def test_init(self):
'''Test init'''
fofn = os.path.join(data_dir, 'summary_test_init.fofn')
s = summary.Summary('out', fofn=fofn)
self.assertEqual(s.filenames, ['file1', 'file2'])
s = summary.Summary('out', filenames=['file42'])
self.assertEqual(s.filenames, ['file42'])
s = summary.Summary('out', fofn=fofn, filenames=['file42'])
self.assertEqual(s.filenames, ['file42', 'file1', 'file2'])
def test_load_file(self):
'''Test _load_file'''
s = summary.Summary('out', filenames=['spam', 'eggs'])
infile = os.path.join(data_dir, 'summary_test_load_file.in.tsv')
lines = [[
'gene1', '27', '42', '1', '822', '822', '100.0', '.', '.', '.',
'.', '.', '.', 'gene1.scaffold.1', '1490', '.', '.', '.', '.', '.',
'.'
],
[
'gene2', '15', '44', '2', '780', '780', '100.0', '.', '.',
'.', '.', '.', '.', 'gene2.scaffold.2', '1124', '.', '.',
'.', '.', '.', '.'
],
[
'gene2', '15', '46', '2', '780', '770', '99.0', '.', '.',
'.', '.', '.', '.', 'gene2.scaffold.3', '1097', '.', '.',
'.', '.', '.', '.'
],
[
'gene3', '187', '48', '3', '750', '750', '98.93', 'SNP',
'SYN', '.', '318', '318', 'C', 'gene3.scaffold.1', '1047',
'319', '319', 'G', '.', '.', '.'
]]
dicts = [s._line2dict('\t'.join(x)) for x in lines]
expected = {
'gene1': [dicts[0]],
'gene2': dicts[1:3],
'gene3': [dicts[3]]
}
got = s._load_file(infile)
self.assertEqual(expected, got)
def test_line2dict(self):
'''Test _line2dict'''
line = '\t'.join([
'gene1', '187', '42', '3', '750', '750', '98.93', 'SNP', 'SYN',
'.', '66', '66', 'A', 'gene1.scaffold.1', '1047', '67', '67', 'C',
'42', 'A', '22,20'
])
s = summary.Summary('out', filenames=['spam', 'eggs'])
expected = {
'gene': 'gene1',
'flag': flag.Flag(187),
'reads': 42,
'cluster': '3',
'gene_len': 750,
'assembled': 750,
'pc_ident': 98.93,
'var_type': 'SNP',
'var_effect': 'SYN',
'new_aa': '.',
'gene_start': 66,
'gene_end': 66,
'gene_nt': 'A',
'scaffold': 'gene1.scaffold.1',
'scaff_len': 1047,
'scaff_start': 67,
'scaff_end': 67,
'scaff_nt': 'C',
'read_depth': 42,
'alt_bases': 'A',
'ref_alt_depth': '22,20'
}
self.assertEqual(s._line2dict(line), expected)
def test_whole_run(self):
'''Test whole run to check csv ok (skip making tree)'''
tmp_out = 'tmp.summary_test_whole_run.out'''
infiles = [
os.path.join(data_dir, 'summary_test_whole_run.in.1.tsv'),
os.path.join(data_dir, 'summary_test_whole_run.in.2.tsv'),
]
s = summary.Summary(
tmp_out,
filenames=infiles,
make_phandango_tree=False,
show_var_groups=True,
show_known_vars=True,
show_novel_vars=True
)
s.run()
expected_file = os.path.join(data_dir, 'summary_test_whole_run.out.csv')
# we don't know the full path of the input files, so check all the other columns
with open(expected_file) as f:
expected = [line.rstrip().split(',', maxsplit=1)[1] for line in f]
with open(tmp_out + '.csv') as f:
got = [line.rstrip().split(',', maxsplit=1)[1] for line in f]
self.assertEqual(expected, got)
os.unlink(tmp_out + '.csv')
os.unlink(tmp_out + '.phandango.csv')
def test_to_matrix_all_cols(self):
'''Test _to_matrix all columns'''
infiles = [
os.path.join(data_dir, 'summary_to_matrix.1.tsv'),
os.path.join(data_dir, 'summary_to_matrix.2.tsv')
]
fofn = 'tmp.summary_to_matrix_all_cols'
with open(fofn, 'w') as f:
print(infiles[0], 'sample1', file=f)
print(infiles[1], file=f)
s = summary.Summary('out', fofn=fofn, show_var_groups=True, show_known_vars=True, show_novel_vars=True)
os.unlink(fofn)
s.samples = summary.Summary._load_input_files(s.filenames, 90)
s._gather_unfiltered_output_data()
got_phandango_header, got_csv_header, got_matrix = summary.Summary._to_matrix(s.filenames, s.all_data, s.all_potential_columns, s.cluster_columns)
expected_phandango_header = ['name', 'noncoding1.assembled:o1', 'noncoding1.match:o1', 'noncoding1.ref_seq:o2', 'noncoding1.pct_id:c1', 'noncoding1.known_var:o1', 'noncoding1.novel_var:o1', 'noncoding1.id1:o1', 'noncoding1.id1.%:c2', 'noncoding1.id3:o1', 'noncoding1.id3.%:c2', 'noncoding1.14GT:o1', 'noncoding1.14GT.%:c2', 'noncoding1.14T:o1', 'noncoding1.14T.%:c2', 'noncoding1.6G:o1', 'noncoding1.6G.%:c2', 'noncoding2.assembled:o1', 'noncoding2.match:o1', 'noncoding2.ref_seq:o3', 'noncoding2.pct_id:c1', 'noncoding2.known_var:o1', 'noncoding2.novel_var:o1', 'noncoding2.id2:o1', 'noncoding2.id2.%:c2', 'noncoding2.42T:o1', 'noncoding2.42T.%:c2', 'noncoding2.52GT:o1', 'noncoding2.52GT.%:c2', 'presence_absence1.assembled:o1', 'presence_absence1.match:o1', 'presence_absence1.ref_seq:o4', 'presence_absence1.pct_id:c1', 'presence_absence1.known_var:o1', 'presence_absence1.novel_var:o1', 'presence_absence1.A10V:o1']
expected_csv_header = ['name', 'noncoding1.assembled', 'noncoding1.match', 'noncoding1.ref_seq', 'noncoding1.pct_id', 'noncoding1.known_var', 'noncoding1.novel_var', 'noncoding1.id1', 'noncoding1.id1.%', 'noncoding1.id3', 'noncoding1.id3.%', 'noncoding1.14GT', 'noncoding1.14GT.%', 'noncoding1.14T', 'noncoding1.14T.%', 'noncoding1.6G', 'noncoding1.6G.%', 'noncoding2.assembled', 'noncoding2.match', 'noncoding2.ref_seq', 'noncoding2.pct_id', 'noncoding2.known_var', 'noncoding2.novel_var', 'noncoding2.id2', 'noncoding2.id2.%', 'noncoding2.42T', 'noncoding2.42T.%', 'noncoding2.52GT', 'noncoding2.52GT.%', 'presence_absence1.assembled', 'presence_absence1.match', 'presence_absence1.ref_seq', 'presence_absence1.pct_id', 'presence_absence1.known_var', 'presence_absence1.novel_var', 'presence_absence1.A10V']
expected_matrix = [
['sample1', 'yes', 'yes', 'noncoding_ref1', '98.33', 'yes', 'no', 'yes', 100.0, 'no', 'NA', 'no', 'NA', 'yes', 100.0, 'no', 'NA', 'yes', 'yes', 'noncoding_ref2', '98.33', 'yes', 'no', 'yes_multi_het', 'NA', 'yes', 100.0, 'het', 40.0, 'yes', 'yes', 'presence_absence_ref1', '98.96', 'no', 'yes', 'yes'],
[infiles[1], 'yes', 'yes', 'noncoding_ref1', '98.33', 'yes', 'no', 'het', 80.0, 'yes', 100.0, 'het', 80.0, 'no', 'NA', 'yes', 100.0, 'yes', 'yes', 'noncoding_ref2', '98.33', 'yes', 'no', 'het', 40.0, 'no', 'NA', 'het', 40.0, 'yes', 'yes', 'presence_absence1', '98.96', 'no', 'yes', 'yes']
]
self.assertEqual(expected_phandango_header, got_phandango_header)
self.assertEqual(expected_csv_header, got_csv_header)
self.assertEqual(expected_matrix, got_matrix)
def test_to_matrix_assembled_only(self):
'''Test _to_matrix with assembled column only'''
infiles = [
os.path.join(data_dir, 'summary_to_matrix.1.tsv'),
os.path.join(data_dir, 'summary_to_matrix.2.tsv')
]
s = summary.Summary('out', filenames=infiles, cluster_cols='assembled')
s.samples = summary.Summary._load_input_files(s.filenames, 90)
s._gather_unfiltered_output_data()
got_phandango_header, got_csv_header, got_matrix = summary.Summary._to_matrix(
s.filenames, s.all_data, s.all_potential_columns,
s.cluster_columns)
expected_phandango_header = [
'name', 'noncoding1.assembled:o1', 'noncoding2.assembled:o1',
'presence_absence1.assembled:o1'
]
expected_csv_header = [
'name', 'noncoding1.assembled', 'noncoding2.assembled',
'presence_absence1.assembled'
]
expected_matrix = [[infiles[0], 'yes', 'yes', 'yes'],
[infiles[1], 'yes', 'yes', 'yes']]
self.assertEqual(expected_phandango_header, got_phandango_header)
self.assertEqual(expected_csv_header, got_csv_header)
self.assertEqual(expected_matrix, got_matrix)
def test_to_matrix_with_groups(self):
'''Test _to_matrix with groups'''
infiles = [
os.path.join(data_dir, 'summary_to_matrix.1.tsv'),
os.path.join(data_dir, 'summary_to_matrix.2.tsv')
]
s = summary.Summary('out', filenames=infiles, show_var_groups=True)
s.samples = summary.Summary._load_input_files(s.filenames, 90)
s._gather_unfiltered_output_data()
got_phandango_header, got_csv_header, got_matrix = summary.Summary._to_matrix(
s.filenames, s.all_data, s.all_potential_columns,
s.cluster_columns)
expected_phandango_header = [
'name', 'noncoding1.assembled:o1', 'noncoding1.match:o1',
'noncoding1.ref_seq:o2', 'noncoding1.pct_id:c1',
'noncoding1.ctg_cov:c3', 'noncoding1.known_var:o1',
'noncoding1.novel_var:o1', 'noncoding1.id1:o1',
'noncoding1.id1.%:c2', 'noncoding1.id3:o1', 'noncoding1.id3.%:c2',
'noncoding2.assembled:o1', 'noncoding2.match:o1',
'noncoding2.ref_seq:o3', 'noncoding2.pct_id:c1',
'noncoding2.ctg_cov:c3', 'noncoding2.known_var:o1',
'noncoding2.novel_var:o1', 'noncoding2.id2:o1',
'noncoding2.id2.%:c2', 'presence_absence1.assembled:o1',
'presence_absence1.match:o1', 'presence_absence1.ref_seq:o4',
'presence_absence1.pct_id:c1', 'presence_absence1.ctg_cov:c3',
'presence_absence1.known_var:o1', 'presence_absence1.novel_var:o1'
]
expected_csv_header = [
'name', 'noncoding1.assembled', 'noncoding1.match',
'noncoding1.ref_seq', 'noncoding1.pct_id', 'noncoding1.ctg_cov',
'noncoding1.known_var', 'noncoding1.novel_var', 'noncoding1.id1',
'noncoding1.id1.%', 'noncoding1.id3', 'noncoding1.id3.%',
'noncoding2.assembled', 'noncoding2.match', 'noncoding2.ref_seq',
'noncoding2.pct_id', 'noncoding2.ctg_cov', 'noncoding2.known_var',
'noncoding2.novel_var', 'noncoding2.id2', 'noncoding2.id2.%',
'presence_absence1.assembled', 'presence_absence1.match',
'presence_absence1.ref_seq', 'presence_absence1.pct_id',
'presence_absence1.ctg_cov', 'presence_absence1.known_var',
'presence_absence1.novel_var'
]
expected_matrix = [[
infiles[0], 'yes', 'yes', 'noncoding_ref1', '98.33', '10.0', 'yes',
'no', 'yes', 100.0, 'no', 'NA', 'yes', 'yes', 'noncoding_ref2',
'98.33', '10.0', 'yes', 'no', 'yes_multi_het', 'NA', 'yes', 'yes',
'presence_absence_ref1', '98.96', '20.1', 'no', 'yes'
],
[
infiles[1], 'yes', 'yes', 'noncoding_ref1',
'98.33', '50.1', 'yes', 'no', 'het', 80.0,
'yes', 100.0, 'yes', 'yes', 'noncoding_ref2',
'98.33', '10.0', 'yes', 'no', 'het', 40.0,
'yes', 'yes', 'presence_absence1', '98.96',
'51.1', 'no', 'yes'
]]
self.assertEqual(expected_phandango_header, got_phandango_header)
self.assertEqual(expected_csv_header, got_csv_header)
self.assertEqual(expected_matrix, got_matrix)
def test_write_tsv(self):
'''Test _write_tsv'''
tmp_out = 'tmp.out.tsv'
s = summary.Summary(tmp_out, filenames=['spam', 'eggs'])
s.rows_out = [
['filename', 'gene1', 'gene3'],
['file2', 1, 3],
['file3', 2, 4],
]
s._write_tsv()
expected = os.path.join(data_dir, 'summary_test_write_tsv.out.tsv')
self.assertTrue(filecmp.cmp(tmp_out, expected, shallow=False))
os.unlink(tmp_out)
def test_gather_output_rows(self):
'''Test _gather_output_rows'''
infiles = [
os.path.join(data_dir, 'summary_test_gather_output_rows.in.1.tsv'),
os.path.join(data_dir, 'summary_test_gather_output_rows.in.2.tsv')
]
s = summary.Summary('out', filenames=infiles)
s._gather_output_rows()
expected = [
['filename', 'gene1', 'gene2', 'gene3'],
[infiles[0], 3, 2, 0],
[infiles[1], 3, 0, 3],
]
self.assertEqual(expected, s.rows_out)
def test_to_summary_number(self):
'''Test _to_summary_number'''
s = summary.Summary('out', filenames=['spam', 'eggs'])
tests = [
(0, 0),
(64, 0),
(7, 1),
(259, 1),
(15, 2),
(27, 3),
]
for t in tests:
l = [{'flag': flag.Flag(t[0]), 'assembled': 42, 'pc_ident': 99}]
self.assertEqual(s._to_summary_number(l), t[1])
l = [{'flag': flag.Flag(27), 'assembled': 42, 'pc_ident': 89}]
self.assertEqual(s._to_summary_number(l), 0)
def test_filter_output_rows(self):
'''Test _filter_output_rows'''
s = summary.Summary('out', filenames=['spam', 'eggs'])
s.rows_out = [
['filename', 'gene1', 'gene2', 'gene3'],
['file1', 0, 0, 0],
['file2', 1, 0, 3],
['file3', 2, 0, 4],
]
expected = [
['filename', 'gene1', 'gene3'],
['file2', 1, 3],
['file3', 2, 4],
]
s._filter_output_rows()
self.assertEqual(s.rows_out, expected)
def test_to_matrix_cluster_only(self):
'''Test _to_matrix with cluster columns only'''
infiles = [
os.path.join(data_dir, 'summary_to_matrix.1.tsv'),
os.path.join(data_dir, 'summary_to_matrix.2.tsv')
]
s = summary.Summary('out', filenames=infiles)
s.samples = summary.Summary._load_input_files(s.filenames, 90)
s._gather_unfiltered_output_data()
got_phandango_header, got_csv_header, got_matrix = summary.Summary._to_matrix(s.filenames, s.all_data, s.all_potential_columns, s.cluster_columns)
expected_phandango_header = ['name', 'noncoding1.assembled:o1', 'noncoding1.match:o1', 'noncoding1.ref_seq:o2', 'noncoding1.pct_id:c1', 'noncoding1.known_var:o1', 'noncoding1.novel_var:o1', 'noncoding2.assembled:o1', 'noncoding2.match:o1', 'noncoding2.ref_seq:o3', 'noncoding2.pct_id:c1', 'noncoding2.known_var:o1', 'noncoding2.novel_var:o1', 'presence_absence1.assembled:o1', 'presence_absence1.match:o1', 'presence_absence1.ref_seq:o4', 'presence_absence1.pct_id:c1', 'presence_absence1.known_var:o1', 'presence_absence1.novel_var:o1']
expected_csv_header = ['name', 'noncoding1.assembled', 'noncoding1.match', 'noncoding1.ref_seq', 'noncoding1.pct_id', 'noncoding1.known_var', 'noncoding1.novel_var', 'noncoding2.assembled', 'noncoding2.match', 'noncoding2.ref_seq', 'noncoding2.pct_id', 'noncoding2.known_var', 'noncoding2.novel_var', 'presence_absence1.assembled', 'presence_absence1.match', 'presence_absence1.ref_seq', 'presence_absence1.pct_id', 'presence_absence1.known_var', 'presence_absence1.novel_var']
expected_matrix = [
[infiles[0], 'yes', 'yes', 'noncoding_ref1', '98.33', 'yes', 'no', 'yes', 'yes', 'noncoding_ref2', '98.33', 'yes', 'no', 'yes', 'yes', 'presence_absence_ref1', '98.96', 'no', 'yes'],
[infiles[1], 'yes', 'yes', 'noncoding_ref1', '98.33', 'yes', 'no', 'yes', 'yes', 'noncoding_ref2', '98.33', 'yes', 'no', 'yes', 'yes', 'presence_absence1', '98.96', 'no', 'yes']
]
self.assertEqual(expected_phandango_header, got_phandango_header)
self.assertEqual(expected_csv_header, got_csv_header)
self.assertEqual(expected_matrix, got_matrix)
def test_to_matrix_with_vars(self):
'''Test _to_matrix with vars'''
infiles = [
os.path.join(data_dir, 'summary_to_matrix.1.tsv'),
os.path.join(data_dir, 'summary_to_matrix.2.tsv')
]
s = summary.Summary('out', filenames=infiles, show_known_vars=True, show_novel_vars=True)
s.samples = summary.Summary._load_input_files(s.filenames, 90)
s._gather_unfiltered_output_data()
got_phandango_header, got_csv_header, got_matrix = summary.Summary._to_matrix(s.filenames, s.all_data, s.all_potential_columns, s.cluster_columns)
expected_phandango_header = ['name', 'noncoding1.assembled:o1', 'noncoding1.match:o1', 'noncoding1.ref_seq:o2', 'noncoding1.pct_id:c1', 'noncoding1.known_var:o1', 'noncoding1.novel_var:o1', 'noncoding1.14GT:o1', 'noncoding1.14GT.%:c2', 'noncoding1.14T:o1', 'noncoding1.14T.%:c2', 'noncoding1.6G:o1', 'noncoding1.6G.%:c2', 'noncoding2.assembled:o1', 'noncoding2.match:o1', 'noncoding2.ref_seq:o3', 'noncoding2.pct_id:c1', 'noncoding2.known_var:o1', 'noncoding2.novel_var:o1', 'noncoding2.42T:o1', 'noncoding2.42T.%:c2', 'noncoding2.52GT:o1', 'noncoding2.52GT.%:c2', 'presence_absence1.assembled:o1', 'presence_absence1.match:o1', 'presence_absence1.ref_seq:o4', 'presence_absence1.pct_id:c1', 'presence_absence1.known_var:o1', 'presence_absence1.novel_var:o1', 'presence_absence1.A10V:o1']
expected_csv_header = ['name', 'noncoding1.assembled', 'noncoding1.match', 'noncoding1.ref_seq', 'noncoding1.pct_id', 'noncoding1.known_var', 'noncoding1.novel_var', 'noncoding1.14GT', 'noncoding1.14GT.%', 'noncoding1.14T', 'noncoding1.14T.%', 'noncoding1.6G', 'noncoding1.6G.%', 'noncoding2.assembled', 'noncoding2.match', 'noncoding2.ref_seq', 'noncoding2.pct_id', 'noncoding2.known_var', 'noncoding2.novel_var', 'noncoding2.42T', 'noncoding2.42T.%', 'noncoding2.52GT', 'noncoding2.52GT.%', 'presence_absence1.assembled', 'presence_absence1.match', 'presence_absence1.ref_seq', 'presence_absence1.pct_id', 'presence_absence1.known_var', 'presence_absence1.novel_var', 'presence_absence1.A10V']
expected_matrix = [
[infiles[0], 'yes', 'yes', 'noncoding_ref1', '98.33', 'yes', 'no', 'no', 'NA', 'yes', 100.0, 'no', 'NA', 'yes', 'yes', 'noncoding_ref2', '98.33', 'yes', 'no', 'yes', 100.0, 'het', 40.0, 'yes', 'yes', 'presence_absence_ref1', '98.96', 'no', 'yes', 'yes'],
[infiles[1], 'yes', 'yes', 'noncoding_ref1', '98.33', 'yes', 'no', 'het', 80.0, 'no', 'NA', 'yes', 100.0, 'yes', 'yes', 'noncoding_ref2', '98.33', 'yes', 'no', 'no', 'NA', 'het', 40.0, 'yes', 'yes', 'presence_absence1', '98.96', 'no', 'yes', 'yes']
]
self.assertEqual(expected_phandango_header, got_phandango_header)
self.assertEqual(expected_csv_header, got_csv_header)
self.assertEqual(expected_matrix, got_matrix)
def test_gather_unfiltered_output_data(self):
'''test gather_unfiltered_output_data'''
infiles = [
os.path.join(data_dir, 'summary_gather_unfiltered_output_data.in.1.tsv'),
os.path.join(data_dir, 'summary_gather_unfiltered_output_data.in.2.tsv')
]
expected_all = {
infiles[0]: {
'noncoding1': {
'summary': {
'assembled': 'yes',
'known_var': 'yes',
'match': 'yes',
'novel_var': 'no',
'pct_id': '98.33',
'ref_seq': 'noncoding_ref1'
},
'groups': {},
'vars': {},
},
'noncoding2': {
'summary': {
'assembled': 'yes',
'known_var': 'yes',
'match': 'yes',
'novel_var': 'no',
'pct_id': '98.33',
'ref_seq': 'noncoding_ref2'
},
'groups': {},
'vars': {},
},
'presence_absence1': {
'summary': {
'assembled': 'yes',
'known_var': 'no',
'match': 'yes',
'novel_var': 'yes',
'pct_id': '98.96',
'ref_seq': 'presence_absence_ref1'
},
'groups': {},
'vars': {},
},
'presence_absence2': {
'summary': {
'assembled': 'partial',
'known_var': 'no',
'match': 'no',
'novel_var': 'yes',
'pct_id': '99.1',
'ref_seq': 'presence_absence_ref2'
},
'groups': {},
'vars': {}
}
},
infiles[1]: {
'noncoding1': {
'summary': {'assembled': 'yes',
'known_var': 'yes',
'match': 'yes',
'novel_var': 'no',
'pct_id': '98.33',
'ref_seq': 'noncoding_ref1'
},
'groups': {},
'vars': {},
},
'noncoding2': {
'summary': {
'assembled': 'yes',
'known_var': 'yes',
'match': 'yes',
'novel_var': 'no',
'pct_id': '98.33',
'ref_seq': 'noncoding_ref2'
},
'groups': {},
'vars': {},
},
'presence_absence1': {
'summary': {
'assembled': 'yes',
'known_var': 'no',
'match': 'yes',
'novel_var': 'yes',
'pct_id': '98.96',
'ref_seq': 'presence_absence1'
},
'groups': {},
'vars': {}
},
}
}
expected_potential_cols = {
'noncoding1': {
'summary': {
'assembled',
'known_var',
'match',
'novel_var',
'pct_id',
'ref_seq'
},
'groups': set(),
'vars': set()
},
'noncoding2': {
'summary': {
'assembled',
'known_var',
'match',
'novel_var',
'pct_id',
'ref_seq'
},
'groups': set(),
'vars': set()
},
'presence_absence1': {
'summary': {
'assembled',
'known_var',
'match',
'novel_var',
'pct_id',
'ref_seq'
},
'groups': set(),
'vars': set()
},
'presence_absence2': {
'summary': {
'assembled',
'known_var',
'match',
'novel_var',
'pct_id',
'ref_seq'
},
'groups': set(),
'vars': set()
}
}
self.maxDiff = None
s = summary.Summary('out', filenames=infiles)
s.samples = summary.Summary._load_input_files(s.filenames, 90)
s._gather_unfiltered_output_data()
self.assertEqual(expected_potential_cols, s.all_potential_columns)
self.assertEqual(expected_all, s.all_data)
expected_potential_cols['noncoding1']['groups'] = {'id3', 'id1', 'id1.%', 'id3.%'}
expected_potential_cols['noncoding2']['groups'] = {'id2.%', 'id2'}
expected_all[infiles[0]]['noncoding1']['groups'] = {'id1': 'yes', 'id1.%': 100.0}
expected_all[infiles[0]]['noncoding2']['groups'] = {'id2': 'yes_multi_het', 'id2.%': 'NA'}
expected_all[infiles[1]]['noncoding1']['groups'] = {'id1': 'het', 'id1.%': 80.0, 'id3': 'yes', 'id3.%': 100.0}
expected_all[infiles[1]]['noncoding2']['groups'] = {'id2': 'het', 'id2.%': 40.0}
s = summary.Summary('out', filenames=infiles, show_var_groups=True)
s.samples = summary.Summary._load_input_files(s.filenames, 90)
s._gather_unfiltered_output_data()
self.assertEqual(expected_potential_cols, s.all_potential_columns)
self.assertEqual(expected_all, s.all_data)
expected_potential_cols['noncoding1']['vars'] = {'14T', '14T.%', '14GT', '14GT.%', '6G', '6G.%'}
expected_potential_cols['noncoding2']['vars'] = {'52GT', '52GT.%', '42T', '42T.%'}
expected_all[infiles[0]]['noncoding1']['vars'] = {'14T': 'yes', '14T.%': 100.0}
expected_all[infiles[0]]['noncoding2']['vars'] = {'42T': 'yes', '42T.%': 100.0, '52GT': 'het', '52GT.%': 40.0}
expected_all[infiles[1]]['noncoding1']['vars'] = {'14GT': 'het', '14GT.%': 80.0, '6G': 'yes', '6G.%': 100.0}
expected_all[infiles[1]]['noncoding2']['vars'] = {'52GT': 'het', '52GT.%': 40.0}
s = summary.Summary('out', filenames=infiles, show_var_groups=True, show_known_vars=True)
s.samples = summary.Summary._load_input_files(s.filenames, 90)
s._gather_unfiltered_output_data()
self.assertEqual(expected_potential_cols, s.all_potential_columns)
self.assertEqual(expected_all, s.all_data)
expected_potential_cols['presence_absence1']['vars'] = {'A10V'}
expected_potential_cols['presence_absence2']['vars'] = {'V175L'}
expected_all[infiles[0]]['presence_absence1']['vars'] = {'A10V': 'yes'}
expected_all[infiles[0]]['presence_absence2']['vars'] = {'V175L': 'yes'}
expected_all[infiles[1]]['presence_absence1']['vars'] = {'A10V': 'yes'}
s = summary.Summary('out', filenames=infiles, show_var_groups=True, show_known_vars=True, show_novel_vars=True)
s.samples = summary.Summary._load_input_files(s.filenames, 90)
s._gather_unfiltered_output_data()
self.assertEqual(expected_potential_cols, s.all_potential_columns)
self.assertEqual(expected_all, s.all_data)