Python Dataset.array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 array [as 别名]
 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)]))

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