-
Notifications
You must be signed in to change notification settings - Fork 3.8k
/
simple_example.py
52 lines (43 loc) · 1.42 KB
/
simple_example.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
# coding: utf-8
from pathlib import Path
import pandas as pd
from sklearn.metrics import mean_squared_error
import lightgbm as lgb
print("Loading data...")
# load or create your dataset
regression_example_dir = Path(__file__).absolute().parents[1] / "regression"
df_train = pd.read_csv(str(regression_example_dir / "regression.train"), header=None, sep="\t")
df_test = pd.read_csv(str(regression_example_dir / "regression.test"), header=None, sep="\t")
y_train = df_train[0]
y_test = df_test[0]
X_train = df_train.drop(0, axis=1)
X_test = df_test.drop(0, axis=1)
# create dataset for lightgbm
lgb_train = lgb.Dataset(X_train, y_train)
lgb_eval = lgb.Dataset(X_test, y_test, reference=lgb_train)
# specify your configurations as a dict
params = {
"boosting_type": "gbdt",
"objective": "regression",
"metric": {"l2", "l1"},
"num_leaves": 31,
"learning_rate": 0.05,
"feature_fraction": 0.9,
"bagging_fraction": 0.8,
"bagging_freq": 5,
"verbose": 0,
}
print("Starting training...")
# train
gbm = lgb.train(
params, lgb_train, num_boost_round=20, valid_sets=lgb_eval, callbacks=[lgb.early_stopping(stopping_rounds=5)]
)
print("Saving model...")
# save model to file
gbm.save_model("model.txt")
print("Starting predicting...")
# predict
y_pred = gbm.predict(X_test, num_iteration=gbm.best_iteration)
# eval
rmse_test = mean_squared_error(y_test, y_pred) ** 0.5
print(f"The RMSE of prediction is: {rmse_test}")