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

Update python benchmarking script (#4164)

Browse Source 
* a few tweaks to speed up data generation

* del variable to save memory

* switch to random numpy arrays
This commit is contained in:
Rong Ou 2019-02-20 18:16:09 -08:00 committed by Rory Mitchell
parent 54793544a2
commit 8e0a08fbcf
1 changed files with 13 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
tests/benchmark/benchmark_tree.py
View File

@ -5,8 +5,6 @@ import ast
import time import time
import numpy as np import numpy as np
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
import xgboost as xgb import xgboost as xgb
RNG = np.random.RandomState(1994) RNG = np.random.RandomState(1994)
@ -28,20 +26,27 @@ def run_benchmark(args):
print("Generating dataset: {} rows * {} columns".format(args.rows, args.columns)) print("Generating dataset: {} rows * {} columns".format(args.rows, args.columns))
print("{}/{} test/train split".format(args.test_size, 1.0 - args.test_size)) print("{}/{} test/train split".format(args.test_size, 1.0 - args.test_size))
tmp = time.time() tmp = time.time()
X, y = make_classification(args.rows, n_features=args.columns, n_redundant=0, X = RNG.rand(args.rows, args.columns)
n_informative=args.columns, n_repeated=0, random_state=7) y = RNG.randint(0, 2, args.rows)
if args.sparsity < 1.0: if 0.0 < args.sparsity < 1.0:
X = np.array([[np.nan if RNG.uniform(0, 1) < args.sparsity else x for x in x_row] X = np.array([[np.nan if RNG.uniform(0, 1) < args.sparsity else x for x in x_row]
for x_row in X]) for x_row in X])
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=args.test_size, train_rows = int(args.rows * (1.0 - args.test_size))
random_state=7) test_rows = int(args.rows * args.test_size)
X_train = X[:train_rows, :]
X_test = X[-test_rows:, :]
y_train = y[:train_rows]
y_test = y[-test_rows:]
print("Generate Time: %s seconds" % (str(time.time() - tmp))) print("Generate Time: %s seconds" % (str(time.time() - tmp)))
del X, y
tmp = time.time() tmp = time.time()
print("DMatrix Start") print("DMatrix Start")
dtrain = xgb.DMatrix(X_train, y_train) dtrain = xgb.DMatrix(X_train, y_train, nthread=-1)
dtest = xgb.DMatrix(X_test, y_test, nthread=-1) dtest = xgb.DMatrix(X_test, y_test, nthread=-1)
print("DMatrix Time: %s seconds" % (str(time.time() - tmp))) print("DMatrix Time: %s seconds" % (str(time.time() - tmp)))
del X_train, y_train, X_test, y_test
dtest.save_binary('dtest.dm') dtest.save_binary('dtest.dm')
dtrain.save_binary('dtrain.dm') dtrain.save_binary('dtrain.dm')