https://github.com/linsamtw/xgb_python_vs_r
https://github.com/linsamtw/xgb_python_vs_r
Last synced: over 1 year ago
JSON representation
- Host: GitHub
- URL: https://github.com/linsamtw/xgb_python_vs_r
- Owner: linsamtw
- Created: 2017-05-12T06:35:30.000Z (about 9 years ago)
- Default Branch: master
- Last Pushed: 2017-05-12T09:01:06.000Z (about 9 years ago)
- Last Synced: 2025-02-01T01:51:22.622Z (over 1 year ago)
- Language: Python
- Size: 25.4 KB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# xgb_python_vs_r
the xgb.cv in python and r is different
for example:
# we train iris dataset by xgb.cv in R
```sh
[2] train-merror:0.056667+0.028674 test-merror:0.040000+0.028284
[3] train-merror:0.040000+0.016330 test-merror:0.046667+0.024944
Stopping. Best iteration:
[2] train-merror:0.056667+0.028674 test-merror:0.040000+0.028284
```
# train iris by xgb.cv in Python
```sh
train-merror-mean test-merror-mean
0.046667 0.046667
```
the params of r and python are same
```sh
xgb_params=list(
objective="multi:softmax",
eta= 0.01,
max_depth= 1,
colsample_bytree= 0.7,
subsample = 0.7
num_class = 3)
```
results are different, if we use other data, that will more different, but we don't know why
================================================
PS:
# R version 3.3.3 (2017-03-06)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: Ubuntu 16.04.2 LTS
locale:
[1] LC_CTYPE=zh_TW.UTF-8 LC_NUMERIC=C LC_TIME=zh_TW.UTF-8
[4] LC_COLLATE=zh_TW.UTF-8 LC_MONETARY=zh_TW.UTF-8 LC_MESSAGES=zh_TW.UTF-8
[7] LC_PAPER=zh_TW.UTF-8 LC_NAME=C LC_ADDRESS=C
[10] LC_TELEPHONE=C LC_MEASUREMENT=zh_TW.UTF-8 LC_IDENTIFICATION=C
attached base packages:
[1] stats graphics grDevices utils datasets methods base
other attached packages:
[1] Matrix_1.2-8 mice_2.30 timeDate_3012.100 xgboost_0.6-4 dplyr_0.5.0
[6] data.table_1.10.4
loaded via a namespace (and not attached):
[1] Rcpp_0.12.10 lattice_0.20-35 assertthat_0.1 MASS_7.3-45 grid_3.3.3
[6] R6_2.2.0 DBI_0.6-1 magrittr_1.5 stringi_1.1.5 rpart_4.1-10
[11] splines_3.3.3 tools_3.3.3 survival_2.41-3 nnet_7.3-12 tibble_1.3.0
# python
xgb.__version__
Out[107]: '0.6'