/
plot_example.py
66 lines (52 loc) · 1.93 KB
/
plot_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
53
54
55
56
57
58
59
60
61
62
63
64
65
66
# coding: utf-8
from pathlib import Path
import pandas as pd
import lightgbm as lgb
if lgb.compat.MATPLOTLIB_INSTALLED:
import matplotlib.pyplot as plt
else:
raise ImportError("You need to install matplotlib and restart your session for plot_example.py.")
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,
feature_name=[f"f{i + 1}" for i in range(X_train.shape[-1])],
categorical_feature=[21],
)
lgb_test = lgb.Dataset(X_test, y_test, reference=lgb_train)
# specify your configurations as a dict
params = {"num_leaves": 5, "metric": ("l1", "l2"), "verbose": 0}
evals_result = {} # to record eval results for plotting
print("Starting training...")
# train
gbm = lgb.train(
params,
lgb_train,
num_boost_round=100,
valid_sets=[lgb_train, lgb_test],
callbacks=[lgb.log_evaluation(10), lgb.record_evaluation(evals_result)],
)
print("Plotting metrics recorded during training...")
ax = lgb.plot_metric(evals_result, metric="l1")
plt.show()
print("Plotting feature importances...")
ax = lgb.plot_importance(gbm, max_num_features=10)
plt.show()
print("Plotting split value histogram...")
ax = lgb.plot_split_value_histogram(gbm, feature="f26", bins="auto")
plt.show()
print("Plotting 54th tree...") # one tree use categorical feature to split
ax = lgb.plot_tree(gbm, tree_index=53, figsize=(15, 15), show_info=["split_gain"])
plt.show()
print("Plotting 54th tree with graphviz...")
graph = lgb.create_tree_digraph(gbm, tree_index=53, name="Tree54")
graph.render(view=True)