forked from sb-ai-lab/LightAutoML
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathdemo7.py
53 lines (37 loc) · 1.45 KB
/
demo7.py
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
#!/usr/bin/env python
# coding: utf-8
import numpy as np
import pandas as pd
from sklearn.metrics import roc_auc_score
from sklearn.model_selection import train_test_split
from lightautoml.automl.presets.tabular_presets import TabularAutoML
from lightautoml.dataset.roles import DatetimeRole
from lightautoml.tasks import Task
np.random.seed(42)
data = pd.read_csv("./data/sampled_app_train.csv")
data["BIRTH_DATE"] = (np.datetime64("2018-01-01") + data["DAYS_BIRTH"].astype(np.dtype("timedelta64[D]"))).astype(str)
data["EMP_DATE"] = (
np.datetime64("2018-01-01") + np.clip(data["DAYS_EMPLOYED"], None, 0).astype(np.dtype("timedelta64[D]"))
).astype(str)
data["report_dt"] = np.datetime64("2018-01-01")
data["constant"] = 1
data["allnan"] = np.nan
data.drop(["DAYS_BIRTH", "DAYS_EMPLOYED"], axis=1, inplace=True)
train, test = train_test_split(data, test_size=2000, random_state=42)
roles = {
"target": "TARGET",
DatetimeRole(base_date=True, seasonality=(), base_feats=False): "report_dt",
}
task = Task(
"binary",
)
automl = TabularAutoML(
task=task,
timeout=3600,
)
oof_pred = automl.fit_predict(train, roles=roles)
test_pred = automl.predict(test)
not_nan = np.any(~np.isnan(oof_pred.data), axis=1)
print("Check scores...")
print("OOF score: {}".format(roc_auc_score(train[roles["target"]].values[not_nan], oof_pred.data[not_nan][:, 0])))
print("TEST score: {}".format(roc_auc_score(test[roles["target"]].values, test_pred.data[:, 0])))