Python Table.get_column方法代码示例

# 需要导入模块: from dazzle.core.table import Table [as 别名]
# 或者: from dazzle.core.table.Table import get_column [as 别名]
    def test4():
        from dazzle.core.dataset import DataSet
        from dazzle.core.table import Table

        test_dir = os.path.join("/temp", "dazzle-test")
        ds = DataSet(test_dir, force_create=True)
        t = Table("t", ds, [("a", np.array([np.nan, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, np.nan]))])
        ca = t.get_column("a")
        print(ca.str_values(format="%.4f"))

# 需要导入模块: from dazzle.core.table import Table [as 别名]
# 或者: from dazzle.core.table.Table import get_column [as 别名]
    def test2():
        from dazzle.core.dataset import DataSet
        from dazzle.core.table import Table

        test_dir = os.path.join("/temp", "dazzle-test")
        ds = DataSet(test_dir, force_create=True)
        t = Table("t", ds, [("a", np.int)])
        ca = t.get_column("a")
        #t.append({'a': np.random.randint(10000000, size=5*(10**8)).astype(np.int32)})
        print(ca.__dict__)

# 需要导入模块: from dazzle.core.table import Table [as 别名]
# 或者: from dazzle.core.table.Table import get_column [as 别名]
    def test_add_join_column(self):
        ds = DataSet("/temp/dazzle-test", force_create=True)
        t = Table("t", ds, [('a', np.array([10, 2, 3, 5, 4, 7, 1, 8, 6, 9])),
                            ('c', np.array([100, 20, 30, 50, 40, 70, 10, 80, 60, np.nan]))])

        a_ref = np.array([1, 5, 4, 5, 6, 4, 1, 1, 9, 7, 8, 4, 5, 5, 2, 2, 8, 5, 4, 20])
        u = Table("u", ds, [('a', a_ref), ("y", a_ref * 10)])

        u.get_column("a").ref_column = t.get_column("a")
        t.rebuild({'a': np.int8, 'c': np.int8})
        u.rebuild({'a': np.int8, 'y': np.int16})

        u.add_reference_column(u.get_column("a"), t.get_column("a"))
        # print(t.head(20))
        # print(u.head(30))

        u.add_join_column("result", [u.get_column("a_ref"), t.get_column("c")])
        #print(u.head(30))
        assert np.array_equal(u['result'],
                              [-128, 10, 50, 40, 50, 60, 40, 10, 10, -128, 70, 80, 40, 50, 50, 20, 20, 80, 50, 40, -128])

# 需要导入模块: from dazzle.core.table import Table [as 别名]
# 或者: from dazzle.core.table.Table import get_column [as 别名]
class TestColumn(unittest.TestCase):

    def setUp(self):
        self.a = [6, 4, 7, 4, 6, 9]
        self.test_dir = os.path.join("/temp", "dazzle-test")
        ds = DataSet(self.test_dir, force_create=True)
        self.t = Table("t", ds, [("a", np.array([1, 3], dtype=np.int8)), ("x", np.array([2, 4], dtype=np.float))], force_create=True)
        self.ca = self.t.get_column("a")

    @raises(DazzleError)
    def test_data_dir01(self):
        """no table associated"""
        print(LiteralColumn("a", np.array([], np.int)).data_dir)

    def test_data_dir02(self):
        self.assertEqual(self.ca.data_dir, os.path.join(self.test_dir, "t", "a"))

    @raises(DazzleError)
    def test_carray01(self):
        """no table associated"""
        print(LiteralColumn("a", np.array([], np.int)).carray)

    def test_carray02(self):
        assert_array_equal(self.ca.carray[:], [1, 3])

    @raises(DazzleError)
    def test_init01(self):
        LiteralColumn("", [])

    @raises(DazzleError)
    def test_init02(self):
        LiteralColumn("1a", [])

    @raises(DazzleError)
    def test_init03(self):
        LiteralColumn("_a", [])

    @raises(DazzleError)
    def test_init04(self):
        LiteralColumn("a", "XX")

    @raises(DazzleError)
    def test_init05(self):
        LiteralColumn("a", self)

    def test_init06(self):
        assert_array_equal(self.ca.carray[:], [1, 3])

    def test_len01(self):
        self.assertEqual(len(self.ca), 2)

    def test_position01(self):
        self.t.append({'a': self.a, 'x': self.a})
        self.assertEqual(self.ca.position, 0)

    def test_position02(self):
        self.t.append({'a': self.a, 'x': self.a})
        self.assertEqual(self.t.get_column("x").position, 1)

    def test_getitem01(self):
        self.assertEqual(self.ca[0], 1)

    def test_getitem02(self):
        self.assertEqual(self.ca[1], 3)

    @raises(IndexError)
    def test_getitem03(self):
        self.t.append({'a': self.a, 'x': self.a})
        _ = self.ca[10]

    def test_getitem04(self):
        self.t.append({'a': self.a, 'x': self.a})
        assert_array_equal(self.ca[:], self.ca.carray[:])

    def test_getitem05(self):
        self.t.append({'a': self.a, 'x': self.a})
        assert_array_equal(self.ca[0:5], [1, 3, 6, 4, 7])

    def test_setitem01(self):
        self.ca[0] = 2
        self.assertEqual(self.ca[0], 2)
        assert_array_equal(self.ca.carray[:], [2, 3])

    def test_append01(self):
        self.t.append({'a': self.a, 'x': self.a})
        self.ca.append(self.a)
        assert_array_equal(self.ca.carray[:], [1, 3, 6, 4, 7, 4, 6, 9, 6, 4, 7, 4, 6, 9])

    @raises(DazzleError)
    def test_rename01(self):
        self.t.append({'a': self.a, 'x': self.a})
        self.ca.rename("")

    @raises(DazzleError)
    def test_rename02(self):
        self.t.append({'a': self.a, 'x': self.a})
        self.ca.rename("x")

    def test_rename03(self):
        self.ca.rename("b")
#.........这里部分代码省略.........

# 需要导入模块: from dazzle.core.table import Table [as 别名]
# 或者: from dazzle.core.table.Table import get_column [as 别名]

#.........这里部分代码省略.........
        test_dir = os.path.join("/temp/dazzle-test2")
        ds2 = DataSet(test_dir, force_create=True)
        Table.copy("_", ds2, "/temp/dazzle-test/t")

    def test_copy04(self):
        test_dir = os.path.join("/temp/dazzle-test2")
        ds2 = DataSet(test_dir, force_create=True)
        t = Table.copy("t", ds2, "/temp/dazzle-test/t")
        assert_equal_table(t, self.ds.get_table("t"))

    @raises(FileNotFoundError)
    def test_from_csv01(self):
        Table.from_csv("Category", self.ds, "/bim/bam/test.csv", usecols=['CategoryID', 'ParentCategoryID'], verbose=False)

    @raises(ValueError)
    def test_from_csv02(self):
        Table.from_csv("Category", self.ds, "/temp/dazzle-test/dataset.json", usecols=['CategoryID', 'ParentCategoryID'], verbose=False)

    @raises(DazzleError)
    def test_from_csv03(self):
        cat = Table.from_csv("Category", self.ds, os.path.join(AVITO_DATA_DIR, "Category.tsv"), verbose=False)

    def test_from_csv04(self):
        cat = Table.from_csv("Category", self.ds, os.path.join(AVITO_DATA_DIR, "Category.tsv"), delimiter='\t',
                                   usecols=['CategoryID', 'ParentCategoryID'], verbose=False)
        self.assertEqual(len(cat.ctable), 68)
        self.assertEqual(len(cat.columns), 2)

    def test_from_dataframe01(self):
        df = pd.DataFrame({'a': [1,2], 'b': [3., 4.]})
        v = Table.from_dataframe("v", self.ds, df)
        self.assertEqual(len(v.ctable), 2)

    def test_get_column01(self):
        self.assertTrue(self.t.get_column("x") is None)

    def test_get_column02(self):
        self.assertEqual(self.t.get_column("a").name, "a")

    @raises(ValueError)
    def test_remove_column01(self):
        self.t.remove_column("x")

    def test_remove_column02(self):
        self.t.remove_column("a")
        self.assertTrue(self.t.get_column("a") is None)
        self.assertEqual(self.t.columns[0], self.t.get_column("b"))
        self.assertEqual(self.t.ctable.names[0], "b")

    def test_to_dataframe01(self):
        self.assertEqual(len(self.u.to_dataframe()), 2)

    def test_append01(self):
        self.t.append({'a': [1,2], 'b': [3., 4.]})
        self.assert_table_content(self.t, {
            'len': 2,
            'columns': [('a', {'content': [1,2]}), ('b', {'content': [3., 4.]})]})

    def test_append02(self):
        self.t.append({'b': [3., 4.], 'a': [1,2]})
        self.assert_table_content(self.t, {
            'len': 2,
            'columns': [('a', {'content': [1,2]}), ('b', {'content': [3., 4.]})]})

    def test_append03(self):
        self.t.append({'a': [5.4, 2], 'b': [3., 4.]})