Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

GPU Plugin: Add subsample, colsample_bytree, colsample_bylevel (#1895)

Browse Source
This commit is contained in:
Rory Mitchell
2016-12-23 04:30:36 +13:00
committed by Tianqi Chen
parent cee4aafb93
commit b49b339183
10 changed files with 331 additions and 324 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
demo/gpu_acceleration/bosch.py
View File

@@ -5,12 +5,12 @@ import time
import random
from sklearn.cross_validation import StratifiedKFold
#For sub sampling rows from input file
#For sampling rows from input file
random_seed = 9
subsample = 0.4
subset = 0.4
n_rows = 1183747;
train_rows = int(n_rows * subsample)
train_rows = int(n_rows * subset)
random.seed(random_seed)
skip = sorted(random.sample(xrange(1,n_rows + 1),n_rows-train_rows))
data = pd.read_csv("../data/train_numeric.csv", index_col=0, dtype=np.float32, skiprows=skip)