lingyuzeng/qsar
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add 1dqsar

Browse Source
This commit is contained in:
mm644706215
2025-03-03 20:23:09 +08:00
parent 0c941671cc
commit 4cb2d9f56c
8 changed files with 1687 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
1d-qsar/cuda/RFE_cuml_permutation_update.log Normal file
View File

@@ -0,0 +1,38 @@
nohup: ignoring input
Number of training samples: 81, Number of features: 156
/root/micromamba/envs/rapids-25.02/lib/python3.12/site-packages/cuml/internals/api_decorators.py:363: UserWarning: For reproducible results in Random Forest Classifier or for almost reproducible results in Random Forest Regressor, n_streams=1 is recommended. If n_streams is > 1, results may vary due to stream/thread timing differences, even when random_state is set
return init_func(self, *args, **kwargs)
/root/micromamba/envs/rapids-25.02/lib/python3.12/site-packages/cuml/internals/api_decorators.py:188: UserWarning: The number of bins, `n_bins` is greater than the number of samples used for training. Changing `n_bins` to number of training samples.
ret = func(*args, **kwargs)
/root/micromamba/envs/rapids-25.02/lib/python3.12/site-packages/cuml/internals/api_decorators.py:188: UserWarning: To use pickling first train using float32 data to fit the estimator
ret = func(*args, **kwargs)
n_estimators: 50, CV MSE: 5.2602
n_estimators: 100, CV MSE: 5.0974
n_estimators: 150, CV MSE: 5.1422
n_estimators: 200, CV MSE: 5.0988
n_estimators: 250, CV MSE: 4.9330
n_estimators: 300, CV MSE: 4.9259
n_estimators: 350, CV MSE: 4.9253
Optimal number of trees determined: 350
Current number of features: 156, CV MSE: 4.9253
Removed feature index: 133, feature name: fr_allylic_oxid, permutation importance: -0.0004
Current number of features: 155, CV MSE: 4.9970
Removed feature index: 124, feature name: fr_Ar_N, permutation importance: -0.0009
Current number of features: 154, CV MSE: 4.7611
Removed feature index: 152, feature name: fr_pyridine, permutation importance: -0.0006
Current number of features: 153, CV MSE: 4.7928
Removed feature index: 47, feature name: PEOE_VSA10, permutation importance: -0.0001
Current number of features: 152, CV MSE: 4.7032
Removed feature index: 107, feature name: NumAromaticHeterocycles, permutation importance: -0.0010
Current number of features: 151, CV MSE: 4.7571
Removed feature index: 155, feature name: fr_unbrch_alkane, permutation importance: -0.0000
Current number of features: 150, CV MSE: 4.7501
Removed feature index: 11, feature name: MinPartialCharge, permutation importance: -0.0004
Current number of features: 149, CV MSE: 4.8415
Removed feature index: 52, feature name: PEOE_VSA2, permutation importance: -0.0001
Current number of features: 148, CV MSE: 4.7807
Removed feature index: 143, feature name: fr_ketone, permutation importance: -0.0001
Current number of features: 147, CV MSE: 4.7937
Removed feature index: 12, feature name: MaxAbsPartialCharge, permutation importance: -0.0008
Current number of features: 146, CV MSE: 4.7589
Removed feature index: 2, feature name: MinAbsEStateIndex, permutation importance: -0.0007