Python Dataset.groupby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 groupby [as 别名]
 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'))

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

#.........这里部分代码省略.........
        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']))

# 需要导入模块: from holoviews import Dataset [as 别名]
# 或者: from holoviews.Dataset import groupby [as 别名]
 def test_grid_3d_groupby_concat_roundtrip(self):
     array = np.random.rand(4, 5, 3, 2)
     orig = Dataset((range(2), range(3), range(5), range(4), array), ['A', 'B', 'x', 'y'], 'z')
     self.assertEqual(concat(orig.groupby(['A', 'B'])), orig)

# 需要导入模块: from holoviews import Dataset [as 别名]
# 或者: from holoviews.Dataset import groupby [as 别名]
 def test_dataset_dynamic_groupby_with_transposed_dimensions(self):
     dat = np.zeros((3,5,7))
     dataset = Dataset((range(7), range(5), range(3), dat), ['z','x','y'], 'value')
     grouped = dataset.groupby('z', kdims=['y', 'x'], dynamic=True)
     self.assertEqual(grouped[2].dimension_values(2, flat=False), dat[:, :, -1].T)

# 需要导入模块: from holoviews import Dataset [as 别名]
# 或者: from holoviews.Dataset import groupby [as 别名]
class GridDatasetTest(HomogeneousColumnTypes, ComparisonTestCase):
    """
    Test of the NdDataset interface (mostly for backwards compatibility)
    """

    def setUp(self):
        self.restore_datatype = Dataset.datatype
        Dataset.datatype = ['grid']
        self.data_instance_type = dict
        self.init_data()

    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_dataset_array_init_hm(self):
        "Tests support for arrays (homogeneous)"
        exception = "None of the available storage backends "\
         "were able to support the supplied data format."
        with self.assertRaisesRegexp(Exception, exception):
            Dataset(np.column_stack([self.xs, self.xs_2]),
                    kdims=['x'], vdims=['x2'])

    def test_dataset_dataframe_init_hm(self):
        "Tests support for homogeneous DataFrames"
        if pd is None:
            raise SkipTest("Pandas not available")
        exception = "None of the available storage backends "\
         "were able to support the supplied data format."
        with self.assertRaisesRegexp(Exception, exception):
            Dataset(pd.DataFrame({'x':self.xs, 'x2':self.xs_2}),
                    kdims=['x'], vdims=['x2'])

    def test_dataset_ndelement_init_hm(self):
        "Tests support for homogeneous NdElement (backwards compatibility)"
        exception = "None of the available storage backends "\
         "were able to support the supplied data format."
        with self.assertRaisesRegexp(Exception, exception):
            Dataset(NdElement(zip(self.xs, self.xs_2),
                              kdims=['x'], vdims=['x2']))

    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_2D_reduce_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(np.array(dataset.reduce(['x', 'y'], np.mean)),
                         np.mean(array))

    def test_dataset_add_dimensions_value_hm(self):
        with self.assertRaisesRegexp(Exception, 'Cannot add key dimension to a dense representation.'):
            self.dataset_hm.add_dimension('z', 1, 0)

    def test_dataset_add_dimensions_values_hm(self):
        table =  self.dataset_hm.add_dimension('z', 1, range(1,12), vdim=True)
        self.assertEqual(table.vdims[1], 'z')
        self.compare_arrays(table.dimension_values('z'), np.array(list(range(1,12))))

    def test_dataset_sort_vdim_hm(self):
        exception = ('Compressed format cannot be sorted, either instantiate '
                     'in the desired order or use the expanded format.')
        with self.assertRaisesRegexp(Exception, exception):
            self.dataset_hm.sort('y')

    def test_dataset_groupby(self):
        self.assertEqual(self.dataset_hm.groupby('x').keys(), list(self.xs))

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

#.........这里部分代码省略.........
    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_column_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_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_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_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(len(table)))

    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))))

    # 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)