1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
| import numpy as np
| import pytest
|
| import pandas as pd
| from pandas import (
| DataFrame,
| merge_ordered,
| )
| import pandas._testing as tm
|
|
| @pytest.fixture
| def left():
| return DataFrame({"key": ["a", "c", "e"], "lvalue": [1, 2.0, 3]})
|
|
| @pytest.fixture
| def right():
| return DataFrame({"key": ["b", "c", "d", "f"], "rvalue": [1, 2, 3.0, 4]})
|
|
| class TestMergeOrdered:
| def test_basic(self, left, right):
| result = merge_ordered(left, right, on="key")
| expected = DataFrame(
| {
| "key": ["a", "b", "c", "d", "e", "f"],
| "lvalue": [1, np.nan, 2, np.nan, 3, np.nan],
| "rvalue": [np.nan, 1, 2, 3, np.nan, 4],
| }
| )
|
| tm.assert_frame_equal(result, expected)
|
| def test_ffill(self, left, right):
| result = merge_ordered(left, right, on="key", fill_method="ffill")
| expected = DataFrame(
| {
| "key": ["a", "b", "c", "d", "e", "f"],
| "lvalue": [1.0, 1, 2, 2, 3, 3.0],
| "rvalue": [np.nan, 1, 2, 3, 3, 4],
| }
| )
| tm.assert_frame_equal(result, expected)
|
| def test_multigroup(self, left, right):
| left = pd.concat([left, left], ignore_index=True)
|
| left["group"] = ["a"] * 3 + ["b"] * 3
|
| result = merge_ordered(
| left, right, on="key", left_by="group", fill_method="ffill"
| )
| expected = DataFrame(
| {
| "key": ["a", "b", "c", "d", "e", "f"] * 2,
| "lvalue": [1.0, 1, 2, 2, 3, 3.0] * 2,
| "rvalue": [np.nan, 1, 2, 3, 3, 4] * 2,
| }
| )
| expected["group"] = ["a"] * 6 + ["b"] * 6
|
| tm.assert_frame_equal(result, expected.loc[:, result.columns])
|
| result2 = merge_ordered(
| right, left, on="key", right_by="group", fill_method="ffill"
| )
| tm.assert_frame_equal(result, result2.loc[:, result.columns])
|
| result = merge_ordered(left, right, on="key", left_by="group")
| assert result["group"].notna().all()
|
| def test_merge_type(self, left, right):
| class NotADataFrame(DataFrame):
| @property
| def _constructor(self):
| return NotADataFrame
|
| nad = NotADataFrame(left)
| result = nad.merge(right, on="key")
|
| assert isinstance(result, NotADataFrame)
|
| @pytest.mark.parametrize(
| "df_seq, pattern",
| [
| ((), "[Nn]o objects"),
| ([], "[Nn]o objects"),
| ({}, "[Nn]o objects"),
| ([None], "objects.*None"),
| ([None, None], "objects.*None"),
| ],
| )
| def test_empty_sequence_concat(self, df_seq, pattern):
| # GH 9157
| with pytest.raises(ValueError, match=pattern):
| pd.concat(df_seq)
|
| @pytest.mark.parametrize(
| "arg", [[DataFrame()], [None, DataFrame()], [DataFrame(), None]]
| )
| def test_empty_sequence_concat_ok(self, arg):
| pd.concat(arg)
|
| def test_doc_example(self):
| left = DataFrame(
| {
| "group": list("aaabbb"),
| "key": ["a", "c", "e", "a", "c", "e"],
| "lvalue": [1, 2, 3] * 2,
| }
| )
|
| right = DataFrame({"key": ["b", "c", "d"], "rvalue": [1, 2, 3]})
|
| result = merge_ordered(left, right, fill_method="ffill", left_by="group")
|
| expected = DataFrame(
| {
| "group": list("aaaaabbbbb"),
| "key": ["a", "b", "c", "d", "e"] * 2,
| "lvalue": [1, 1, 2, 2, 3] * 2,
| "rvalue": [np.nan, 1, 2, 3, 3] * 2,
| }
| )
|
| tm.assert_frame_equal(result, expected)
|
| @pytest.mark.parametrize(
| "left, right, on, left_by, right_by, expected",
| [
| (
| DataFrame({"G": ["g", "g"], "H": ["h", "h"], "T": [1, 3]}),
| DataFrame({"T": [2], "E": [1]}),
| ["T"],
| ["G", "H"],
| None,
| DataFrame(
| {
| "G": ["g"] * 3,
| "H": ["h"] * 3,
| "T": [1, 2, 3],
| "E": [np.nan, 1.0, np.nan],
| }
| ),
| ),
| (
| DataFrame({"G": ["g", "g"], "H": ["h", "h"], "T": [1, 3]}),
| DataFrame({"T": [2], "E": [1]}),
| "T",
| ["G", "H"],
| None,
| DataFrame(
| {
| "G": ["g"] * 3,
| "H": ["h"] * 3,
| "T": [1, 2, 3],
| "E": [np.nan, 1.0, np.nan],
| }
| ),
| ),
| (
| DataFrame({"T": [2], "E": [1]}),
| DataFrame({"G": ["g", "g"], "H": ["h", "h"], "T": [1, 3]}),
| ["T"],
| None,
| ["G", "H"],
| DataFrame(
| {
| "T": [1, 2, 3],
| "E": [np.nan, 1.0, np.nan],
| "G": ["g"] * 3,
| "H": ["h"] * 3,
| }
| ),
| ),
| ],
| )
| def test_list_type_by(self, left, right, on, left_by, right_by, expected):
| # GH 35269
| result = merge_ordered(
| left=left,
| right=right,
| on=on,
| left_by=left_by,
| right_by=right_by,
| )
|
| tm.assert_frame_equal(result, expected)
|
| def test_left_by_length_equals_to_right_shape0(self):
| # GH 38166
| left = DataFrame([["g", "h", 1], ["g", "h", 3]], columns=list("GHE"))
| right = DataFrame([[2, 1]], columns=list("ET"))
| result = merge_ordered(left, right, on="E", left_by=["G", "H"])
| expected = DataFrame(
| {"G": ["g"] * 3, "H": ["h"] * 3, "E": [1, 2, 3], "T": [np.nan, 1.0, np.nan]}
| )
|
| tm.assert_frame_equal(result, expected)
|
| def test_elements_not_in_by_but_in_df(self):
| # GH 38167
| left = DataFrame([["g", "h", 1], ["g", "h", 3]], columns=list("GHE"))
| right = DataFrame([[2, 1]], columns=list("ET"))
| msg = r"\{'h'\} not found in left columns"
| with pytest.raises(KeyError, match=msg):
| merge_ordered(left, right, on="E", left_by=["G", "h"])
|
|
