def test_angola_example_file_object_output_correct():
with open(example_file_path, 'rb') as example_file:
genotype, additional = RecrudescenceFileParser.parse_file(example_file)
assert genotype.shape == expected_genotype_shape
assert additional.shape == expected_additional_shape
np.testing.assert_array_equal(genotype.columns.to_numpy(),
expected_columns)
np.testing.assert_array_equal(additional.columns.to_numpy(),
expected_columns)
pd.testing.assert_series_equal(genotype.iloc[0],
expected_genotype_row_0.iloc[0])
pd.testing.assert_series_equal(additional.iloc[0],
expected_additional_row_0.iloc[0])
3 NA 82.0 78 149.6 159.9 NA NA
4 NA 82.0 NA 175.7 187.2 NA NA
5 NA 81.8 NA 164.2 175.0 NA NA
6 NA 79.0 NA 149.4 160.0 NA NA
7 NA 78.6 NA 147.9 158.8 NA NA
8 NA 88.0 NA 170.0 181.4 NA NA
9 NA 78.6 NA 148.6 159.9 NA NA
10 NA 82.0 NA 152.4 163.1 NA NA
11 NA 81.7 NA 148.8 160.4 NA NA
12 NA 81.7 NA 163.2 175.3 NA NA
'''
# NOTE: Makes this reliant on AlgorithmInstance tests passing
example_file = os.path.join(os.path.dirname(__file__),
'../Angola2017_example.xlsx')
genotypedata, additional = RecrudescenceFileParser.parse_file(example_file)
genotypedata_RR = AlgorithmInstance._get_samples_from_site(
genotypedata, 'Benguela')
additional_neutral = AlgorithmInstance._replace_sample_names(
AlgorithmInstance._get_samples_from_site(additional, 'Benguela'),
'Additional_')
expected_maxMOI = 5
locirepeats = np.array([2, 2, 3, 3, 3, 3, 3])
expected_ids = pd.unique(
["BQ17-269", "BD17-040", "BD17-083", "BD17-085", "BD17-087", "BD17-090"])
expected_locinames = pd.unique(
["313", "383", "TA1", "POLYA", "PFPK2", "2490", "TA109"])
alleles_definitions_RR = AlgorithmSiteInstance._get_allele_definitions(
genotypedata_RR, additional_neutral, expected_locinames.size, locirepeats)