def test_dataset_reindex_non_constant(self):
with DatatypeContext([self.datatype, 'dictionary' , 'dataframe', 'grid'], self.rgb):
ds = Dataset(self.rgb)
reindexed = ds.reindex(['y'], ['R'])
data = Dataset(ds.columns(['y', 'R']),
kdims=['y'], vdims=[ds.vdims[0]])
self.assertEqual(reindexed, data)
def test_dataset_reindex_non_constant(self):
ds = Dataset(self.rgb)
reindexed = ds.reindex(['y'], ['R'])
data = Dataset(ds.columns(['y', 'R']),
kdims=['y'],
vdims=[ds.vdims[0]])
self.assertEqual(reindexed, data)
def test_dataset_reindex_constant(self):
with DatatypeContext([self.datatype, 'dictionary', 'dataframe', 'grid'], self.image):
selected = Dataset(self.image.select(x=0))
reindexed = selected.reindex(['y'])
data = Dataset(selected.columns(['y', 'z']),
kdims=['y'], vdims=['z'])
self.assertEqual(reindexed, data)
def test_dataset_groupby_drop_dims_dynamic(self):
array = np.random.rand(3, 20, 10)
ds = Dataset({'x': range(10), 'y': range(20), 'z': range(3), 'Val': array},
kdims=['x', 'y', 'z'], vdims=['Val'])
with DatatypeContext([self.datatype, 'columns', 'dataframe']):
partial = ds.to(Dataset, kdims=['x'], vdims=['Val'], groupby='y', dynamic=True)
self.assertEqual(partial[19]['Val'], array[:, -1, :].T.flatten())
def _table_data(self):
if self.format in ('json', 'csv'):
io = StringIO()
else:
io = BytesIO()
table = self._select_download.value
query = {
filt.field: filt.query
for filt in self.filters if filt.query is not None and (
filt.table is None or filt.table == table)
}
data = self.source.get(table, **query)
for filt in self.filters:
if not isinstance(filt, ParamFilter):
continue
from holoviews import Dataset
if filt.value is not None:
ds = Dataset(data)
data = ds.select(filt.value).data
if self.format == 'csv':
data.to_csv(io, **self.kwargs)
elif self.format == 'json':
data.to_json(io, **self.kwargs)
elif self.format == 'xlsx':
data.to_excel(io, **self.kwargs)
elif self.format == 'parquet':
data.to_parquet(io, **self.kwargs)
io.seek(0)
return io
def test_dataset_2D_aggregate_partial_hm_alias(self):
array = np.random.rand(11, 11)
dataset = Dataset({'x':self.xs, 'y':self.y_ints, 'z': array},
kdims=[('x', 'X'), ('y', 'Y')], vdims=[('z', 'Z')])
self.assertEqual(dataset.aggregate(['X'], np.mean),
Dataset({'x':self.xs, 'z': np.mean(array, axis=0)},
kdims=[('x', 'X')], vdims=[('z', 'Z')]))
def test_to_holomap_dask(self):
if dd is None:
raise SkipTest("Dask required to test .to with dask dataframe.")
ddf = dd.from_pandas(self.df, npartitions=2)
dds = Dataset(
ddf,
kdims=[
Dimension('a', label="The a Column"),
Dimension('b', label="The b Column"),
Dimension('c', label="The c Column"),
Dimension('d', label="The d Column"),
]
)
curve_hmap = dds.to(Curve, 'a', 'b', groupby=['c'])
# Check HoloMap element datasets
for v in self.df.c.drop_duplicates():
curve = curve_hmap.data[(v,)]
self.assertEqual(
curve.dataset, self.ds
)
# Execute pipeline
self.assertEqual(curve.pipeline(curve.dataset), curve)
def test_dataset_reindex_non_constant(self):
with DatatypeContext([self.datatype, 'dictionary' , 'dataframe', 'grid'], self.rgb):
ds = Dataset(self.rgb)
reindexed = ds.reindex(['y'], ['R'])
data = Dataset(ds.columns(['y', 'R']),
kdims=['y'], vdims=[ds.vdims[0]])
self.assertEqual(reindexed, data)
def test_dataset_2D_aggregate_partial_hm(self):
array = np.random.rand(11, 11)
dataset = Dataset({'x':self.xs, 'y':self.y_ints, 'z': array},
kdims=['x', 'y'], vdims=['z'])
self.assertEqual(dataset.aggregate(['x'], np.mean),
Dataset({'x':self.xs, 'z': np.mean(array, axis=0)},
kdims=['x'], vdims=['z']))
def test_dataset_redim_with_alias_dframe(self):
test_df = pd.DataFrame({'x': range(10), 'y': range(0,20,2)})
dataset = Dataset(test_df, kdims=[('x', 'X-label')], vdims=['y'])
redim_df = pd.DataFrame({'X': range(10), 'y': range(0,20,2)})
dataset_redim = Dataset(redim_df, kdims=['X'], vdims=['y'])
self.assertEqual(dataset.redim(**{'X-label':'X'}), dataset_redim)
self.assertEqual(dataset.redim(**{'x':'X'}), dataset_redim)
def test_dataset_groupby_path(self):
ds = Dataset([(0, 0, 1), (0, 1, 2), (1, 2, 3), (1, 3, 4)],
['group', 'x', 'y'])
subpaths = ds.groupby('group', group_type=Path)
self.assertEqual(len(subpaths), 2)
self.assertEqual(subpaths[0], Path([(0, 1), (1, 2)]))
self.assertEqual(subpaths[1], Path([(2, 3), (3, 4)]))
def test_dataset_groupby(self):
group1 = {'Age':[10,16], 'Weight':[15,18], 'Height':[0.8,0.6]}
group2 = {'Age':[12], 'Weight':[10], 'Height':[0.8]}
grouped = HoloMap([('M', Dataset(group1, kdims=['Age'], vdims=self.vdims)),
('F', Dataset(group2, kdims=['Age'], vdims=self.vdims))],
kdims=['Gender'])
self.assertEqual(self.table.groupby(['Gender']), grouped)
def test_dataset_redim_with_alias_dframe(self):
test_df = pd.DataFrame({'x': range(10), 'y': range(0,20,2)})
dataset = Dataset(test_df, kdims=[('x', 'X-label')], vdims=['y'])
redim_df = pd.DataFrame({'X': range(10), 'y': range(0,20,2)})
dataset_redim = Dataset(redim_df, kdims=['X'], vdims=['y'])
self.assertEqual(dataset.redim(**{'X-label':'X'}), dataset_redim)
self.assertEqual(dataset.redim(**{'x':'X'}), dataset_redim)
def test_dataset_sort_vdim_hm(self):
xs_2 = np.array(self.xs_2)
dataset = Dataset(np.column_stack([self.xs, -xs_2]),
kdims=['x'], vdims=['y'])
dataset_sorted = Dataset(np.column_stack([self.xs[::-1], -xs_2[::-1]]),
kdims=['x'], vdims=['y'])
self.assertEqual(dataset.sort('y'), dataset_sorted)
def test_dataset_2D_aggregate_partial_hm(self):
array = np.random.rand(11, 11)
dataset = Dataset({'x':self.xs, 'y':self.y_ints, 'z': array},
kdims=['x', 'y'], vdims=['z'])
self.assertEqual(dataset.aggregate(['x'], np.mean),
Dataset({'x':self.xs, 'z': np.mean(array, axis=0)},
kdims=['x'], vdims=['z']))
def test_dataset_sort_reverse_vdim_hm(self):
xs_2 = np.array(self.xs_2)
dataset = Dataset(np.column_stack([self.xs, -xs_2]),
kdims=['x'], vdims=['y'])
dataset_sorted = Dataset(np.column_stack([self.xs, -xs_2]),
kdims=['x'], vdims=['y'])
self.assertEqual(dataset.sort('y', reverse=True), dataset_sorted)
def setUp(self):
self.df = pd.DataFrame({
'a': [1, 1, 3, 3, 2, 2, 0, 0],
'b': [10, 20, 30, 40, 10, 20, 30, 40],
'c': ['A', 'A', 'B', 'B', 'C', 'C', 'D', 'D'],
'd': [-1, -2, -3, -4, -5, -6, -7, -8]
})
self.ds = Dataset(
self.df,
kdims=[
Dimension('a', label="The a Column"),
Dimension('b', label="The b Column"),
Dimension('c', label="The c Column"),
Dimension('d', label="The d Column"),
]
)
self.ds2 = Dataset(
self.df.iloc[2:],
kdims=[
Dimension('a', label="The a Column"),
Dimension('b', label="The b Column"),
Dimension('c', label="The c Column"),
Dimension('d', label="The d Column"),
]
)
def test_dataset_reindex_constant(self):
with DatatypeContext([self.datatype, 'dictionary', 'dataframe', 'grid'], self.image):
selected = Dataset(self.image.select(x=0))
reindexed = selected.reindex(['y'])
data = Dataset(selected.columns(['y', 'z']),
kdims=['y'], vdims=['z'])
self.assertEqual(reindexed, data)
def test_dataset_sort_vdim_hm(self):
xs_2 = np.array(self.xs_2)
dataset = Dataset(np.column_stack([self.xs, -xs_2]),
kdims=['x'], vdims=['y'])
dataset_sorted = Dataset(np.column_stack([self.xs[::-1], -xs_2[::-1]]),
kdims=['x'], vdims=['y'])
self.assertEqual(dataset.sort('y'), dataset_sorted)
def test_collapse_nested(self):
inner1 = UniformNdMapping({1: Dataset([(1, 2)], ['x', 'y'])}, 'Y')
inner2 = UniformNdMapping({1: Dataset([(3, 4)], ['x', 'y'])}, 'Y')
outer = UniformNdMapping({1: inner1, 2: inner2}, 'X')
collapsed = outer.collapse()
expected = Dataset([(1, 1, 1, 2), (2, 1, 3, 4)], ['X', 'Y', 'x', 'y'])
self.assertEqual(collapsed, expected)
def get_data(self):
"""
Queries the Source for the specified table applying any
filters and transformations specified on the View. Unlike
`get_value` this should be used when multiple return values
are expected.
Returns
-------
DataFrame
The queried table after filtering and transformations are
applied.
"""
if self._cache is not None:
return self._cache
query = {
filt.field: filt.query
for filt in self.filters if filt.query is not None and (
filt.table is None or filt.table == self.table)
}
data = self.source.get(self.table, **query)
for transform in self.transforms:
data = transform.apply(data)
if len(data):
data = self.source._filter_dataframe(data, **query)
for filt in self.filters:
if not isinstance(filt, ParamFilter):
continue
from holoviews import Dataset
if filt.value is not None:
ds = Dataset(data)
data = ds.select(filt.value).data
self._cache = data
return data
def test_dataset_groupby_drop_dims_with_vdim(self):
array = np.random.rand(3, 20, 10)
ds = Dataset({'x': range(10), 'y': range(20), 'z': range(3), 'Val': array, 'Val2': array*2},
kdims=['x', 'y', 'z'], vdims=['Val', 'Val2'])
with DatatypeContext([self.datatype, 'dictionary' , 'dataframe'], (ds, Dataset)):
partial = ds.to(Dataset, kdims=['Val'], vdims=['Val2'], groupby='y')
self.assertEqual(partial.last['Val'], array[:, -1, :].T.flatten())
def setUp(self):
self.xs = range(11)
self.y_ints = [i * 2 for i in range(11)]
self.ys = np.linspace(0, 1, 11)
self.columns = Dataset(np.column_stack([self.xs, self.y_ints]),
kdims=['x'],
vdims=['y'])
def test_dataset_sort_vdim_hm_alias(self):
xs_2 = np.array(self.xs_2)
dataset = Dataset(np.column_stack([self.xs, -xs_2]),
kdims=[('x', 'X-label')], vdims=[('y', 'Y-label')])
dataset_sorted = Dataset(np.column_stack([self.xs[::-1], -xs_2[::-1]]),
kdims=[('x', 'X-label')], vdims=[('y', 'Y-label')])
self.assertEqual(dataset.sort('y'), dataset_sorted)
self.assertEqual(dataset.sort('Y-label'), dataset_sorted)
def test_dataset_2D_aggregate_spread_fn_with_duplicates(self):
dataset = Dataset({'x': np.array([0, 0, 1, 1]), 'y': np.array([0, 1, 2, 3]),
'z': np.array([1, 2, 3, 4])},
kdims=['x', 'y'], vdims=['z'])
agg = dataset.aggregate('x', function=np.mean, spreadfn=np.var)
self.assertEqual(agg, Dataset({'x': np.array([0, 1]), 'z': np.array([1.5, 3.5]),
'z_var': np.array([0.25, 0.25])},
kdims=['x'], vdims=['z', 'z_var']))
def test_xarray_dataset_with_scalar_dim_canonicalize(self):
import xarray as xr
xs = [0, 1]
ys = [0.1, 0.2, 0.3]
zs = np.array([[[0, 1], [2, 3], [4, 5]]])
xrarr = xr.DataArray(zs, coords={'x': xs, 'y': ys, 't': [1]}, dims=['t', 'y', 'x'])
ds = Dataset(xrarr, kdims=['x', 'y'], vdims=['z'], datatype=['xarray'])
self.assertEqual(ds.dimension_values(2, flat=False).ndim, 2)
def test_dataset_1D_reduce_hm(self):
dataset = Dataset({
'x': self.xs,
'y': self.y_ints
},
kdims=['x'],
vdims=['y'])
self.assertEqual(dataset.reduce('x', np.mean), 10)
def test_aggregate_ndoverlay(self):
ds = Dataset([(0.2, 0.3, 0), (0.4, 0.7, 1), (0, 0.99, 2)], kdims=['x', 'y', 'z'])
ndoverlay = ds.to(Points, ['x', 'y'], [], 'z').overlay()
expected = Image(([0.25, 0.75], [0.25, 0.75], [[1, 0], [2, 0]]),
vdims=['Count'])
img = aggregate(ndoverlay, dynamic=False, x_range=(0, 1), y_range=(0, 1),
width=2, height=2)
self.assertEqual(img, expected)
def test_dataset_1D_reduce_hm_alias(self):
dataset = Dataset({
'x': self.xs,
'y': self.y_ints
},
kdims=[('x', 'X')],
vdims=[('y', 'Y')])
self.assertEqual(dataset.reduce('X', np.mean), 10)
def init_data(self):
self.xs = range(11)
self.xs_2 = [el**2 for el in self.xs]
self.y_ints = [i * 2 for i in range(11)]
self.dataset_hm = Dataset((self.xs, self.y_ints),
kdims=['x'],
vdims=['y'])
def test_aggregate_ndoverlay(self):
ds = Dataset([(0.2, 0.3, 0), (0.4, 0.7, 1), (0, 0.99, 2)], kdims=['x', 'y', 'z'])
ndoverlay = ds.to(Points, ['x', 'y'], [], 'z').overlay()
expected = Image(([0.25, 0.75], [0.25, 0.75], [[1, 0], [2, 0]]),
vdims=['Count'])
img = aggregate(ndoverlay, dynamic=False, x_range=(0, 1), y_range=(0, 1),
width=2, height=2)
self.assertEqual(img, expected)
def test_dataset_groupby_dynamic(self):
array = np.random.rand(11, 11)
dataset = Dataset({'x':self.xs, 'y':self.y_ints, 'z': array},
kdims=['x', 'y'], vdims=['z'])
grouped = dataset.groupby('x', dynamic=True)
first = Dataset({'y': self.y_ints, 'z': array[:, 0]},
kdims=['y'], vdims=['z'])
self.assertEqual(grouped[0], first)
def test_dataset_2D_reduce_hm_alias(self):
array = np.random.rand(11, 11)
dataset = Dataset({'x':self.xs, 'y':self.y_ints, 'z': array},
kdims=[('x', 'X'), ('y', 'Y')], vdims=[('z', 'Z')])
self.assertEqual(np.array(dataset.reduce(['x', 'y'], np.mean)),
np.mean(array))
self.assertEqual(np.array(dataset.reduce(['X', 'Y'], np.mean)),
np.mean(array))
def test_dataset_groupby_dynamic_alias(self):
array = np.random.rand(11, 11)
dataset = Dataset({'x':self.xs, 'y':self.y_ints, 'z': array},
kdims=[('x', 'X'), ('y', 'Y')], vdims=[('z', 'Z')])
grouped = dataset.groupby('X', dynamic=True)
first = Dataset({'y': self.y_ints, 'z': array[:, 0]},
kdims=[('y', 'Y')], vdims=[('z', 'Z')])
self.assertEqual(grouped[0], first)
def test_dataset_sort_vdim_hm_alias(self):
xs_2 = np.array(self.xs_2)
dataset = Dataset(np.column_stack([self.xs, -xs_2]),
kdims=[('x', 'X-label')], vdims=[('y', 'Y-label')])
dataset_sorted = Dataset(np.column_stack([self.xs[::-1], -xs_2[::-1]]),
kdims=[('x', 'X-label')], vdims=[('y', 'Y-label')])
self.assertEqual(dataset.sort('y'), dataset_sorted)
self.assertEqual(dataset.sort('Y-label'), dataset_sorted)
def test_constructors_dataset(self):
ds = Dataset(self.df)
self.assertIs(ds, ds.dataset)
# Check pipeline
ops = ds.pipeline.operations
self.assertEqual(len(ops), 1)
self.assertIs(ops[0].output_type, Dataset)
self.assertEqual(ds, ds.pipeline(ds.dataset))
def test_dataset_groupby_dynamic_alias(self):
array = np.random.rand(11, 11)
dataset = Dataset({'x':self.xs, 'y':self.y_ints, 'z': array},
kdims=[('x', 'X'), ('y', 'Y')], vdims=[('z', 'Z')])
with DatatypeContext([self.datatype, 'dictionary' , 'dataframe'], dataset):
grouped = dataset.groupby('X', dynamic=True)
first = Dataset({'y': self.y_ints, 'z': array[:, 0]},
kdims=[('y', 'Y')], vdims=[('z', 'Z')])
self.assertEqual(grouped[0], first)
def init_column_data(self):
self.xs = np.array(range(11))
self.xs_2 = self.xs**2
self.y_ints = self.xs*2
self.dataset_hm = Dataset((self.xs, self.y_ints),
kdims=['x'], vdims=['y'])
self.dataset_hm_alias = Dataset((self.xs, self.y_ints),
kdims=[('x', 'X')], vdims=[('y', 'Y')])
def test_dataset_groupby_multiple_dims(self):
dataset = Dataset((range(8), range(8), range(8), range(8),
np.random.rand(8, 8, 8, 8)),
kdims=['a', 'b', 'c', 'd'], vdims=['Value'])
grouped = dataset.groupby(['c', 'd'])
keys = list(product(range(8), range(8)))
self.assertEqual(list(grouped.keys()), keys)
for c, d in keys:
self.assertEqual(grouped[c, d], dataset.select(c=c, d=d).reindex(['a', 'b']))
def test_dataset_groupby_alias(self):
group1 = {'age':[10,16], 'weight':[15,18], 'height':[0.8,0.6]}
group2 = {'age':[12], 'weight':[10], 'height':[0.8]}
grouped = HoloMap([('M', Dataset(group1, kdims=[('age', 'Age')],
vdims=self.alias_vdims)),
('F', Dataset(group2, kdims=[('age', 'Age')],
vdims=self.alias_vdims))],
kdims=[('gender', 'Gender')])
self.assertEqual(self.alias_table.groupby('Gender'), grouped)
def init_data(self):
self.kdims = ['Gender', 'Age']
self.vdims = ['Weight', 'Height']
self.gender, self.age = ['M','M','F'], [10,16,12]
self.weight, self.height = [15,18,10], [0.8,0.6,0.8]
self.table = Dataset({'Gender':self.gender, 'Age':self.age,
'Weight':self.weight, 'Height':self.height},
kdims=self.kdims, vdims=self.vdims)
super(HeterogeneousColumnTypes, self).init_data()
self.ys = np.linspace(0, 1, 11)
self.zs = np.sin(self.xs)
self.dataset_ht = Dataset({'x':self.xs, 'y':self.ys},
kdims=['x'], vdims=['y'])
def init_data(self):
self.xs = range(11)
self.xs_2 = [el**2 for el in self.xs]
self.y_ints = [i*2 for i in range(11)]
self.dataset_hm = Dataset((self.xs, self.y_ints),
kdims=['x'], vdims=['y'])
def init_column_data(self):
self.kdims = ['Gender', 'Age']
self.vdims = ['Weight', 'Height']
self.gender, self.age = np.array(['M','M','F']), np.array([10,16,12])
self.weight, self.height = np.array([15,18,10]), np.array([0.8,0.6,0.8])
self.table = Dataset({'Gender':self.gender, 'Age':self.age,
'Weight':self.weight, 'Height':self.height},
kdims=self.kdims, vdims=self.vdims)
self.alias_kdims = [('gender', 'Gender'), ('age', 'Age')]
self.alias_vdims = [('weight', 'Weight'), ('height', 'Height')]
self.alias_table = Dataset({'gender':self.gender, 'age':self.age,
'weight':self.weight, 'height':self.height},
kdims=self.alias_kdims, vdims=self.alias_vdims)
super(HeterogeneousColumnTests, self).init_column_data()
self.ys = np.linspace(0, 1, 11)
self.zs = np.sin(self.xs)
self.dataset_ht = Dataset({'x':self.xs, 'y':self.ys},
kdims=['x'], vdims=['y'])
class HoloMapTest(ComparisonTestCase):
def setUp(self):
self.xs = range(11)
self.y_ints = [i*2 for i in range(11)]
self.ys = np.linspace(0, 1, 11)
self.columns = Dataset(np.column_stack([self.xs, self.y_ints]),
kdims=['x'], vdims=['y'])
def test_holomap_redim(self):
hmap = HoloMap({i: Dataset({'x':self.xs, 'y': self.ys * i},
kdims=['x'], vdims=['y'])
for i in range(10)}, kdims=['z'])
redimmed = hmap.redim(x='Time')
self.assertEqual(redimmed.dimensions('all', True),
['z', 'Time', 'y'])
def test_holomap_redim_nested(self):
hmap = HoloMap({i: Dataset({'x':self.xs, 'y': self.ys * i},
kdims=['x'], vdims=['y'])
for i in range(10)}, kdims=['z'])
redimmed = hmap.redim(x='Time', z='Magnitude')
self.assertEqual(redimmed.dimensions('all', True),
['Magnitude', 'Time', 'y'])
def test_columns_collapse_heterogeneous(self):
collapsed = HoloMap({i: Dataset({'x':self.xs, 'y': self.ys * i},
kdims=['x'], vdims=['y'])
for i in range(10)}, kdims=['z']).collapse('z', np.mean)
expected = Dataset({'x':self.xs, 'y': self.ys * 4.5}, kdims=['x'], vdims=['y'])
self.compare_dataset(collapsed, expected)
def test_columns_sample_homogeneous(self):
samples = self.columns.sample([0, 5, 10]).dimension_values('y')
self.assertEqual(samples, np.array([0, 10, 20]))
def test_holomap_map_with_none(self):
hmap = HoloMap({i: Dataset({'x':self.xs, 'y': self.ys * i},
kdims=['x'], vdims=['y'])
for i in range(10)}, kdims=['z'])
mapped = hmap.map(lambda x: x if x.range(1)[1] > 0 else None, Dataset)
self.assertEqual(hmap[1:10], mapped)
def test_holomap_hist_two_dims(self):
hmap = HoloMap({i: Dataset({'x':self.xs, 'y': self.ys * i},
kdims=['x'], vdims=['y'])
for i in range(10)}, kdims=['z'])
hists = hmap.hist(dimension=['x', 'y'])
self.assertEqual(hists['right'].last.kdims, ['y'])
self.assertEqual(hists['top'].last.kdims, ['x'])
class HoloMapTest(ComparisonTestCase):
def setUp(self):
self.xs = range(11)
self.y_ints = [i*2 for i in range(11)]
self.ys = np.linspace(0, 1, 11)
self.columns = Dataset(np.column_stack([self.xs, self.y_ints]),
kdims=['x'], vdims=['y'])
def test_columns_collapse_heterogeneous(self):
collapsed = HoloMap({i: Dataset({'x':self.xs, 'y': self.ys * i},
kdims=['x'], vdims=['y'])
for i in range(10)}, kdims=['z']).collapse('z', np.mean)
expected = Dataset({'x':self.xs, 'y': self.ys * 4.5}, kdims=['x'], vdims=['y'])
self.compare_dataset(collapsed, expected)
def test_columns_sample_homogeneous(self):
samples = self.columns.sample([0, 5, 10]).dimension_values('y')
self.assertEqual(samples, np.array([0, 10, 20]))
def test_dataset_scalar_sort(self):
ds = Dataset({'A': 1, 'B': np.arange(10)[::-1]}, kdims=['A', 'B'])
self.assertEqual(ds.sort().dimension_values('B'), np.arange(10))
class HomogeneousColumnTests(object):
"""
Tests for data formats that require all dataset to have the same
type (e.g numpy arrays)
"""
def init_column_data(self):
self.xs = np.array(range(11))
self.xs_2 = self.xs**2
self.y_ints = self.xs*2
self.dataset_hm = Dataset((self.xs, self.y_ints),
kdims=['x'], vdims=['y'])
self.dataset_hm_alias = Dataset((self.xs, self.y_ints),
kdims=[('x', 'X')], vdims=[('y', 'Y')])
# Test the array constructor (homogeneous data) to be supported by
# all interfaces.
def test_dataset_array_init_hm(self):
dataset = Dataset(np.column_stack([self.xs, self.xs_2]),
kdims=['x'], vdims=['x2'])
self.assertTrue(isinstance(dataset.data, self.data_type))
def test_dataset_array_init_hm_tuple_dims(self):
dataset = Dataset(np.column_stack([self.xs, self.xs_2]),
kdims=[('x', 'X')], vdims=[('x2', 'X2')])
self.assertTrue(isinstance(dataset.data, self.data_type))
def test_dataset_dataframe_init_hm(self):
"Tests support for homogeneous DataFrames"
if pd is None:
raise SkipTest("Pandas not available")
dataset = Dataset(pd.DataFrame({'x':self.xs, 'x2':self.xs_2}),
kdims=['x'], vdims=['x2'])
self.assertTrue(isinstance(dataset.data, self.data_type))
def test_dataset_dataframe_init_hm_alias(self):
"Tests support for homogeneous DataFrames"
if pd is None:
raise SkipTest("Pandas not available")
dataset = Dataset(pd.DataFrame({'x':self.xs, 'x2':self.xs_2}),
kdims=[('x', 'X-label')], vdims=[('x2', 'X2-label')])
self.assertTrue(isinstance(dataset.data, self.data_type))
def test_dataset_empty_list_init(self):
dataset = Dataset([], kdims=['x'], vdims=['y'])
for d in 'xy':
self.assertEqual(dataset.dimension_values(d), np.array([]))
def test_dataset_dict_dim_not_found_raises_on_array(self):
with self.assertRaises(ValueError):
Dataset({'x': np.zeros(5)}, kdims=['Test'], vdims=[])
def test_dataset_dict_dim_not_found_raises_on_scalar(self):
with self.assertRaises(ValueError):
Dataset({'x': 1}, kdims=['Test'], vdims=[])
# Properties and information
def test_dataset_shape(self):
self.assertEqual(self.dataset_hm.shape, (11, 2))
def test_dataset_range(self):
self.assertEqual(self.dataset_hm.range('y'), (0, 20))
def test_dataset_closest(self):
closest = self.dataset_hm.closest([0.51, 1, 9.9])
self.assertEqual(closest, [1., 1., 10.])
# Operations
def test_dataset_sort_hm(self):
ds = Dataset(([2, 2, 1], [2,1,2], [0.1, 0.2, 0.3]),
kdims=['x', 'y'], vdims=['z']).sort()
ds_sorted = Dataset(([1, 2, 2], [2, 1, 2], [0.3, 0.2, 0.1]),
kdims=['x', 'y'], vdims=['z'])
self.assertEqual(ds.sort(), ds_sorted)
def test_dataset_sort_reverse_hm(self):
ds = Dataset(([2, 1, 2, 1], [2, 2, 1, 1], [0.1, 0.2, 0.3, 0.4]),
kdims=['x', 'y'], vdims=['z'])
ds_sorted = Dataset(([2, 2, 1, 1], [2, 1, 2, 1], [0.1, 0.3, 0.2, 0.4]),
kdims=['x', 'y'], vdims=['z'])
self.assertEqual(ds.sort(reverse=True), ds_sorted)
def test_dataset_sort_vdim_hm(self):
xs_2 = np.array(self.xs_2)
dataset = Dataset(np.column_stack([self.xs, -xs_2]),
kdims=['x'], vdims=['y'])
dataset_sorted = Dataset(np.column_stack([self.xs[::-1], -xs_2[::-1]]),
kdims=['x'], vdims=['y'])
self.assertEqual(dataset.sort('y'), dataset_sorted)
def test_dataset_sort_reverse_vdim_hm(self):
xs_2 = np.array(self.xs_2)
dataset = Dataset(np.column_stack([self.xs, -xs_2]),
kdims=['x'], vdims=['y'])
dataset_sorted = Dataset(np.column_stack([self.xs, -xs_2]),
kdims=['x'], vdims=['y'])
self.assertEqual(dataset.sort('y', reverse=True), dataset_sorted)
def test_dataset_sort_vdim_hm_alias(self):
xs_2 = np.array(self.xs_2)
dataset = Dataset(np.column_stack([self.xs, -xs_2]),
kdims=[('x', 'X-label')], vdims=[('y', 'Y-label')])
dataset_sorted = Dataset(np.column_stack([self.xs[::-1], -xs_2[::-1]]),
kdims=[('x', 'X-label')], vdims=[('y', 'Y-label')])
self.assertEqual(dataset.sort('y'), dataset_sorted)
self.assertEqual(dataset.sort('Y-label'), dataset_sorted)
def test_dataset_redim_hm_kdim(self):
redimmed = self.dataset_hm.redim(x='Time')
self.assertEqual(redimmed.dimension_values('Time'),
self.dataset_hm.dimension_values('x'))
def test_dataset_redim_hm_kdim_range_aux(self):
redimmed = self.dataset_hm.redim.range(x=(-100,3))
self.assertEqual(redimmed.kdims[0].range, (-100,3))
def test_dataset_redim_hm_kdim_soft_range_aux(self):
redimmed = self.dataset_hm.redim.soft_range(x=(-100,30))
self.assertEqual(redimmed.kdims[0].soft_range, (-100,30))
def test_dataset_redim_hm_kdim_alias(self):
redimmed = self.dataset_hm_alias.redim(x='Time')
self.assertEqual(redimmed.dimension_values('Time'),
self.dataset_hm_alias.dimension_values('x'))
def test_dataset_redim_hm_vdim(self):
redimmed = self.dataset_hm.redim(y='Value')
self.assertEqual(redimmed.dimension_values('Value'),
self.dataset_hm.dimension_values('y'))
def test_dataset_redim_hm_vdim_alias(self):
redimmed = self.dataset_hm_alias.redim(y=Dimension(('val', 'Value')))
self.assertEqual(redimmed.dimension_values('Value'),
self.dataset_hm_alias.dimension_values('y'))
def test_dataset_sample_hm(self):
samples = self.dataset_hm.sample([0, 5, 10]).dimension_values('y')
self.assertEqual(samples, np.array([0, 10, 20]))
def test_dataset_sample_hm_alias(self):
samples = self.dataset_hm_alias.sample([0, 5, 10]).dimension_values('y')
self.assertEqual(samples, np.array([0, 10, 20]))
def test_dataset_array_hm(self):
self.assertEqual(self.dataset_hm.array(),
np.column_stack([self.xs, self.y_ints]))
def test_dataset_array_hm_alias(self):
self.assertEqual(self.dataset_hm_alias.array(),
np.column_stack([self.xs, self.y_ints]))
def test_dataset_add_dimensions_value_hm(self):
table = self.dataset_hm.add_dimension('z', 1, 0)
self.assertEqual(table.kdims[1], 'z')
self.compare_arrays(table.dimension_values('z'), np.zeros(table.shape[0]))
def test_dataset_add_dimensions_values_hm(self):
table = self.dataset_hm.add_dimension('z', 1, range(1,12))
self.assertEqual(table.kdims[1], 'z')
self.compare_arrays(table.dimension_values('z'), np.array(list(range(1,12))))
def test_dataset_slice_hm(self):
dataset_slice = Dataset({'x':range(5, 9), 'y':[2 * i for i in range(5, 9)]},
kdims=['x'], vdims=['y'])
self.assertEqual(self.dataset_hm[5:9], dataset_slice)
def test_dataset_slice_hm_alias(self):
dataset_slice = Dataset({'x':range(5, 9), 'y':[2 * i for i in range(5, 9)]},
kdims=[('x', 'X')], vdims=[('y', 'Y')])
self.assertEqual(self.dataset_hm_alias[5:9], dataset_slice)
def test_dataset_slice_fn_hm(self):
dataset_slice = Dataset({'x':range(5, 9), 'y':[2 * i for i in range(5, 9)]},
kdims=['x'], vdims=['y'])
self.assertEqual(self.dataset_hm[lambda x: (x >= 5) & (x < 9)], dataset_slice)
def test_dataset_1D_reduce_hm(self):
dataset = Dataset({'x':self.xs, 'y':self.y_ints}, kdims=['x'], vdims=['y'])
self.assertEqual(dataset.reduce('x', np.mean), 10)
def test_dataset_1D_reduce_hm_alias(self):
dataset = Dataset({'x':self.xs, 'y':self.y_ints}, kdims=[('x', 'X')],
vdims=[('y', 'Y')])
self.assertEqual(dataset.reduce('X', np.mean), 10)
def test_dataset_2D_reduce_hm(self):
dataset = Dataset({'x':self.xs, 'y':self.y_ints, 'z':[el ** 2 for el in self.y_ints]},
kdims=['x', 'y'], vdims=['z'])
self.assertEqual(np.array(dataset.reduce(['x', 'y'], np.mean)),
np.array(140))
def test_dataset_2D_aggregate_partial_hm(self):
z_ints = [el**2 for el in self.y_ints]
dataset = Dataset({'x':self.xs, 'y':self.y_ints, 'z':z_ints},
kdims=['x', 'y'], vdims=['z'])
self.assertEqual(dataset.aggregate(['x'], np.mean),
Dataset({'x':self.xs, 'z':z_ints}, kdims=['x'], vdims=['z']))
# Indexing
def test_dataset_index_column_idx_hm(self):
self.assertEqual(self.dataset_hm[5], self.y_ints[5])
def test_dataset_index_column_ht(self):
self.compare_arrays(self.dataset_hm['y'], self.y_ints)
def test_dataset_array_ht(self):
self.assertEqual(self.dataset_hm.array(),
np.column_stack([self.xs, self.y_ints]))
# Tabular indexing
def test_dataset_iloc_slice_rows(self):
sliced = self.dataset_hm.iloc[1:4]
table = Dataset({'x': self.xs[1:4], 'y': self.y_ints[1:4]},
kdims=['x'], vdims=['y'], datatype=['dictionary'])
self.assertEqual(sliced, table)
def test_dataset_iloc_slice_rows_slice_cols(self):
sliced = self.dataset_hm.iloc[1:4, 1:]
table = Dataset({'y': self.y_ints[1:4]}, kdims=[], vdims=['y'],
datatype=['dictionary'])
self.assertEqual(sliced, table)
def test_dataset_iloc_slice_rows_list_cols(self):
sliced = self.dataset_hm.iloc[1:4, [0, 1]]
table = Dataset({'x': self.xs[1:4], 'y': self.y_ints[1:4]},
kdims=['x'], vdims=['y'], datatype=['dictionary'])
self.assertEqual(sliced, table)
def test_dataset_iloc_slice_rows_index_cols(self):
sliced = self.dataset_hm.iloc[1:4, 1]
table = Dataset({'y': self.y_ints[1:4]}, kdims=[], vdims=['y'],
datatype=['dictionary'])
self.assertEqual(sliced, table)
def test_dataset_iloc_list_rows(self):
sliced = self.dataset_hm.iloc[[0, 2]]
table = Dataset({'x': self.xs[[0, 2]], 'y': self.y_ints[[0, 2]]},
kdims=['x'], vdims=['y'], datatype=['dictionary'])
self.assertEqual(sliced, table)
def test_dataset_iloc_list_rows_list_cols(self):
sliced = self.dataset_hm.iloc[[0, 2], [0, 1]]
table = Dataset({'x': self.xs[[0, 2]], 'y': self.y_ints[[0, 2]]},
kdims=['x'], vdims=['y'], datatype=['dictionary'])
self.assertEqual(sliced, table)
def test_dataset_iloc_list_rows_list_cols_by_name(self):
sliced = self.dataset_hm.iloc[[0, 2], ['x', 'y']]
table = Dataset({'x': self.xs[[0, 2]], 'y': self.y_ints[[0, 2]]},
kdims=['x'], vdims=['y'], datatype=['dictionary'])
self.assertEqual(sliced, table)
def test_dataset_iloc_list_rows_slice_cols(self):
sliced = self.dataset_hm.iloc[[0, 2], slice(0, 2)]
table = Dataset({'x': self.xs[[0, 2]], 'y': self.y_ints[[0, 2]]},
kdims=['x'], vdims=['y'], datatype=['dictionary'])
self.assertEqual(sliced, table)
def test_dataset_iloc_index_rows_index_cols(self):
indexed = self.dataset_hm.iloc[1, 1]
self.assertEqual(indexed, self.y_ints[1])
def test_dataset_iloc_index_rows_slice_cols(self):
indexed = self.dataset_hm.iloc[1, :2]
table = Dataset({'x':self.xs[[1]], 'y':self.y_ints[[1]]},
kdims=['x'], vdims=['y'], datatype=['dictionary'])
self.assertEqual(indexed, table)
def test_dataset_iloc_list_cols(self):
sliced = self.dataset_hm.iloc[:, [0, 1]]
table = Dataset({'x':self.xs, 'y':self.y_ints},
kdims=['x'], vdims=['y'], datatype=['dictionary'])
self.assertEqual(sliced, table)
def test_dataset_iloc_list_cols_by_name(self):
sliced = self.dataset_hm.iloc[:, ['x', 'y']]
table = Dataset({'x':self.xs, 'y':self.y_ints},
kdims=['x'], vdims=['y'], datatype=['dictionary'])
self.assertEqual(sliced, table)
def test_dataset_iloc_ellipsis_list_cols(self):
sliced = self.dataset_hm.iloc[..., [0, 1]]
table = Dataset({'x':self.xs, 'y':self.y_ints},
kdims=['x'], vdims=['y'], datatype=['dictionary'])
self.assertEqual(sliced, table)
def test_dataset_iloc_ellipsis_list_cols_by_name(self):
sliced = self.dataset_hm.iloc[..., ['x', 'y']]
table = Dataset({'x':self.xs, 'y':self.y_ints},
kdims=['x'], vdims=['y'], datatype=['dictionary'])
self.assertEqual(sliced, table)
def test_dataset_get_array(self):
arr = self.dataset_hm.array()
self.assertEqual(arr, np.column_stack([self.xs, self.y_ints]))
def test_dataset_get_array_by_dimension(self):
arr = self.dataset_hm.array(['x'])
self.assertEqual(arr, self.xs[:, np.newaxis])
@pd_skip
def test_dataset_get_dframe(self):
df = self.dataset_hm.dframe()
self.assertEqual(df.x.values, self.xs)
self.assertEqual(df.y.values, self.y_ints)
@pd_skip
def test_dataset_get_dframe_by_dimension(self):
df = self.dataset_hm.dframe(['x'])
self.assertEqual(df, pd.DataFrame({'x': self.xs}, dtype=df.dtypes[0]))
def test_dataset_scalar_constructor(self):
ds = Dataset({'A': 1, 'B': np.arange(10)}, kdims=['A', 'B'])
self.assertEqual(ds.dimension_values('A'), np.ones(10))
def test_dataset_scalar_array(self):
ds = Dataset({'A': 1, 'B': np.arange(10)}, kdims=['A', 'B'])
self.assertEqual(ds.array(), np.column_stack([np.ones(10), np.arange(10)]))
class HeterogeneousColumnTests(HomogeneousColumnTests):
"""
Tests for data formats that allow dataset to have varied types
"""
def init_column_data(self):
self.kdims = ['Gender', 'Age']
self.vdims = ['Weight', 'Height']
self.gender, self.age = np.array(['M','M','F']), np.array([10,16,12])
self.weight, self.height = np.array([15,18,10]), np.array([0.8,0.6,0.8])
self.table = Dataset({'Gender':self.gender, 'Age':self.age,
'Weight':self.weight, 'Height':self.height},
kdims=self.kdims, vdims=self.vdims)
self.alias_kdims = [('gender', 'Gender'), ('age', 'Age')]
self.alias_vdims = [('weight', 'Weight'), ('height', 'Height')]
self.alias_table = Dataset({'gender':self.gender, 'age':self.age,
'weight':self.weight, 'height':self.height},
kdims=self.alias_kdims, vdims=self.alias_vdims)
super(HeterogeneousColumnTests, self).init_column_data()
self.ys = np.linspace(0, 1, 11)
self.zs = np.sin(self.xs)
self.dataset_ht = Dataset({'x':self.xs, 'y':self.ys},
kdims=['x'], vdims=['y'])
# Test the constructor to be supported by all interfaces supporting
# heterogeneous column types.
@pd_skip
def test_dataset_dataframe_init_ht(self):
"Tests support for heterogeneous DataFrames"
dataset = Dataset(pd.DataFrame({'x':self.xs, 'y':self.ys}), kdims=['x'], vdims=['y'])
self.assertTrue(isinstance(dataset.data, self.data_type))
@pd_skip
def test_dataset_dataframe_init_ht_alias(self):
"Tests support for heterogeneous DataFrames"
dataset = Dataset(pd.DataFrame({'x':self.xs, 'y':self.ys}),
kdims=[('x', 'X')], vdims=[('y', 'Y')])
self.assertTrue(isinstance(dataset.data, self.data_type))
# Test literal formats
def test_dataset_expanded_dimvals_ht(self):
self.assertEqual(self.table.dimension_values('Gender', expanded=False),
np.array(['M', 'F']))
def test_dataset_implicit_indexing_init(self):
dataset = Scatter(self.ys, kdims=['x'], vdims=['y'])
self.assertTrue(isinstance(dataset.data, self.data_type))
def test_dataset_tuple_init(self):
dataset = Dataset((self.xs, self.ys), kdims=['x'], vdims=['y'])
self.assertTrue(isinstance(dataset.data, self.data_type))
def test_dataset_tuple_init_alias(self):
dataset = Dataset((self.xs, self.ys), kdims=[('x', 'X')], vdims=[('y', 'Y')])
self.assertTrue(isinstance(dataset.data, self.data_type))
def test_dataset_simple_zip_init(self):
dataset = Dataset(zip(self.xs, self.ys), kdims=['x'], vdims=['y'])
self.assertTrue(isinstance(dataset.data, self.data_type))
def test_dataset_simple_zip_init_alias(self):
dataset = Dataset(zip(self.xs, self.ys), kdims=[('x', 'X')], vdims=[('y', 'Y')])
self.assertTrue(isinstance(dataset.data, self.data_type))
def test_dataset_zip_init(self):
dataset = Dataset(zip(self.gender, self.age,
self.weight, self.height),
kdims=self.kdims, vdims=self.vdims)
self.assertTrue(isinstance(dataset.data, self.data_type))
def test_dataset_zip_init_alias(self):
dataset = self.alias_table.clone(zip(self.gender, self.age,
self.weight, self.height))
self.assertTrue(isinstance(dataset.data, self.data_type))
def test_dataset_odict_init(self):
dataset = Dataset(OrderedDict(zip(self.xs, self.ys)), kdims=['A'], vdims=['B'])
self.assertTrue(isinstance(dataset.data, self.data_type))
def test_dataset_odict_init_alias(self):
dataset = Dataset(OrderedDict(zip(self.xs, self.ys)),
kdims=[('a', 'A')], vdims=[('b', 'B')])
self.assertTrue(isinstance(dataset.data, self.data_type))
def test_dataset_dict_init(self):
dataset = Dataset(dict(zip(self.xs, self.ys)), kdims=['A'], vdims=['B'])
self.assertTrue(isinstance(dataset.data, self.data_type))
def test_dataset_range_with_dimension_range(self):
dt64 = np.array([np.datetime64(datetime.datetime(2017, 1, i)) for i in range(1, 4)])
ds = Dataset(dt64, [Dimension('Date', range=(dt64[0], dt64[-1]))])
self.assertEqual(ds.range('Date'), (dt64[0], dt64[-1]))
# Operations
@pd_skip
def test_dataset_redim_with_alias_dframe(self):
test_df = pd.DataFrame({'x': range(10), 'y': range(0,20,2)})
dataset = Dataset(test_df, kdims=[('x', 'X-label')], vdims=['y'])
redim_df = pd.DataFrame({'X': range(10), 'y': range(0,20,2)})
dataset_redim = Dataset(redim_df, kdims=['X'], vdims=['y'])
self.assertEqual(dataset.redim(**{'X-label':'X'}), dataset_redim)
self.assertEqual(dataset.redim(**{'x':'X'}), dataset_redim)
def test_dataset_mixed_type_range(self):
ds = Dataset((['A', 'B', 'C', None],), 'A')
self.assertEqual(ds.range(0), ('A', 'C'))
def test_dataset_sort_vdim_ht(self):
dataset = Dataset({'x':self.xs, 'y':-self.ys},
kdims=['x'], vdims=['y'])
dataset_sorted = Dataset({'x': self.xs[::-1], 'y':-self.ys[::-1]},
kdims=['x'], vdims=['y'])
self.assertEqual(dataset.sort('y'), dataset_sorted)
def test_dataset_sort_string_ht(self):
dataset_sorted = Dataset({'Gender':['F', 'M', 'M'], 'Age':[12, 10, 16],
'Weight':[10,15,18], 'Height':[0.8,0.8,0.6]},
kdims=self.kdims, vdims=self.vdims)
self.assertEqual(self.table.sort(), dataset_sorted)
def test_dataset_sample_ht(self):
samples = self.dataset_ht.sample([0, 5, 10]).dimension_values('y')
self.assertEqual(samples, np.array([0, 0.5, 1]))
def test_dataset_reduce_ht(self):
reduced = Dataset({'Age':self.age, 'Weight':self.weight, 'Height':self.height},
kdims=self.kdims[1:], vdims=self.vdims)
self.assertEqual(self.table.reduce(['Gender'], np.mean), reduced)
def test_dataset_1D_reduce_ht(self):
self.assertEqual(self.dataset_ht.reduce('x', np.mean), np.float64(0.5))
def test_dataset_2D_reduce_ht(self):
reduced = Dataset({'Weight':[14.333333333333334], 'Height':[0.73333333333333339]},
kdims=[], vdims=self.vdims)
self.assertEqual(self.table.reduce(function=np.mean), reduced)
def test_dataset_2D_partial_reduce_ht(self):
dataset = Dataset({'x':self.xs, 'y':self.ys, 'z':self.zs},
kdims=['x', 'y'], vdims=['z'])
reduced = Dataset({'x':self.xs, 'z':self.zs},
kdims=['x'], vdims=['z'])
self.assertEqual(dataset.reduce(['y'], np.mean), reduced)
def test_dataset_2D_aggregate_spread_fn_with_duplicates(self):
dataset = Dataset({'x': np.array([0, 0, 1, 1]), 'y': np.array([0, 1, 2, 3]),
'z': np.array([1, 2, 3, 4])},
kdims=['x', 'y'], vdims=['z'])
agg = dataset.aggregate('x', function=np.mean, spreadfn=np.var)
self.assertEqual(agg, Dataset({'x': np.array([0, 1]), 'z': np.array([1.5, 3.5]),
'z_var': np.array([0.25, 0.25])},
kdims=['x'], vdims=['z', 'z_var']))
def test_dataset_aggregate_ht(self):
aggregated = Dataset({'Gender':['M', 'F'], 'Weight':[16.5, 10], 'Height':[0.7, 0.8]},
kdims=self.kdims[:1], vdims=self.vdims)
self.compare_dataset(self.table.aggregate(['Gender'], np.mean), aggregated)
def test_dataset_aggregate_string_types(self):
ds = Dataset({'Gender':['M', 'M'], 'Weight':[20, 10], 'Name':['Peter', 'Matt']},
kdims='Gender', vdims=['Weight', 'Name'])
aggregated = Dataset({'Gender': ['M'], 'Weight': [15]},
kdims='Gender', vdims=['Weight'])
self.compare_dataset(ds.aggregate(['Gender'], np.mean), aggregated)
def test_dataset_aggregate_string_types_size(self):
ds = Dataset({'Gender':['M', 'M'], 'Weight':[20, 10], 'Name':['Peter', 'Matt']},
kdims='Gender', vdims=['Weight', 'Name'])
aggregated = Dataset({'Gender': ['M'], 'Weight': [2], 'Name': [2]},
kdims='Gender', vdims=['Weight', 'Name'])
self.compare_dataset(ds.aggregate(['Gender'], np.size), aggregated)
def test_dataset_aggregate_ht_alias(self):
aggregated = Dataset({'gender':['M', 'F'], 'weight':[16.5, 10], 'height':[0.7, 0.8]},
kdims=self.alias_kdims[:1], vdims=self.alias_vdims)
self.compare_dataset(self.alias_table.aggregate('Gender', np.mean), aggregated)
def test_dataset_2D_aggregate_partial_ht(self):
dataset = Dataset({'x':self.xs, 'y':self.ys, 'z':self.zs},
kdims=['x', 'y'], vdims=['z'])
reduced = Dataset({'x':self.xs, 'z':self.zs},
kdims=['x'], vdims=['z'])
self.assertEqual(dataset.aggregate(['x'], np.mean), reduced)
def test_dataset_empty_aggregate(self):
dataset = Dataset([], kdims=self.kdims, vdims=self.vdims)
aggregated = Dataset([], kdims=self.kdims[:1], vdims=self.vdims)
self.compare_dataset(dataset.aggregate(['Gender'], np.mean), aggregated)
def test_dataset_empty_aggregate_with_spreadfn(self):
dataset = Dataset([], kdims=self.kdims, vdims=self.vdims)
aggregated = Dataset([], kdims=self.kdims[:1], vdims=[d for vd in self.vdims for d in [vd, vd+'_std']])
self.compare_dataset(dataset.aggregate(['Gender'], np.mean, np.std), aggregated)
def test_dataset_groupby(self):
group1 = {'Age':[10,16], 'Weight':[15,18], 'Height':[0.8,0.6]}
group2 = {'Age':[12], 'Weight':[10], 'Height':[0.8]}
grouped = HoloMap([('M', Dataset(group1, kdims=['Age'], vdims=self.vdims)),
('F', Dataset(group2, kdims=['Age'], vdims=self.vdims))],
kdims=['Gender'], sort=False)
print(grouped.keys())
self.assertEqual(self.table.groupby(['Gender']), grouped)
def test_dataset_groupby_alias(self):
group1 = {'age':[10,16], 'weight':[15,18], 'height':[0.8,0.6]}
group2 = {'age':[12], 'weight':[10], 'height':[0.8]}
grouped = HoloMap([('M', Dataset(group1, kdims=[('age', 'Age')],
vdims=self.alias_vdims)),
('F', Dataset(group2, kdims=[('age', 'Age')],
vdims=self.alias_vdims))],
kdims=[('gender', 'Gender')], sort=False)
self.assertEqual(self.alias_table.groupby('Gender'), grouped)
def test_dataset_groupby_second_dim(self):
group1 = {'Gender':['M'], 'Weight':[15], 'Height':[0.8]}
group2 = {'Gender':['M'], 'Weight':[18], 'Height':[0.6]}
group3 = {'Gender':['F'], 'Weight':[10], 'Height':[0.8]}
grouped = HoloMap([(10, Dataset(group1, kdims=['Gender'], vdims=self.vdims)),
(16, Dataset(group2, kdims=['Gender'], vdims=self.vdims)),
(12, Dataset(group3, kdims=['Gender'], vdims=self.vdims))],
kdims=['Age'], sort=False)
self.assertEqual(self.table.groupby(['Age']), grouped)
def test_dataset_groupby_dynamic(self):
grouped_dataset = self.table.groupby('Gender', dynamic=True)
self.assertEqual(grouped_dataset['M'],
self.table.select(Gender='M').reindex(['Age']))
self.assertEqual(grouped_dataset['F'],
self.table.select(Gender='F').reindex(['Age']))
def test_dataset_groupby_dynamic_alias(self):
grouped_dataset = self.alias_table.groupby('Gender', dynamic=True)
self.assertEqual(grouped_dataset['M'],
self.alias_table.select(gender='M').reindex(['Age']))
self.assertEqual(grouped_dataset['F'],
self.alias_table.select(gender='F').reindex(['Age']))
def test_dataset_add_dimensions_value_ht(self):
table = self.dataset_ht.add_dimension('z', 1, 0)
self.assertEqual(table.kdims[1], 'z')
self.compare_arrays(table.dimension_values('z'), np.zeros(table.shape[0]))
def test_dataset_add_dimensions_value_ht_alias(self):
table = self.dataset_ht.add_dimension(('z', 'Z'), 1, 0)
self.assertEqual(table.kdims[1], 'z')
self.compare_arrays(table.dimension_values('z'), np.zeros(table.shape[0]))
def test_dataset_add_dimensions_values_ht(self):
table = self.dataset_ht.add_dimension('z', 1, range(1,12))
self.assertEqual(table.kdims[1], 'z')
self.compare_arrays(table.dimension_values('z'), np.array(list(range(1,12))))
def test_redim_with_extra_dimension(self):
dataset = self.dataset_ht.add_dimension('Temp', 0, 0).clone(kdims=['x', 'y'], vdims=[])
redimmed = dataset.redim(x='Time')
self.assertEqual(redimmed.dimension_values('Time'),
self.dataset_ht.dimension_values('x'))
# Indexing
def test_dataset_index_row_gender_female(self):
indexed = Dataset({'Gender':['F'], 'Age':[12],
'Weight':[10], 'Height':[0.8]},
kdims=self.kdims, vdims=self.vdims)
row = self.table['F',:]
self.assertEquals(row, indexed)
def test_dataset_index_rows_gender_male(self):
row = self.table['M',:]
indexed = Dataset({'Gender':['M', 'M'], 'Age':[10, 16],
'Weight':[15,18], 'Height':[0.8,0.6]},
kdims=self.kdims, vdims=self.vdims)
self.assertEquals(row, indexed)
def test_dataset_select_rows_gender_male(self):
row = self.table.select(Gender='M')
indexed = Dataset({'Gender':['M', 'M'], 'Age':[10, 16],
'Weight':[15,18], 'Height':[0.8,0.6]},
kdims=self.kdims, vdims=self.vdims)
self.assertEquals(row, indexed)
def test_dataset_select_rows_gender_male_alias(self):
row = self.alias_table.select(Gender='M')
alias_row = self.alias_table.select(gender='M')
indexed = Dataset({'gender':['M', 'M'], 'age':[10, 16],
'weight':[15,18], 'height':[0.8,0.6]},
kdims=self.alias_kdims, vdims=self.alias_vdims)
self.assertEquals(row, indexed)
self.assertEquals(alias_row, indexed)
def test_dataset_index_row_age(self):
indexed = Dataset({'Gender':['F'], 'Age':[12],
'Weight':[10], 'Height':[0.8]},
kdims=self.kdims, vdims=self.vdims)
self.assertEquals(self.table[:, 12], indexed)
def test_dataset_index_item_table(self):
indexed = Dataset({'Gender':['F'], 'Age':[12],
'Weight':[10], 'Height':[0.8]},
kdims=self.kdims, vdims=self.vdims)
self.assertEquals(self.table['F', 12], indexed)
def test_dataset_index_value1(self):
self.assertEquals(self.table['F', 12, 'Weight'], 10)
def test_dataset_index_value2(self):
self.assertEquals(self.table['F', 12, 'Height'], 0.8)
def test_dataset_index_column_ht(self):
self.compare_arrays(self.dataset_ht['y'], self.ys)
def test_dataset_boolean_index(self):
row = self.table[np.array([True, True, False])]
indexed = Dataset({'Gender':['M', 'M'], 'Age':[10, 16],
'Weight':[15,18], 'Height':[0.8,0.6]},
kdims=self.kdims, vdims=self.vdims)
self.assertEquals(row, indexed)
def test_dataset_value_dim_index(self):
row = self.table[:, :, 'Weight']
indexed = Dataset({'Gender':['M', 'M', 'F'], 'Age':[10, 16, 12],
'Weight':[15,18, 10]},
kdims=self.kdims, vdims=self.vdims[:1])
self.assertEquals(row, indexed)
def test_dataset_value_dim_scalar_index(self):
row = self.table['M', 10, 'Weight']
self.assertEquals(row, 15)
# Tabular indexing
def test_dataset_iloc_slice_rows(self):
sliced = self.table.iloc[1:2]
table = Dataset({'Gender':self.gender[1:2], 'Age':self.age[1:2],
'Weight':self.weight[1:2], 'Height':self.height[1:2]},
kdims=self.kdims, vdims=self.vdims)
self.assertEqual(sliced, table)
def test_dataset_iloc_slice_rows_slice_cols(self):
sliced = self.table.iloc[1:2, 1:3]
table = Dataset({'Age':self.age[1:2], 'Weight':self.weight[1:2]},
kdims=self.kdims[1:], vdims=self.vdims[:1])
self.assertEqual(sliced, table)
def test_dataset_iloc_slice_rows_list_cols(self):
sliced = self.table.iloc[1:2, [1, 3]]
table = Dataset({'Age':self.age[1:2], 'Height':self.height[1:2]},
kdims=self.kdims[1:], vdims=self.vdims[1:])
self.assertEqual(sliced, table)
def test_dataset_iloc_slice_rows_index_cols(self):
sliced = self.table.iloc[1:2, 2]
table = Dataset({'Weight':self.weight[1:2]}, kdims=[], vdims=self.vdims[:1])
self.assertEqual(sliced, table)
def test_dataset_iloc_list_rows(self):
sliced = self.table.iloc[[0, 2]]
table = Dataset({'Gender':self.gender[[0, 2]], 'Age':self.age[[0, 2]],
'Weight':self.weight[[0, 2]], 'Height':self.height[[0, 2]]},
kdims=self.kdims, vdims=self.vdims)
self.assertEqual(sliced, table)
def test_dataset_iloc_list_rows_list_cols(self):
sliced = self.table.iloc[[0, 2], [0, 2]]
table = Dataset({'Gender':self.gender[[0, 2]], 'Weight':self.weight[[0, 2]]},
kdims=self.kdims[:1], vdims=self.vdims[:1])
self.assertEqual(sliced, table)
def test_dataset_iloc_list_rows_list_cols_by_name(self):
sliced = self.table.iloc[[0, 2], ['Gender', 'Weight']]
table = Dataset({'Gender':self.gender[[0, 2]], 'Weight':self.weight[[0, 2]]},
kdims=self.kdims[:1], vdims=self.vdims[:1])
self.assertEqual(sliced, table)
def test_dataset_iloc_list_rows_slice_cols(self):
sliced = self.table.iloc[[0, 2], slice(1, 3)]
table = Dataset({'Age':self.age[[0, 2]], 'Weight':self.weight[[0, 2]]},
kdims=self.kdims[1:], vdims=self.vdims[:1])
self.assertEqual(sliced, table)
def test_dataset_iloc_index_rows_index_cols(self):
indexed = self.table.iloc[1, 1]
self.assertEqual(indexed, self.age[1])
def test_dataset_iloc_index_rows_slice_cols(self):
indexed = self.table.iloc[1, 1:3]
table = Dataset({'Age':self.age[[1]], 'Weight':self.weight[[1]]},
kdims=self.kdims[1:], vdims=self.vdims[:1])
self.assertEqual(indexed, table)
def test_dataset_iloc_list_cols(self):
sliced = self.table.iloc[:, [0, 2]]
table = Dataset({'Gender':self.gender, 'Weight':self.weight},
kdims=self.kdims[:1], vdims=self.vdims[:1])
self.assertEqual(sliced, table)
def test_dataset_iloc_list_cols_by_name(self):
sliced = self.table.iloc[:, ['Gender', 'Weight']]
table = Dataset({'Gender':self.gender, 'Weight':self.weight},
kdims=self.kdims[:1], vdims=self.vdims[:1])
self.assertEqual(sliced, table)
def test_dataset_iloc_ellipsis_list_cols(self):
sliced = self.table.iloc[..., [0, 2]]
table = Dataset({'Gender':self.gender, 'Weight':self.weight},
kdims=self.kdims[:1], vdims=self.vdims[:1])
self.assertEqual(sliced, table)
def test_dataset_iloc_ellipsis_list_cols_by_name(self):
sliced = self.table.iloc[..., ['Gender', 'Weight']]
table = Dataset({'Gender':self.gender, 'Weight':self.weight},
kdims=self.kdims[:1], vdims=self.vdims[:1])
self.assertEqual(sliced, table)
# Casting
def test_dataset_array_ht(self):
self.assertEqual(self.dataset_ht.array(),
np.column_stack([self.xs, self.ys]))
def test_dataset_scalar_sample(self):
ds = Dataset({'A': 1, 'B': np.arange(10)}, kdims=['A', 'B'])
self.assertEqual(ds.sample([(1,)]).dimension_values('B'), np.arange(10))
def test_dataset_scalar_groupby(self):
ds = Dataset({'A': 1, 'B': np.arange(10)}, kdims=['A', 'B'])
groups = ds.groupby('A')
self.assertEqual(groups, HoloMap({1: Dataset({'B': np.arange(10)}, 'B')}, 'A'))
def test_dataset_empty_aggregate_with_spreadfn(self):
dataset = Dataset([], kdims=self.kdims, vdims=self.vdims)
aggregated = Dataset([], kdims=self.kdims[:1], vdims=[d for vd in self.vdims for d in [vd, vd+'_std']])
self.compare_dataset(dataset.aggregate(['Gender'], np.mean, np.std), aggregated)
def test_dataset_mixed_type_range(self):
ds = Dataset((['A', 'B', 'C', None],), 'A')
self.assertEqual(ds.range(0), ('A', 'C'))
def test_dataset_sort_vdim_ht(self):
dataset = Dataset({'x':self.xs, 'y':-self.ys},
kdims=['x'], vdims=['y'])
dataset_sorted = Dataset({'x': self.xs[::-1], 'y':-self.ys[::-1]},
kdims=['x'], vdims=['y'])
self.assertEqual(dataset.sort('y'), dataset_sorted)
def test_dataset_aggregate_string_types_size(self):
ds = Dataset({'Gender':['M', 'M'], 'Weight':[20, 10], 'Name':['Peter', 'Matt']},
kdims='Gender', vdims=['Weight', 'Name'])
aggregated = Dataset({'Gender': ['M'], 'Weight': [2], 'Name': [2]},
kdims='Gender', vdims=['Weight', 'Name'])
self.compare_dataset(ds.aggregate(['Gender'], np.size), aggregated)
def test_dataset_range_with_dimension_range(self):
dt64 = np.array([np.datetime64(datetime.datetime(2017, 1, i)) for i in range(1, 4)])
ds = Dataset(dt64, [Dimension('Date', range=(dt64[0], dt64[-1]))])
self.assertEqual(ds.range('Date'), (dt64[0], dt64[-1]))
def test_dataset_scalar_empty_select(self):
ds = Dataset({'A': 1, 'B': np.arange(10)}, kdims=['A', 'B'])
self.assertEqual(ds.select(A=0).dimension_values('B'), np.array([]))
def test_dataset_2D_aggregate_partial_ht(self):
dataset = Dataset({'x':self.xs, 'y':self.ys, 'z':self.zs},
kdims=['x', 'y'], vdims=['z'])
reduced = Dataset({'x':self.xs, 'z':self.zs},
kdims=['x'], vdims=['z'])
self.assertEqual(dataset.aggregate(['x'], np.mean), reduced)
def test_dataset_empty_aggregate(self):
dataset = Dataset([], kdims=self.kdims, vdims=self.vdims)
aggregated = Dataset([], kdims=self.kdims[:1], vdims=self.vdims)
self.compare_dataset(dataset.aggregate(['Gender'], np.mean), aggregated)
