Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[v1 BUG]: error and cost much time #1132

Open
jia-huang opened this issue Dec 24, 2024 · 0 comments
Open

[v1 BUG]: error and cost much time #1132

jia-huang opened this issue Dec 24, 2024 · 0 comments
Labels
bug Something isn't working v1-wontfix issues that will not be fixed in time for the final stable v1.x release (v1.7)

Comments

@jia-huang
Copy link

When running the following command, the following error message appears, but the program still runs and completes successfully. What is the cause of this error? Will this error affect the final classification performance of the model?

Additionally, for a dataset with 30,000 entries, it takes 3 hours to train one model and complete one epoch. What could be the reason for this? Is this normal? My computer configuration is as follows:

command:
chemprop_train --dataset_type classification
--save_dir ../chemprop_model/SD1_activity_checkpoints_3
--features_generator rdkit_2d_normalized --no_features_scaling
--epochs 30 --ensemble_size 10 --extra_metrics prc-auc --data_path D:/Huangjia/shenwuxinxi/chemprop_data/Nature/SD1_activity_train.csv
--separate_val_path D:/Huangjia/shenwuxinxi/chemprop_data/Nature/SD1_activity_val.csv
--separate_test_path D:/Huangjia/shenwuxinxi/chemprop_data/Nature/SD1_activity_test.csv
--target_columns Lable
--smiles_columns SMILES
--config_path shoudong-paper2_1-config.json

JSON file (model configuration):
{
"message-hidden-dim": 1600,
"depth": 5,
"dropout": 0.15,
"ffn-num-layers": 1,
"ffn-hidden-dim": 1600
}

The computer configuration is as follows:
13th Gen Intel(R) Core(TM) i9-13900K 3.00 GHz
128 GB (128 GB 可用)
4090 显卡

Error message:
Could not compute EState_VSA3 for molecule
Traceback (most recent call last):
File "C:\Users\PS\miniconda3\envs\hjpy38mri\lib\site-packages\descriptastorus\descriptors\rdNormalizedDescriptors.py", line 81, in applyNormalizedFunc
return cdfs[name](rdDescriptors.applyFunc(funcs, name,m))
File "C:\Users\PS\miniconda3\envs\hjpy38mri\lib\site-packages\descriptastorus\descriptors\rdNormalizedDescriptors.py", line 68, in cdf
v = dist.cdf(np.clip(v, minV, maxV), loc=loc, scale=scale, *arg)
File "<array_function internals>", line 200, in clip
File "C:\Users\PS\miniconda3\envs\hjpy38mri\lib\site-packages\numpy\core\fromnumeric.py", line 2180, in clip
return _wrapfunc(a, 'clip', a_min, a_max, out=out, **kwargs)
File "C:\Users\PS\miniconda3\envs\hjpy38mri\lib\site-packages\numpy\core\fromnumeric.py", line 54, in _wrapfunc
return _wrapit(obj, method, *args, **kwds)
File "C:\Users\PS\miniconda3\envs\hjpy38mri\lib\site-packages\numpy\core\fromnumeric.py", line 43, in wrapit
result = getattr(asarray(obj), method)(*args, **kwds)
File "C:\Users\PS\miniconda3\envs\hjpy38mri\lib\site-packages\numpy\core_methods.py", line 161, in clip
return clip_dep_invoke_with_casting(
File "C:\Users\PS\miniconda3\envs\hjpy38mri\lib\site-packages\numpy\core_methods.py", line 115, in clip_dep_invoke_with_casting
return ufunc(*args, out=out, **kwargs)
TypeError: '>=' not supported between instances of 'NoneType' and 'float'
function application failed (EState_VSA4->C=CCOC(=O)[C@@h]1[C@H]2C(=O)OC@HC@HN2C@H[C@@]12C(=O)Nc1ccc(I)cc12)
Traceback (most recent call last):
File "C:\Users\PS\miniconda3\envs\hjpy38mri\lib\site-packages\descriptastorus\descriptors\rdDescriptors.py", line 432, in applyFunc
return functionsname
File "C:\Users\PS\miniconda3\envs\hjpy38mri\lib\site-packages\rdkit\Chem\EState\EState_VSA.py", line 110, in EState_VSA_bin
return EState_VSA
(mol, force=False)[nbin]
File "C:\Users\PS\miniconda3\envs\hjpy38mri\lib\site-packages\rdkit\Chem\EState\EState_VSA.py", line 72, in EState_VSA

propContribs = EStateIndices
(mol, force=force)
File "C:\Users\PS\miniconda3\envs\hjpy38mri\lib\site-packages\rdkit\Chem\EState\EState.py", line 48, in EStateIndices
Is = numpy.zeros(nAtoms, numpy.float)
File "C:\Users\PS\miniconda3\envs\hjpy38mri\lib\site-packages\numpy_init
.py", line 305, in getattr
raise AttributeError(former_attrs[attr])
AttributeError: module 'numpy' has no attribute 'float'.
np.float was a deprecated alias for the builtin float. To avoid this error in existing code, use float by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use n p.float64 here.
The aliases was originally deprecated in NumPy 1.20; for more details and guidance see the original release note at:
https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
Could not compute EState_VSA4 for molecule
Traceback (most recent call last):
File "C:\Users\PS\miniconda3\envs\hjpy38mri\lib\site-packages\descriptastorus\descriptors\rdNormalizedDescriptors.py", line 81, in applyNormalizedFunc
return cdfs[name](rdDescriptors.applyFunc(funcs, name,m))
File "C:\Users\PS\miniconda3\envs\hjpy38mri\lib\site-packages\descriptastorus\descriptors\rdNormalizedDescriptors.py", line 68, in cdf
v = dist.cdf(np.clip(v, minV, maxV), loc=loc, scale=scale, *arg)
File "<array_function internals>", line 200, in clip
File "C:\Users\PS\miniconda3\envs\hjpy38mri\lib\site-packages\numpy\core\fromnumeric.py", line 2180, in clip
return _wrapfunc(a, 'clip', a_min, a_max, out=out, **kwargs)
File "C:\Users\PS\miniconda3\envs\hjpy38mri\lib\site-packages\numpy\core\fromnumeric.py", line 54, in _wrapfunc
return _wrapit(obj, method, *args, **kwds)
File "C:\Users\PS\miniconda3\envs\hjpy38mri\lib\site-packages\numpy\core\fromnumeric.py", line 43, in _wrapit
result = getattr(asarray(obj), method)(*args, **kwds)
File "C:\Users\PS\miniconda3\envs\hjpy38mri\lib\site-packages\numpy\core_methods.py", line 161, in _clip
return _clip_dep_invoke_with_casting(
File "C:\Users\PS\miniconda3\envs\hjpy38mri\lib\site-packages\numpy\core_methods.py", line 115, in _clip_dep_invoke_with_casting
return ufunc(*args, out=out, **kwargs)
TypeError: '>=' not supported between instances of 'NoneType' and 'float'
Traceback (most recent call last):
File "C:\Users\PS\miniconda3\envs\hjpy38mri\lib\site-packages\descriptastorus\descriptors\rdNormalizedDescriptors.py", line 81, in applyNormalizedFunc
return cdfs[name](rdDescriptors.applyFunc(funcs, name,m))
File "C:\Users\PS\miniconda3\envs\hjpy38mri\lib\site-packages\descriptastorus\descriptors\rdNormalizedDescriptors.py", line 68, in cdf
v = dist.cdf(np.clip(v, minV, maxV), loc=loc, scale=scale, *arg)
File "<array_function internals>", line 200, in clip
File "C:\Users\PS\miniconda3\envs\hjpy38mri\lib\site-packages\numpy\core\fromnumeric.py", line 2180, in clip
return _wrapfunc(a, 'clip', a_min, a_max, out=out, **kwargs)
File "C:\Users\PS\miniconda3\envs\hjpy38mri\lib\site-packages\numpy\core\fromnumeric.py", line 54, in _wrapfunc
return _wrapit(obj, method, *args, **kwds)
File "C:\Users\PS\miniconda3\envs\hjpy38mri\lib\site-packages\numpy\core\fromnumeric.py", line 43, in _wrapit
result = getattr(asarray(obj), method)(*args, **kwds)
File "C:\Users\PS\miniconda3\envs\hjpy38mri\lib\site-packages\numpy\core_methods.py", line 161, in _clip
return _clip_dep_invoke_with_casting(
File "C:\Users\PS\miniconda3\envs\hjpy38mri\lib\site-packages\numpy\core_methods.py", line 115, in _clip_dep_invoke_with_casting
return ufunc(*args, out=out, **kwargs)
TypeError: '>=' not supported between instances of 'NoneType' and 'float'

@jia-huang jia-huang added bug Something isn't working v1-wontfix issues that will not be fixed in time for the final stable v1.x release (v1.7) labels Dec 24, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working v1-wontfix issues that will not be fixed in time for the final stable v1.x release (v1.7)
Projects
None yet
Development

No branches or pull requests

1 participant