search

JDACS4C-IMPROVE / Singularity

Singularity definitions that can be extended to support execution of community models.
MIT License
3 stars 5 forks source link

Test DeepTTC #37

Closed wilke closed 1 year ago

wilke commented 1 year ago

Status: Failed Command: singularity exec --bind ${TEST_DIR}:/candle_data_dir build/DeepTTC.sif train.sh 4 /candle_data_dir Depends on:

Output:

PRAD              818
MB                546
CLL               272
ACC               137
Name: count, dtype: int64
Traceback (most recent call last):
  File "/usr/local/DeepTTC/deepttc_baseline_pytorch.py", line 279, in <module>
    main()
  File "/usr/local/DeepTTC/deepttc_baseline_pytorch.py", line 271, in main
    run(args)
  File "/usr/local/DeepTTC/deepttc_baseline_pytorch.py", line 247, in run
    train_drug, test_drug, train_rna, test_rna = loader.load_data()
  File "/usr/local/DeepTTC/deepttc_baseline_pytorch.py", line 133, in load_data
    train_drug, test_drug, train_rna, test_rna = self._process_data(self.args)
  File "/usr/local/DeepTTC/deepttc_baseline_pytorch.py", line 188, in _process_data
    train_drug, test_drug = obj.Getdata.ByCancer(random_seed=args.rng_seed)
  File "/usr/local/DeepTTC/Step1_getData.py", line 213, in ByCancer
    train_data, test_data = self._split(df=drug_cell_df, col=self.cancer_id,
  File "/usr/local/DeepTTC/Step1_getData.py", line 175, in _split
    train_data = train_data.append(sub_train)
  File "/opt/conda/lib/python3.10/site-packages/pandas/core/generic.py", line 5989, in __getattr__
    return object.__getattribute__(self, name)
AttributeError: 'DataFrame' object has no attribute 'append'. Did you mean: '_append'?
wilke commented 1 year ago

Command: IMPROVE_RESULT val_loss: 1.7727327054408248

Output:

Validation at Epoch 2 with loss:1.60653, MSE: 1.86214 , Pearson Correlation: 0.87763 with p-value: 0.0 Spearman Correlation: 0.83264 with p_value: 0.0 , Concordance Index: 0.82473
{'val_loss': 1.8621445139104555, 'rmse': 1.3646041601543122, 'pcc': 0.8776368581577472, 'scc': 0.8326412524002879, 'r2': 0.7668459324633321, 'best_epoch': 1}
Training at Epoch 3 iteration 0 with loss 1.86644. Total time 0.02583 hours
Currenf MSE: 1.7727327054408248
Validation at Epoch 3 with loss:1.71383, MSE: 1.77273 , Pearson Correlation: 0.88492 with p-value: 0.0 Spearman Correlation: 0.84164 with p_value: 0.0 , Concordance Index: 0.82975
{'val_loss': 1.7727327054408248, 'rmse': 1.3314400870639373, 'pcc': 0.8849223686446626, 'scc': 0.8416452175582434, 'r2': 0.7780409426651591, 'best_epoch': 2}

IMPROVE_RESULT val_loss:        1.7727327054408248

Status: OK

wilke commented 1 year ago

Missing commits - develop is failing

wilke commented 1 year ago
  1. Modified definition file, new version in switch-to-improve-branch
  2. Created improve branch in DeepTTC
  3. Switched build branch in definition file
  4. Build and tested image:
singularity run --nv --bind `pwd`/tmp:/candle_data_dir build/DeepTTC.sif train.sh 3 /candle_data_dir --epochs 1
....
Checkpoint save interval == 0 -> checkpoints are disabled.
Training at Epoch 1 iteration 0 with loss 14.3121. Total time 0.00055 hours
Currenf MSE: 2.1630810230494517
Validation at Epoch 1 with loss:1.75420, MSE: 2.16308 , Pearson Correlation: 0.85460 with p-value: 0.0 Spearman Correlation: 0.80406 with p_value: 0.0 , Concordance Index: 0.80849
{'val_loss': 2.1630810230494517, 'rmse': 1.4707416574808274, 'pcc': 0.8546015608904385, 'scc': 0.8040606021397423, 'r2': 0.7291664877951529, 'best_epoch': 0}

IMPROVE_RESULT val_loss:        2.1630810230494517