forked from feast-dev/feast
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathconftest.py
More file actions
216 lines (180 loc) · 6.28 KB
/
conftest.py
File metadata and controls
216 lines (180 loc) · 6.28 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
# Copyright 2021 The Feast Authors
#
# 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
#
# https://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 logging
import multiprocessing
import time
from datetime import datetime, timedelta
from multiprocessing import Process
from sys import platform
from typing import List
import pandas as pd
import pytest
from _pytest.nodes import Item
from feast import FeatureStore
from tests.data.data_creator import create_dataset
from tests.integration.feature_repos.integration_test_repo_config import (
IntegrationTestRepoConfig,
)
from tests.integration.feature_repos.repo_configuration import (
FULL_REPO_CONFIGS,
REDIS_CONFIG,
Environment,
construct_test_environment,
construct_universal_data_sources,
construct_universal_datasets,
construct_universal_entities,
)
logger = logging.getLogger(__name__)
def pytest_configure(config):
if platform in ["darwin", "windows"]:
multiprocessing.set_start_method("spawn")
else:
multiprocessing.set_start_method("fork")
config.addinivalue_line(
"markers", "integration: mark test that has external dependencies"
)
config.addinivalue_line("markers", "benchmark: mark benchmarking tests")
config.addinivalue_line(
"markers", "universal: mark tests that use the universal feature repo"
)
def pytest_addoption(parser):
parser.addoption(
"--integration",
action="store_true",
default=False,
help="Run tests with external dependencies",
)
parser.addoption(
"--benchmark", action="store_true", default=False, help="Run benchmark tests",
)
parser.addoption(
"--universal", action="store_true", default=False, help="Run universal tests",
)
def pytest_collection_modifyitems(config, items: List[Item]):
should_run_integration = config.getoption("--integration") is True
should_run_benchmark = config.getoption("--benchmark") is True
should_run_universal = config.getoption("--universal") is True
integration_tests = [t for t in items if "integration" in t.keywords]
if not should_run_integration:
for t in integration_tests:
items.remove(t)
else:
items.clear()
for t in integration_tests:
items.append(t)
benchmark_tests = [t for t in items if "benchmark" in t.keywords]
if not should_run_benchmark:
for t in benchmark_tests:
items.remove(t)
else:
items.clear()
for t in benchmark_tests:
items.append(t)
universal_tests = [t for t in items if "universal" in t.keywords]
if should_run_universal:
items.clear()
for t in universal_tests:
items.append(t)
@pytest.fixture
def simple_dataset_1() -> pd.DataFrame:
now = datetime.utcnow()
ts = pd.Timestamp(now).round("ms")
data = {
"id_join_key": [1, 2, 1, 3, 3],
"float_col": [0.1, 0.2, 0.3, 4, 5],
"int64_col": [1, 2, 3, 4, 5],
"string_col": ["a", "b", "c", "d", "e"],
"ts_1": [
ts,
ts - timedelta(hours=4),
ts - timedelta(hours=3),
ts - timedelta(hours=2),
ts - timedelta(hours=1),
],
}
return pd.DataFrame.from_dict(data)
@pytest.fixture
def simple_dataset_2() -> pd.DataFrame:
now = datetime.utcnow()
ts = pd.Timestamp(now).round("ms")
data = {
"id_join_key": ["a", "b", "c", "d", "e"],
"float_col": [0.1, 0.2, 0.3, 4, 5],
"int64_col": [1, 2, 3, 4, 5],
"string_col": ["a", "b", "c", "d", "e"],
"ts_1": [
ts,
ts - timedelta(hours=4),
ts - timedelta(hours=3),
ts - timedelta(hours=2),
ts - timedelta(hours=1),
],
}
return pd.DataFrame.from_dict(data)
def start_test_local_server(repo_path: str, port: int):
fs = FeatureStore(repo_path)
fs.serve("localhost", port, no_access_log=True)
@pytest.fixture(
params=FULL_REPO_CONFIGS, scope="session", ids=[str(c) for c in FULL_REPO_CONFIGS]
)
def environment(request, worker_id: str):
e = construct_test_environment(request.param, worker_id=worker_id)
proc = Process(
target=start_test_local_server,
args=(e.feature_store.repo_path, e.get_local_server_port()),
daemon=True,
)
if e.python_feature_server and e.test_repo_config.provider == "local":
proc.start()
# Wait for server to start
time.sleep(3)
def cleanup():
e.feature_store.teardown()
if proc.is_alive():
proc.kill()
request.addfinalizer(cleanup)
return e
@pytest.fixture()
def local_redis_environment(request, worker_id):
e = construct_test_environment(
IntegrationTestRepoConfig(online_store=REDIS_CONFIG), worker_id=worker_id
)
def cleanup():
e.feature_store.teardown()
request.addfinalizer(cleanup)
return e
@pytest.fixture(scope="session")
def universal_data_sources(request, environment):
entities = construct_universal_entities()
datasets = construct_universal_datasets(
entities, environment.start_date, environment.end_date
)
datasources = construct_universal_data_sources(
datasets, environment.data_source_creator
)
def cleanup():
# logger.info("Running cleanup in %s, Request: %s", worker_id, request.param)
environment.data_source_creator.teardown()
request.addfinalizer(cleanup)
return entities, datasets, datasources
@pytest.fixture(scope="session")
def e2e_data_sources(environment: Environment, request):
df = create_dataset()
data_source = environment.data_source_creator.create_data_source(
df, environment.feature_store.project, field_mapping={"ts_1": "ts"},
)
def cleanup():
environment.data_source_creator.teardown()
request.addfinalizer(cleanup)
return df, data_source