The following example shows a single model cross validation using td_lightgbm.
return_cvbooster argument is not yet supported for cv().
>>> opt_cv_s = td_lightgbm.cv(params={}, train_set=obj_s1, callbacks=[td_lightgbm.early_stopping(5)])
>>> opt_cv_s
[LightGBM] [Warning] Auto-choosing col-wise multi-threading, the overhead of testing was 0.000058 seconds.
You can set `force_col_wise=true` to remove the overhead.
[LightGBM] [Info] Total Bins 532
[LightGBM] [Info] Number of data points in the train set: 320, number of used features: 4
[LightGBM] [Warning] Auto-choosing col-wise multi-threading, the overhead of testing was 0.000054 seconds.
You can set `force_col_wise=true` to remove the overhead.
[LightGBM] [Info] Total Bins 532
[LightGBM] [Info] Number of data points in the train set: 320, number of used features: 4
[LightGBM] [Warning] Auto-choosing col-wise multi-threading, the overhead of testing was 0.000051 seconds.
You can set `force_col_wise=true` to remove the overhead.
[LightGBM] [Info] Total Bins 532
[LightGBM] [Info] Number of data points in the train set: 320, number of used features: 4
[LightGBM] [Warning] Auto-choosing col-wise multi-threading, the overhead of testing was 0.000045 seconds.
You can set `force_col_wise=true` to remove the overhead.
[LightGBM] [Info] Total Bins 532
[LightGBM] [Info] Number of data points in the train set: 320, number of used features: 4
[LightGBM] [Warning] Auto-choosing col-wise multi-threading, the overhead of testing was 0.000047 seconds.
You can set `force_col_wise=true` to remove the overhead.
[LightGBM] [Info] Total Bins 532
[LightGBM] [Info] Number of data points in the train set: 320, number of used features: 4
Training until validation scores don't improve for 5 rounds
Early stopping, best iteration is:
[57] cv_agg's l2: 0.067099 + 0.0151336
{'l2-mean': [0.22023353349592326,
0.19595424631042407,
...
...
0.06726610385135459,
0.06709902214997468],
'l2-stdv': [0.0015084316502001842,
0.0029052033405121175,
...
...
0.015130340427949404,
0.015133573776865996]}