-
Notifications
You must be signed in to change notification settings - Fork 1.3k
Expand file tree
/
Copy pathutils.py
More file actions
133 lines (117 loc) · 3.63 KB
/
utils.py
File metadata and controls
133 lines (117 loc) · 3.63 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
from datetime import datetime, timedelta
import pandas as pd
from feast import Entity
from feast.data_source import DataSource
from feast.infra.offline_stores.contrib.spark_offline_store.tests.data_source import (
SparkDataSourceCreator,
)
from tests.universal.feature_repos.integration_test_repo_config import (
IntegrationTestRepoConfig,
)
from tests.universal.feature_repos.repo_configuration import (
construct_test_environment,
)
from tests.universal.feature_repos.universal.online_store.redis import (
RedisOnlineStoreCreator,
)
now = datetime.now()
today = datetime.today()
driver = Entity(
name="driver_id",
description="driver id",
)
def create_entity_df() -> pd.DataFrame:
entity_df = pd.DataFrame(
[
{"driver_id": 1001, "event_timestamp": today},
{"driver_id": 1002, "event_timestamp": today},
]
)
return entity_df
def create_feature_dataset(spark_environment) -> DataSource:
yesterday = today - timedelta(days=1)
last_week = today - timedelta(days=7)
df = pd.DataFrame(
[
{
"driver_id": 1001,
"event_timestamp": yesterday,
"created": now - timedelta(hours=2),
"conv_rate": 0.8,
"acc_rate": 0.5,
"avg_daily_trips": 15,
},
{
"driver_id": 1001,
"event_timestamp": last_week,
"created": now - timedelta(hours=3),
"conv_rate": 0.75,
"acc_rate": 0.9,
"avg_daily_trips": 14,
},
{
"driver_id": 1002,
"event_timestamp": yesterday,
"created": now - timedelta(hours=2),
"conv_rate": 0.7,
"acc_rate": 0.4,
"avg_daily_trips": 12,
},
{
"driver_id": 1002,
"event_timestamp": yesterday - timedelta(days=1),
"created": now - timedelta(hours=2),
"conv_rate": 0.3,
"acc_rate": 0.6,
"avg_daily_trips": 12,
},
]
)
ds = spark_environment.data_source_creator.create_data_source(
df,
spark_environment.feature_store.project,
timestamp_field="event_timestamp",
created_timestamp_column="created",
)
return ds
def create_spark_environment():
spark_config = IntegrationTestRepoConfig(
provider="local",
online_store_creator=RedisOnlineStoreCreator,
offline_store_creator=SparkDataSourceCreator,
batch_engine={"type": "spark.engine", "partitions": 10},
)
spark_environment = construct_test_environment(
spark_config, None, entity_key_serialization_version=3
)
spark_environment.setup()
return spark_environment
def _check_online_features(
fs,
driver_id,
feature,
expected_value,
full_feature_names: bool = True,
):
online_response = fs.get_online_features(
features=[feature],
entity_rows=[{"driver_id": driver_id}],
full_feature_names=full_feature_names,
).to_dict()
feature_ref = "__".join(feature.split(":"))
assert len(online_response["driver_id"]) == 1
assert online_response["driver_id"][0] == driver_id
assert abs(online_response[feature_ref][0] - expected_value < 1e-6), (
"Transformed result"
)
def _check_offline_features(
fs,
feature,
entity_df,
size: int = 4,
):
offline_df = fs.get_historical_features(
entity_df=entity_df,
features=[feature],
).to_df()
assert len(offline_df) == size