Commit dcaf2525 authored by peastman's avatar peastman
Browse files

yapf

parent b7980a0b

examples/factors/FACTORS_tf_model.py

+17 −12
Original line number Diff line number Diff line
@@ -33,11 +33,17 @@ for trial in range(num_trials): 
  n_layers = 3

  nb_epoch = 125

  model = dc.models.TensorflowMultitaskRegressor(

      len(FACTORS_tasks), train_dataset.get_data_shape()[0],

      layer_sizes=[1000]*n_layers, dropouts=[.25]*n_layers,

      len(FACTORS_tasks),

      train_dataset.get_data_shape()[0],

      layer_sizes=[1000] * n_layers,

      dropouts=[.25] * n_layers,

      weight_init_stddevs=[.02] * n_layers,

      bias_init_consts=[1.]*n_layers, learning_rate=.0003,

      penalty=.0001, penalty_type="l2", optimizer="adam", batch_size=100,

      bias_init_consts=[1.] * n_layers,

      learning_rate=.0003,

      penalty=.0001,

      penalty_type="l2",

      optimizer="adam",

      batch_size=100,

      logdir="FACTORS_tf_model")



  #Use R2 classification metric
@@ -54,9 +60,8 @@ for trial in range(num_trials): 
  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("----------------------------------------------------------------")
@@ -76,8 +81,8 @@ for trial in range(num_trials): 
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/factors/FACTORS_tf_singletask.py

+18 −9
Original line number Diff line number Diff line
@@ -33,14 +33,24 @@ metric = dc.metrics.Metric(dc.metrics.pearson_r2_score, task_averager=np.mean) 
n_layers = 3

nb_epoch = 125

n_features = train_dataset.get_data_shape()[0]





def task_model_builder(m_dir):

  return dc.models.TensorflowMultitaskRegressor(

      n_tasks=1, n_features=n_features, logdir=m_dir,

      layer_sizes=[1000]*n_layers, dropouts=[.25]*n_layers,

      weight_init_stddevs=[.02]*n_layers, bias_init_consts=[1.]*n_layers,

      learning_rate=.0003, penalty=.0001, penalty_type="l2", optimizer="adam",

      n_tasks=1,

      n_features=n_features,

      logdir=m_dir,

      layer_sizes=[1000] * n_layers,

      dropouts=[.25] * n_layers,

      weight_init_stddevs=[.02] * n_layers,

      bias_init_consts=[1.] * n_layers,

      learning_rate=.0003,

      penalty=.0001,

      penalty_type="l2",

      optimizer="adam",

      batch_size=100)





all_results = []

for trial in range(num_trials):

  print("Starting trial %d" % trial)
@@ -57,9 +67,8 @@ for trial in range(num_trials): 
  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("----------------------------------------------------------------")

  print("Scores for trial %d" % trial)
@@ -80,8 +89,8 @@ for trial in range(num_trials): 
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("----------------------------------------------------------------")

  print("Scores for trial %d" % trial)

  print("----------------------------------------------------------------")

examples/kinase/KINASE_tf_model.py

+15 −10
Original line number Diff line number Diff line
@@ -36,11 +36,17 @@ for trial in range(num_trials): 
  n_layers = 3

  nb_epoch = 50

  model = dc.models.TensorflowMultitaskRegressor(

      len(KINASE_tasks), train_dataset.get_data_shape()[0],

      layer_sizes=[1000]*n_layers, dropouts=[.25]*n_layers,

      len(KINASE_tasks),

      train_dataset.get_data_shape()[0],

      layer_sizes=[1000] * n_layers,

      dropouts=[.25] * n_layers,

      weight_init_stddevs=[.02] * n_layers,

      bias_init_consts=[.5]*n_layers, learning_rate=.0003,

      penalty=.0001, penalty_type="l2", optimizer="adam", batch_size=100,

      bias_init_consts=[.5] * n_layers,

      learning_rate=.0003,

      penalty=.0001,

      penalty_type="l2",

      optimizer="adam",

      batch_size=100,

      verbosity="high")



  #Use R2 classification metric
@@ -57,9 +63,8 @@ for trial in range(num_trials): 
  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 @@ for trial in range(num_trials): 
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/kinase/KINASE_tf_singletask.py

+20 −11
Original line number Diff line number Diff line
@@ -33,19 +33,29 @@ metric = dc.metrics.Metric(dc.metrics.pearson_r2_score, task_averager=np.mean) 
n_layers = 3

nb_epoch = 50

n_features = train_dataset.get_data_shape()[0]





def task_model_builder(m_dir):

  return dc.models.TensorflowMultitaskRegressor(

      n_tasks=1, n_features=n_features, logdir=m_dir,

      layer_sizes=[1000]*n_layers, dropouts=[.25]*n_layers,

      weight_init_stddevs=[.02]*n_layers, bias_init_consts=[1.]*n_layers,

      learning_rate=.0003, penalty=.0001, penalty_type="l2", optimizer="adam",

      n_tasks=1,

      n_features=n_features,

      logdir=m_dir,

      layer_sizes=[1000] * n_layers,

      dropouts=[.25] * n_layers,

      weight_init_stddevs=[.02] * n_layers,

      bias_init_consts=[1.] * n_layers,

      learning_rate=.0003,

      penalty=.0001,

      penalty_type="l2",

      optimizer="adam",

      batch_size=100)





all_results = []

for trial in range(num_trials):

  print("Starting trial %d" % trial)

  model = dc.models.SingletaskToMultitask(KINASE_tasks, task_model_builder,

                                          model_dir="KINASE_tf_singletask")

  model = dc.models.SingletaskToMultitask(

      KINASE_tasks, task_model_builder, model_dir="KINASE_tf_singletask")



  print("Fitting Model")

  model.fit(train_dataset, nb_epoch=nb_epoch, max_checkpoints_to_keep=1)
@@ -58,9 +68,8 @@ for trial in range(num_trials): 
  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("----------------------------------------------------------------")

  print("Scores for trial %d" % trial)
@@ -81,8 +90,8 @@ for trial in range(num_trials): 
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("----------------------------------------------------------------")

  print("Scores for trial %d" % trial)

  print("----------------------------------------------------------------")

examples/uv/UV_tf_model.py

+15 −10
Original line number Diff line number Diff line
@@ -33,11 +33,17 @@ for trial in range(num_trials): 
  n_layers = 3

  nb_epoch = 50

  model = dc.models.TensorflowMultitaskRegressor(

      len(UV_tasks), train_dataset.get_data_shape()[0],

      layer_sizes=[1000]*n_layers, dropouts=[.25]*n_layers,

      len(UV_tasks),

      train_dataset.get_data_shape()[0],

      layer_sizes=[1000] * n_layers,

      dropouts=[.25] * n_layers,

      weight_init_stddevs=[.02] * n_layers,

      bias_init_consts=[1.]*n_layers, learning_rate=.0003,

      penalty=.0001, penalty_type="l2", optimizer="adam", batch_size=100,

      bias_init_consts=[1.] * n_layers,

      learning_rate=.0003,

      penalty=.0001,

      penalty_type="l2",

      optimizer="adam",

      batch_size=100,

      logdir="UV_tf_model")



  #Use R2 classification metric
@@ -54,9 +60,8 @@ for trial in range(num_trials): 
  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("----------------------------------------------------------------")
@@ -76,8 +81,8 @@ for trial in range(num_trials): 
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("----------------------------------------------------------------")

CRA Git | Maintained and supported by SUSTech CRA and CCSE