Commit 1d2e091b authored by miaecle's avatar miaecle
Browse files

updating random splitting results

parent 72e75dce

README.md

+20 −20
Original line number Diff line number Diff line
@@ -234,26 +234,26 @@ Random splitting 


|Dataset    |Model               |Train score/ROC-AUC|Valid score/ROC-AUC|

|-----------|--------------------|-------------------|-------------------|

|tox21      |logistic regression |0.903              |0.741              |

|           |Multitask network   |0.846              |0.812              |

|           |robust MT-NN        |0.844              |0.793              |

|           |graph convolution   |0.872              |0.816              |

|muv        |logistic regression |0.961              |0.696              |

|           |Multitask network   |0.895              |0.740              |

|           |robust MT-NN        |0.914              |0.667              |

|           |graph convolution   |0.846              |0.776              |

|pcba       |logistic regression |0.807        	     |0.772              |

|           |Multitask network   |0.811        	     |0.787              |

|           |robust MT-NN        |0.809              |0.778              |

|           |graph convolution   |0.875       	     |0.844              |

|sider      |logistic regression |0.932        	     |0.628              |

|           |Multitask network   |0.779        	     |0.665              |

|           |robust MT-NN        |0.761              |0.621              |

|           |graph convolution   |0.706        	     |0.638              |

|toxcast    |logistic regression |0.737        	     |0.543              |

|           |Multitask network   |0.831        	     |0.684              |

|           |robust MT-NN        |0.814              |0.692              |

|           |graph convolution   |0.820        	     |0.692              |

|tox21      |logistic regression |0.903              |0.735              |

|           |Multitask network   |0.856              |0.783              |

|           |robust MT-NN        |0.855              |0.773              |

|           |graph convolution   |0.865              |0.827              |

|muv        |logistic regression |0.957              |0.719              |

|           |Multitask network   |0.902              |0.734              |

|           |robust MT-NN        |0.933              |0.732              |

|           |graph convolution   |0.860              |0.730              |

|pcba       |logistic regression |0.808        	     |0.776              |

|           |Multitask network   |0.811        	     |0.778              |

|           |robust MT-NN        |0.811              |0.771              |

|           |graph convolution   |0.872       	     |0.844              |

|sider      |logistic regression |0.929        	     |0.656              |

|           |Multitask network   |0.777        	     |0.655              |

|           |robust MT-NN        |0.804              |0.630              |

|           |graph convolution   |0.705        	     |0.618              |

|toxcast    |logistic regression |0.725        	     |0.586              |

|           |Multitask network   |0.836        	     |0.684              |

|           |robust MT-NN        |0.822              |0.681              |

|           |graph convolution   |0.820        	     |0.717              |



Scaffold splitting

examples/benchmark_low_data.py

+2 −2
Original line number Diff line number Diff line
@@ -85,7 +85,7 @@ def low_data_benchmark_loading_datasets(hyper_parameters, cross_valid=False, 
  splitter = splitters[split]



  #running model

  for count, hp in enumerate(hyper_parameters[model]):

  for count_hp, hp in enumerate(hyper_parameters[model]):

    # Loading general settings

    # Number of folds for split 

    K = hp['K']
@@ -108,7 +108,7 @@ def low_data_benchmark_loading_datasets(hyper_parameters, cross_valid=False, 
                         model=model, verbosity=verbosity)

      time_finish_fitting = time.time() 

      with open(os.path.join(out_path, 'results.csv'),'a') as f:

        f.write('\n'+str(count)+','+str(count_iter)+',')

        f.write('\n'+str(count_hp)+','+str(count_iter)+',')

        f.write(dataset+','+model+',')

        f.write('valid,')

        for i in valid_scores:

examples/stable_results.csv

+12 −12
Original line number Diff line number Diff line
@@ -29,18 +29,18 @@ 
0,sider,random,classification,train,tf_robust,0.8047109857,valid,tf_robust,0.6303796949,time_for_running,144.951164961

0,sider,random,classification,train,logreg,0.9293807224,valid,logreg,0.6562281389,time_for_running,88.3968729973

0,sider,random,classification,train,graphconv,0.7049051898,valid,graphconv,0.6176319797,time_for_running,52.2268190384

0,muv,random,classification,train,tf,0.8953200915,valid,tf,0.7396286547,time_for_running,376.079932213

0,muv,random,classification,train,tf_robust,0.9142442363,valid,tf_robust,0.6672445505,time_for_running,564.25266695

0,muv,random,classification,train,logreg,0.9608985781,valid,logreg,0.6956532843,time_for_running,446.927948952

0,muv,random,classification,train,graphconv,0.8460695576,valid,graphconv,0.7755425716,time_for_running,1871.64626002

0,toxcast,random,classification,train,tf,0.8306986464,valid,tf,0.6840850646,time_for_running,2287.80405498

0,toxcast,random,classification,train,tf_robust,0.8140336561,valid,tf_robust,0.6921436476,time_for_running,4112.52007484

0,toxcast,random,classification,train,logreg,0.7373983296,valid,logreg,0.5433428006,time_for_running,2637.63535094

0,toxcast,random,classification,train,graphconv,0.82008075,valid,graphconv,0.6925051431,time_for_running,894.896769047

0,pcba,random,classification,train,tf,0.810876083,valid,tf,0.787010593,time_for_running,8910.69580603

0,pcba,random,classification,train,tf_robust,0.8092694566,valid,tf_robust,0.7776478785,time_for_running,14205.0440209

0,pcba,random,classification,train,logreg,0.8065139555,valid,logreg,0.7724261671,time_for_running,10074.3197708

0,pcba,random,classification,train,graphconv,0.8750284011,valid,graphconv,0.8443492695,time_for_running,14665.9515259

0,muv,random,classification,train,tf,0.9018813012,valid,tf,0.7342366564,time_for_running,341.123150826

0,muv,random,classification,train,tf_robust,0.9333028119,valid,tf_robust,0.7322266795,time_for_running,536.017292023

0,muv,random,classification,train,logreg,0.9574538412,valid,logreg,0.719356797,time_for_running,279.70366621

0,muv,random,classification,train,graphconv,0.8603805962,valid,graphconv,0.7301446288,time_for_running,1389.00893307

0,toxcast,random,classification,train,tf,0.8355451184,valid,tf,0.6839842449,time_for_running,1586.05935192

0,toxcast,random,classification,train,tf_robust,0.8222576181,valid,tf_robust,0.6809804928,time_for_running,2853.99277091

0,toxcast,random,classification,train,logreg,0.7247358775,valid,logreg,0.5863769673,time_for_running,1727.54739904

0,toxcast,random,classification,train,graphconv,0.8197750838,valid,graphconv,0.7167623189,time_for_running,701.734670877

0,pcba,random,classification,train,tf,0.8111402898,valid,tf,0.7782012264,time_for_running,9671.60542989

0,pcba,random,classification,train,tf_robust,0.8105697364,valid,tf_robust,0.7709857227,time_for_running,16777.595228

0,pcba,random,classification,train,logreg,0.8075221378,valid,logreg,0.7758407198,time_for_running,8754.5542872

0,pcba,random,classification,train,graphconv,0.872172184,valid,graphconv,0.8435271472,time_for_running,11502.8221002

0,delaney,random,regression,train,tf_regression,0.7791066217,valid,tf_regression,0.6164873014,time_for_running,35.6433098316

0,tox21,scaffold,classification,train,tf,0.8626085326,valid,tf,0.7030201614,time_for_running,63.5685660839

0,tox21,scaffold,classification,train,tf_robust,0.8608722489,valid,tf_robust,0.7100530015,time_for_running,101.614424944

CRA Git | Maintained and supported by SUSTech CRA and CCSE