update robustMT to tg

deepchem/models/tests/test_overfit.py

@@ -598,7 +598,6 @@ def test_tf_robust_multitask_classification_overfit(self):
 
     # Fit trained model
     model.fit(dataset, nb_epoch=25)
-    model.save()
 
     # Eval model on train
     scores = model.evaluate(dataset, [classification_metric])
@@ -766,7 +765,6 @@ def test_tf_robust_multitask_regression_overfit(self):
 
     # Fit trained model
     model.fit(dataset, nb_epoch=25)
-    model.save()
 
     # Eval model on train
     scores = model.evaluate(dataset, [regression_metric])

deepchem/molnet/__init__.py

@@ -33,4 +33,4 @@
 from deepchem.molnet.dnasim import simulate_single_motif_detection
 
 from deepchem.molnet.run_benchmark import run_benchmark
-from deepchem.molnet.run_benchmark_low_data import run_benchmark_low_data
+#from deepchem.molnet.run_benchmark_low_data import run_benchmark_low_data

deepchem/molnet/run_benchmark_models.py

@@ -95,18 +95,18 @@ def benchmark_classification(train_dataset,
     learning_rate = hyper_parameters['learning_rate']
 
     # Building tensorflow MultiTaskDNN model
-    model = deepchem.models.TensorflowMultiTaskClassifier(
+    model = deepchem.models.MultiTaskClassifier(
         len(tasks),
         n_features,
         layer_sizes=layer_sizes,
         weight_init_stddevs=weight_init_stddevs,
         bias_init_consts=bias_init_consts,
         dropouts=dropouts,
-        penalty=penalty,
-        penalty_type=penalty_type,
+        weight_decay_penalty=penalty,
+        weight_decay_penalty_type=penalty_type,
         batch_size=batch_size,
         learning_rate=learning_rate,
-        seed=seed)
+        random_seed=seed)
 
   elif model_name == 'tf_robust':
     layer_sizes = hyper_parameters['layer_sizes']
@@ -137,11 +137,11 @@ def benchmark_classification(train_dataset,
         bypass_weight_init_stddevs=bypass_weight_init_stddevs,
         bypass_bias_init_consts=bypass_bias_init_consts,
         bypass_dropouts=bypass_dropouts,
-        penalty=penalty,
-        penalty_type=penalty_type,
+        weight_decay_penalty=penalty,
+        weight_decay_penalty_type=penalty_type,
         batch_size=batch_size,
         learning_rate=learning_rate,
-        seed=seed)
+        random_seed=seed)
 
   elif model_name == 'logreg':
     penalty = hyper_parameters['penalty']
@@ -461,15 +461,15 @@ def benchmark_regression(train_dataset,
     nb_epoch = hyper_parameters['nb_epoch']
     learning_rate = hyper_parameters['learning_rate']
 
-    model = deepchem.models.TensorflowMultiTaskRegressor(
+    model = deepchem.models.MultiTaskRegressor(
         len(tasks),
         n_features,
         layer_sizes=layer_sizes,
         weight_init_stddevs=weight_init_stddevs,
         bias_init_consts=bias_init_consts,
         dropouts=dropouts,
-        penalty=penalty,
-        penalty_type=penalty_type,
+        weight_decay_penalty=penalty,
+        weight_decay_penalty_type=penalty_type,
         batch_size=batch_size,
         learning_rate=learning_rate,
         seed=seed)
@@ -486,15 +486,15 @@ def benchmark_regression(train_dataset,
     learning_rate = hyper_parameters['learning_rate']
     fit_transformers = [hyper_parameters['fit_transformers'](train_dataset)]
 
-    model = deepchem.models.TensorflowMultiTaskFitTransformRegressor(
+    model = deepchem.models.MultiTaskFitTransformRegressor(
         n_tasks=len(tasks),
         n_features=n_features,
         layer_sizes=layer_sizes,
         weight_init_stddevs=weight_init_stddevs,
         bias_init_consts=bias_init_consts,
         dropouts=dropouts,
-        penalty=penalty,
-        penalty_type=penalty_type,
+        weight_decay_penalty=penalty,
+        weight_decay_penalty_type=penalty_type,
         batch_size=batch_size,
         learning_rate=learning_rate,
         fit_transformers=fit_transformers,
@@ -774,6 +774,7 @@ def model_builder(model_dir_xgb):
   return train_scores, valid_scores, test_scores
 
 
+'''
 def low_data_benchmark_classification(train_dataset,
                                       valid_dataset,
                                       n_features,
@@ -883,3 +884,4 @@ def low_data_benchmark_classification(train_dataset,
       valid_dataset, metric, n_pos, n_neg, n_trials=n_eval_trials)
 
   return valid_scores
+'''

examples/factors/FACTORS_tf_robust.py

@@ -37,14 +37,20 @@
 all_results = []
 for trial in range(num_trials):
   model = dc.models.RobustMultitaskRegressor(
-      len(FACTORS_tasks), train_dataset.get_data_shape()[0],
-      layer_sizes=[1000]*n_layers, bypass_layer_sizes=[100]*n_bypass_layers,
-      dropouts=[.25]*n_layers, bypass_dropouts=[.25]*n_bypass_layers, 
-      weight_init_stddevs=[.02]*n_layers, bias_init_consts=[1.]*n_layers,
-      bypass_weight_init_stddevs=[.02]*n_bypass_layers,
-      bypass_bias_init_consts=[1.]*n_bypass_layers,
-      learning_rate=.0003, penalty=.0001, penalty_type="l2",
-      optimizer="adam", batch_size=100, logdir="FACTORS_tf_bypass")
+      len(FACTORS_tasks),
+      train_dataset.get_data_shape()[0],
+      layer_sizes=[1000] * n_layers,
+      bypass_layer_sizes=[100] * n_bypass_layers,
+      dropouts=[.25] * n_layers,
+      bypass_dropouts=[.25] * n_bypass_layers,
+      weight_init_stddevs=[.02] * n_layers,
+      bias_init_consts=[1.] * n_layers,
+      bypass_weight_init_stddevs=[.02] * n_bypass_layers,
+      bypass_bias_init_consts=[1.] * n_bypass_layers,
+      learning_rate=.0003,
+      weight_decay_penalty=.0001,
+      weight_decay_penalty_type="l2",
+      batch_size=100)
 
   print("Fitting Model")
   model.fit(train_dataset, nb_epoch=nb_epoch)
@@ -57,9 +63,8 @@
   test_score, test_task_scores = model.evaluate(
       test_dataset, [metric], transformers, per_task_metrics=True)
 
-  all_results.append((train_score, train_task_scores,
-                      valid_score, valid_task_scores,
-                      test_score, test_task_scores))
+  all_results.append((train_score, train_task_scores, valid_score,
+                      valid_task_scores, test_score, test_task_scores))
 
   print("Scores for trial %d" % trial)
   print("----------------------------------------------------------------")
@@ -79,8 +84,8 @@
 print("####################################################################")
 
 for trial in range(num_trials):
-  (train_score, train_task_scores, valid_score, valid_task_scores,
-   test_score, test_task_scores) = all_results[trial]
+  (train_score, train_task_scores, valid_score, valid_task_scores, test_score,
+   test_task_scores) = all_results[trial]
 
   print("Scores for trial %d" % trial)
   print("----------------------------------------------------------------")

examples/hopv/hopv_robustMT_models.py

@@ -39,9 +39,8 @@
     bypass_weight_init_stddevs=[.02] * n_bypass_layers,
     bypass_bias_init_consts=[.5] * n_bypass_layers,
     learning_rate=.0003,
-    penalty=.0001,
-    penalty_type="l2",
-    optimizer="adam",
+    weight_decay_penalty=.0001,
+    weight_decay_penalty_type="l2",
     batch_size=100)
 
 # Fit trained model

examples/kaggle/KAGGLE_tf_robust.py

@@ -48,11 +48,9 @@
       bypass_weight_init_stddevs=[.02] * n_bypass_layers,
       bypass_bias_init_consts=[1.] * n_bypass_layers,
       learning_rate=.00003,
-      penalty=.0004,
-      penalty_type="l2",
-      optimizer="adam",
-      batch_size=100,
-      logdir="KAGGLE_tf_bypass")
+      weight_decay_penalty=.0004,
+      weight_decay_penalty_type="l2",
+      batch_size=100)
 
   print("Fitting Model")
   model.fit(train_dataset, nb_epoch=nb_epoch)

examples/kinase/KINASE_tf_robust.py

@@ -40,14 +40,20 @@
 all_results = []
 for trial in range(num_trials):
   model = dc.models.RobustMultitaskRegressor(
-      len(KINASE_tasks), train_dataset.get_data_shape()[0],
-      layer_sizes=[500]*n_layers, bypass_layer_sizes=[50]*n_bypass_layers,
-      dropouts=[.25]*n_layers, bypass_dropouts=[.25]*n_bypass_layers, 
-      weight_init_stddevs=[.02]*n_layers, bias_init_consts=[.5]*n_layers,
-      bypass_weight_init_stddevs=[.02]*n_bypass_layers,
-      bypass_bias_init_consts=[.5]*n_bypass_layers,
-      learning_rate=.0003, penalty=.0001, penalty_type="l2",
-      optimizer="adam", batch_size=100)
+      len(KINASE_tasks),
+      train_dataset.get_data_shape()[0],
+      layer_sizes=[500] * n_layers,
+      bypass_layer_sizes=[50] * n_bypass_layers,
+      dropouts=[.25] * n_layers,
+      bypass_dropouts=[.25] * n_bypass_layers,
+      weight_init_stddevs=[.02] * n_layers,
+      bias_init_consts=[.5] * n_layers,
+      bypass_weight_init_stddevs=[.02] * n_bypass_layers,
+      bypass_bias_init_consts=[.5] * n_bypass_layers,
+      learning_rate=.0003,
+      weight_decay_penalty=.0001,
+      weight_decay_penalty_type="l2",
+      batch_size=100)
 
   print("Fitting Model")
   model.fit(train_dataset, nb_epoch=nb_epoch)
@@ -60,9 +66,8 @@
   test_score, test_task_scores = model.evaluate(
       test_dataset, [metric], transformers, per_task_metrics=True)
 
-  all_results.append((train_score, train_task_scores,
-                      valid_score, valid_task_scores,
-                      test_score, test_task_scores))
+  all_results.append((train_score, train_task_scores, valid_score,
+                      valid_task_scores, test_score, test_task_scores))
 
   print("Scores for trial %d" % trial)
   print("----------------------------------------------------------------")
@@ -82,8 +87,8 @@
 print("####################################################################")
 
 for trial in range(num_trials):
-  (train_score, train_task_scores, valid_score, valid_task_scores,
-   test_score, test_task_scores) = all_results[trial]
+  (train_score, train_task_scores, valid_score, valid_task_scores, test_score,
+   test_task_scores) = all_results[trial]
 
   print("Scores for trial %d" % trial)
   print("----------------------------------------------------------------")

examples/tox21/tox21_robustMT_models.py

@@ -36,14 +36,12 @@
     bypass_weight_init_stddevs=[.02] * n_bypass_layers,
     bypass_bias_init_consts=[.5] * n_bypass_layers,
     learning_rate=.0003,
-    penalty=.0001,
-    penalty_type="l2",
-    optimizer="adam",
+    weight_decay_penalty=.0001,
+    weight_decay_penalty_type="l2",
     batch_size=100)
 
 # Fit trained model
 model.fit(train_dataset, nb_epoch=nb_epoch)
-model.save()
 
 print("Evaluating model")
 train_scores = model.evaluate(train_dataset, [metric], transformers)

examples/uv/UV_tf_robust.py

@@ -37,14 +37,20 @@
 all_results = []
 for trial in range(num_trials):
   model = dc.models.RobustMultitaskRegressor(
-      len(UV_tasks), train_dataset.get_data_shape()[0],
-      layer_sizes=[500]*n_layers, bypass_layer_sizes=[40]*n_bypass_layers,
-      dropouts=[.25]*n_layers, bypass_dropouts=[.25]*n_bypass_layers, 
-      weight_init_stddevs=[.02]*n_layers, bias_init_consts=[.5]*n_layers,
-      bypass_weight_init_stddevs=[.02]*n_bypass_layers,
-      bypass_bias_init_consts=[.5]*n_bypass_layers,
-      learning_rate=.0003, penalty=.0001, penalty_type="l2",
-      optimizer="adam", batch_size=100, logdir="UV_tf_robust")
+      len(UV_tasks),
+      train_dataset.get_data_shape()[0],
+      layer_sizes=[500] * n_layers,
+      bypass_layer_sizes=[40] * n_bypass_layers,
+      dropouts=[.25] * n_layers,
+      bypass_dropouts=[.25] * n_bypass_layers,
+      weight_init_stddevs=[.02] * n_layers,
+      bias_init_consts=[.5] * n_layers,
+      bypass_weight_init_stddevs=[.02] * n_bypass_layers,
+      bypass_bias_init_consts=[.5] * n_bypass_layers,
+      learning_rate=.0003,
+      weight_decay_penalty=.0001,
+      weight_decay_penalty_type="l2",
+      batch_size=100)
 
   print("Fitting Model")
   model.fit(train_dataset, nb_epoch=nb_epoch)
@@ -57,9 +63,8 @@
   test_score, test_task_scores = model.evaluate(
       test_dataset, [metric], transformers, per_task_metrics=True)
 
-  all_results.append((train_score, train_task_scores,
-                      valid_score, valid_task_scores,
-                      test_score, test_task_scores))
+  all_results.append((train_score, train_task_scores, valid_score,
+                      valid_task_scores, test_score, test_task_scores))
 
   print("Scores for trial %d" % trial)
   print("----------------------------------------------------------------")
@@ -79,8 +84,8 @@
 print("####################################################################")
 
 for trial in range(num_trials):
-  (train_score, train_task_scores, valid_score, valid_task_scores,
-   test_score, test_task_scores) = all_results[trial]
+  (train_score, train_task_scores, valid_score, valid_task_scores, test_score,
+   test_task_scores) = all_results[trial]
 
   print("Scores for trial %d" % trial)
   print("----------------------------------------------------------------")