def test_to_and_from_dataframe(self):
x = np.random.randn(10)
y = np.random.randn(10)
t = list('abcdefghij')
ds = Dataset(
OrderedDict([
('a', ('t', x)),
('b', ('t', y)),
('t', ('t', t)),
]))
expected = pd.DataFrame(np.array([x, y]).T,
columns=['a', 'b'],
index=pd.Index(t, name='t'))
actual = ds.to_dataframe()
# use the .equals method to check all DataFrame metadata
assert expected.equals(actual), (expected, actual)
# check roundtrip
self.assertDatasetIdentical(ds, Dataset.from_dataframe(actual))
# test a case with a MultiIndex
w = np.random.randn(2, 3)
ds = Dataset({'w': (('x', 'y'), w)})
ds['y'] = ('y', list('abc'))
exp_index = pd.MultiIndex.from_arrays(
[[0, 0, 0, 1, 1, 1], ['a', 'b', 'c', 'a', 'b', 'c']],
names=['x', 'y'])
expected = pd.DataFrame(w.reshape(-1), columns=['w'], index=exp_index)
actual = ds.to_dataframe()
self.assertTrue(expected.equals(actual))
# check roundtrip
self.assertDatasetIdentical(ds, Dataset.from_dataframe(actual))
def test_to_and_from_dataframe(self):
x = np.random.randn(10)
y = np.random.randn(10)
t = list('abcdefghij')
ds = Dataset({'a': ('t', x), 'b': ('t', y), 't': ('t', t)})
expected = pd.DataFrame(np.array([x, y]).T, columns=['a', 'b'],
index=pd.Index(t, name='t'))
actual = ds.to_dataframe()
# use the .equals method to check all DataFrame metadata
self.assertTrue(expected.equals(actual))
# check roundtrip
self.assertDatasetIdentical(ds, Dataset.from_dataframe(actual))
# test a case with a MultiIndex
w = np.random.randn(2, 3)
ds = Dataset({'w': (('x', 'y'), w)})
ds['y'] = ('y', list('abc'))
exp_index = pd.MultiIndex.from_arrays(
[[0, 0, 0, 1, 1, 1], ['a', 'b', 'c', 'a', 'b', 'c']],
names=['x', 'y'])
expected = pd.DataFrame(w.reshape(-1), columns=['w'], index=exp_index)
actual = ds.to_dataframe()
self.assertTrue(expected.equals(actual))
# check roundtrip
self.assertDatasetIdentical(ds, Dataset.from_dataframe(actual))
def test_to_and_from_dataframe(self):
x = np.random.randn(10)
y = np.random.randn(10)
t = list('abcdefghij')
ds = Dataset(OrderedDict([('a', ('t', x)),
('b', ('t', y)),
('t', ('t', t))]))
expected = pd.DataFrame(np.array([x, y]).T, columns=['a', 'b'],
index=pd.Index(t, name='t'))
actual = ds.to_dataframe()
# use the .equals method to check all DataFrame metadata
assert expected.equals(actual), (expected, actual)
# verify coords are included
actual = ds.set_coords('b').to_dataframe()
assert expected.equals(actual), (expected, actual)
# check roundtrip
self.assertDatasetIdentical(ds, Dataset.from_dataframe(actual))
# test a case with a MultiIndex
w = np.random.randn(2, 3)
ds = Dataset({'w': (('x', 'y'), w)})
ds['y'] = ('y', list('abc'))
exp_index = pd.MultiIndex.from_arrays(
[[0, 0, 0, 1, 1, 1], ['a', 'b', 'c', 'a', 'b', 'c']],
names=['x', 'y'])
expected = pd.DataFrame(w.reshape(-1), columns=['w'], index=exp_index)
actual = ds.to_dataframe()
self.assertTrue(expected.equals(actual))
# check roundtrip
self.assertDatasetIdentical(ds, Dataset.from_dataframe(actual))
# check pathological cases
df = pd.DataFrame([1])
actual = Dataset.from_dataframe(df)
expected = Dataset({0: ('index', [1])})
self.assertDatasetIdentical(expected, actual)
df = pd.DataFrame()
actual = Dataset.from_dataframe(df)
expected = Dataset()
self.assertDatasetIdentical(expected, actual)
