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

Update bosch.py (#2482)

Browse Source 
- fix deprecated expression on StratifiedKFold
- use range instead of xrange
This commit is contained in:
69guitar1015 2017-07-07 09:05:09 +09:00 committed by Yuan (Terry) Tang
parent e939192978
commit 9091493250
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
demo/gpu_acceleration/bosch.py
View File

@ -12,7 +12,7 @@ subset = 0.4
n_rows = 1183747; n_rows = 1183747;
train_rows = int(n_rows * subset) train_rows = int(n_rows * subset)
random.seed(random_seed) random.seed(random_seed)
skip = sorted(random.sample(xrange(1,n_rows + 1),n_rows-train_rows)) skip = sorted(random.sample(range(1,n_rows + 1),n_rows-train_rows))
data = pd.read_csv("../data/train_numeric.csv", index_col=0, dtype=np.float32, skiprows=skip) data = pd.read_csv("../data/train_numeric.csv", index_col=0, dtype=np.float32, skiprows=skip)
y = data['Response'].values y = data['Response'].values
del data['Response'] del data['Response']
@ -28,9 +28,9 @@ param['tree_method'] = 'gpu_exact'
num_round = 20 num_round = 20
cv = StratifiedKFold(y, n_folds=5) skf = StratifiedKFold(n_splits=5)
for i, (train, test) in enumerate(cv): for i, (train, test) in enumerate(skf.split(X, y)):
dtrain = xgb.DMatrix(X[train], label=y[train]) dtrain = xgb.DMatrix(X[train], label=y[train])
tmp = time.time() tmp = time.time()
bst = xgb.train(param, dtrain, num_round) bst = xgb.train(param, dtrain, num_round)