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
|
import xgboost as xgb
from sklearn.datasets import fetch_covtype
from sklearn.model_selection import train_test_split
import time
# Fetch dataset using sklearn
cov = fetch_covtype()
X = cov.data
y = cov.target
# Create 0.75/0.25 train/test split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, train_size=0.75,
random_state=42)
# Specify sufficient boosting iterations to reach a minimum
num_round = 3000
# Leave most parameters as default
param = {'objective': 'multi:softmax', # Specify multiclass classification
'num_class': 8, # Number of possible output classes
'tree_method': 'gpu_hist' # Use GPU accelerated algorithm
}
# Convert input data from numpy to XGBoost format
dtrain = xgb.DMatrix(X_train, label=y_train)
dtest = xgb.DMatrix(X_test, label=y_test)
gpu_res = {} # Store accuracy result
tmp = time.time()
# Train model
xgb.train(param, dtrain, num_round, evals=[(dtest, 'test')], evals_result=gpu_res)
print("GPU Training Time: %s seconds" % (str(time.time() - tmp)))
# Repeat for CPU algorithm
tmp = time.time()
param['tree_method'] = 'hist'
cpu_res = {}
xgb.train(param, dtrain, num_round, evals=[(dtest, 'test')], evals_result=cpu_res)
print("CPU Training Time: %s seconds" % (str(time.time() - tmp)))
|
