mode, probably best to set verbose=False
setup_logger.setup(verbose=False)
version_node = "version"
rid_node = "/0/META/ROW/id"
cid_node = "/0/META/COL/id"
data_node = "/0/DATA/0/matrix"
row_meta_group_node = "/0/META/ROW"
col_meta_group_node = "/0/META/COL"
def parse(gctx_file_path, convert_neg_666=True, rid=None, cid=None):
"""
Primary method of script. Reads in path to a gctx file and parses into GCToo object.
Input:
Mandatory:
"rids in concatenated_meta_df do not agree with rids in data_df.")
# Reset rids in concatenated_meta_df
reset_ids_in_meta_df(concatenated_meta_df)
# Replace rids in data_df with the new ones from concatenated_meta_df
# (just an array of unique integers, zero-indexed)
data_df.index = pd.Index(concatenated_meta_df.index.values)
def reset_ids_in_meta_df(meta_df):
""" Meta_df is modified inplace. """
# Record original index name, and then change it so that the column that it
# becomes will be appropriately named
original_index_name = meta_df.index.name
meta_df.index.name = "old_id"
# Reset index
meta_df.reset_index(inplace=True)
# Change the index name back to what it was
meta_df.index.name = original_index_name
if __name__ == "__main__":
args = build_parser().parse_args(sys.argv[1:])
setup_logger.setup(verbose=args.verbose)
main(args)
set(mini_gctoo.row_metadata_df[c])))
self.assertTrue(
set(mini_gctoo.row_metadata_df[c]) == set(
mini_gctoo_row_metadata[c]),
"Values in column {} differ between expected metadata and written row metadata!"
.format(c))
# check col metadata
self.assertTrue(
set(mini_gctoo.col_metadata_df.columns) == set(
mini_gctoo_col_metadata.columns),
"Mismatch between expected col metadata columns {} and column values written to file: {}"
.format(mini_gctoo.col_metadata_df.columns,
mini_gctoo_col_metadata.columns))
self.assertTrue(
set(mini_gctoo.col_metadata_df.index) == set(
mini_gctoo.col_metadata_df.index),
"Mismatch between expect col metadata index {} and index values written to file: {}"
.format(mini_gctoo.col_metadata_df.index,
mini_gctoo_col_metadata.index))
for c in list(mini_gctoo.col_metadata_df.columns):
self.assertTrue(
set(mini_gctoo.col_metadata_df[c]) == set(
mini_gctoo_col_metadata[c]),
"Values in column {} differ between expected metadata and written col metadata!"
.format(c))
if __name__ == "__main__":
setup_logger.setup(verbose=True)
unittest.main()
