Benchmark (ONNX) for DecisionTreeRegressor#
Overview#
(Source code, png, hires.png, pdf)
Detailed graphs#
(Source code, png, hires.png, pdf)
Configuration#
<<<
from pyquickhelper.pandashelper import df2rst
import pandas
name = os.path.join(
__WD__, "../../onnx/results/bench_plot_onnxruntime_decision_tree_reg.time.csv")
df = pandas.read_csv(name)
print(df2rst(df, number_format=4))
>>>
name |
version |
value |
---|---|---|
date |
2019-12-21 |
|
python |
3.7.2 (default, Mar 1 2019, 18:34:21) [GCC 6.3.0 20170516] |
|
platform |
linux |
|
OS |
Linux-4.9.0-8-amd64-x86_64-with-debian-9.6 |
|
machine |
x86_64 |
|
processor |
||
release |
4.9.0-8-amd64 |
|
architecture |
(‘64bit’, ‘’) |
|
mlprodict |
0.3 |
|
numpy |
1.17.4 |
openblas, language=c |
onnx |
1.6.34 |
opset=12 |
onnxruntime |
1.1.995 |
CPU-DNNL-MKL-ML |
pandas |
0.25.3 |
|
skl2onnx |
1.6.994 |
|
sklearn |
0.22 |
Raw results#
bench_plot_onnxruntime_decision_tree_reg.csv
<<<
from pyquickhelper.pandashelper import df2rst
from pymlbenchmark.benchmark.bench_helper import bench_pivot
import pandas
name = os.path.join(
__WD__, "../../onnx/results/bench_plot_onnxruntime_decision_tree_reg.perf.csv")
df = pandas.read_csv(name)
piv = bench_pivot(df).reset_index(drop=False)
piv['speedup_py'] = piv['skl'] / piv['onxpython_compiled']
piv['speedup_ort'] = piv['skl'] / piv['onxonnxruntime1']
print(df2rst(piv, number_format=4))
method |
skl_nb_base_estimators |
N |
dim |
max_depth |
number |
count |
error_c |
onnx_opset |
onxonnxruntime1 |
onxpython_compiled |
skl |
speedup_py |
speedup_ort |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
predict |
-1 |
1 |
1 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1 |
1 |
3 |
1 |
10 |
0 |
12 |
2.942e-05 |
1.271e-05 |
|||
predict |
-1 |
1 |
1 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1 |
1 |
10 |
1 |
10 |
0 |
12 |
2.612e-05 |
1.035e-05 |
|||
predict |
-1 |
1 |
1 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1 |
1 |
20 |
1 |
10 |
0 |
12 |
2.74e-05 |
1.212e-05 |
|||
predict |
-1 |
1 |
5 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1 |
5 |
3 |
1 |
10 |
0 |
12 |
2.665e-05 |
1.009e-05 |
|||
predict |
-1 |
1 |
5 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1 |
5 |
10 |
1 |
10 |
0 |
12 |
2.659e-05 |
1.061e-05 |
|||
predict |
-1 |
1 |
5 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1 |
5 |
20 |
1 |
10 |
0 |
12 |
2.889e-05 |
1.229e-05 |
|||
predict |
-1 |
1 |
10 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1 |
10 |
3 |
1 |
10 |
0 |
12 |
2.862e-05 |
1.102e-05 |
|||
predict |
-1 |
1 |
10 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1 |
10 |
10 |
1 |
10 |
0 |
12 |
2.817e-05 |
1.092e-05 |
|||
predict |
-1 |
1 |
10 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1 |
10 |
20 |
1 |
10 |
0 |
12 |
2.911e-05 |
1.229e-05 |
|||
predict |
-1 |
1 |
20 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1 |
20 |
3 |
1 |
10 |
0 |
12 |
2.938e-05 |
1.176e-05 |
|||
predict |
-1 |
1 |
20 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1 |
20 |
10 |
1 |
10 |
0 |
12 |
2.711e-05 |
1.07e-05 |
|||
predict |
-1 |
1 |
20 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1 |
20 |
20 |
1 |
10 |
0 |
12 |
2.882e-05 |
1.22e-05 |
|||
predict |
-1 |
1 |
50 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1 |
50 |
3 |
1 |
10 |
0 |
12 |
3.095e-05 |
1.162e-05 |
|||
predict |
-1 |
1 |
50 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1 |
50 |
10 |
1 |
10 |
0 |
12 |
2.673e-05 |
1.134e-05 |
|||
predict |
-1 |
1 |
50 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1 |
50 |
20 |
1 |
10 |
0 |
12 |
3.037e-05 |
1.251e-05 |
|||
predict |
-1 |
1 |
100 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1 |
100 |
3 |
1 |
10 |
0 |
12 |
2.992e-05 |
1.137e-05 |
|||
predict |
-1 |
1 |
100 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1 |
100 |
10 |
1 |
10 |
0 |
12 |
2.753e-05 |
1.094e-05 |
|||
predict |
-1 |
1 |
100 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1 |
100 |
20 |
1 |
10 |
0 |
12 |
2.843e-05 |
1.172e-05 |
|||
predict |
-1 |
1 |
200 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1 |
200 |
3 |
1 |
10 |
0 |
12 |
2.932e-05 |
1.199e-05 |
|||
predict |
-1 |
1 |
200 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1 |
200 |
10 |
1 |
10 |
0 |
12 |
2.743e-05 |
1.137e-05 |
|||
predict |
-1 |
1 |
200 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1 |
200 |
20 |
1 |
10 |
0 |
12 |
3.05e-05 |
1.241e-05 |
|||
predict |
-1 |
10 |
1 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10 |
1 |
3 |
1 |
10 |
0 |
12 |
2.355e-05 |
9.584e-06 |
|||
predict |
-1 |
10 |
1 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10 |
1 |
10 |
1 |
10 |
0 |
12 |
2.554e-05 |
1.044e-05 |
|||
predict |
-1 |
10 |
1 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10 |
1 |
20 |
1 |
10 |
0 |
12 |
2.76e-05 |
1.512e-05 |
|||
predict |
-1 |
10 |
5 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10 |
5 |
3 |
1 |
10 |
0 |
12 |
2.371e-05 |
9.484e-06 |
|||
predict |
-1 |
10 |
5 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10 |
5 |
10 |
1 |
10 |
0 |
12 |
2.544e-05 |
1.096e-05 |
|||
predict |
-1 |
10 |
5 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10 |
5 |
20 |
1 |
10 |
0 |
12 |
3.29e-05 |
1.771e-05 |
|||
predict |
-1 |
10 |
10 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10 |
10 |
3 |
1 |
10 |
0 |
12 |
2.38e-05 |
9.505e-06 |
|||
predict |
-1 |
10 |
10 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10 |
10 |
10 |
1 |
10 |
0 |
12 |
2.549e-05 |
1.184e-05 |
|||
predict |
-1 |
10 |
10 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10 |
10 |
20 |
1 |
10 |
0 |
12 |
3.302e-05 |
1.812e-05 |
|||
predict |
-1 |
10 |
20 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10 |
20 |
3 |
1 |
10 |
0 |
12 |
2.509e-05 |
9.971e-06 |
|||
predict |
-1 |
10 |
20 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10 |
20 |
10 |
1 |
10 |
0 |
12 |
2.584e-05 |
1.103e-05 |
|||
predict |
-1 |
10 |
20 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10 |
20 |
20 |
1 |
10 |
0 |
12 |
3.332e-05 |
1.794e-05 |
|||
predict |
-1 |
10 |
50 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10 |
50 |
3 |
1 |
10 |
0 |
12 |
2.57e-05 |
1.069e-05 |
|||
predict |
-1 |
10 |
50 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10 |
50 |
10 |
1 |
10 |
0 |
12 |
2.713e-05 |
1.297e-05 |
|||
predict |
-1 |
10 |
50 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10 |
50 |
20 |
1 |
10 |
0 |
12 |
3.515e-05 |
1.857e-05 |
|||
predict |
-1 |
10 |
100 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10 |
100 |
3 |
1 |
10 |
0 |
12 |
2.662e-05 |
1.115e-05 |
|||
predict |
-1 |
10 |
100 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10 |
100 |
10 |
1 |
10 |
0 |
12 |
2.737e-05 |
1.261e-05 |
|||
predict |
-1 |
10 |
100 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10 |
100 |
20 |
1 |
10 |
0 |
12 |
3.49e-05 |
1.77e-05 |
|||
predict |
-1 |
10 |
200 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10 |
200 |
3 |
1 |
10 |
0 |
12 |
2.743e-05 |
1.157e-05 |
|||
predict |
-1 |
10 |
200 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10 |
200 |
10 |
1 |
10 |
0 |
12 |
2.942e-05 |
1.399e-05 |
|||
predict |
-1 |
10 |
200 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10 |
200 |
20 |
1 |
10 |
0 |
12 |
3.651e-05 |
1.997e-05 |
|||
predict |
-1 |
100 |
1 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
100 |
1 |
3 |
1 |
10 |
0 |
12 |
2.797e-05 |
2.21e-05 |
|||
predict |
-1 |
100 |
1 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
100 |
1 |
10 |
1 |
10 |
0 |
12 |
3.741e-05 |
1.887e-05 |
|||
predict |
-1 |
100 |
1 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
100 |
1 |
20 |
1 |
10 |
0 |
12 |
5.135e-05 |
2.589e-05 |
|||
predict |
-1 |
100 |
5 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
100 |
5 |
3 |
1 |
10 |
0 |
12 |
3.048e-05 |
1.824e-05 |
|||
predict |
-1 |
100 |
5 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
100 |
5 |
10 |
1 |
10 |
0 |
12 |
4.155e-05 |
2.076e-05 |
|||
predict |
-1 |
100 |
5 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
100 |
5 |
20 |
1 |
10 |
0 |
12 |
9.151e-05 |
3.589e-05 |
|||
predict |
-1 |
100 |
10 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
100 |
10 |
3 |
1 |
10 |
0 |
12 |
3.176e-05 |
1.853e-05 |
|||
predict |
-1 |
100 |
10 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
100 |
10 |
10 |
1 |
10 |
0 |
12 |
4.035e-05 |
2.149e-05 |
|||
predict |
-1 |
100 |
10 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
100 |
10 |
20 |
1 |
10 |
0 |
12 |
8.77e-05 |
3.762e-05 |
|||
predict |
-1 |
100 |
20 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
100 |
20 |
3 |
1 |
10 |
0 |
12 |
3.271e-05 |
1.971e-05 |
|||
predict |
-1 |
100 |
20 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
100 |
20 |
10 |
1 |
10 |
0 |
12 |
4.251e-05 |
2.197e-05 |
|||
predict |
-1 |
100 |
20 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
100 |
20 |
20 |
1 |
10 |
0 |
12 |
8.976e-05 |
3.75e-05 |
|||
predict |
-1 |
100 |
50 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
100 |
50 |
3 |
1 |
10 |
0 |
12 |
3.544e-05 |
2.128e-05 |
|||
predict |
-1 |
100 |
50 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
100 |
50 |
10 |
1 |
10 |
0 |
12 |
4.383e-05 |
2.48e-05 |
|||
predict |
-1 |
100 |
50 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
100 |
50 |
20 |
1 |
10 |
0 |
12 |
9.452e-05 |
3.924e-05 |
|||
predict |
-1 |
100 |
100 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
100 |
100 |
3 |
1 |
10 |
0 |
12 |
3.865e-05 |
2.488e-05 |
|||
predict |
-1 |
100 |
100 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
100 |
100 |
10 |
1 |
10 |
0 |
12 |
4.734e-05 |
2.747e-05 |
|||
predict |
-1 |
100 |
100 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
100 |
100 |
20 |
1 |
10 |
0 |
12 |
9.299e-05 |
4.113e-05 |
|||
predict |
-1 |
100 |
200 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
100 |
200 |
3 |
1 |
10 |
0 |
12 |
4.589e-05 |
3.208e-05 |
|||
predict |
-1 |
100 |
200 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
100 |
200 |
10 |
1 |
10 |
0 |
12 |
5.535e-05 |
3.382e-05 |
|||
predict |
-1 |
100 |
200 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
100 |
200 |
20 |
1 |
10 |
0 |
12 |
0.0001004 |
4.768e-05 |
|||
predict |
-1 |
1000 |
1 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1000 |
1 |
3 |
1 |
10 |
0 |
12 |
6.036e-05 |
2.615e-05 |
|||
predict |
-1 |
1000 |
1 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1000 |
1 |
10 |
1 |
10 |
0 |
12 |
0.0001052 |
3.74e-05 |
|||
predict |
-1 |
1000 |
1 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1000 |
1 |
20 |
1 |
10 |
0 |
12 |
0.0002113 |
7.175e-05 |
|||
predict |
-1 |
1000 |
5 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1000 |
5 |
3 |
1 |
10 |
0 |
12 |
6.355e-05 |
2.744e-05 |
|||
predict |
-1 |
1000 |
5 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1000 |
5 |
10 |
1 |
10 |
0 |
12 |
0.0001276 |
4.651e-05 |
|||
predict |
-1 |
1000 |
5 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1000 |
5 |
20 |
1 |
10 |
0 |
12 |
0.0004054 |
0.0001241 |
|||
predict |
-1 |
1000 |
10 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1000 |
10 |
3 |
1 |
10 |
0 |
12 |
6.836e-05 |
3.073e-05 |
|||
predict |
-1 |
1000 |
10 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1000 |
10 |
10 |
1 |
10 |
0 |
12 |
0.0001332 |
4.981e-05 |
|||
predict |
-1 |
1000 |
10 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1000 |
10 |
20 |
1 |
10 |
0 |
12 |
0.0004259 |
0.0001358 |
|||
predict |
-1 |
1000 |
20 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1000 |
20 |
3 |
1 |
10 |
0 |
12 |
7.518e-05 |
3.808e-05 |
|||
predict |
-1 |
1000 |
20 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1000 |
20 |
10 |
1 |
10 |
0 |
12 |
0.0001386 |
5.544e-05 |
|||
predict |
-1 |
1000 |
20 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1000 |
20 |
20 |
1 |
10 |
0 |
12 |
0.0004373 |
0.0001436 |
|||
predict |
-1 |
1000 |
50 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1000 |
50 |
3 |
1 |
10 |
0 |
12 |
9.536e-05 |
5.581e-05 |
|||
predict |
-1 |
1000 |
50 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1000 |
50 |
10 |
1 |
10 |
0 |
12 |
0.0001637 |
7.451e-05 |
|||
predict |
-1 |
1000 |
50 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1000 |
50 |
20 |
1 |
10 |
0 |
12 |
0.0005401 |
0.0001822 |
|||
predict |
-1 |
1000 |
100 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1000 |
100 |
3 |
1 |
10 |
0 |
12 |
0.0001343 |
9.903e-05 |
|||
predict |
-1 |
1000 |
100 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1000 |
100 |
10 |
1 |
10 |
0 |
12 |
0.0001983 |
0.0001176 |
|||
predict |
-1 |
1000 |
100 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1000 |
100 |
20 |
1 |
10 |
0 |
12 |
0.0004948 |
0.0001868 |
|||
predict |
-1 |
1000 |
200 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1000 |
200 |
3 |
1 |
10 |
0 |
12 |
0.0002113 |
0.0001643 |
|||
predict |
-1 |
1000 |
200 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1000 |
200 |
10 |
1 |
10 |
0 |
12 |
0.0002732 |
0.0001872 |
|||
predict |
-1 |
1000 |
200 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
1000 |
200 |
20 |
1 |
10 |
0 |
12 |
0.0005666 |
0.0002624 |
|||
predict |
-1 |
10000 |
1 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10000 |
1 |
3 |
1 |
10 |
0 |
12 |
0.0003443 |
9.876e-05 |
|||
predict |
-1 |
10000 |
1 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10000 |
1 |
10 |
1 |
10 |
0 |
12 |
0.0007122 |
0.0001695 |
|||
predict |
-1 |
10000 |
1 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10000 |
1 |
20 |
1 |
10 |
0 |
12 |
0.00162 |
0.0003958 |
|||
predict |
-1 |
10000 |
5 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10000 |
5 |
3 |
1 |
10 |
0 |
12 |
0.0003777 |
0.0001402 |
|||
predict |
-1 |
10000 |
5 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10000 |
5 |
10 |
1 |
10 |
0 |
12 |
0.0009206 |
0.0002507 |
|||
predict |
-1 |
10000 |
5 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10000 |
5 |
20 |
1 |
10 |
0 |
12 |
0.002965 |
0.0008024 |
|||
predict |
-1 |
10000 |
10 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10000 |
10 |
3 |
1 |
10 |
0 |
12 |
0.0004114 |
0.0001555 |
|||
predict |
-1 |
10000 |
10 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10000 |
10 |
10 |
1 |
10 |
0 |
12 |
0.0009831 |
0.0002969 |
|||
predict |
-1 |
10000 |
10 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10000 |
10 |
20 |
1 |
10 |
0 |
12 |
0.003278 |
0.0009183 |
|||
predict |
-1 |
10000 |
20 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10000 |
20 |
3 |
1 |
10 |
0 |
12 |
0.0004735 |
0.0002261 |
|||
predict |
-1 |
10000 |
20 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10000 |
20 |
10 |
1 |
10 |
0 |
12 |
0.001044 |
0.0003622 |
|||
predict |
-1 |
10000 |
20 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10000 |
20 |
20 |
1 |
10 |
0 |
12 |
0.003502 |
0.001036 |
|||
predict |
-1 |
10000 |
50 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10000 |
50 |
3 |
1 |
10 |
0 |
12 |
0.0006777 |
0.0004291 |
|||
predict |
-1 |
10000 |
50 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10000 |
50 |
10 |
1 |
10 |
0 |
12 |
0.001277 |
0.0005626 |
|||
predict |
-1 |
10000 |
50 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10000 |
50 |
20 |
1 |
10 |
0 |
12 |
0.004109 |
0.001362 |
|||
predict |
-1 |
10000 |
100 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10000 |
100 |
3 |
1 |
10 |
0 |
12 |
0.001114 |
0.0008403 |
|||
predict |
-1 |
10000 |
100 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10000 |
100 |
10 |
1 |
10 |
0 |
12 |
0.001682 |
0.0009601 |
|||
predict |
-1 |
10000 |
100 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10000 |
100 |
20 |
1 |
10 |
0 |
12 |
0.005157 |
0.001865 |
|||
predict |
-1 |
10000 |
200 |
3 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10000 |
200 |
3 |
1 |
10 |
0 |
12 |
0.002316 |
0.001861 |
|||
predict |
-1 |
10000 |
200 |
10 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10000 |
200 |
10 |
1 |
10 |
0 |
12 |
0.002888 |
0.001973 |
|||
predict |
-1 |
10000 |
200 |
20 |
1 |
10 |
0 |
-1 |
|||||
predict |
-1 |
10000 |
200 |
20 |
1 |
10 |
0 |
12 |
0.005932 |
0.002932 |
|||
predict |
1 |
1 |
1 |
3 |
1 |
10 |
0 |
-1 |
6.865e-05 |
||||
predict |
1 |
1 |
1 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1 |
1 |
10 |
1 |
10 |
0 |
-1 |
5.308e-05 |
||||
predict |
1 |
1 |
1 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1 |
1 |
20 |
1 |
10 |
0 |
-1 |
5.709e-05 |
||||
predict |
1 |
1 |
1 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1 |
5 |
3 |
1 |
10 |
0 |
-1 |
7.351e-05 |
||||
predict |
1 |
1 |
5 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1 |
5 |
10 |
1 |
10 |
0 |
-1 |
5.488e-05 |
||||
predict |
1 |
1 |
5 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1 |
5 |
20 |
1 |
10 |
0 |
-1 |
6.255e-05 |
||||
predict |
1 |
1 |
5 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1 |
10 |
3 |
1 |
10 |
0 |
-1 |
0.0001097 |
||||
predict |
1 |
1 |
10 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1 |
10 |
10 |
1 |
10 |
0 |
-1 |
5.641e-05 |
||||
predict |
1 |
1 |
10 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1 |
10 |
20 |
1 |
10 |
0 |
-1 |
5.938e-05 |
||||
predict |
1 |
1 |
10 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1 |
20 |
3 |
1 |
10 |
0 |
-1 |
0.0001232 |
||||
predict |
1 |
1 |
20 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1 |
20 |
10 |
1 |
10 |
0 |
-1 |
5.663e-05 |
||||
predict |
1 |
1 |
20 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1 |
20 |
20 |
1 |
10 |
0 |
-1 |
5.753e-05 |
||||
predict |
1 |
1 |
20 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1 |
50 |
3 |
1 |
10 |
0 |
-1 |
0.000122 |
||||
predict |
1 |
1 |
50 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1 |
50 |
10 |
1 |
10 |
0 |
-1 |
5.732e-05 |
||||
predict |
1 |
1 |
50 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1 |
50 |
20 |
1 |
10 |
0 |
-1 |
6.766e-05 |
||||
predict |
1 |
1 |
50 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1 |
100 |
3 |
1 |
10 |
0 |
-1 |
0.000114 |
||||
predict |
1 |
1 |
100 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1 |
100 |
10 |
1 |
10 |
0 |
-1 |
5.591e-05 |
||||
predict |
1 |
1 |
100 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1 |
100 |
20 |
1 |
10 |
0 |
-1 |
6.105e-05 |
||||
predict |
1 |
1 |
100 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1 |
200 |
3 |
1 |
10 |
0 |
-1 |
6.116e-05 |
||||
predict |
1 |
1 |
200 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1 |
200 |
10 |
1 |
10 |
0 |
-1 |
5.9e-05 |
||||
predict |
1 |
1 |
200 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1 |
200 |
20 |
1 |
10 |
0 |
-1 |
5.764e-05 |
||||
predict |
1 |
1 |
200 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10 |
1 |
3 |
1 |
10 |
0 |
-1 |
5.172e-05 |
||||
predict |
1 |
10 |
1 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10 |
1 |
10 |
1 |
10 |
0 |
-1 |
5.271e-05 |
||||
predict |
1 |
10 |
1 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10 |
1 |
20 |
1 |
10 |
0 |
-1 |
5.666e-05 |
||||
predict |
1 |
10 |
1 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10 |
5 |
3 |
1 |
10 |
0 |
-1 |
5.202e-05 |
||||
predict |
1 |
10 |
5 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10 |
5 |
10 |
1 |
10 |
0 |
-1 |
5.312e-05 |
||||
predict |
1 |
10 |
5 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10 |
5 |
20 |
1 |
10 |
0 |
-1 |
5.869e-05 |
||||
predict |
1 |
10 |
5 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10 |
10 |
3 |
1 |
10 |
0 |
-1 |
5.137e-05 |
||||
predict |
1 |
10 |
10 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10 |
10 |
10 |
1 |
10 |
0 |
-1 |
5.599e-05 |
||||
predict |
1 |
10 |
10 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10 |
10 |
20 |
1 |
10 |
0 |
-1 |
5.897e-05 |
||||
predict |
1 |
10 |
10 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10 |
20 |
3 |
1 |
10 |
0 |
-1 |
5.103e-05 |
||||
predict |
1 |
10 |
20 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10 |
20 |
10 |
1 |
10 |
0 |
-1 |
5.359e-05 |
||||
predict |
1 |
10 |
20 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10 |
20 |
20 |
1 |
10 |
0 |
-1 |
5.81e-05 |
||||
predict |
1 |
10 |
20 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10 |
50 |
3 |
1 |
10 |
0 |
-1 |
5.426e-05 |
||||
predict |
1 |
10 |
50 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10 |
50 |
10 |
1 |
10 |
0 |
-1 |
5.473e-05 |
||||
predict |
1 |
10 |
50 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10 |
50 |
20 |
1 |
10 |
0 |
-1 |
6.08e-05 |
||||
predict |
1 |
10 |
50 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10 |
100 |
3 |
1 |
10 |
0 |
-1 |
5.311e-05 |
||||
predict |
1 |
10 |
100 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10 |
100 |
10 |
1 |
10 |
0 |
-1 |
5.403e-05 |
||||
predict |
1 |
10 |
100 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10 |
100 |
20 |
1 |
10 |
0 |
-1 |
5.844e-05 |
||||
predict |
1 |
10 |
100 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10 |
200 |
3 |
1 |
10 |
0 |
-1 |
5.325e-05 |
||||
predict |
1 |
10 |
200 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10 |
200 |
10 |
1 |
10 |
0 |
-1 |
5.593e-05 |
||||
predict |
1 |
10 |
200 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10 |
200 |
20 |
1 |
10 |
0 |
-1 |
5.983e-05 |
||||
predict |
1 |
10 |
200 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
100 |
1 |
3 |
1 |
10 |
0 |
-1 |
5.455e-05 |
||||
predict |
1 |
100 |
1 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
100 |
1 |
10 |
1 |
10 |
0 |
-1 |
6.076e-05 |
||||
predict |
1 |
100 |
1 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
100 |
1 |
20 |
1 |
10 |
0 |
-1 |
8.118e-05 |
||||
predict |
1 |
100 |
1 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
100 |
5 |
3 |
1 |
10 |
0 |
-1 |
5.523e-05 |
||||
predict |
1 |
100 |
5 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
100 |
5 |
10 |
1 |
10 |
0 |
-1 |
6.426e-05 |
||||
predict |
1 |
100 |
5 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
100 |
5 |
20 |
1 |
10 |
0 |
-1 |
0.0001035 |
||||
predict |
1 |
100 |
5 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
100 |
10 |
3 |
1 |
10 |
0 |
-1 |
5.498e-05 |
||||
predict |
1 |
100 |
10 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
100 |
10 |
10 |
1 |
10 |
0 |
-1 |
6.45e-05 |
||||
predict |
1 |
100 |
10 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
100 |
10 |
20 |
1 |
10 |
0 |
-1 |
0.0001052 |
||||
predict |
1 |
100 |
10 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
100 |
20 |
3 |
1 |
10 |
0 |
-1 |
5.518e-05 |
||||
predict |
1 |
100 |
20 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
100 |
20 |
10 |
1 |
10 |
0 |
-1 |
6.517e-05 |
||||
predict |
1 |
100 |
20 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
100 |
20 |
20 |
1 |
10 |
0 |
-1 |
0.0001047 |
||||
predict |
1 |
100 |
20 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
100 |
50 |
3 |
1 |
10 |
0 |
-1 |
5.787e-05 |
||||
predict |
1 |
100 |
50 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
100 |
50 |
10 |
1 |
10 |
0 |
-1 |
6.776e-05 |
||||
predict |
1 |
100 |
50 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
100 |
50 |
20 |
1 |
10 |
0 |
-1 |
0.0001057 |
||||
predict |
1 |
100 |
50 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
100 |
100 |
3 |
1 |
10 |
0 |
-1 |
6.089e-05 |
||||
predict |
1 |
100 |
100 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
100 |
100 |
10 |
1 |
10 |
0 |
-1 |
7.053e-05 |
||||
predict |
1 |
100 |
100 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
100 |
100 |
20 |
1 |
10 |
0 |
-1 |
0.0001028 |
||||
predict |
1 |
100 |
100 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
100 |
200 |
3 |
1 |
10 |
0 |
-1 |
6.732e-05 |
||||
predict |
1 |
100 |
200 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
100 |
200 |
10 |
1 |
10 |
0 |
-1 |
7.664e-05 |
||||
predict |
1 |
100 |
200 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
100 |
200 |
20 |
1 |
10 |
0 |
-1 |
0.0001099 |
||||
predict |
1 |
100 |
200 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1000 |
1 |
3 |
1 |
10 |
0 |
-1 |
8.031e-05 |
||||
predict |
1 |
1000 |
1 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1000 |
1 |
10 |
1 |
10 |
0 |
-1 |
0.000127 |
||||
predict |
1 |
1000 |
1 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1000 |
1 |
20 |
1 |
10 |
0 |
-1 |
0.0002263 |
||||
predict |
1 |
1000 |
1 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1000 |
5 |
3 |
1 |
10 |
0 |
-1 |
8.431e-05 |
||||
predict |
1 |
1000 |
5 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1000 |
5 |
10 |
1 |
10 |
0 |
-1 |
0.000148 |
||||
predict |
1 |
1000 |
5 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1000 |
5 |
20 |
1 |
10 |
0 |
-1 |
0.000355 |
||||
predict |
1 |
1000 |
5 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1000 |
10 |
3 |
1 |
10 |
0 |
-1 |
8.425e-05 |
||||
predict |
1 |
1000 |
10 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1000 |
10 |
10 |
1 |
10 |
0 |
-1 |
0.0001512 |
||||
predict |
1 |
1000 |
10 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1000 |
10 |
20 |
1 |
10 |
0 |
-1 |
0.0003756 |
||||
predict |
1 |
1000 |
10 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1000 |
20 |
3 |
1 |
10 |
0 |
-1 |
9.148e-05 |
||||
predict |
1 |
1000 |
20 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1000 |
20 |
10 |
1 |
10 |
0 |
-1 |
0.0001575 |
||||
predict |
1 |
1000 |
20 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1000 |
20 |
20 |
1 |
10 |
0 |
-1 |
0.0003894 |
||||
predict |
1 |
1000 |
20 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1000 |
50 |
3 |
1 |
10 |
0 |
-1 |
0.0001124 |
||||
predict |
1 |
1000 |
50 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1000 |
50 |
10 |
1 |
10 |
0 |
-1 |
0.0001819 |
||||
predict |
1 |
1000 |
50 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1000 |
50 |
20 |
1 |
10 |
0 |
-1 |
0.000467 |
||||
predict |
1 |
1000 |
50 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1000 |
100 |
3 |
1 |
10 |
0 |
-1 |
0.0001692 |
||||
predict |
1 |
1000 |
100 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1000 |
100 |
10 |
1 |
10 |
0 |
-1 |
0.0002373 |
||||
predict |
1 |
1000 |
100 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1000 |
100 |
20 |
1 |
10 |
0 |
-1 |
0.0004488 |
||||
predict |
1 |
1000 |
100 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1000 |
200 |
3 |
1 |
10 |
0 |
-1 |
0.0002454 |
||||
predict |
1 |
1000 |
200 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1000 |
200 |
10 |
1 |
10 |
0 |
-1 |
0.0003143 |
||||
predict |
1 |
1000 |
200 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
1000 |
200 |
20 |
1 |
10 |
0 |
-1 |
0.0005299 |
||||
predict |
1 |
1000 |
200 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10000 |
1 |
3 |
1 |
10 |
0 |
-1 |
0.0002954 |
||||
predict |
1 |
10000 |
1 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10000 |
1 |
10 |
1 |
10 |
0 |
-1 |
0.0007131 |
||||
predict |
1 |
10000 |
1 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10000 |
1 |
20 |
1 |
10 |
0 |
-1 |
0.001525 |
||||
predict |
1 |
10000 |
1 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10000 |
5 |
3 |
1 |
10 |
0 |
-1 |
0.0003198 |
||||
predict |
1 |
10000 |
5 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10000 |
5 |
10 |
1 |
10 |
0 |
-1 |
0.0009482 |
||||
predict |
1 |
10000 |
5 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10000 |
5 |
20 |
1 |
10 |
0 |
-1 |
0.002539 |
||||
predict |
1 |
10000 |
5 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10000 |
10 |
3 |
1 |
10 |
0 |
-1 |
0.0003728 |
||||
predict |
1 |
10000 |
10 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10000 |
10 |
10 |
1 |
10 |
0 |
-1 |
0.001008 |
||||
predict |
1 |
10000 |
10 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10000 |
10 |
20 |
1 |
10 |
0 |
-1 |
0.002761 |
||||
predict |
1 |
10000 |
10 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10000 |
20 |
3 |
1 |
10 |
0 |
-1 |
0.000439 |
||||
predict |
1 |
10000 |
20 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10000 |
20 |
10 |
1 |
10 |
0 |
-1 |
0.001073 |
||||
predict |
1 |
10000 |
20 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10000 |
20 |
20 |
1 |
10 |
0 |
-1 |
0.002989 |
||||
predict |
1 |
10000 |
20 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10000 |
50 |
3 |
1 |
10 |
0 |
-1 |
0.0006492 |
||||
predict |
1 |
10000 |
50 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10000 |
50 |
10 |
1 |
10 |
0 |
-1 |
0.001287 |
||||
predict |
1 |
10000 |
50 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10000 |
50 |
20 |
1 |
10 |
0 |
-1 |
0.003393 |
||||
predict |
1 |
10000 |
50 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10000 |
100 |
3 |
1 |
10 |
0 |
-1 |
0.001142 |
||||
predict |
1 |
10000 |
100 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10000 |
100 |
10 |
1 |
10 |
0 |
-1 |
0.001754 |
||||
predict |
1 |
10000 |
100 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10000 |
100 |
20 |
1 |
10 |
0 |
-1 |
0.004283 |
||||
predict |
1 |
10000 |
100 |
20 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10000 |
200 |
3 |
1 |
10 |
0 |
-1 |
0.002168 |
||||
predict |
1 |
10000 |
200 |
3 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10000 |
200 |
10 |
1 |
10 |
0 |
-1 |
0.002816 |
||||
predict |
1 |
10000 |
200 |
10 |
1 |
10 |
0 |
12 |
|||||
predict |
1 |
10000 |
200 |
20 |
1 |
10 |
0 |
-1 |
0.005127 |
||||
predict |
1 |
10000 |
200 |
20 |
1 |
10 |
0 |
12 |
<<<
from pyquickhelper.pandashelper import df2rst
import pandas
name = os.path.join(
__WD__, "../../onnx/results/bench_plot_onnxruntime_decision_tree_reg.perf.csv")
df = pandas.read_csv(name)
df = df[df['lib'] == 'skl']
print(df2rst(df, number_format=4))
method |
lib |
skl_nb_base_estimators |
skl_dt_nodes |
N |
dim |
max_depth |
repeat |
number |
min |
max |
min3 |
max3 |
mean |
lower |
upper |
count |
median |
error_c |
onnx_nodes |
onnx_opset |
ort_size |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
predict |
skl |
1 |
15 |
1 |
1 |
3 |
10 |
1 |
4.757e-05 |
0.0002056 |
4.991e-05 |
6.299e-05 |
6.865e-05 |
4.757e-05 |
0.000159 |
10 |
5.239e-05 |
0 |
|||
predict |
skl |
1 |
15 |
10 |
1 |
3 |
10 |
1 |
4.72e-05 |
6.664e-05 |
4.86e-05 |
5.326e-05 |
5.172e-05 |
4.72e-05 |
6.281e-05 |
10 |
4.946e-05 |
0 |
|||
predict |
skl |
1 |
15 |
100 |
1 |
3 |
10 |
1 |
4.915e-05 |
7.383e-05 |
5.092e-05 |
5.478e-05 |
5.455e-05 |
4.915e-05 |
6.849e-05 |
10 |
5.253e-05 |
0 |
|||
predict |
skl |
1 |
15 |
1000 |
1 |
3 |
10 |
1 |
7.739e-05 |
9.535e-05 |
7.833e-05 |
7.882e-05 |
8.031e-05 |
7.739e-05 |
9.036e-05 |
10 |
7.849e-05 |
0 |
|||
predict |
skl |
1 |
15 |
10000 |
1 |
3 |
10 |
1 |
0.0002853 |
0.0003136 |
0.0002871 |
0.0003049 |
0.0002954 |
0.0002853 |
0.0003136 |
10 |
0.0002899 |
0 |
|||
predict |
skl |
1 |
1473 |
1 |
1 |
10 |
10 |
1 |
4.674e-05 |
8.29e-05 |
4.862e-05 |
5.242e-05 |
5.308e-05 |
4.674e-05 |
7.325e-05 |
10 |
4.911e-05 |
0 |
|||
predict |
skl |
1 |
1473 |
10 |
1 |
10 |
10 |
1 |
4.862e-05 |
6.559e-05 |
5.018e-05 |
5.373e-05 |
5.271e-05 |
4.862e-05 |
6.23e-05 |
10 |
5.056e-05 |
0 |
|||
predict |
skl |
1 |
1473 |
100 |
1 |
10 |
10 |
1 |
5.641e-05 |
7.299e-05 |
5.849e-05 |
6.143e-05 |
6.076e-05 |
5.641e-05 |
6.994e-05 |
10 |
5.907e-05 |
0 |
|||
predict |
skl |
1 |
1473 |
1000 |
1 |
10 |
10 |
1 |
0.0001214 |
0.0001424 |
0.0001229 |
0.0001285 |
0.000127 |
0.0001214 |
0.0001386 |
10 |
0.0001256 |
0 |
|||
predict |
skl |
1 |
1473 |
10000 |
1 |
10 |
10 |
1 |
0.0006987 |
0.0007801 |
0.0007013 |
0.0007078 |
0.0007131 |
0.0006987 |
0.0007594 |
10 |
0.0007053 |
0 |
|||
predict |
skl |
1 |
2.83e+04 |
1 |
1 |
20 |
10 |
1 |
4.683e-05 |
0.00012 |
4.893e-05 |
5.275e-05 |
5.709e-05 |
4.683e-05 |
9.856e-05 |
10 |
4.93e-05 |
0 |
|||
predict |
skl |
1 |
2.83e+04 |
10 |
1 |
20 |
10 |
1 |
5.075e-05 |
7.017e-05 |
5.388e-05 |
5.829e-05 |
5.666e-05 |
5.075e-05 |
6.717e-05 |
10 |
5.536e-05 |
0 |
|||
predict |
skl |
1 |
2.83e+04 |
100 |
1 |
20 |
10 |
1 |
7.121e-05 |
9.604e-05 |
7.694e-05 |
8.517e-05 |
8.118e-05 |
7.121e-05 |
9.441e-05 |
10 |
8.03e-05 |
0 |
|||
predict |
skl |
1 |
2.83e+04 |
1000 |
1 |
20 |
10 |
1 |
0.0002136 |
0.0002596 |
0.0002189 |
0.0002304 |
0.0002263 |
0.0002136 |
0.0002522 |
10 |
0.000221 |
0 |
|||
predict |
skl |
1 |
2.83e+04 |
10000 |
1 |
20 |
10 |
1 |
0.001492 |
0.001678 |
0.001499 |
0.001532 |
0.001525 |
0.001492 |
0.001629 |
10 |
0.001502 |
0 |
|||
predict |
skl |
1 |
15 |
1 |
5 |
3 |
10 |
1 |
4.63e-05 |
0.000163 |
4.922e-05 |
0.0001078 |
7.351e-05 |
4.63e-05 |
0.0001488 |
10 |
5.059e-05 |
0 |
|||
predict |
skl |
1 |
15 |
10 |
5 |
3 |
10 |
1 |
4.724e-05 |
7.067e-05 |
4.879e-05 |
5.191e-05 |
5.202e-05 |
4.724e-05 |
6.533e-05 |
10 |
4.918e-05 |
0 |
|||
predict |
skl |
1 |
15 |
100 |
5 |
3 |
10 |
1 |
5.026e-05 |
6.904e-05 |
5.318e-05 |
5.576e-05 |
5.523e-05 |
5.026e-05 |
6.543e-05 |
10 |
5.326e-05 |
0 |
|||
predict |
skl |
1 |
15 |
1000 |
5 |
3 |
10 |
1 |
7.782e-05 |
0.0001001 |
7.958e-05 |
8.559e-05 |
8.431e-05 |
7.782e-05 |
9.94e-05 |
10 |
8.09e-05 |
0 |
|||
predict |
skl |
1 |
15 |
10000 |
5 |
3 |
10 |
1 |
0.000307 |
0.0003843 |
0.0003095 |
0.0003168 |
0.0003198 |
0.000307 |
0.0003642 |
10 |
0.0003098 |
0 |
|||
predict |
skl |
1 |
2047 |
1 |
5 |
10 |
10 |
1 |
4.615e-05 |
0.0001014 |
4.772e-05 |
5.305e-05 |
5.488e-05 |
4.615e-05 |
8.587e-05 |
10 |
4.979e-05 |
0 |
|||
predict |
skl |
1 |
2047 |
10 |
5 |
10 |
10 |
1 |
4.816e-05 |
6.672e-05 |
4.975e-05 |
5.504e-05 |
5.312e-05 |
4.816e-05 |
6.376e-05 |
10 |
5.106e-05 |
0 |
|||
predict |
skl |
1 |
2047 |
100 |
5 |
10 |
10 |
1 |
5.989e-05 |
7.911e-05 |
6.07e-05 |
6.599e-05 |
6.426e-05 |
5.989e-05 |
7.551e-05 |
10 |
6.179e-05 |
0 |
|||
predict |
skl |
1 |
2047 |
1000 |
5 |
10 |
10 |
1 |
0.0001433 |
0.0001616 |
0.0001446 |
0.0001489 |
0.000148 |
0.0001433 |
0.00016 |
10 |
0.0001455 |
0 |
|||
predict |
skl |
1 |
2047 |
10000 |
5 |
10 |
10 |
1 |
0.0009333 |
0.001012 |
0.0009375 |
0.0009446 |
0.0009482 |
0.0009333 |
0.0009917 |
10 |
0.0009407 |
0 |
|||
predict |
skl |
1 |
1.349e+05 |
1 |
5 |
20 |
10 |
1 |
4.763e-05 |
0.0001224 |
4.961e-05 |
6.606e-05 |
6.255e-05 |
4.763e-05 |
0.0001071 |
10 |
5.109e-05 |
0 |
|||
predict |
skl |
1 |
1.349e+05 |
10 |
5 |
20 |
10 |
1 |
5.367e-05 |
7.318e-05 |
5.598e-05 |
6.026e-05 |
5.869e-05 |
5.367e-05 |
6.963e-05 |
10 |
5.634e-05 |
0 |
|||
predict |
skl |
1 |
1.349e+05 |
100 |
5 |
20 |
10 |
1 |
9.43e-05 |
0.0001253 |
9.755e-05 |
0.0001078 |
0.0001035 |
9.43e-05 |
0.0001212 |
10 |
0.0001005 |
0 |
|||
predict |
skl |
1 |
1.349e+05 |
1000 |
5 |
20 |
10 |
1 |
0.0003151 |
0.0004574 |
0.0003245 |
0.0003644 |
0.000355 |
0.0003151 |
0.0004387 |
10 |
0.0003401 |
0 |
|||
predict |
skl |
1 |
1.349e+05 |
10000 |
5 |
20 |
10 |
1 |
0.002423 |
0.003233 |
0.002448 |
0.002473 |
0.002539 |
0.002423 |
0.003001 |
10 |
0.002449 |
0 |
|||
predict |
skl |
1 |
15 |
1 |
10 |
3 |
10 |
1 |
4.718e-05 |
0.0003127 |
4.833e-05 |
0.0001322 |
0.0001097 |
4.718e-05 |
0.0002824 |
10 |
5.318e-05 |
0 |
|||
predict |
skl |
1 |
15 |
10 |
10 |
3 |
10 |
1 |
4.649e-05 |
7.005e-05 |
4.786e-05 |
5.188e-05 |
5.137e-05 |
4.649e-05 |
6.45e-05 |
10 |
4.861e-05 |
0 |
|||
predict |
skl |
1 |
15 |
100 |
10 |
3 |
10 |
1 |
5.077e-05 |
7.013e-05 |
5.148e-05 |
5.819e-05 |
5.498e-05 |
5.077e-05 |
6.621e-05 |
10 |
5.204e-05 |
0 |
|||
predict |
skl |
1 |
15 |
1000 |
10 |
3 |
10 |
1 |
8.057e-05 |
0.0001002 |
8.137e-05 |
8.461e-05 |
8.425e-05 |
8.057e-05 |
9.542e-05 |
10 |
8.188e-05 |
0 |
|||
predict |
skl |
1 |
15 |
10000 |
10 |
3 |
10 |
1 |
0.0003463 |
0.00049 |
0.000356 |
0.0003714 |
0.0003728 |
0.0003463 |
0.0004513 |
10 |
0.0003613 |
0 |
|||
predict |
skl |
1 |
2047 |
1 |
10 |
10 |
10 |
1 |
4.654e-05 |
0.0001122 |
4.901e-05 |
5.322e-05 |
5.641e-05 |
4.654e-05 |
9.334e-05 |
10 |
4.99e-05 |
0 |
|||
predict |
skl |
1 |
2047 |
10 |
10 |
10 |
10 |
1 |
4.91e-05 |
7.42e-05 |
5.077e-05 |
5.807e-05 |
5.599e-05 |
4.91e-05 |
7.144e-05 |
10 |
5.234e-05 |
0 |
|||
predict |
skl |
1 |
2047 |
100 |
10 |
10 |
10 |
1 |
6.008e-05 |
8.279e-05 |
6.063e-05 |
6.489e-05 |
6.45e-05 |
6.008e-05 |
7.756e-05 |
10 |
6.168e-05 |
0 |
|||
predict |
skl |
1 |
2047 |
1000 |
10 |
10 |
10 |
1 |
0.0001475 |
0.0001653 |
0.0001487 |
0.0001511 |
0.0001512 |
0.0001475 |
0.000161 |
10 |
0.0001492 |
0 |
|||
predict |
skl |
1 |
2047 |
10000 |
10 |
10 |
10 |
1 |
0.00098 |
0.001136 |
0.0009938 |
0.001002 |
0.001008 |
0.00098 |
0.001093 |
10 |
0.0009984 |
0 |
|||
predict |
skl |
1 |
1.57e+05 |
1 |
10 |
20 |
10 |
1 |
4.829e-05 |
0.0001389 |
4.935e-05 |
5.243e-05 |
5.938e-05 |
4.829e-05 |
0.0001115 |
10 |
4.989e-05 |
0 |
|||
predict |
skl |
1 |
1.57e+05 |
10 |
10 |
20 |
10 |
1 |
5.464e-05 |
7.357e-05 |
5.582e-05 |
5.977e-05 |
5.897e-05 |
5.464e-05 |
6.985e-05 |
10 |
5.664e-05 |
0 |
|||
predict |
skl |
1 |
1.57e+05 |
100 |
10 |
20 |
10 |
1 |
9.265e-05 |
0.0001297 |
9.859e-05 |
0.0001153 |
0.0001052 |
9.265e-05 |
0.0001273 |
10 |
0.0001014 |
0 |
|||
predict |
skl |
1 |
1.57e+05 |
1000 |
10 |
20 |
10 |
1 |
0.0003355 |
0.0004778 |
0.0003482 |
0.0003878 |
0.0003756 |
0.0003355 |
0.0004578 |
10 |
0.0003615 |
0 |
|||
predict |
skl |
1 |
1.57e+05 |
10000 |
10 |
20 |
10 |
1 |
0.00265 |
0.003491 |
0.002661 |
0.002704 |
0.002761 |
0.00265 |
0.003241 |
10 |
0.002668 |
0 |
|||
predict |
skl |
1 |
15 |
1 |
20 |
3 |
10 |
1 |
4.801e-05 |
0.0003809 |
5.114e-05 |
0.0001436 |
0.0001232 |
4.801e-05 |
0.000328 |
10 |
6.928e-05 |
0 |
|||
predict |
skl |
1 |
15 |
10 |
20 |
3 |
10 |
1 |
4.684e-05 |
6.504e-05 |
4.812e-05 |
5.264e-05 |
5.103e-05 |
4.684e-05 |
6.166e-05 |
10 |
4.862e-05 |
0 |
|||
predict |
skl |
1 |
15 |
100 |
20 |
3 |
10 |
1 |
5.134e-05 |
7.133e-05 |
5.2e-05 |
5.563e-05 |
5.518e-05 |
5.134e-05 |
6.662e-05 |
10 |
5.269e-05 |
0 |
|||
predict |
skl |
1 |
15 |
1000 |
20 |
3 |
10 |
1 |
8.707e-05 |
0.0001107 |
8.837e-05 |
9.322e-05 |
9.148e-05 |
8.707e-05 |
0.0001047 |
10 |
8.884e-05 |
0 |
|||
predict |
skl |
1 |
15 |
10000 |
20 |
3 |
10 |
1 |
0.0004069 |
0.0006 |
0.000417 |
0.0004321 |
0.000439 |
0.0004069 |
0.0005459 |
10 |
0.0004247 |
0 |
|||
predict |
skl |
1 |
2047 |
1 |
20 |
10 |
10 |
1 |
4.714e-05 |
0.000103 |
4.967e-05 |
5.681e-05 |
5.663e-05 |
4.714e-05 |
8.761e-05 |
10 |
5.143e-05 |
0 |
|||
predict |
skl |
1 |
2047 |
10 |
20 |
10 |
10 |
1 |
4.88e-05 |
6.684e-05 |
5.068e-05 |
5.541e-05 |
5.359e-05 |
4.88e-05 |
6.374e-05 |
10 |
5.182e-05 |
0 |
|||
predict |
skl |
1 |
2047 |
100 |
20 |
10 |
10 |
1 |
6.115e-05 |
8.087e-05 |
6.237e-05 |
6.51e-05 |
6.517e-05 |
6.115e-05 |
7.627e-05 |
10 |
6.262e-05 |
0 |
|||
predict |
skl |
1 |
2047 |
1000 |
20 |
10 |
10 |
1 |
0.0001537 |
0.0001724 |
0.0001544 |
0.0001595 |
0.0001575 |
0.0001537 |
0.000168 |
10 |
0.000155 |
0 |
|||
predict |
skl |
1 |
2047 |
10000 |
20 |
10 |
10 |
1 |
0.001039 |
0.001245 |
0.001052 |
0.00107 |
0.001073 |
0.001039 |
0.001188 |
10 |
0.001055 |
0 |
|||
predict |
skl |
1 |
1.603e+05 |
1 |
20 |
20 |
10 |
1 |
4.739e-05 |
0.0001224 |
4.883e-05 |
5.322e-05 |
5.753e-05 |
4.739e-05 |
0.0001003 |
10 |
4.932e-05 |
0 |
|||
predict |
skl |
1 |
1.603e+05 |
10 |
20 |
20 |
10 |
1 |
5.401e-05 |
7.334e-05 |
5.502e-05 |
5.907e-05 |
5.81e-05 |
5.401e-05 |
6.96e-05 |
10 |
5.569e-05 |
0 |
|||
predict |
skl |
1 |
1.603e+05 |
100 |
20 |
20 |
10 |
1 |
9.523e-05 |
0.0001314 |
9.947e-05 |
0.0001086 |
0.0001047 |
9.523e-05 |
0.0001247 |
10 |
0.0001003 |
0 |
|||
predict |
skl |
1 |
1.603e+05 |
1000 |
20 |
20 |
10 |
1 |
0.0003478 |
0.0005039 |
0.0003614 |
0.0004071 |
0.0003894 |
0.0003478 |
0.0004793 |
10 |
0.0003751 |
0 |
|||
predict |
skl |
1 |
1.603e+05 |
10000 |
20 |
20 |
10 |
1 |
0.002883 |
0.003689 |
0.002897 |
0.002933 |
0.002989 |
0.002883 |
0.003449 |
10 |
0.002904 |
0 |
|||
predict |
skl |
1 |
15 |
1 |
50 |
3 |
10 |
1 |
4.737e-05 |
0.0003189 |
5.115e-05 |
0.000145 |
0.000122 |
4.737e-05 |
0.0002957 |
10 |
9.119e-05 |
0 |
|||
predict |
skl |
1 |
15 |
10 |
50 |
3 |
10 |
1 |
4.787e-05 |
8.871e-05 |
4.897e-05 |
5.278e-05 |
5.426e-05 |
4.787e-05 |
7.748e-05 |
10 |
4.921e-05 |
0 |
|||
predict |
skl |
1 |
15 |
100 |
50 |
3 |
10 |
1 |
5.366e-05 |
7.567e-05 |
5.464e-05 |
5.815e-05 |
5.787e-05 |
5.366e-05 |
7.042e-05 |
10 |
5.497e-05 |
0 |
|||
predict |
skl |
1 |
15 |
1000 |
50 |
3 |
10 |
1 |
0.0001035 |
0.0001605 |
0.0001047 |
0.0001108 |
0.0001124 |
0.0001035 |
0.000145 |
10 |
0.000105 |
0 |
|||
predict |
skl |
1 |
15 |
10000 |
50 |
3 |
10 |
1 |
0.0006082 |
0.0008501 |
0.0006151 |
0.0006283 |
0.0006492 |
0.0006082 |
0.0007899 |
10 |
0.0006204 |
0 |
|||
predict |
skl |
1 |
2047 |
1 |
50 |
10 |
10 |
1 |
4.675e-05 |
0.0001158 |
4.934e-05 |
5.473e-05 |
5.732e-05 |
4.675e-05 |
9.62e-05 |
10 |
5.005e-05 |
0 |
|||
predict |
skl |
1 |
2047 |
10 |
50 |
10 |
10 |
1 |
4.971e-05 |
7.147e-05 |
5.079e-05 |
5.633e-05 |
5.473e-05 |
4.971e-05 |
6.735e-05 |
10 |
5.18e-05 |
0 |
|||
predict |
skl |
1 |
2047 |
100 |
50 |
10 |
10 |
1 |
6.328e-05 |
8.525e-05 |
6.384e-05 |
6.895e-05 |
6.776e-05 |
6.328e-05 |
8.051e-05 |
10 |
6.483e-05 |
0 |
|||
predict |
skl |
1 |
2047 |
1000 |
50 |
10 |
10 |
1 |
0.0001716 |
0.0002481 |
0.0001719 |
0.000181 |
0.0001819 |
0.0001716 |
0.0002257 |
10 |
0.0001725 |
0 |
|||
predict |
skl |
1 |
2047 |
10000 |
50 |
10 |
10 |
1 |
0.001243 |
0.001506 |
0.001258 |
0.001275 |
0.001287 |
0.001243 |
0.001432 |
10 |
0.001262 |
0 |
|||
predict |
skl |
1 |
1.524e+05 |
1 |
50 |
20 |
10 |
1 |
4.879e-05 |
0.0001284 |
5.149e-05 |
6.575e-05 |
6.766e-05 |
4.879e-05 |
0.0001245 |
10 |
5.284e-05 |
0 |
|||
predict |
skl |
1 |
1.524e+05 |
10 |
50 |
20 |
10 |
1 |
5.38e-05 |
7.677e-05 |
5.654e-05 |
6.544e-05 |
6.08e-05 |
5.38e-05 |
7.379e-05 |
10 |
5.814e-05 |
0 |
|||
predict |
skl |
1 |
1.524e+05 |
100 |
50 |
20 |
10 |
1 |
9.744e-05 |
0.0001289 |
0.0001013 |
0.000108 |
0.0001057 |
9.744e-05 |
0.0001231 |
10 |
0.0001022 |
0 |
|||
predict |
skl |
1 |
1.524e+05 |
1000 |
50 |
20 |
10 |
1 |
0.0004083 |
0.0006255 |
0.0004267 |
0.0004865 |
0.000467 |
0.0004083 |
0.0005883 |
10 |
0.0004465 |
0 |
|||
predict |
skl |
1 |
1.524e+05 |
10000 |
50 |
20 |
10 |
1 |
0.003316 |
0.003799 |
0.003338 |
0.003371 |
0.003393 |
0.003316 |
0.003661 |
10 |
0.003351 |
0 |
|||
predict |
skl |
1 |
15 |
1 |
100 |
3 |
10 |
1 |
4.789e-05 |
0.0003194 |
4.946e-05 |
0.0001396 |
0.000114 |
4.789e-05 |
0.0002964 |
10 |
5.296e-05 |
0 |
|||
predict |
skl |
1 |
15 |
10 |
100 |
3 |
10 |
1 |
4.863e-05 |
7.67e-05 |
4.928e-05 |
5.205e-05 |
5.311e-05 |
4.863e-05 |
6.92e-05 |
10 |
4.958e-05 |
0 |
|||
predict |
skl |
1 |
15 |
100 |
100 |
3 |
10 |
1 |
5.696e-05 |
7.69e-05 |
5.778e-05 |
6.256e-05 |
6.089e-05 |
5.696e-05 |
7.256e-05 |
10 |
5.807e-05 |
0 |
|||
predict |
skl |
1 |
15 |
1000 |
100 |
3 |
10 |
1 |
0.0001384 |
0.000286 |
0.0001549 |
0.0001641 |
0.0001692 |
0.0001384 |
0.0002474 |
10 |
0.0001604 |
0 |
|||
predict |
skl |
1 |
15 |
10000 |
100 |
3 |
10 |
1 |
0.00108 |
0.001337 |
0.001101 |
0.001152 |
0.001142 |
0.00108 |
0.001286 |
10 |
0.001112 |
0 |
|||
predict |
skl |
1 |
2039 |
1 |
100 |
10 |
10 |
1 |
4.677e-05 |
0.0001065 |
4.868e-05 |
5.3e-05 |
5.591e-05 |
4.677e-05 |
8.946e-05 |
10 |
4.991e-05 |
0 |
|||
predict |
skl |
1 |
2039 |
10 |
100 |
10 |
10 |
1 |
4.949e-05 |
7.105e-05 |
5.098e-05 |
5.431e-05 |
5.403e-05 |
4.949e-05 |
6.628e-05 |
10 |
5.113e-05 |
0 |
|||
predict |
skl |
1 |
2039 |
100 |
100 |
10 |
10 |
1 |
6.62e-05 |
8.697e-05 |
6.75e-05 |
7.216e-05 |
7.053e-05 |
6.62e-05 |
8.243e-05 |
10 |
6.79e-05 |
0 |
|||
predict |
skl |
1 |
2039 |
1000 |
100 |
10 |
10 |
1 |
0.0002092 |
0.0003639 |
0.0002221 |
0.0002314 |
0.0002373 |
0.0002092 |
0.0003216 |
10 |
0.0002263 |
0 |
|||
predict |
skl |
1 |
2039 |
10000 |
100 |
10 |
10 |
1 |
0.001684 |
0.001962 |
0.001706 |
0.001761 |
0.001754 |
0.001684 |
0.001909 |
10 |
0.00173 |
0 |
|||
predict |
skl |
1 |
1.487e+05 |
1 |
100 |
20 |
10 |
1 |
4.742e-05 |
0.0001209 |
4.855e-05 |
5.73e-05 |
6.105e-05 |
4.742e-05 |
0.0001059 |
10 |
5.032e-05 |
0 |
|||
predict |
skl |
1 |
1.487e+05 |
10 |
100 |
20 |
10 |
1 |
5.356e-05 |
7.387e-05 |
5.564e-05 |
5.955e-05 |
5.844e-05 |
5.356e-05 |
6.982e-05 |
10 |
5.586e-05 |
0 |
|||
predict |
skl |
1 |
1.487e+05 |
100 |
100 |
20 |
10 |
1 |
9.405e-05 |
0.0001209 |
9.681e-05 |
0.0001049 |
0.0001028 |
9.405e-05 |
0.000119 |
10 |
0.0001 |
0 |
|||
predict |
skl |
1 |
1.487e+05 |
1000 |
100 |
20 |
10 |
1 |
0.0003882 |
0.0007023 |
0.0003992 |
0.0004468 |
0.0004488 |
0.0003882 |
0.0006272 |
10 |
0.0004126 |
0 |
|||
predict |
skl |
1 |
1.487e+05 |
10000 |
100 |
20 |
10 |
1 |
0.004142 |
0.004755 |
0.004182 |
0.004318 |
0.004283 |
0.004142 |
0.004627 |
10 |
0.00421 |
0 |
|||
predict |
skl |
1 |
15 |
1 |
200 |
3 |
10 |
1 |
4.766e-05 |
0.0001326 |
5.065e-05 |
5.61e-05 |
6.116e-05 |
4.766e-05 |
0.000109 |
10 |
5.229e-05 |
0 |
|||
predict |
skl |
1 |
15 |
10 |
200 |
3 |
10 |
1 |
4.892e-05 |
7.046e-05 |
5.002e-05 |
5.391e-05 |
5.325e-05 |
4.892e-05 |
6.551e-05 |
10 |
5.061e-05 |
0 |
|||
predict |
skl |
1 |
15 |
100 |
200 |
3 |
10 |
1 |
6.311e-05 |
8.834e-05 |
6.361e-05 |
6.732e-05 |
6.732e-05 |
6.311e-05 |
8.171e-05 |
10 |
6.398e-05 |
0 |
|||
predict |
skl |
1 |
15 |
1000 |
200 |
3 |
10 |
1 |
0.0002111 |
0.0004009 |
0.0002176 |
0.0002453 |
0.0002454 |
0.0002111 |
0.0003512 |
10 |
0.0002284 |
0 |
|||
predict |
skl |
1 |
15 |
10000 |
200 |
3 |
10 |
1 |
0.002109 |
0.002273 |
0.002131 |
0.002206 |
0.002168 |
0.002109 |
0.002273 |
10 |
0.002142 |
0 |
|||
predict |
skl |
1 |
2007 |
1 |
200 |
10 |
10 |
1 |
4.663e-05 |
0.0001241 |
4.708e-05 |
6.47e-05 |
5.9e-05 |
4.663e-05 |
0.0001042 |
10 |
4.761e-05 |
0 |
|||
predict |
skl |
1 |
2007 |
10 |
200 |
10 |
10 |
1 |
5.086e-05 |
7.613e-05 |
5.24e-05 |
5.614e-05 |
5.593e-05 |
5.086e-05 |
7.006e-05 |
10 |
5.308e-05 |
0 |
|||
predict |
skl |
1 |
2007 |
100 |
200 |
10 |
10 |
1 |
7.229e-05 |
9.461e-05 |
7.389e-05 |
7.676e-05 |
7.664e-05 |
7.229e-05 |
8.921e-05 |
10 |
7.402e-05 |
0 |
|||
predict |
skl |
1 |
2007 |
1000 |
200 |
10 |
10 |
1 |
0.0002791 |
0.0004904 |
0.0002875 |
0.000318 |
0.0003143 |
0.0002791 |
0.0004328 |
10 |
0.0002907 |
0 |
|||
predict |
skl |
1 |
2007 |
10000 |
200 |
10 |
10 |
1 |
0.00275 |
0.002994 |
0.002767 |
0.002892 |
0.002816 |
0.00275 |
0.002975 |
10 |
0.002771 |
0 |
|||
predict |
skl |
1 |
1.38e+05 |
1 |
200 |
20 |
10 |
1 |
4.756e-05 |
0.0001215 |
4.897e-05 |
5.352e-05 |
5.764e-05 |
4.756e-05 |
9.979e-05 |
10 |
4.999e-05 |
0 |
|||
predict |
skl |
1 |
1.38e+05 |
10 |
200 |
20 |
10 |
1 |
5.502e-05 |
7.694e-05 |
5.601e-05 |
6.058e-05 |
5.983e-05 |
5.502e-05 |
7.242e-05 |
10 |
5.7e-05 |
0 |
|||
predict |
skl |
1 |
1.38e+05 |
100 |
200 |
20 |
10 |
1 |
0.0001025 |
0.0001362 |
0.0001047 |
0.0001131 |
0.0001099 |
0.0001025 |
0.0001292 |
10 |
0.0001052 |
0 |
|||
predict |
skl |
1 |
1.38e+05 |
1000 |
200 |
20 |
10 |
1 |
0.0004726 |
0.0008355 |
0.00048 |
0.0005101 |
0.0005299 |
0.0004726 |
0.0007361 |
10 |
0.0004902 |
0 |
|||
predict |
skl |
1 |
1.38e+05 |
10000 |
200 |
20 |
10 |
1 |
0.005101 |
0.005174 |
0.005115 |
0.00513 |
0.005127 |
0.005101 |
0.005168 |
10 |
0.005124 |
0 |
Benchmark code#
bench_plot_onnxruntime_decision_tree_reg.py
# coding: utf-8
"""
Benchmark of :epkg:`onnxruntime` on DecisionTree.
"""
# Authors: Xavier Dupré (benchmark)
# License: MIT
import matplotlib
matplotlib.use('Agg')
import os
from time import perf_counter as time
import numpy
import pandas
import matplotlib.pyplot as plt
import sklearn
from sklearn.tree import DecisionTreeRegressor
from sklearn.utils._testing import ignore_warnings
from sklearn.utils.extmath import softmax
from scipy.special import expit
from pymlbenchmark.context import machine_information
from pymlbenchmark.benchmark import BenchPerf
from pymlbenchmark.external import OnnxRuntimeBenchPerfTestRegression
from pymlbenchmark.plotting import plot_bench_results
model_name = "DecisionTreeRegressor"
filename = os.path.splitext(os.path.split(__file__)[-1])[0]
@ignore_warnings(category=FutureWarning)
def run_bench(repeat=10, verbose=False):
pbefore = dict(dim=[1, 5, 10, 20, 50, 100, 200],
max_depth=[3, 10, 20])
pafter = dict(N=[1, 10, 100, 1000, 10000])
test = lambda dim=None, **opts: OnnxRuntimeBenchPerfTestRegression(
DecisionTreeRegressor, dim=dim, **opts)
bp = BenchPerf(pbefore, pafter, test)
with sklearn.config_context(assume_finite=True):
start = time()
results = list(bp.enumerate_run_benchs(repeat=repeat, verbose=verbose,
stop_if_error=False))
end = time()
results_df = pandas.DataFrame(results)
print("Total time = %0.3f sec\n" % (end - start))
return results_df
#########################
# Runs the benchmark
# ++++++++++++++++++
df = run_bench(verbose=True)
df.to_csv("%s.perf.csv" % filename, index=False)
print(df.head())
#########################
# Extract information about the machine used
# ++++++++++++++++++++++++++++++++++++++++++
pkgs = ['numpy', 'pandas', 'sklearn', 'skl2onnx',
'onnxruntime', 'onnx', 'mlprodict']
dfi = pandas.DataFrame(machine_information(pkgs))
dfi.to_csv("%s.time.csv" % filename, index=False)
print(dfi)
#############################
# Plot the results
# ++++++++++++++++
def label_fct(la):
la = la.replace("onxpython_compiled", "opy")
la = la.replace("onxpython", "opy")
la = la.replace("onxonnxruntime1", "ort")
la = la.replace("fit_intercept", "fi")
la = la.replace("True", "1")
la = la.replace("False", "0")
la = la.replace("max_depth", "mxd")
return la
plot_bench_results(df, row_cols='N', col_cols='max_depth',
x_value='dim',
title="%s\nBenchmark scikit-learn / onnxruntime" % model_name,
label_fct=label_fct)
plt.savefig("%s.png" % filename)
import sys
if "--quiet" not in sys.argv:
plt.show()