def __init__(self, report_tsv, mlst_file, outprefix):
self.summary_sample = summary_sample.SummarySample(report_tsv)
self.mlst_profile = mlst_profile.MlstProfile(mlst_file,
duplicate_warnings=False)
self.outprefix = outprefix
self.allele_calls = {}
self.any_allele_unsure = False
def test_variant_column_names_tuples_and_het_snps(self):
'''Test _variant_column_names_tuples_and_het_snps'''
infile = os.path.join(
data_dir,
'summary_sample_test_column_names_tuples_and_het_snps.tsv')
sample_summary = summary_sample.SummarySample(infile)
sample_summary.clusters = sample_summary._load_file(infile, 90)
sample_summary.column_summary_data = sample_summary._column_summary_data(
)
expected_column_names = {
'cluster.v': {('variants_only1', 'S5T', 'ungrouped', None)},
'cluster.n': {('noncoding1', 'A6G', 'grouped', 'id2'),
('noncoding1', 'A14T', 'ungrouped', None),
('noncoding1', 'G15T', 'novel', None)},
'cluster.p': {('presence_absence1', 'A10V', 'grouped', 'id3')}
}
got_column_names, got_het_snps = sample_summary._variant_column_names_tuples_and_het_snps(
)
self.assertEqual(expected_column_names, got_column_names)
expected_het_snps = {
'cluster.v': {},
'cluster.n': {
'.': {
'A14T': 80.0
}
},
'cluster.p': {},
}
self.assertEqual(expected_het_snps, got_het_snps)
def test_column_summary_data(self):
'''Test _column_summary_data'''
infile = os.path.join(data_dir,
'summary_sample_test_column_summary_data.tsv')
sample_summary = summary_sample.SummarySample(infile)
sample_summary.clusters = sample_summary._load_file(infile, 90)
expected = {
'cluster.n': {
'assembled': 'yes',
'match': 'yes',
'ref_seq': 'noncoding1',
'known_var': 'yes',
'novel_var': 'yes',
'pct_id': '98.33'
},
'cluster.p': {
'assembled': 'yes',
'match': 'yes',
'ref_seq': 'presence_absence1',
'known_var': 'yes',
'novel_var': 'no',
'pct_id': '98.96'
},
'cluster.v': {
'assembled': 'yes',
'match': 'yes',
'ref_seq': 'variants_only1',
'known_var': 'yes',
'novel_var': 'no',
'pct_id': '100.0'
}
}
self.maxDiff = None
got = sample_summary._column_summary_data()
self.assertEqual(expected, got)
def _load_input_files(cls, filenames, min_id, verbose=False, only_clusters=None):
samples = {}
for filename in filenames:
samples[filename] = summary_sample.SummarySample(filename, min_pc_id=min_id, only_clusters=only_clusters)
samples[filename].run()
if verbose:
print('Loaded file', filename, flush=True)
return samples
def test_load_input_files(self):
'''Test _load_input_files'''
file1 = os.path.join(data_dir, 'summary_test_load_input_files.1.tsv')
file2 = os.path.join(data_dir, 'summary_test_load_input_files.2.tsv')
sample1 = summary_sample.SummarySample(file1)
sample2 = summary_sample.SummarySample(file2)
sample1.run()
sample2.run()
got = summary.Summary._load_input_files([file1, file2], 90)
expected = {file1: sample1, file2: sample2}
self.assertEqual(expected, got)
sample1 = summary_sample.SummarySample(file1, only_clusters={'noncoding1'})
sample2 = summary_sample.SummarySample(file2, only_clusters={'noncoding1'})
sample1.run()
sample2.run()
expected = {file1: sample1, file2: sample2}
got = summary.Summary._load_input_files([file1, file2], 90, only_clusters={'noncoding1'})
self.assertEqual(expected, got)
def test_var_groups(self):
'''test _var_groups'''
infile = os.path.join(data_dir, 'summary_sample_test_var_groups.tsv')
sample_summary = summary_sample.SummarySample(infile)
sample_summary.clusters = sample_summary._load_file(infile, 90)
got = sample_summary._var_groups()
expected = {
'cluster.n': {'id1', 'id2'},
'cluster.p': {'id3'},
'cluster.v': {'id4'}
}
self.assertEqual(expected, got)