def test_no_rows(self):
index = pd.Index([], name='Feature ID', dtype=object)
columns = ['Taxon']
df = pd.DataFrame([], index=index, columns=columns, dtype=object)
with self.assertRaisesRegex(ValueError, 'one row of data'):
_dataframe_to_tsv_taxonomy_format(df)
def test_no_columns(self):
index = pd.Index(['seq1', 'seq2'], name='Feature ID', dtype=object)
columns = []
df = pd.DataFrame([[], []], index=index, columns=columns, dtype=object)
with self.assertRaisesRegex(ValueError, 'one column of data'):
_dataframe_to_tsv_taxonomy_format(df)
def test_no_columns(self):
index = pd.Index(['seq1', 'seq2'], name='Feature ID', dtype=object)
columns = []
df = pd.DataFrame([[], []], index=index, columns=columns, dtype=object)
with self.assertRaisesRegex(ValueError, 'one column of data'):
_dataframe_to_tsv_taxonomy_format(df)
def test_no_rows(self):
index = pd.Index([], name='Feature ID', dtype=object)
columns = ['Taxon']
df = pd.DataFrame([], index=index, columns=columns, dtype=object)
with self.assertRaisesRegex(ValueError, 'one row of data'):
_dataframe_to_tsv_taxonomy_format(df)
def test_duplicate_columns(self):
index = pd.Index(['seq1', 'seq2'], name='Feature ID', dtype=object)
columns = ['Taxon', 'Taxon']
df = pd.DataFrame([['abc', 'def'], ['ghi', 'jkl']], index=index,
columns=columns, dtype=object)
with self.assertRaisesRegex(ValueError, "duplicated: Taxon"):
_dataframe_to_tsv_taxonomy_format(df)
def test_invalid_taxon_column_name(self):
index = pd.Index(['seq1', 'seq2'], name='Feature ID', dtype=object)
columns = ['Foo']
df = pd.DataFrame([['abc'], ['def']], index=index, columns=columns,
dtype=object)
with self.assertRaisesRegex(ValueError, "`Taxon`, found 'Foo'"):
_dataframe_to_tsv_taxonomy_format(df)
def test_duplicate_columns(self):
index = pd.Index(['seq1', 'seq2'], name='Feature ID', dtype=object)
columns = ['Taxon', 'Taxon']
df = pd.DataFrame([['abc', 'def'], ['ghi', 'jkl']], index=index,
columns=columns, dtype=object)
with self.assertRaisesRegex(ValueError, "duplicated: Taxon"):
_dataframe_to_tsv_taxonomy_format(df)
def test_invalid_taxon_column_name(self):
index = pd.Index(['seq1', 'seq2'], name='Feature ID', dtype=object)
columns = ['Foo']
df = pd.DataFrame([['abc'], ['def']], index=index, columns=columns,
dtype=object)
with self.assertRaisesRegex(ValueError, "`Taxon`, found 'Foo'"):
_dataframe_to_tsv_taxonomy_format(df)
def test_2_columns(self):
index = pd.Index(['seq1', 'seq2'], name='Feature ID', dtype=object)
df = pd.DataFrame(
[['k__Bacteria; p__Proteobacteria', '42'], ['k__Bacteria', '43']],
index=index,
columns=['Taxon', 'Confidence'],
dtype=object)
exp = ('Feature ID\tTaxon\tConfidence\n'
'seq1\tk__Bacteria; p__Proteobacteria\t42\n'
'seq2\tk__Bacteria\t43\n')
obs = _dataframe_to_tsv_taxonomy_format(df)
with obs.open() as fh:
self.assertEqual(fh.read(), exp)
def test_2_columns(self):
index = pd.Index(['seq1', 'seq2'], name='Feature ID', dtype=object)
df = pd.DataFrame([['k__Bacteria; p__Proteobacteria', '42'],
['k__Bacteria', '43']], index=index,
columns=['Taxon', 'Confidence'], dtype=object)
exp = (
'Feature ID\tTaxon\tConfidence\n'
'seq1\tk__Bacteria; p__Proteobacteria\t42\n'
'seq2\tk__Bacteria\t43\n'
)
obs = _dataframe_to_tsv_taxonomy_format(df)
with obs.open() as fh:
self.assertEqual(fh.read(), exp)
