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

reformat benchmark_tree.py to get rid of lint errors (#4126)

Browse Source
This commit is contained in:
Rong Ou 2019-02-12 21:54:56 -08:00 committed by Rory Mitchell
parent 9b917cda4f
commit 3be1b9ae30
2 changed files with 51 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
python-package/.pylintrc
View File

@ -2,6 +2,8 @@
ignore=tests
extension-pkg-whitelist=numpy
disiable=unexpected-special-method-signature,too-many-nested-blocks
dummy-variables-rgx=(unused|)_.*
@ -19,3 +21,6 @@ attr-naming-style=snake_case
argument-naming-style=snake_case
variable-naming-style=snake_case
class-attribute-naming-style=snake_case
# Allow single-letter variables
variable-rgx=[a-zA-Z_][a-z0-9_]{0,30}$

76
tests/benchmark/benchmark_tree.py
View File

@ -1,65 +1,81 @@
# pylint: skip-file
import sys, argparse
import xgboost as xgb
"""Run benchmark on the tree booster."""
import argparse
import ast
import time
import numpy as np
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
import time
import ast
import xgboost as xgb
rng = np.random.RandomState(1994)
RNG = np.random.RandomState(1994)
def run_benchmark(args):
"""Runs the benchmark."""
try:
dtest = xgb.DMatrix('dtest.dm')
dtrain = xgb.DMatrix('dtrain.dm')
if not (dtest.num_col() == args.columns \
if not (dtest.num_col() == args.columns
and dtrain.num_col() == args.columns):
raise ValueError("Wrong cols")
if not (dtest.num_row() == args.rows * args.test_size \
and dtrain.num_row() == args.rows * (1-args.test_size)):
if not (dtest.num_row() == args.rows * args.test_size
and dtrain.num_row() == args.rows * (1 - args.test_size)):
raise ValueError("Wrong rows")
except:
except xgb.core.XGBoostError:
print("Generating dataset: {} rows * {} columns".format(args.rows, args.columns))
print("{}/{} test/train split".format(args.test_size, 1.0 - args.test_size))
tmp = time.time()
X, y = make_classification(args.rows, n_features=args.columns, n_redundant=0, n_informative=args.columns, n_repeated=0, random_state=7)
X, y = make_classification(args.rows, n_features=args.columns, n_redundant=0,
n_informative=args.columns, n_repeated=0, random_state=7)
if args.sparsity < 1.0:
X = np.array([[np.nan if rng.uniform(0, 1) < args.sparsity else x for x in x_row] for x_row in X])
X = np.array([[np.nan if RNG.uniform(0, 1) < args.sparsity else x for x in x_row]
for x_row in X])
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=args.test_size, random_state=7)
print ("Generate Time: %s seconds" % (str(time.time() - tmp)))
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=args.test_size,
random_state=7)
print("Generate Time: %s seconds" % (str(time.time() - tmp)))
tmp = time.time()
print ("DMatrix Start")
print("DMatrix Start")
dtrain = xgb.DMatrix(X_train, y_train)
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)))
dtest.save_binary('dtest.dm')
dtrain.save_binary('dtrain.dm')
param = {'objective': 'binary:logistic'}
if args.params is not '':
if args.params != '':
param.update(ast.literal_eval(args.params))
param['tree_method'] = args.tree_method
print("Training with '%s'" % param['tree_method'])
tmp = time.time()
xgb.train(param, dtrain, args.iterations, evals=[(dtest, "test")])
print ("Train Time: %s seconds" % (str(time.time() - tmp)))
print("Train Time: %s seconds" % (str(time.time() - tmp)))
parser = argparse.ArgumentParser()
parser.add_argument('--tree_method', default='gpu_hist')
parser.add_argument('--sparsity', type=float, default=0.0)
parser.add_argument('--rows', type=int, default=1000000)
parser.add_argument('--columns', type=int, default=50)
parser.add_argument('--iterations', type=int, default=500)
parser.add_argument('--test_size', type=float, default=0.25)
parser.add_argument('--params', default='', help='Provide additional parameters as a Python dict string, e.g. --params \"{\'max_depth\':2}\"')
args = parser.parse_args()
run_benchmark(args)
def main():
"""The main function.
Defines and parses command line arguments and calls the benchmark.
"""
parser = argparse.ArgumentParser()
parser.add_argument('--tree_method', default='gpu_hist')
parser.add_argument('--sparsity', type=float, default=0.0)
parser.add_argument('--rows', type=int, default=1000000)
parser.add_argument('--columns', type=int, default=50)
parser.add_argument('--iterations', type=int, default=500)
parser.add_argument('--test_size', type=float, default=0.25)
parser.add_argument('--params', default='',
help='Provide additional parameters as a Python dict string, e.g. --params '
'\"{\'max_depth\':2}\"')
args = parser.parse_args()
run_benchmark(args)
if __name__ == '__main__':
main()