Python merge.merge方法代码示例

# 需要导入模块: from pandas.core.reshape import merge [as 别名]
# 或者: from pandas.core.reshape.merge import merge [as 别名]
def test_merge_on_multikey(self, left, right, join_type):
        on_cols = ['key1', 'key2']
        result = (left.join(right, on=on_cols, how=join_type)
                  .reset_index(drop=True))

        expected = pd.merge(left, right.reset_index(),
                            on=on_cols, how=join_type)

        tm.assert_frame_equal(result, expected)

        result = (left.join(right, on=on_cols, how=join_type, sort=True)
                  .reset_index(drop=True))

        expected = pd.merge(left, right.reset_index(),
                            on=on_cols, how=join_type, sort=True)

        tm.assert_frame_equal(result, expected) 

# 需要导入模块: from pandas.core.reshape import merge [as 别名]
# 或者: from pandas.core.reshape.merge import merge [as 别名]
def test_merge_index_singlekey_right_vs_left(self):
        left = DataFrame({'key': ['a', 'b', 'c', 'd', 'e', 'e', 'a'],
                          'v1': np.random.randn(7)})
        right = DataFrame({'v2': np.random.randn(4)},
                          index=['d', 'b', 'c', 'a'])

        merged1 = merge(left, right, left_on='key',
                        right_index=True, how='left', sort=False)
        merged2 = merge(right, left, right_on='key',
                        left_index=True, how='right', sort=False)
        assert_frame_equal(merged1, merged2.loc[:, merged1.columns])

        merged1 = merge(left, right, left_on='key',
                        right_index=True, how='left', sort=True)
        merged2 = merge(right, left, right_on='key',
                        left_index=True, how='right', sort=True)
        assert_frame_equal(merged1, merged2.loc[:, merged1.columns]) 

# 需要导入模块: from pandas.core.reshape import merge [as 别名]
# 或者: from pandas.core.reshape.merge import merge [as 别名]
def test_merge_index_singlekey_inner(self):
        left = DataFrame({'key': ['a', 'b', 'c', 'd', 'e', 'e', 'a'],
                          'v1': np.random.randn(7)})
        right = DataFrame({'v2': np.random.randn(4)},
                          index=['d', 'b', 'c', 'a'])

        # inner join
        result = merge(left, right, left_on='key', right_index=True,
                       how='inner')
        expected = left.join(right, on='key').loc[result.index]
        assert_frame_equal(result, expected)

        result = merge(right, left, right_on='key', left_index=True,
                       how='inner')
        expected = left.join(right, on='key').loc[result.index]
        assert_frame_equal(result, expected.loc[:, result.columns]) 

# 需要导入模块: from pandas.core.reshape import merge [as 别名]
# 或者: from pandas.core.reshape.merge import merge [as 别名]
def test_merge_different_column_key_names(self):
        left = DataFrame({'lkey': ['foo', 'bar', 'baz', 'foo'],
                          'value': [1, 2, 3, 4]})
        right = DataFrame({'rkey': ['foo', 'bar', 'qux', 'foo'],
                           'value': [5, 6, 7, 8]})

        merged = left.merge(right, left_on='lkey', right_on='rkey',
                            how='outer', sort=True)

        exp = pd.Series(['bar', 'baz', 'foo', 'foo', 'foo', 'foo', np.nan],
                        name='lkey')
        tm.assert_series_equal(merged['lkey'], exp)

        exp = pd.Series(['bar', np.nan, 'foo', 'foo', 'foo', 'foo', 'qux'],
                        name='rkey')
        tm.assert_series_equal(merged['rkey'], exp)

        exp = pd.Series([2, 3, 1, 1, 4, 4, np.nan], name='value_x')
        tm.assert_series_equal(merged['value_x'], exp)

        exp = pd.Series([6, np.nan, 5, 8, 5, 8, 7], name='value_y')
        tm.assert_series_equal(merged['value_y'], exp) 

# 需要导入模块: from pandas.core.reshape import merge [as 别名]
# 或者: from pandas.core.reshape.merge import merge [as 别名]
def test_merge_join_key_dtype_cast(self):
        # #8596

        df1 = DataFrame({'key': [1], 'v1': [10]})
        df2 = DataFrame({'key': [2], 'v1': [20]})
        df = merge(df1, df2, how='outer')
        assert df['key'].dtype == 'int64'

        df1 = DataFrame({'key': [True], 'v1': [1]})
        df2 = DataFrame({'key': [False], 'v1': [0]})
        df = merge(df1, df2, how='outer')

        # GH13169
        # this really should be bool
        assert df['key'].dtype == 'object'

        df1 = DataFrame({'val': [1]})
        df2 = DataFrame({'val': [2]})
        lkey = np.array([1])
        rkey = np.array([2])
        df = merge(df1, df2, left_on=lkey, right_on=rkey, how='outer')
        assert df['key_0'].dtype == 'int64' 

# 需要导入模块: from pandas.core.reshape import merge [as 别名]
# 或者: from pandas.core.reshape.merge import merge [as 别名]
def test_merge_all_na_column(self, series_of_dtype,
                                 series_of_dtype_all_na):
        # GH 25183
        df_left = pd.DataFrame(
            {'key': series_of_dtype, 'value': series_of_dtype_all_na},
            columns=['key', 'value'])
        df_right = pd.DataFrame(
            {'key': series_of_dtype, 'value': series_of_dtype_all_na},
            columns=['key', 'value'])
        expected = pd.DataFrame({
            'key': series_of_dtype,
            'value_x': series_of_dtype_all_na,
            'value_y': series_of_dtype_all_na,
        }, columns=['key', 'value_x', 'value_y'])
        actual = df_left.merge(df_right, on='key')
        assert_frame_equal(actual, expected) 

# 需要导入模块: from pandas.core.reshape import merge [as 别名]
# 或者: from pandas.core.reshape.merge import merge [as 别名]
def test_other_datetime_unit(self):
        # GH 13389
        df1 = pd.DataFrame({'entity_id': [101, 102]})
        s = pd.Series([None, None], index=[101, 102], name='days')

        for dtype in ['datetime64[D]', 'datetime64[h]', 'datetime64[m]',
                      'datetime64[s]', 'datetime64[ms]', 'datetime64[us]',
                      'datetime64[ns]']:

            df2 = s.astype(dtype).to_frame('days')
            # coerces to datetime64[ns], thus sholuld not be affected
            assert df2['days'].dtype == 'datetime64[ns]'

            result = df1.merge(df2, left_on='entity_id', right_index=True)

            exp = pd.DataFrame({'entity_id': [101, 102],
                                'days': np.array(['nat', 'nat'],
                                                 dtype='datetime64[ns]')},
                               columns=['entity_id', 'days'])
            tm.assert_frame_equal(result, exp) 

# 需要导入模块: from pandas.core.reshape import merge [as 别名]
# 或者: from pandas.core.reshape.merge import merge [as 别名]
def test_other_timedelta_unit(self, unit):
        # GH 13389
        df1 = pd.DataFrame({'entity_id': [101, 102]})
        s = pd.Series([None, None], index=[101, 102], name='days')

        dtype = "m8[{}]".format(unit)
        df2 = s.astype(dtype).to_frame('days')
        assert df2['days'].dtype == 'm8[ns]'

        result = df1.merge(df2, left_on='entity_id', right_index=True)

        exp = pd.DataFrame({'entity_id': [101, 102],
                            'days': np.array(['nat', 'nat'],
                                             dtype=dtype)},
                           columns=['entity_id', 'days'])
        tm.assert_frame_equal(result, exp) 

# 需要导入模块: from pandas.core.reshape import merge [as 别名]
# 或者: from pandas.core.reshape.merge import merge [as 别名]
def test_overlapping_columns_error_message(self):
        df = DataFrame({'key': [1, 2, 3],
                        'v1': [4, 5, 6],
                        'v2': [7, 8, 9]})
        df2 = DataFrame({'key': [1, 2, 3],
                         'v1': [4, 5, 6],
                         'v2': [7, 8, 9]})

        df.columns = ['key', 'foo', 'foo']
        df2.columns = ['key', 'bar', 'bar']
        expected = DataFrame({'key': [1, 2, 3],
                              'v1': [4, 5, 6],
                              'v2': [7, 8, 9],
                              'v3': [4, 5, 6],
                              'v4': [7, 8, 9]})
        expected.columns = ['key', 'foo', 'foo', 'bar', 'bar']
        assert_frame_equal(merge(df, df2), expected)

        # #2649, #10639
        df2.columns = ['key1', 'foo', 'foo']
        msg = (r"Data columns not unique: Index\(\[u?'foo', u?'foo'\],"
               r" dtype='object'\)")
        with pytest.raises(MergeError, match=msg):
            merge(df, df2) 

# 需要导入模块: from pandas.core.reshape import merge [as 别名]
# 或者: from pandas.core.reshape.merge import merge [as 别名]
def test_merge_on_datetime64tz_empty(self):
        # https://github.com/pandas-dev/pandas/issues/25014
        dtz = pd.DatetimeTZDtype(tz='UTC')
        right = pd.DataFrame({'date': [pd.Timestamp('2018', tz=dtz.tz)],
                              'value': [4.0],
                              'date2': [pd.Timestamp('2019', tz=dtz.tz)]},
                             columns=['date', 'value', 'date2'])
        left = right[:0]
        result = left.merge(right, on='date')
        expected = pd.DataFrame({
            'value_x': pd.Series(dtype=float),
            'date2_x': pd.Series(dtype=dtz),
            'date': pd.Series(dtype=dtz),
            'value_y': pd.Series(dtype=float),
            'date2_y': pd.Series(dtype=dtz),
        }, columns=['value_x', 'date2_x', 'date', 'value_y', 'date2_y'])
        tm.assert_frame_equal(result, expected) 

# 需要导入模块: from pandas.core.reshape import merge [as 别名]
# 或者: from pandas.core.reshape.merge import merge [as 别名]
def test_merge_on_index_with_more_values(self, how):
        # GH 24212
        # pd.merge gets [-1, -1, 0, 1] as right_indexer, ensure that -1 is
        # interpreted as a missing value instead of the last element
        df1 = pd.DataFrame([[1, 2], [2, 4], [3, 6], [4, 8]],
                           columns=['a', 'b'])
        df2 = pd.DataFrame([[3, 30], [4, 40]],
                           columns=['a', 'c'])
        df1.set_index('a', drop=False, inplace=True)
        df2.set_index('a', inplace=True)
        result = pd.merge(df1, df2, left_index=True, right_on='a', how=how)
        expected = pd.DataFrame([[1, 2, np.nan],
                                 [2, 4, np.nan],
                                 [3, 6, 30.0],
                                 [4, 8, 40.0]],
                                columns=['a', 'b', 'c'])
        expected.set_index('a', drop=False, inplace=True)
        assert_frame_equal(result, expected) 

# 需要导入模块: from pandas.core.reshape import merge [as 别名]
# 或者: from pandas.core.reshape.merge import merge [as 别名]
def test_merge_on_ints_floats_warning(self):
        # GH 16572
        # merge will produce a warning when merging on int and
        # float columns where the float values are not exactly
        # equal to their int representation
        A = DataFrame({'X': [1, 2, 3]})
        B = DataFrame({'Y': [1.1, 2.5, 3.0]})
        expected = DataFrame({'X': [3], 'Y': [3.0]})

        with tm.assert_produces_warning(UserWarning):
            result = A.merge(B, left_on='X', right_on='Y')
            assert_frame_equal(result, expected)

        with tm.assert_produces_warning(UserWarning):
            result = B.merge(A, left_on='Y', right_on='X')
            assert_frame_equal(result, expected[['Y', 'X']])

        # test no warning if float has NaNs
        B = DataFrame({'Y': [np.nan, np.nan, 3.0]})

        with tm.assert_produces_warning(None):
            result = B.merge(A, left_on='Y', right_on='X')
            assert_frame_equal(result, expected[['Y', 'X']]) 

# 需要导入模块: from pandas.core.reshape import merge [as 别名]
# 或者: from pandas.core.reshape.merge import merge [as 别名]
def test_merge_incompat_infer_boolean_object(self):
        # GH21119: bool + object bool merge OK
        df1 = DataFrame({'key': Series([True, False], dtype=object)})
        df2 = DataFrame({'key': [True, False]})

        expected = DataFrame({'key': [True, False]}, dtype=object)
        result = pd.merge(df1, df2, on='key')
        assert_frame_equal(result, expected)
        result = pd.merge(df2, df1, on='key')
        assert_frame_equal(result, expected)

        # with missing value
        df1 = DataFrame({'key': Series([True, False, np.nan], dtype=object)})
        df2 = DataFrame({'key': [True, False]})

        expected = DataFrame({'key': [True, False]}, dtype=object)
        result = pd.merge(df1, df2, on='key')
        assert_frame_equal(result, expected)
        result = pd.merge(df2, df1, on='key')
        assert_frame_equal(result, expected) 

# 需要导入模块: from pandas.core.reshape import merge [as 别名]
# 或者: from pandas.core.reshape.merge import merge [as 别名]
def tests_merge_categorical_unordered_equal(self):
        # GH-19551
        df1 = DataFrame({
            'Foo': Categorical(['A', 'B', 'C'], categories=['A', 'B', 'C']),
            'Left': ['A0', 'B0', 'C0'],
        })

        df2 = DataFrame({
            'Foo': Categorical(['C', 'B', 'A'], categories=['C', 'B', 'A']),
            'Right': ['C1', 'B1', 'A1'],
        })
        result = pd.merge(df1, df2, on=['Foo'])
        expected = DataFrame({
            'Foo': pd.Categorical(['A', 'B', 'C']),
            'Left': ['A0', 'B0', 'C0'],
            'Right': ['A1', 'B1', 'C1'],
        })
        assert_frame_equal(result, expected) 

# 需要导入模块: from pandas.core.reshape import merge [as 别名]
# 或者: from pandas.core.reshape.merge import merge [as 别名]
def test_self_join_multiple_categories(self):
        # GH 16767
        # non-duplicates should work with multiple categories
        m = 5
        df = pd.DataFrame({
            'a': ['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j'] * m,
            'b': ['t', 'w', 'x', 'y', 'z'] * 2 * m,
            'c': [letter
                  for each in ['m', 'n', 'u', 'p', 'o']
                  for letter in [each] * 2 * m],
            'd': [letter
                  for each in ['aa', 'bb', 'cc', 'dd', 'ee',
                               'ff', 'gg', 'hh', 'ii', 'jj']
                  for letter in [each] * m]})

        # change them all to categorical variables
        df = df.apply(lambda x: x.astype('category'))

        # self-join should equal ourselves
        result = pd.merge(df, df, on=list(df.columns))

        assert_frame_equal(result, df)