search

JDACS4C-IMPROVE / DrugCell

A visible neural network model for drug response prediction
MIT License
0 stars 2 forks source link

Warning: SpearmanRConstantInputWarning: An input array is constant; the correlation coefficient is not defined. #38

Closed wilke closed 11 months ago

wilke commented 11 months ago

We might want to fix that:

INFO:DrugCell: TEST Epoch [1/1], loss: 0.83281. This took 39.4 secs. /opt/conda/lib/python3.7/site-packages/scipy/stats/stats.py:4484: SpearmanRConstantInputWarning: An input array is constant; the correlation coefficient is not defined. warnings.warn(SpearmanRConstantInputWarning()) nan Best performed model (epoch) 0 {'test_loss': 0.0008328101038932801, 'test_pcc': -2.8085122494303505e-07, 'test_MSE': 0.8901301622390747, 'test_r2': -19.574140548706055, 'test_scc': nan, 'IMPROVE RESULT': 0.8901301622390747}

IMPROVE_RESULT MSE: 0.8901301622390747

rohandavidg commented 11 months ago

Just fixed this issue INFO:CandleCkpt:Callback initialized. Checkpoint save interval == 0 -> checkpoints are disabled. INFO:CandleCkpt:Checkpoint save interval == 0 -> checkpoints are disabled. INFO:DrugCell:== Epoch [0/200] == INFO:DrugCell: TRAINING Epoch [1/200], loss: 31.50916. This took 35.8 secs. INFO:DrugCell: TEST Epoch [1/200], loss: 0.86188. This took 41.4 secs. nan INFO:DrugCell:== Epoch [1/200] == INFO:DrugCell: TRAINING Epoch [2/200], loss: 31.43307. This took 32.4 secs. INFO:DrugCell: TEST Epoch [2/200], loss: 0.85998. This took 37.8 secs. nan INFO:DrugCell:== Epoch [2/200] == INFO:DrugCell: TRAINING Epoch [3/200], loss: 31.35702. This took 33.5 secs. INFO:DrugCell: TEST Epoch [3/200], loss: 0.85807. This took 39.1 secs. nan INFO:DrugCell:== Epoch [3/200] == INFO:DrugCell: TRAINING Epoch [4/200], loss: 31.28103. This took 33.7 secs. INFO:DrugCell: TEST Epoch [4/200], loss: 0.85616. This took 39.3 secs. 0.6228883221333422

rohandavidg commented 11 months ago

fixed this issue with the latest pull request