Python Columns.groupby方法代码示例

# 需要导入模块: from holoviews import Columns [as 别名]
# 或者: from holoviews.Columns import groupby [as 别名]
 def test_columns_groupby(self):
     columns = Columns(self.column_data, kdims=self.kdims,
                       vdims=self.vdims)
     cols = self.kdims + self.vdims
     group1 = pd.DataFrame(self.column_data[:2], columns=cols)
     group2 = pd.DataFrame(self.column_data[2:], columns=cols)
     grouped = HoloMap({'M': Columns(group1, kdims=['Age'], vdims=self.vdims),
                        'F': Columns(group2, kdims=['Age'], vdims=self.vdims)},
                       kdims=['Gender'])
     self.assertEqual(columns.groupby(['Gender']), grouped)

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

#.........这里部分代码省略.........
    def test_columns_reduce_ht(self):
        reduced = Columns({'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_columns_1D_reduce_ht(self):
        self.assertEqual(self.columns_ht.reduce('x', np.mean), np.float64(0.5))

    def test_columns_2D_reduce_ht(self):
        reduced = Columns({'Weight':[14.333333333333334], 'Height':[0.73333333333333339]},
                          kdims=[], vdims=self.vdims)
        self.assertEqual(self.table.reduce(function=np.mean), reduced)

    def test_columns_2D_partial_reduce_ht(self):
        columns = Columns({'x':self.xs, 'y':self.ys, 'z':self.zs},
                          kdims=['x', 'y'], vdims=['z'])
        reduced = Columns({'x':self.xs, 'z':self.zs},
                          kdims=['x'], vdims=['z'])
        self.assertEqual(columns.reduce(['y'], np.mean), reduced)

    def test_column_aggregate_ht(self):
        aggregated = Columns({'Gender':['M','F'], 'Weight':[16.5,10], 'Height':[0.7,0.8]},
                             kdims=self.kdims[:1], vdims=self.vdims)
        self.compare_columns(self.table.aggregate(['Gender'], np.mean), aggregated)

    def test_columns_2D_aggregate_partial_ht(self):
        columns = Columns({'x':self.xs, 'y':self.ys, 'z':self.zs},
                          kdims=['x', 'y'], vdims=['z'])
        reduced = Columns({'x':self.xs, 'z':self.zs},
                          kdims=['x'], vdims=['z'])
        self.assertEqual(columns.aggregate(['x'], np.mean), reduced)


    def test_columns_groupby(self):
        group1 = {'Age':[10,16], 'Weight':[15,18], 'Height':[0.8,0.6]}
        group2 = {'Age':[12], 'Weight':[10], 'Height':[0.8]}
        with sorted_context(False):
            grouped = HoloMap([('M', Columns(group1, kdims=['Age'], vdims=self.vdims)),
                               ('F', Columns(group2, kdims=['Age'], vdims=self.vdims))],
                              kdims=['Gender'])
        self.assertEqual(self.table.groupby(['Gender']), grouped)


    def test_columns_add_dimensions_value_ht(self):
        table = self.columns_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_columns_add_dimensions_values_ht(self):
        table = self.columns_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_columns_index_row_gender_female(self):
        indexed = Columns({'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_columns_index_rows_gender_male(self):
        row = self.table['M',:]
        indexed = Columns({'Gender':['M','M'],'Age':[10,16],
                           'Weight':[15,18], 'Height':[0.8,0.6]},

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

    def setUp(self):
        self.restore_datatype = Columns.datatype
        Columns.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.columns_hm = Columns((self.xs, self.y_ints),
                                  kdims=['x'], vdims=['y'])

    def test_columns_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):
            Columns(np.column_stack([self.xs, self.xs_2]),
                    kdims=['x'], vdims=['x2'])

    def test_columns_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):
            Columns(pd.DataFrame({'x':self.xs, 'x2':self.xs_2}),
                    kdims=['x'], vdims=['x2'])

    def test_columns_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):
            Columns(NdElement(zip(self.xs, self.xs_2),
                              kdims=['x'], vdims=['x2']))

    def test_columns_2D_aggregate_partial_hm(self):
        array = np.random.rand(11, 11)
        columns = Columns({'x':self.xs, 'y':self.y_ints, 'z': array},
                          kdims=['x', 'y'], vdims=['z'])
        self.assertEqual(columns.aggregate(['x'], np.mean),
                         Columns({'x':self.xs, 'z': np.mean(array, axis=1)},
                                 kdims=['x'], vdims=['z']))

    def test_columns_2D_reduce_hm(self):
        array = np.random.rand(11, 11)
        columns = Columns({'x':self.xs, 'y':self.y_ints, 'z': array},
                          kdims=['x', 'y'], vdims=['z'])
        self.assertEqual(np.array(columns.reduce(['x', 'y'], np.mean)),
                         np.mean(array))

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

    def test_columns_add_dimensions_values_hm(self):
        table =  self.columns_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_columns_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.columns_hm.sort('y')


    def test_columns_groupby(self):
        self.assertEqual(self.columns_hm.groupby('x').keys(), list(self.xs))