def test_add_alpha_diversity_values_to_mapping_file(self):
"""checks a mapping file is added with the proper fields """
# regular case no special cases for avg method
expected_mapping_file_data = MAPPING_FILE_DATA_WITH_ALPHA_A
expected_mapping_file_headers = ['SampleID', 'BarcodeSequence',
'LinkerPrimerSequence', 'Treatment', 'DOB', 'Description',
'chao1_alpha', 'chao1_normalized_alpha', 'chao1_alpha_label',
'PD_whole_tree_alpha', 'PD_whole_tree_normalized_alpha',
'PD_whole_tree_alpha_label']
out_mapping_file_data, out_mapping_file_headers =\
add_alpha_diversity_values_to_mapping_file(self.metrics,
self.sample_ids, self.alpha_diversity_data,
self.mapping_file_headers, self.mapping_file_data, 4, 'equal')
self.assertEquals(out_mapping_file_data, expected_mapping_file_data)
self.assertEquals(
out_mapping_file_headers,
expected_mapping_file_headers)
# regular case no special cases for quantile method
expected_mapping_file_data = MAPPING_FILE_DATA_WITH_ALPHA_B
out_mapping_file_data, out_mapping_file_headers =\
add_alpha_diversity_values_to_mapping_file(self.metrics,
self.sample_ids, self.alpha_diversity_data,
self.mapping_file_headers, self.mapping_file_data, 4, 'quantile')
self.assertEquals(out_mapping_file_data, expected_mapping_file_data)
self.assertEquals(
out_mapping_file_headers,
expected_mapping_file_headers)
def test_add_alpha_diversity_values_to_mapping_file(self):
"""checks a mapping file is added with the proper fields """
# regular case no special cases for avg method
expected_mapping_file_data = MAPPING_FILE_DATA_WITH_ALPHA_A
expected_mapping_file_headers = [
'SampleID', 'BarcodeSequence', 'LinkerPrimerSequence', 'Treatment',
'DOB', 'Description', 'chao1_alpha', 'chao1_normalized_alpha',
'chao1_alpha_label', 'PD_whole_tree_alpha',
'PD_whole_tree_normalized_alpha', 'PD_whole_tree_alpha_label'
]
out_mapping_file_data, out_mapping_file_headers =\
add_alpha_diversity_values_to_mapping_file(self.metrics,
self.sample_ids, self.alpha_diversity_data,
self.mapping_file_headers, self.mapping_file_data, 4, 'equal')
self.assertEquals(out_mapping_file_data, expected_mapping_file_data)
self.assertEquals(out_mapping_file_headers,
expected_mapping_file_headers)
# regular case no special cases for quantile method
expected_mapping_file_data = MAPPING_FILE_DATA_WITH_ALPHA_B
out_mapping_file_data, out_mapping_file_headers =\
add_alpha_diversity_values_to_mapping_file(self.metrics,
self.sample_ids, self.alpha_diversity_data,
self.mapping_file_headers, self.mapping_file_data, 4, 'quantile')
self.assertEquals(out_mapping_file_data, expected_mapping_file_data)
self.assertEquals(out_mapping_file_headers,
expected_mapping_file_headers)
def test_add_alpha_diversity_values_to_mapping_file(self):
"""checks a mapping file is added with the proper fields """
# regular case no special cases for avg method
expected_mapping_file_data = MAPPING_FILE_DATA_WITH_ALPHA_A
expected_mapping_file_headers = [
"SampleID",
"BarcodeSequence",
"LinkerPrimerSequence",
"Treatment",
"DOB",
"Description",
"chao1_alpha",
"chao1_normalized_alpha",
"chao1_alpha_label",
"PD_whole_tree_alpha",
"PD_whole_tree_normalized_alpha",
"PD_whole_tree_alpha_label",
]
out_mapping_file_data, out_mapping_file_headers = add_alpha_diversity_values_to_mapping_file(
self.metrics,
self.sample_ids,
self.alpha_diversity_data,
self.mapping_file_headers,
self.mapping_file_data,
4,
"equal",
)
self.assertEquals(out_mapping_file_data, expected_mapping_file_data)
self.assertEquals(out_mapping_file_headers, expected_mapping_file_headers)
# regular case no special cases for quantile method
expected_mapping_file_data = MAPPING_FILE_DATA_WITH_ALPHA_B
out_mapping_file_data, out_mapping_file_headers = add_alpha_diversity_values_to_mapping_file(
self.metrics,
self.sample_ids,
self.alpha_diversity_data,
self.mapping_file_headers,
self.mapping_file_data,
4,
"quantile",
)
self.assertEquals(out_mapping_file_data, expected_mapping_file_data)
self.assertEquals(out_mapping_file_headers, expected_mapping_file_headers)
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
alpha_fps = opts.alpha_fps
mapping_fp = opts.mapping_fp
output_mapping_fp = opts.output_mapping_fp
binning_method = opts.binning_method
missing_value_name = opts.missing_value_name
depth = opts.depth
# make sure the number of bins is an integer
try:
number_of_bins = int(opts.number_of_bins)
except ValueError:
raise ValueError, 'The number of bins must be an integer, not %s'\
% opts.number_of_bins
# if using collated data, make sure they specify a depth
if depth is not None:
alpha_dict = {}
# build up a dictionary with the filenames as keys and lines as values
for single_alpha_fp in alpha_fps:
alpha_dict[splitext(basename(single_alpha_fp))[0]] = open(
single_alpha_fp, 'U').readlines()
# format the collated data
metrics, alpha_sample_ids, alpha_data = mean_alpha(alpha_dict,
depth)
# when not using collated data, the user can only specify one input file
else:
if len(alpha_fps) > 1:
option_parser.error('A comma-separated list of files should only be'
' passed with the --alpha_fps option when using collated alpha '
'diversity data and also selecting a rarefaction depth with the'
' --depth option.')
else:
metrics, alpha_sample_ids, alpha_data = parse_matrix(open(
alpha_fps[0], 'U'))
# parse the data from the files
mapping_file_data, mapping_file_headers, comments = parse_mapping_file(
open(mapping_fp, 'U'))
# add the alpha diversity data to the mapping file
out_mapping_file_data, out_mapping_file_headers = \
add_alpha_diversity_values_to_mapping_file(metrics, alpha_sample_ids,
alpha_data, mapping_file_headers, mapping_file_data, number_of_bins,
binning_method, missing_value_name)
# format the new data and write it down
lines = format_mapping_file(out_mapping_file_headers, out_mapping_file_data)
fd_out = open(output_mapping_fp, 'w')
fd_out.writelines(lines)
fd_out.close()
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
alpha_fps = opts.alpha_fps
mapping_fp = opts.mapping_fp
output_mapping_fp = opts.output_mapping_fp
binning_method = opts.binning_method
missing_value_name = opts.missing_value_name
depth = opts.depth
number_of_bins = opts.number_of_bins
collated_input = opts.collated_input
# if using collated data, make sure they specify a depth
if collated_input:
alpha_dict = {}
# build up a dictionary with the filenames as keys and lines as values
for single_alpha_fp in alpha_fps:
alpha_dict[splitext(basename(single_alpha_fp))[0]] = open(
single_alpha_fp, 'U').readlines()
# format the collated data
try:
metrics, alpha_sample_ids, alpha_data = mean_alpha(
alpha_dict, depth)
except ValueError as e: # see mean_alpha for the possible exceptions
option_parser.error(e.message)
# when not using collated data, the user can only specify one input file
else:
if len(alpha_fps) > 1:
option_parser.error(
'A comma-separated list of files should only be'
' passed with the --alpha_fps option when using collated alpha '
'diversity data and also selecting a rarefaction depth with the'
' --depth option.')
else:
metrics, alpha_sample_ids, alpha_data = parse_matrix(
open(alpha_fps[0], 'U'))
# parse the data from the files
mapping_file_data, mapping_file_headers, comments = parse_mapping_file(
open(mapping_fp, 'U'))
# add the alpha diversity data to the mapping file
out_mapping_file_data, out_mapping_file_headers = \
add_alpha_diversity_values_to_mapping_file(metrics, alpha_sample_ids,
alpha_data, mapping_file_headers, mapping_file_data, number_of_bins,
binning_method, missing_value_name)
# format the new data and write it down
lines = format_mapping_file(out_mapping_file_headers,
out_mapping_file_data)
fd_out = open(output_mapping_fp, 'w')
fd_out.writelines(lines)
fd_out.close()
" passed with the --alpha_fps option when using collated alpha "
"diversity data and also selecting a rarefaction depth with the"
" --depth option."
)
else:
metrics, alpha_sample_ids, alpha_data = parse_matrix(open(alpha_fps[0], "U"))
# parse the data from the files
mapping_file_data, mapping_file_headers, comments = parse_mapping_file(open(mapping_fp, "U"))
# add the alpha diversity data to the mapping file
out_mapping_file_data, out_mapping_file_headers = add_alpha_diversity_values_to_mapping_file(
metrics,
alpha_sample_ids,
alpha_data,
mapping_file_headers,
mapping_file_data,
number_of_bins,
binning_method,
missing_value_name,
)
# format the new data and write it down
lines = format_mapping_file(out_mapping_file_headers, out_mapping_file_data)
fd_out = open(output_mapping_fp, "w")
fd_out.writelines(lines)
fd_out.close()
if __name__ == "__main__":
main()
else:
if len(alpha_fps) > 1:
option_parser.error(
'A comma-separated list of files should only be'
' passed with the --alpha_fps option when using collated alpha '
'diversity data and also selecting a rarefaction depth with the'
' --depth option.')
else:
metrics, alpha_sample_ids, alpha_data = parse_matrix(
open(alpha_fps[0], 'U'))
# parse the data from the files
mapping_file_data, mapping_file_headers, comments = parse_mapping_file(
open(mapping_fp, 'U'))
# add the alpha diversity data to the mapping file
out_mapping_file_data, out_mapping_file_headers = \
add_alpha_diversity_values_to_mapping_file(metrics, alpha_sample_ids,
alpha_data, mapping_file_headers, mapping_file_data, number_of_bins,
binning_method, missing_value_name)
# format the new data and write it down
lines = format_mapping_file(out_mapping_file_headers,
out_mapping_file_data)
fd_out = open(output_mapping_fp, 'w')
fd_out.writelines(lines)
fd_out.close()
if __name__ == "__main__":
main()
