Python Dataset.sample方法代码示例

# 需要导入模块: from holoviews import Dataset [as 别名]
# 或者: from holoviews.Dataset import sample [as 别名]
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'])

# 需要导入模块: from holoviews import Dataset [as 别名]
# 或者: from holoviews.Dataset import sample [as 别名]
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]))

# 需要导入模块: from holoviews import Dataset [as 别名]
# 或者: from holoviews.Dataset import sample [as 别名]
 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))

# 需要导入模块: from holoviews import Dataset [as 别名]
# 或者: from holoviews.Dataset import sample [as 别名]

#.........这里部分代码省略.........
        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)]},

# 需要导入模块: from holoviews import Dataset [as 别名]
# 或者: from holoviews.Dataset import sample [as 别名]

#.........这里部分代码省略.........
    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']))

# 需要导入模块: from holoviews import Dataset [as 别名]
# 或者: from holoviews.Dataset import sample [as 别名]
class HomogeneousColumnTypes(object):
    """
    Tests for data formats that require all dataset to have the same
    type (e.g numpy arrays)
    """

    def setUp(self):
        self.restore_datatype = Dataset.datatype
        self.data_instance_type = None

    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 tearDown(self):
        Dataset.datatype = self.restore_datatype

    # Test the array constructor (homogenous data) to be supported by
    # all interfaces.

    def test_dataset_array_init_hm(self):
        "Tests support for arrays (homogeneous)"
        dataset = Dataset(np.column_stack([self.xs, self.xs_2]),
                          kdims=['x'], vdims=['x2'])
        self.assertTrue(isinstance(dataset.data, self.data_instance_type))

    def test_dataset_ndelement_init_hm(self):
        "Tests support for homogeneous NdElement (backwards compatibility)"
        dataset = Dataset(NdElement(zip(self.xs, self.xs_2),
                                    kdims=['x'], vdims=['x2']))
        self.assertTrue(isinstance(dataset.data, self.data_instance_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_instance_type))

    # 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_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_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_array_hm(self):
        self.assertEqual(self.dataset_hm.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(len(table)))

    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_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_2D_reduce_hm(self):
        dataset = Dataset({'x':self.xs, 'y':self.y_ints, 'z':[el ** 2 for el in self.y_ints]},
#.........这里部分代码省略.........

# 需要导入模块: from holoviews import Dataset [as 别名]
# 或者: from holoviews.Dataset import sample [as 别名]
class HeterogeneousColumnTypes(HomogeneousColumnTypes):
    """
    Tests for data formats that all dataset to have varied types
    """

    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'])

    # Test the constructor to be supported by all interfaces supporting
    # heterogeneous column types.

    def test_dataset_ndelement_init_ht(self):
        "Tests support for heterogeneous NdElement (backwards compatibility)"
        dataset = Dataset(NdElement(zip(self.xs, self.ys), kdims=['x'], vdims=['y']))
        self.assertTrue(isinstance(dataset.data, self.data_instance_type))

    def test_dataset_dataframe_init_ht(self):
        "Tests support for heterogeneous DataFrames"
        if pd is None:
            raise SkipTest("Pandas not available")
        dataset = Dataset(pd.DataFrame({'x':self.xs, 'y':self.ys}), kdims=['x'], vdims=['y'])
        self.assertTrue(isinstance(dataset.data, self.data_instance_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 = Dataset(self.ys, kdims=['x'], vdims=['y'])
        self.assertTrue(isinstance(dataset.data, self.data_instance_type))

    def test_dataset_tuple_init(self):
        dataset = Dataset((self.xs, self.ys), kdims=['x'], vdims=['y'])
        self.assertTrue(isinstance(dataset.data, self.data_instance_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_instance_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_instance_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_instance_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_instance_type))

    # Operations

    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):
#.........这里部分代码省略.........