This repository was archived by the owner on Apr 1, 2026. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 69
Expand file tree
/
Copy pathtest_datetime_ops.py
More file actions
272 lines (193 loc) · 9.2 KB
/
test_datetime_ops.py
File metadata and controls
272 lines (193 loc) · 9.2 KB
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
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
# Copyright 2025 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import pandas as pd
import pytest
from bigframes import operations as ops
import bigframes.pandas as bpd
from bigframes.testing import utils
pytest.importorskip("pytest_snapshot")
def test_date(scalar_types_df: bpd.DataFrame, snapshot):
col_name = "timestamp_col"
bf_df = scalar_types_df[[col_name]]
sql = utils._apply_ops_to_sql(bf_df, [ops.date_op.as_expr(col_name)], [col_name])
snapshot.assert_match(sql, "out.sql")
def test_day(scalar_types_df: bpd.DataFrame, snapshot):
col_name = "timestamp_col"
bf_df = scalar_types_df[[col_name]]
sql = utils._apply_ops_to_sql(bf_df, [ops.day_op.as_expr(col_name)], [col_name])
snapshot.assert_match(sql, "out.sql")
def test_dayofweek(scalar_types_df: bpd.DataFrame, snapshot):
col_names = ["datetime_col", "timestamp_col", "date_col"]
bf_df = scalar_types_df[col_names]
ops_map = {col_name: ops.dayofweek_op.as_expr(col_name) for col_name in col_names}
sql = utils._apply_ops_to_sql(bf_df, list(ops_map.values()), list(ops_map.keys()))
snapshot.assert_match(sql, "out.sql")
def test_dayofyear(scalar_types_df: bpd.DataFrame, snapshot):
col_name = "timestamp_col"
bf_df = scalar_types_df[[col_name]]
sql = utils._apply_ops_to_sql(
bf_df, [ops.dayofyear_op.as_expr(col_name)], [col_name]
)
snapshot.assert_match(sql, "out.sql")
def test_floor_dt(scalar_types_df: bpd.DataFrame, snapshot):
col_names = ["datetime_col", "timestamp_col", "date_col"]
bf_df = scalar_types_df[col_names]
ops_map = {
"timestamp_col_us": ops.FloorDtOp("us").as_expr("timestamp_col"),
"timestamp_col_ms": ops.FloorDtOp("ms").as_expr("timestamp_col"),
"timestamp_col_s": ops.FloorDtOp("s").as_expr("timestamp_col"),
"timestamp_col_min": ops.FloorDtOp("min").as_expr("timestamp_col"),
"timestamp_col_h": ops.FloorDtOp("h").as_expr("timestamp_col"),
"timestamp_col_D": ops.FloorDtOp("D").as_expr("timestamp_col"),
"timestamp_col_W": ops.FloorDtOp("W").as_expr("timestamp_col"),
"timestamp_col_M": ops.FloorDtOp("M").as_expr("timestamp_col"),
"timestamp_col_Q": ops.FloorDtOp("Q").as_expr("timestamp_col"),
"timestamp_col_Y": ops.FloorDtOp("Y").as_expr("timestamp_col"),
"datetime_col_q": ops.FloorDtOp("us").as_expr("datetime_col"),
"datetime_col_us": ops.FloorDtOp("us").as_expr("datetime_col"),
}
sql = utils._apply_ops_to_sql(bf_df, list(ops_map.values()), list(ops_map.keys()))
snapshot.assert_match(sql, "out.sql")
def test_floor_dt_op_invalid_freq(scalar_types_df: bpd.DataFrame):
col_name = "timestamp_col"
bf_df = scalar_types_df[[col_name]]
with pytest.raises(
NotImplementedError, match="Unsupported freq paramater: invalid"
):
utils._apply_ops_to_sql(
bf_df,
[ops.FloorDtOp(freq="invalid").as_expr(col_name)], # type:ignore
[col_name],
)
def test_hour(scalar_types_df: bpd.DataFrame, snapshot):
col_name = "timestamp_col"
bf_df = scalar_types_df[[col_name]]
sql = utils._apply_ops_to_sql(bf_df, [ops.hour_op.as_expr(col_name)], [col_name])
snapshot.assert_match(sql, "out.sql")
def test_minute(scalar_types_df: bpd.DataFrame, snapshot):
col_name = "timestamp_col"
bf_df = scalar_types_df[[col_name]]
sql = utils._apply_ops_to_sql(bf_df, [ops.minute_op.as_expr(col_name)], [col_name])
snapshot.assert_match(sql, "out.sql")
def test_month(scalar_types_df: bpd.DataFrame, snapshot):
col_name = "timestamp_col"
bf_df = scalar_types_df[[col_name]]
sql = utils._apply_ops_to_sql(bf_df, [ops.month_op.as_expr(col_name)], [col_name])
snapshot.assert_match(sql, "out.sql")
def test_normalize(scalar_types_df: bpd.DataFrame, snapshot):
col_name = "timestamp_col"
bf_df = scalar_types_df[[col_name]]
sql = utils._apply_ops_to_sql(
bf_df, [ops.normalize_op.as_expr(col_name)], [col_name]
)
snapshot.assert_match(sql, "out.sql")
def test_quarter(scalar_types_df: bpd.DataFrame, snapshot):
col_name = "timestamp_col"
bf_df = scalar_types_df[[col_name]]
sql = utils._apply_ops_to_sql(bf_df, [ops.quarter_op.as_expr(col_name)], [col_name])
snapshot.assert_match(sql, "out.sql")
def test_second(scalar_types_df: bpd.DataFrame, snapshot):
col_name = "timestamp_col"
bf_df = scalar_types_df[[col_name]]
sql = utils._apply_ops_to_sql(bf_df, [ops.second_op.as_expr(col_name)], [col_name])
snapshot.assert_match(sql, "out.sql")
def test_strftime(scalar_types_df: bpd.DataFrame, snapshot):
col_name = "timestamp_col"
bf_df = scalar_types_df[[col_name]]
sql = utils._apply_ops_to_sql(
bf_df, [ops.StrftimeOp("%Y-%m-%d").as_expr(col_name)], [col_name]
)
snapshot.assert_match(sql, "out.sql")
def test_time(scalar_types_df: bpd.DataFrame, snapshot):
col_name = "timestamp_col"
bf_df = scalar_types_df[[col_name]]
sql = utils._apply_ops_to_sql(bf_df, [ops.time_op.as_expr(col_name)], [col_name])
snapshot.assert_match(sql, "out.sql")
def test_to_datetime(scalar_types_df: bpd.DataFrame, snapshot):
col_name = "int64_col"
bf_df = scalar_types_df[[col_name]]
sql = utils._apply_ops_to_sql(
bf_df, [ops.ToDatetimeOp().as_expr(col_name)], [col_name]
)
snapshot.assert_match(sql, "out.sql")
def test_to_timestamp(scalar_types_df: bpd.DataFrame, snapshot):
col_name = "int64_col"
bf_df = scalar_types_df[[col_name]]
sql = utils._apply_ops_to_sql(
bf_df, [ops.ToTimestampOp().as_expr(col_name)], [col_name]
)
snapshot.assert_match(sql, "out.sql")
def test_unix_micros(scalar_types_df: bpd.DataFrame, snapshot):
col_name = "timestamp_col"
bf_df = scalar_types_df[[col_name]]
sql = utils._apply_ops_to_sql(
bf_df, [ops.UnixMicros().as_expr(col_name)], [col_name]
)
snapshot.assert_match(sql, "out.sql")
def test_unix_millis(scalar_types_df: bpd.DataFrame, snapshot):
col_name = "timestamp_col"
bf_df = scalar_types_df[[col_name]]
sql = utils._apply_ops_to_sql(
bf_df, [ops.UnixMillis().as_expr(col_name)], [col_name]
)
snapshot.assert_match(sql, "out.sql")
def test_unix_seconds(scalar_types_df: bpd.DataFrame, snapshot):
col_name = "timestamp_col"
bf_df = scalar_types_df[[col_name]]
sql = utils._apply_ops_to_sql(
bf_df, [ops.UnixSeconds().as_expr(col_name)], [col_name]
)
snapshot.assert_match(sql, "out.sql")
def test_year(scalar_types_df: bpd.DataFrame, snapshot):
col_name = "timestamp_col"
bf_df = scalar_types_df[[col_name]]
sql = utils._apply_ops_to_sql(bf_df, [ops.year_op.as_expr(col_name)], [col_name])
snapshot.assert_match(sql, "out.sql")
def test_iso_day(scalar_types_df: bpd.DataFrame, snapshot):
col_name = "timestamp_col"
bf_df = scalar_types_df[[col_name]]
sql = utils._apply_ops_to_sql(bf_df, [ops.iso_day_op.as_expr(col_name)], [col_name])
snapshot.assert_match(sql, "out.sql")
def test_iso_week(scalar_types_df: bpd.DataFrame, snapshot):
col_name = "timestamp_col"
bf_df = scalar_types_df[[col_name]]
sql = utils._apply_ops_to_sql(
bf_df, [ops.iso_week_op.as_expr(col_name)], [col_name]
)
snapshot.assert_match(sql, "out.sql")
def test_iso_year(scalar_types_df: bpd.DataFrame, snapshot):
col_name = "timestamp_col"
bf_df = scalar_types_df[[col_name]]
sql = utils._apply_ops_to_sql(
bf_df, [ops.iso_year_op.as_expr(col_name)], [col_name]
)
snapshot.assert_match(sql, "out.sql")
def test_add_timedelta(scalar_types_df: bpd.DataFrame, snapshot):
bf_df = scalar_types_df[["timestamp_col", "date_col"]]
timedelta = pd.Timedelta(1, unit="d")
bf_df["date_add_timedelta"] = bf_df["date_col"] + timedelta
bf_df["timestamp_add_timedelta"] = bf_df["timestamp_col"] + timedelta
bf_df["timedelta_add_date"] = timedelta + bf_df["date_col"]
bf_df["timedelta_add_timestamp"] = timedelta + bf_df["timestamp_col"]
bf_df["timedelta_add_timedelta"] = timedelta + timedelta
snapshot.assert_match(bf_df.sql, "out.sql")
def test_sub_timedelta(scalar_types_df: bpd.DataFrame, snapshot):
bf_df = scalar_types_df[["timestamp_col", "duration_col", "date_col"]]
bf_df["duration_col"] = bpd.to_timedelta(bf_df["duration_col"], unit="us")
bf_df["date_sub_timedelta"] = bf_df["date_col"] - bf_df["duration_col"]
bf_df["timestamp_sub_timedelta"] = bf_df["timestamp_col"] - bf_df["duration_col"]
bf_df["timestamp_sub_date"] = bf_df["date_col"] - bf_df["date_col"]
bf_df["date_sub_timestamp"] = bf_df["timestamp_col"] - bf_df["timestamp_col"]
bf_df["timedelta_sub_timedelta"] = bf_df["duration_col"] - bf_df["duration_col"]
snapshot.assert_match(bf_df.sql, "out.sql")