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
|
"""
Use GPU to speedup SHAP value computation
=========================================
Demonstrates using GPU acceleration to compute SHAP values for feature importance.
"""
import shap
from sklearn.datasets import fetch_california_housing
import xgboost as xgb
# Fetch dataset using sklearn
data = fetch_california_housing()
print(data.DESCR)
X = data.data
y = data.target
num_round = 500
param = {
"eta": 0.05,
"max_depth": 10,
"tree_method": "hist",
"device": "cuda",
}
# GPU accelerated training
dtrain = xgb.DMatrix(X, label=y, feature_names=data.feature_names)
model = xgb.train(param, dtrain, num_round)
# Compute shap values using GPU with xgboost
model.set_param({"device": "cuda"})
shap_values = model.predict(dtrain, pred_contribs=True)
# Compute shap interaction values using GPU
shap_interaction_values = model.predict(dtrain, pred_interactions=True)
# shap will call the GPU accelerated version as long as the device parameter is set to
# "cuda"
explainer = shap.TreeExplainer(model)
shap_values = explainer.shap_values(X)
# visualize the first prediction's explanation
shap.force_plot(
explainer.expected_value,
shap_values[0, :],
X[0, :],
feature_names=data.feature_names,
matplotlib=True,
)
# Show a summary of feature importance
shap.summary_plot(shap_values, X, plot_type="bar", feature_names=data.feature_names)
|
