def test_3_columns(self):
index = pd.Index(['seq1', 'seq2'], name='Feature ID', dtype=object)
exp = pd.DataFrame([['k__Foo; p__Bar', '-1.0'],
['k__Foo; p__Baz', '-42.0']], index=index,
columns=['Taxon', 'Confidence'], dtype=object)
# has_header=None (default)
obs = _taxonomy_formats_to_dataframe(
self.get_data_path(os.path.join('taxonomy', '3-column.tsv')))
assert_frame_equal(obs, exp)
# has_header=True
obs = _taxonomy_formats_to_dataframe(
self.get_data_path(os.path.join('taxonomy', '3-column.tsv')),
has_header=True)
assert_frame_equal(obs, exp)
def test_2_columns(self):
index = pd.Index(['seq1', 'seq2'], name='Feature ID', dtype=object)
exp = pd.DataFrame([['k__Bacteria; p__Proteobacteria'],
['k__Bacteria']], index=index, columns=['Taxon'],
dtype=object)
# has_header=None (default)
obs = _taxonomy_formats_to_dataframe(
self.get_data_path(os.path.join('taxonomy', '2-column.tsv')))
assert_frame_equal(obs, exp)
# has_header=True
obs = _taxonomy_formats_to_dataframe(
self.get_data_path(os.path.join('taxonomy', '2-column.tsv')),
has_header=True)
assert_frame_equal(obs, exp)
def test_3_columns(self):
index = pd.Index(['seq1', 'seq2'], name='Feature ID', dtype=object)
exp = pd.DataFrame([['k__Foo; p__Bar', '-1.0'],
['k__Foo; p__Baz', '-42.0']], index=index,
columns=['Taxon', 'Confidence'], dtype=object)
# has_header=None (default)
obs = _taxonomy_formats_to_dataframe(
self.get_data_path(os.path.join('taxonomy', '3-column.tsv')))
assert_frame_equal(obs, exp)
# has_header=True
obs = _taxonomy_formats_to_dataframe(
self.get_data_path(os.path.join('taxonomy', '3-column.tsv')),
has_header=True)
assert_frame_equal(obs, exp)
def test_2_columns(self):
index = pd.Index(['seq1', 'seq2'], name='Feature ID', dtype=object)
exp = pd.DataFrame([['k__Bacteria; p__Proteobacteria'],
['k__Bacteria']], index=index, columns=['Taxon'],
dtype=object)
# has_header=None (default)
obs = _taxonomy_formats_to_dataframe(
self.get_data_path(os.path.join('taxonomy', '2-column.tsv')))
assert_frame_equal(obs, exp)
# has_header=True
obs = _taxonomy_formats_to_dataframe(
self.get_data_path(os.path.join('taxonomy', '2-column.tsv')),
has_header=True)
assert_frame_equal(obs, exp)
def test_headerless(self):
index = pd.Index(['seq1', 'seq2'], name='Feature ID', dtype=object)
columns = ['Taxon', 'Unnamed Column 1', 'Unnamed Column 2']
exp = pd.DataFrame([['k__Foo; p__Bar', 'some', 'another'],
['k__Foo; p__Baz', 'column', 'column!']],
index=index, columns=columns, dtype=object)
# has_header=None (default)
obs = _taxonomy_formats_to_dataframe(
self.get_data_path(os.path.join('taxonomy',
'headerless.tsv')))
assert_frame_equal(obs, exp)
# has_header=False
obs = _taxonomy_formats_to_dataframe(
self.get_data_path(os.path.join('taxonomy',
'headerless.tsv')),
has_header=False)
assert_frame_equal(obs, exp)
def test_headerless(self):
index = pd.Index(['seq1', 'seq2'], name='Feature ID', dtype=object)
columns = ['Taxon', 'Unnamed Column 1', 'Unnamed Column 2']
exp = pd.DataFrame([['k__Foo; p__Bar', 'some', 'another'],
['k__Foo; p__Baz', 'column', 'column!']],
index=index,
columns=columns,
dtype=object)
# has_header=None (default)
obs = _taxonomy_formats_to_dataframe(
self.get_data_path(os.path.join('taxonomy', 'headerless.tsv')))
assert_frame_equal(obs, exp)
# has_header=False
obs = _taxonomy_formats_to_dataframe(self.get_data_path(
os.path.join('taxonomy', 'headerless.tsv')),
has_header=False)
assert_frame_equal(obs, exp)
def test_valid_but_messy_file(self):
index = pd.Index(
['SEQUENCE1', 'seq2'], name='Feature ID', dtype=object)
exp = pd.DataFrame([['k__Bar; p__Baz', 'foo'],
['some; taxonomy; for; ya', 'bar baz']],
index=index, columns=['Taxon', 'Extra Column'],
dtype=object)
# has_header=None (default)
obs = _taxonomy_formats_to_dataframe(
self.get_data_path(os.path.join('taxonomy',
'valid-but-messy.tsv')))
assert_frame_equal(obs, exp)
# has_header=True
obs = _taxonomy_formats_to_dataframe(
self.get_data_path(os.path.join('taxonomy',
'valid-but-messy.tsv')),
has_header=True)
assert_frame_equal(obs, exp)
def test_valid_but_messy_file(self):
index = pd.Index(
['SEQUENCE1', 'seq2'], name='Feature ID', dtype=object)
exp = pd.DataFrame([['k__Bar; p__Baz', 'foo'],
['some; taxonomy; for; ya', 'bar baz']],
index=index, columns=['Taxon', 'Extra Column'],
dtype=object)
# has_header=None (default)
obs = _taxonomy_formats_to_dataframe(
self.get_data_path(os.path.join('taxonomy',
'valid-but-messy.tsv')))
assert_frame_equal(obs, exp)
# has_header=True
obs = _taxonomy_formats_to_dataframe(
self.get_data_path(os.path.join('taxonomy',
'valid-but-messy.tsv')),
has_header=True)
assert_frame_equal(obs, exp)
def test_duplicate_columns(self):
with self.assertRaisesRegex(ValueError, 'duplicated: Column1'):
_taxonomy_formats_to_dataframe(
self.get_data_path(
os.path.join('taxonomy', 'duplicate-columns.tsv')))
def test_has_header_with_headerless(self):
with self.assertRaisesRegex(ValueError, 'requires a header'):
_taxonomy_formats_to_dataframe(self.get_data_path(
os.path.join('taxonomy', 'headerless.tsv')),
has_header=True)
def test_jagged(self):
with self.assertRaises(pandas.errors.ParserError):
_taxonomy_formats_to_dataframe(
self.get_data_path(os.path.join('taxonomy', 'jagged.tsv')))
def test_empty(self):
with self.assertRaises(pandas.errors.EmptyDataError):
_taxonomy_formats_to_dataframe(
self.get_data_path(os.path.join('taxonomy', 'empty')))
def test_header_only(self):
with self.assertRaisesRegex(ValueError, 'one row of data'):
_taxonomy_formats_to_dataframe(
self.get_data_path(os.path.join('taxonomy',
'header-only.tsv')))
def test_blanks_and_comments(self):
with self.assertRaises(pandas.io.common.EmptyDataError):
_taxonomy_formats_to_dataframe(
self.get_data_path(
os.path.join('taxonomy', 'blanks-and-comments')))
def test_one_column(self):
with self.assertRaisesRegex(ValueError, "two columns, found 1"):
_taxonomy_formats_to_dataframe(
self.get_data_path(os.path.join('taxonomy', '1-column.tsv')))
def test_one_column(self):
with self.assertRaisesRegex(ValueError, "two columns, found 1"):
_taxonomy_formats_to_dataframe(
self.get_data_path(os.path.join('taxonomy', '1-column.tsv')))
def test_blanks_and_comments(self):
with self.assertRaises(pandas.io.common.EmptyDataError):
_taxonomy_formats_to_dataframe(
self.get_data_path(os.path.join('taxonomy',
'blanks-and-comments')))
def test_empty(self):
with self.assertRaises(pandas.io.common.EmptyDataError):
_taxonomy_formats_to_dataframe(
self.get_data_path(os.path.join('taxonomy', 'empty')))
def test_header_only(self):
with self.assertRaisesRegex(ValueError, 'one row of data'):
_taxonomy_formats_to_dataframe(
self.get_data_path(os.path.join('taxonomy',
'header-only.tsv')))
def test_duplicate_columns(self):
with self.assertRaisesRegex(ValueError, 'duplicated: Column1'):
_taxonomy_formats_to_dataframe(
self.get_data_path(os.path.join(
'taxonomy', 'duplicate-columns.tsv')))
def test_jagged(self):
with self.assertRaises(pandas.io.common.CParserError):
_taxonomy_formats_to_dataframe(
self.get_data_path(os.path.join('taxonomy', 'jagged.tsv')))
def test_has_header_with_headerless(self):
with self.assertRaisesRegex(ValueError, 'requires a header'):
_taxonomy_formats_to_dataframe(
self.get_data_path(os.path.join('taxonomy', 'headerless.tsv')),
has_header=True)
