forked from feast-dev/feast
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathdriver_test_data.py
More file actions
141 lines (121 loc) · 7.07 KB
/
Copy pathdriver_test_data.py
File metadata and controls
141 lines (121 loc) · 7.07 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
# This module generates dummy data to be used for tests and examples.
import numpy as np
import pandas as pd
from feast.infra.provider import ENTITY_DF_EVENT_TIMESTAMP_COL
def create_orders_df(
customers, drivers, start_date, end_date, order_count
) -> pd.DataFrame:
"""
Example df generated by this function:
| order_id | driver_id | customer_id | order_is_success | event_timestamp |
+----------+-----------+-------------+------------------+---------------------+
| 100 | 5004 | 1007 | 0 | 2021-03-10 19:31:15 |
| 101 | 5003 | 1006 | 0 | 2021-03-11 22:02:50 |
| 102 | 5010 | 1005 | 0 | 2021-03-13 00:34:24 |
| 103 | 5010 | 1001 | 1 | 2021-03-14 03:05:59 |
"""
df = pd.DataFrame()
df["order_id"] = [order_id for order_id in range(100, 100 + order_count)]
df["driver_id"] = np.random.choice(drivers, order_count)
df["customer_id"] = np.random.choice(customers, order_count)
df["order_is_success"] = np.random.randint(0, 2, size=order_count).astype(np.int32)
df[ENTITY_DF_EVENT_TIMESTAMP_COL] = [
pd.Timestamp(dt, unit="ms", tz="UTC").round("ms")
for dt in pd.date_range(start=start_date, end=end_date, periods=order_count)
]
df.sort_values(
by=[ENTITY_DF_EVENT_TIMESTAMP_COL, "order_id", "driver_id", "customer_id"],
inplace=True,
)
return df
def create_driver_hourly_stats_df(drivers, start_date, end_date) -> pd.DataFrame:
"""
Example df generated by this function:
| datetime | driver_id | conv_rate | acc_rate | avg_daily_trips | created |
|------------------+-----------+-----------+----------+-----------------+------------------|
| 2021-03-17 19:31 | 5010 | 0.229297 | 0.685843 | 861 | 2021-03-24 19:34 |
| 2021-03-17 20:31 | 5010 | 0.781655 | 0.861280 | 769 | 2021-03-24 19:34 |
| 2021-03-17 21:31 | 5010 | 0.150333 | 0.525581 | 778 | 2021-03-24 19:34 |
| 2021-03-17 22:31 | 5010 | 0.951701 | 0.228883 | 570 | 2021-03-24 19:34 |
| 2021-03-17 23:31 | 5010 | 0.819598 | 0.262503 | 473 | 2021-03-24 19:34 |
| | ... | ... | ... | ... | |
| 2021-03-24 16:31 | 5001 | 0.061585 | 0.658140 | 477 | 2021-03-24 19:34 |
| 2021-03-24 17:31 | 5001 | 0.088949 | 0.303897 | 618 | 2021-03-24 19:34 |
| 2021-03-24 18:31 | 5001 | 0.096652 | 0.747421 | 480 | 2021-03-24 19:34 |
| 2021-03-17 19:31 | 5005 | 0.142936 | 0.707596 | 466 | 2021-03-24 19:34 |
| 2021-03-17 19:31 | 5005 | 0.142936 | 0.707596 | 466 | 2021-03-24 19:34 |
"""
df_hourly = pd.DataFrame(
{
"datetime": [
pd.Timestamp(dt, unit="ms", tz="UTC").round("ms")
for dt in pd.date_range(
start=start_date, end=end_date, freq="1H", closed="left"
)
]
}
)
df_all_drivers = pd.DataFrame()
for driver in drivers:
df_hourly_copy = df_hourly.copy()
df_hourly_copy["driver_id"] = driver
df_all_drivers = pd.concat([df_hourly_copy, df_all_drivers])
df_all_drivers.reset_index(drop=True, inplace=True)
rows = df_all_drivers["datetime"].count()
df_all_drivers["conv_rate"] = np.random.random(size=rows).astype(np.float32)
df_all_drivers["acc_rate"] = np.random.random(size=rows).astype(np.float32)
df_all_drivers["avg_daily_trips"] = np.random.randint(0, 1000, size=rows).astype(
np.int32
)
df_all_drivers["created"] = pd.to_datetime(pd.Timestamp.now(tz=None).round("ms"))
# Create duplicate rows that should be filtered by created timestamp
# TODO: These duplicate rows area indirectly being filtered out by the point in time join already. We need to
# inject a bad row at a timestamp where we know it will get joined to the entity dataframe, and then test that
# we are actually filtering it with the created timestamp
late_row = df_all_drivers.iloc[int(rows / 2)]
df_all_drivers = df_all_drivers.append(late_row).append(late_row)
return df_all_drivers
def create_customer_daily_profile_df(customers, start_date, end_date) -> pd.DataFrame:
"""
Example df generated by this function:
| datetime | customer_id | current_balance | avg_passenger_count | lifetime_trip_count | created |
|------------------+-------------+-----------------+---------------------+---------------------+------------------|
| 2021-03-17 19:31 | 1010 | 0.889188 | 0.049057 | 412 | 2021-03-24 19:38 |
| 2021-03-18 19:31 | 1010 | 0.979273 | 0.212630 | 639 | 2021-03-24 19:38 |
| 2021-03-19 19:31 | 1010 | 0.976549 | 0.176881 | 70 | 2021-03-24 19:38 |
| 2021-03-20 19:31 | 1010 | 0.273697 | 0.325012 | 68 | 2021-03-24 19:38 |
| 2021-03-21 19:31 | 1010 | 0.438262 | 0.313009 | 192 | 2021-03-24 19:38 |
| | ... | ... | ... | ... | |
| 2021-03-19 19:31 | 1001 | 0.738860 | 0.857422 | 344 | 2021-03-24 19:38 |
| 2021-03-20 19:31 | 1001 | 0.848397 | 0.745989 | 106 | 2021-03-24 19:38 |
| 2021-03-21 19:31 | 1001 | 0.301552 | 0.185873 | 812 | 2021-03-24 19:38 |
| 2021-03-22 19:31 | 1001 | 0.943030 | 0.561219 | 322 | 2021-03-24 19:38 |
| 2021-03-23 19:31 | 1001 | 0.354919 | 0.810093 | 273 | 2021-03-24 19:38 |
"""
df_daily = pd.DataFrame(
{
"datetime": [
pd.Timestamp(dt, unit="ms", tz="UTC").round("ms")
for dt in pd.date_range(
start=start_date, end=end_date, freq="1D", closed="left"
)
]
}
)
df_all_customers = pd.DataFrame()
for customer in customers:
df_daily_copy = df_daily.copy()
df_daily_copy["customer_id"] = customer
df_all_customers = pd.concat([df_daily_copy, df_all_customers])
df_all_customers.reset_index(drop=True, inplace=True)
rows = df_all_customers["datetime"].count()
df_all_customers["current_balance"] = np.random.random(size=rows).astype(np.float32)
df_all_customers["avg_passenger_count"] = np.random.random(size=rows).astype(
np.float32
)
df_all_customers["lifetime_trip_count"] = np.random.randint(
0, 1000, size=rows
).astype(np.int32)
# TODO: Remove created timestamp in order to test whether its really optional
df_all_customers["created"] = pd.to_datetime(pd.Timestamp.now(tz=None).round("ms"))
return df_all_customers