slryou41 / reaction-gcnn Goto Github PK

Hi there,
I was trying to train your model on a set of Suzuki couplings at my disposal, yet I've got the following error:

Traceback (most recent call last): File "reaction-gcnn/train.py", line 420, in <module> main() File "reaction-gcnn/train.py", line 373, in main args.conv_layers, class_num) File "reaction-gcnn/train.py", line 224, in set_up_predictor n_layers=conv_layers) TypeError: __init__() got an unexpected keyword argument 'hidden_dim'
The same error appears when I use train_attention_model.py instead of train.py. I suppose this may be related to the version of chainer/chainer_chemistry (I installed this just with pip). Could you specify which version did you use in your project?

Here, I have chainer_chemistry=0.7.1 and chainer=7.8.0.

As a side note, a script transforming reaxys CSV into training data could be useful (I found only dictionary preparation in the repo). I think I retro-engineered this, hope that the result is correct.

Hello I want to train your model with my data, hence I have couple questions regarding input format.
In train.py script there are definition of input as below presented

        datafile = 'data/suzuki_type_train_v2.csv'
        class_num = 119
        class_dict = {'M': 28, 'L': 23, 'B': 35, 'S': 10, 'A': 17}
        dataset_filename = 'data.npz'
        labels = ['Yield', 'M', 'L', 'B', 'S', 'A', 'id']

1. The class_num is out_dim from MLP. How and what should I set here? Based on train file it seems it somehow connected with class_dict. My first idea was it should be sum(class_dict.values()) but is not true.

2. class_dict as far as I understand keys are column name in csv and the value is a number of unique value.
   Value in csv should have format 'xNUMx' where x is any characted a NUM should be number (as I see in dataset/suzuki_data_frame_parser.py). There should be continues numbering of different kind of compounds (e.g M0M to M9M and then L10L to L19L if we want to include 10 ligand and 10 metals).
   Please correct me if I am wrong.

3. How labels correspnd to column in csv file and in class_dict? Based on the code I found that csv should have 'Reactant1', 'Reactant2' and 'Product' column? Are there any other obligatory column name?