def test_various_numbers(self):
numbers = [
0.0, -0.0, np.nan, 1.0, 42.0, -33.0, 1e-10, 1.5e15, 0.0003, -4.234,
# This last number should be rounded because it exceeds 15 digits
# of precision.
12.34567891234567
]
index = pd.Index(['id1', 'id2', 'id3', 'id4', 'id5', 'id6', 'id7',
'id8', 'id9', 'id10', 'id11'], name='ID')
md = Metadata(pd.DataFrame({'numbers': numbers}, index=index))
md.save(self.filepath)
with open(self.filepath, 'r') as fh:
obs = fh.read()
exp = (
"ID\tnumbers\n"
"#q2:types\tnumeric\n"
"id1\t0\n"
"id2\t-0\n"
"id3\t\n"
"id4\t1\n"
"id5\t42\n"
"id6\t-33\n"
"id7\t1e-10\n"
"id8\t1.5e+15\n"
"id9\t0.0003\n"
"id10\t-4.234\n"
"id11\t12.3456789123457\n"
)
self.assertEqual(obs, exp)
def test_ids_and_column_names_as_numeric_strings(self):
index = pd.Index(['0.000001', '0.004000', '0.000000'],
dtype=object, name='id')
columns = ['42.0', '1000', '-4.2']
data = [
[2.0, 'b', 2.5],
[1.0, 'b', 4.2],
[3.0, 'c', -9.999]
]
df = pd.DataFrame(data, index=index, columns=columns)
md = Metadata(df)
md.save(self.filepath)
with open(self.filepath, 'r') as fh:
obs = fh.read()
exp = (
"id\t42.0\t1000\t-4.2\n"
"#q2:types\tnumeric\tcategorical\tnumeric\n"
"0.000001\t2\tb\t2.5\n"
"0.004000\t1\tb\t4.2\n"
"0.000000\t3\tc\t-9.999\n"
)
self.assertEqual(obs, exp)
def test_various_numbers(self):
numbers = [
0.0, -0.0, np.nan, 1.0, 42.0, -33.0, 1e-10, 1.5e15, 0.0003, -4.234,
# This last number should be rounded because it exceeds 15 digits
# of precision.
12.34567891234567
]
index = pd.Index(['id1', 'id2', 'id3', 'id4', 'id5', 'id6', 'id7',
'id8', 'id9', 'id10', 'id11'], name='ID')
md = Metadata(pd.DataFrame({'numbers': numbers}, index=index))
md.save(self.filepath)
with open(self.filepath, 'r') as fh:
obs = fh.read()
exp = (
"ID\tnumbers\n"
"#q2:types\tnumeric\n"
"id1\t0\n"
"id2\t-0\n"
"id3\t\n"
"id4\t1\n"
"id5\t42\n"
"id6\t-33\n"
"id7\t1e-10\n"
"id8\t1.5e+15\n"
"id9\t0.0003\n"
"id10\t-4.234\n"
"id11\t12.3456789123457\n"
)
self.assertEqual(obs, exp)
def test_ids_and_column_names_as_numeric_strings(self):
index = pd.Index(['0.000001', '0.004000', '0.000000'],
dtype=object, name='id')
columns = ['42.0', '1000', '-4.2']
data = [
[2.0, 'b', 2.5],
[1.0, 'b', 4.2],
[3.0, 'c', -9.999]
]
df = pd.DataFrame(data, index=index, columns=columns)
md = Metadata(df)
md.save(self.filepath)
with open(self.filepath, 'r') as fh:
obs = fh.read()
exp = (
"id\t42.0\t1000\t-4.2\n"
"#q2:types\tnumeric\tcategorical\tnumeric\n"
"0.000001\t2\tb\t2.5\n"
"0.004000\t1\tb\t4.2\n"
"0.000000\t3\tc\t-9.999\n"
)
self.assertEqual(obs, exp)
def test_minimal(self):
md = Metadata(pd.DataFrame({}, index=pd.Index(['my-id'], name='id')))
md.save(self.filepath)
with open(self.filepath, 'r') as fh:
obs = fh.read()
exp = ("id\n" "#q2:types\n" "my-id\n")
self.assertEqual(obs, exp)
def test_no_columns(self):
md = Metadata(
pd.DataFrame({}, index=pd.Index(['foo', 'bar', 'baz'], name='id')))
md.save(self.filepath)
with open(self.filepath, 'r') as fh:
obs = fh.read()
exp = ("id\n" "#q2:types\n" "foo\n" "bar\n" "baz\n")
self.assertEqual(obs, exp)
def test_no_bom(self):
md = Metadata(pd.DataFrame(
{'col1': [1.0, 2.0, 3.0],
'col2': ['a', 'b', 'c'],
'col3': ['foo', 'bar', '42']},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
md.save(self.filepath)
with open(self.filepath, 'rb') as fh:
obs = fh.read(2)
self.assertEqual(obs, b'id')
def test_minimal(self):
md = Metadata(pd.DataFrame({}, index=pd.Index(['my-id'], name='id')))
md.save(self.filepath)
with open(self.filepath, 'r') as fh:
obs = fh.read()
exp = (
"id\n"
"#q2:types\n"
"my-id\n"
)
self.assertEqual(obs, exp)
def test_no_bom(self):
md = Metadata(
pd.DataFrame(
{
'col1': [1.0, 2.0, 3.0],
'col2': ['a', 'b', 'c'],
'col3': ['foo', 'bar', '42']
},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
md.save(self.filepath)
with open(self.filepath, 'rb') as fh:
obs = fh.read(2)
self.assertEqual(obs, b'id')
def test_single_id(self):
md = Metadata(pd.DataFrame(
{'col1': ['foo'], 'col2': [4.002]},
index=pd.Index(['my-id'], name='featureid')))
md.save(self.filepath)
with open(self.filepath, 'r') as fh:
obs = fh.read()
exp = (
"featureid\tcol1\tcol2\n"
"#q2:types\tcategorical\tnumeric\n"
"my-id\tfoo\t4.002\n"
)
self.assertEqual(obs, exp)
def test_single_column(self):
md = Metadata(
pd.DataFrame({'col1': ['42', '4.3', '4.4000']},
index=pd.Index(['foo', 'bar', 'baz'], name='id')))
md.save(self.filepath)
with open(self.filepath, 'r') as fh:
obs = fh.read()
exp = ("id\tcol1\n"
"#q2:types\tcategorical\n"
"foo\t42\n"
"bar\t4.3\n"
"baz\t4.4000\n")
self.assertEqual(obs, exp)
def test_single_id(self):
md = Metadata(pd.DataFrame(
{'col1': ['foo'], 'col2': [4.002]},
index=pd.Index(['my-id'], name='featureid')))
md.save(self.filepath)
with open(self.filepath, 'r') as fh:
obs = fh.read()
exp = (
"featureid\tcol1\tcol2\n"
"#q2:types\tcategorical\tnumeric\n"
"my-id\tfoo\t4.002\n"
)
self.assertEqual(obs, exp)
def test_unsorted_column_order(self):
index = pd.Index(['id1', 'id2', 'id3'], name='id')
columns = ['z', 'b', 'y']
data = [[1.0, 'a', 'foo'], [2.0, 'b', 'bar'], [3.0, 'c', '42']]
md = Metadata(pd.DataFrame(data, index=index, columns=columns))
md.save(self.filepath)
with open(self.filepath, 'r') as fh:
obs = fh.read()
exp = ("id\tz\tb\ty\n"
"#q2:types\tnumeric\tcategorical\tcategorical\n"
"id1\t1\ta\tfoo\n"
"id2\t2\tb\tbar\n"
"id3\t3\tc\t42\n")
self.assertEqual(obs, exp)
def test_no_columns(self):
md = Metadata(pd.DataFrame(
{}, index=pd.Index(['foo', 'bar', 'baz'], name='id')))
md.save(self.filepath)
with open(self.filepath, 'r') as fh:
obs = fh.read()
exp = (
"id\n"
"#q2:types\n"
"foo\n"
"bar\n"
"baz\n"
)
self.assertEqual(obs, exp)
def test_single_column(self):
md = Metadata(pd.DataFrame(
{'col1': ['42', '4.3', '4.4000']},
index=pd.Index(['foo', 'bar', 'baz'], name='id')))
md.save(self.filepath)
with open(self.filepath, 'r') as fh:
obs = fh.read()
exp = (
"id\tcol1\n"
"#q2:types\tcategorical\n"
"foo\t42\n"
"bar\t4.3\n"
"baz\t4.4000\n"
)
self.assertEqual(obs, exp)
def test_some_missing_data(self):
md = Metadata(
pd.DataFrame({'col1': [42.0, np.nan, -3.5],
'col2': ['a', np.nan, np.nan]},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
md.save(self.filepath)
with open(self.filepath, 'r') as fh:
obs = fh.read()
exp = (
"id\tcol1\tcol2\n"
"#q2:types\tnumeric\tcategorical\n"
"id1\t42\ta\n"
"id2\t\t\n"
"id3\t-3.5\t\n"
)
self.assertEqual(obs, exp)
def test_some_missing_data(self):
md = Metadata(
pd.DataFrame({'col1': [42.0, np.nan, -3.5],
'col2': ['a', np.nan, np.nan]},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
md.save(self.filepath)
with open(self.filepath, 'r') as fh:
obs = fh.read()
exp = (
"id\tcol1\tcol2\n"
"#q2:types\tnumeric\tcategorical\n"
"id1\t42\ta\n"
"id2\t\t\n"
"id3\t-3.5\t\n"
)
self.assertEqual(obs, exp)
def test_alternate_id_header(self):
md = Metadata(pd.DataFrame(
{'col1': [1.0, 2.0, 3.0],
'col2': ['a', 'b', 'c'],
'col3': ['foo', 'bar', '42']},
index=pd.Index(['id1', 'id2', 'id3'], name='#SampleID')))
md.save(self.filepath)
with open(self.filepath, 'r') as fh:
obs = fh.read()
exp = (
"#SampleID\tcol1\tcol2\tcol3\n"
"#q2:types\tnumeric\tcategorical\tcategorical\n"
"id1\t1\ta\tfoo\n"
"id2\t2\tb\tbar\n"
"id3\t3\tc\t42\n"
)
self.assertEqual(obs, exp)
def test_alternate_id_header(self):
md = Metadata(pd.DataFrame(
{'col1': [1.0, 2.0, 3.0],
'col2': ['a', 'b', 'c'],
'col3': ['foo', 'bar', '42']},
index=pd.Index(['id1', 'id2', 'id3'], name='#SampleID')))
md.save(self.filepath)
with open(self.filepath, 'r') as fh:
obs = fh.read()
exp = (
"#SampleID\tcol1\tcol2\tcol3\n"
"#q2:types\tnumeric\tcategorical\tcategorical\n"
"id1\t1\ta\tfoo\n"
"id2\t2\tb\tbar\n"
"id3\t3\tc\t42\n"
)
self.assertEqual(obs, exp)
def test_different_file_extension(self):
md = Metadata(pd.DataFrame(
{'col1': [1.0, 2.0, 3.0],
'col2': ['a', 'b', 'c'],
'col3': ['foo', 'bar', '42']},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
filepath = os.path.join(self.temp_dir, 'metadata.txt')
md.save(filepath)
with open(filepath, 'r') as fh:
obs = fh.read()
exp = (
"id\tcol1\tcol2\tcol3\n"
"#q2:types\tnumeric\tcategorical\tcategorical\n"
"id1\t1\ta\tfoo\n"
"id2\t2\tb\tbar\n"
"id3\t3\tc\t42\n"
)
self.assertEqual(obs, exp)
def test_all_missing_data(self):
# nan-only columns that are numeric or categorical.
md = Metadata(
pd.DataFrame({'col1': [np.nan, np.nan, np.nan],
'col2': np.array([np.nan, np.nan, np.nan],
dtype=object)},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
md.save(self.filepath)
with open(self.filepath, 'r') as fh:
obs = fh.read()
exp = (
"id\tcol1\tcol2\n"
"#q2:types\tnumeric\tcategorical\n"
"id1\t\t\n"
"id2\t\t\n"
"id3\t\t\n"
)
self.assertEqual(obs, exp)
def test_different_file_extension(self):
md = Metadata(pd.DataFrame(
{'col1': [1.0, 2.0, 3.0],
'col2': ['a', 'b', 'c'],
'col3': ['foo', 'bar', '42']},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
filepath = os.path.join(self.temp_dir, 'metadata.txt')
md.save(filepath)
with open(filepath, 'r') as fh:
obs = fh.read()
exp = (
"id\tcol1\tcol2\tcol3\n"
"#q2:types\tnumeric\tcategorical\tcategorical\n"
"id1\t1\ta\tfoo\n"
"id2\t2\tb\tbar\n"
"id3\t3\tc\t42\n"
)
self.assertEqual(obs, exp)
def test_all_missing_data(self):
# nan-only columns that are numeric or categorical.
md = Metadata(
pd.DataFrame(
{
'col1': [np.nan, np.nan, np.nan],
'col2': np.array([np.nan, np.nan, np.nan], dtype=object)
},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
md.save(self.filepath)
with open(self.filepath, 'r') as fh:
obs = fh.read()
exp = ("id\tcol1\tcol2\n"
"#q2:types\tnumeric\tcategorical\n"
"id1\t\t\n"
"id2\t\t\n"
"id3\t\t\n")
self.assertEqual(obs, exp)
def test_unsorted_column_order(self):
index = pd.Index(['id1', 'id2', 'id3'], name='id')
columns = ['z', 'b', 'y']
data = [
[1.0, 'a', 'foo'],
[2.0, 'b', 'bar'],
[3.0, 'c', '42']
]
md = Metadata(pd.DataFrame(data, index=index, columns=columns))
md.save(self.filepath)
with open(self.filepath, 'r') as fh:
obs = fh.read()
exp = (
"id\tz\tb\ty\n"
"#q2:types\tnumeric\tcategorical\tcategorical\n"
"id1\t1\ta\tfoo\n"
"id2\t2\tb\tbar\n"
"id3\t3\tc\t42\n"
)
self.assertEqual(obs, exp)
def test_save_metadata_auto_extension(self):
md = Metadata(
pd.DataFrame(
{
'col1': [1.0, 2.0, 3.0],
'col2': ['a', 'b', 'c'],
'col3': ['foo', 'bar', '42']
},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
# Filename & extension endswith is matching (non-default).
fp = os.path.join(self.temp_dir, 'metadatatsv')
obs_md = md.save(fp, '.tsv')
obs_filename = os.path.basename(obs_md)
self.assertEqual(obs_filename, 'metadatatsv.tsv')
# No period in filename; no extension included.
fp = os.path.join(self.temp_dir, 'metadata')
obs_md = md.save(fp)
obs_filename = os.path.basename(obs_md)
self.assertEqual(obs_filename, 'metadata')
# No period in filename; no period in extension.
fp = os.path.join(self.temp_dir, 'metadata')
obs_md = md.save(fp, 'tsv')
obs_filename = os.path.basename(obs_md)
self.assertEqual(obs_filename, 'metadata.tsv')
# No period in filename; multiple periods in extension.
fp = os.path.join(self.temp_dir, 'metadata')
obs_md = md.save(fp, '..tsv')
obs_filename = os.path.basename(obs_md)
self.assertEqual(obs_filename, 'metadata.tsv')
# Single period in filename; no period in extension.
fp = os.path.join(self.temp_dir, 'metadata.')
obs_md = md.save(fp, 'tsv')
obs_filename = os.path.basename(obs_md)
self.assertEqual(obs_filename, 'metadata.tsv')
# Single period in filename; single period in extension.
fp = os.path.join(self.temp_dir, 'metadata.')
obs_md = md.save(fp, '.tsv')
obs_filename = os.path.basename(obs_md)
self.assertEqual(obs_filename, 'metadata.tsv')
# Single period in filename; multiple periods in extension.
fp = os.path.join(self.temp_dir, 'metadata.')
obs_md = md.save(fp, '..tsv')
obs_filename = os.path.basename(obs_md)
self.assertEqual(obs_filename, 'metadata.tsv')
# Multiple periods in filename; single period in extension.
fp = os.path.join(self.temp_dir, 'metadata..')
obs_md = md.save(fp, '.tsv')
obs_filename = os.path.basename(obs_md)
self.assertEqual(obs_filename, 'metadata.tsv')
# Multiple periods in filename; multiple periods in extension.
fp = os.path.join(self.temp_dir, 'metadata..')
obs_md = md.save(fp, '..tsv')
obs_filename = os.path.basename(obs_md)
self.assertEqual(obs_filename, 'metadata.tsv')
# No extension in filename; no extension input.
fp = os.path.join(self.temp_dir, 'metadata')
obs_md = md.save(fp)
obs_filename = os.path.basename(obs_md)
self.assertEqual(obs_filename, 'metadata')
# No extension in filename; extension input.
fp = os.path.join(self.temp_dir, 'metadata')
obs_md = md.save(fp, '.tsv')
obs_filename = os.path.basename(obs_md)
self.assertEqual(obs_filename, 'metadata.tsv')
# Extension in filename; no extension input.
fp = os.path.join(self.temp_dir, 'metadata.tsv')
obs_md = md.save(fp)
obs_filename = os.path.basename(obs_md)
self.assertEqual(obs_filename, 'metadata.tsv')
# Extension in filename; extension input (non-matching).
fp = os.path.join(self.temp_dir, 'metadata.tsv')
obs_md = md.save(fp, '.txt')
obs_filename = os.path.basename(obs_md)
self.assertEqual(obs_filename, 'metadata.tsv.txt')
# Extension in filename; extension input (matching).
fp = os.path.join(self.temp_dir, 'metadata.tsv')
obs_md = md.save(fp, '.tsv')
obs_filename = os.path.basename(obs_md)
self.assertEqual(obs_filename, 'metadata.tsv')
