Commit 4e6c16a5 authored by Ubuntu's avatar Ubuntu
Browse files

reverted examples

parent ff727ace

examples/bace/bace_datasets.py

+7 −12
Original line number Diff line number Diff line
@@ -10,7 +10,6 @@ import deepchem 
import tempfile

import deepchem as dc





def load_bace(mode="regression", transform=True, split="20-80"):

  """Load BACE-1 dataset as regression/classification problem."""

  assert split in ["20-80", "80-20"]
@@ -18,11 +17,11 @@ def load_bace(mode="regression", transform=True, split="20-80"): 


  current_dir = os.path.dirname(os.path.realpath(__file__))

  if split == "20-80":

    dataset_file = os.path.join(current_dir,

                                "../../datasets/desc_canvas_aug30.csv")

    dataset_file = os.path.join(

        current_dir, "../../datasets/desc_canvas_aug30.csv")

  elif split == "80-20":

    dataset_file = os.path.join(current_dir,

                                "../../datasets/rev8020split_desc.csv")

    dataset_file = os.path.join(

        current_dir, "../../datasets/rev8020split_desc.csv")



  crystal_dataset_file = os.path.join(

      current_dir, "../../datasets/crystal_desc_canvas_aug30.csv")
@@ -33,9 +32,7 @@ def load_bace(mode="regression", transform=True, split="20-80"): 
    bace_tasks = ["Class"]

  featurizer = dc.feat.UserDefinedFeaturizer(user_specified_features)

  loader = dc.data.UserCSVLoader(

      tasks=bace_tasks,

      smiles_field="mol",

      id_field="CID",

      tasks=bace_tasks, smiles_field="mol", id_field="CID",

      featurizer=featurizer)

  dataset = loader.featurize(dataset_file)

  crystal_dataset = loader.featurize(crystal_dataset_file)
@@ -58,12 +55,10 @@ def load_bace(mode="regression", transform=True, split="20-80"): 


  transformers = [

      NormalizationTransformer(transform_X=True, dataset=train_dataset),

      ClippingTransformer(transform_X=True, dataset=train_dataset)

  ]

      ClippingTransformer(transform_X=True, dataset=train_dataset)]

  if mode == "regression":

    transformers += [

        NormalizationTransformer(transform_y=True, dataset=train_dataset)

    ]

      NormalizationTransformer(transform_y=True, dataset=train_dataset)]

  

  for dataset in [train_dataset, valid_dataset, test_dataset, crystal_dataset]:

    for transformer in transformers:

examples/bace/bace_dnn.py

+6 −13
Original line number Diff line number Diff line
@@ -19,8 +19,7 @@ from deepchem.models.keras_models import KerasModel 
def bace_dnn_model(mode="classification", verbosity="high", split="20-80"):

  """Train fully-connected DNNs on BACE dataset."""

  (bace_tasks, train_dataset, valid_dataset, test_dataset, crystal_dataset,

   transformers) = load_bace(

       mode=mode, transform=True, split=split)

   transformers) = load_bace(mode=mode, transform=True, split=split)



  if mode == "regression":

    r2_metric = Metric(metrics.r2_score, verbosity=verbosity)
@@ -39,26 +38,21 @@ def bace_dnn_model(mode="classification", verbosity="high", split="20-80"): 
  else:

    raise ValueError("Invalid mode %s" % mode)



  params_dict = {

      "learning_rate": np.power(10., np.random.uniform(-5, -3, size=5)),

  params_dict = {"learning_rate": np.power(10., np.random.uniform(-5, -3, size=5)),

                 "decay": np.power(10, np.random.uniform(-6, -4, size=5)),

      "nb_epoch": [40]

  }

                 "nb_epoch": [40] }



  n_features = train_dataset.get_data_shape()[0]



  def model_builder(model_params, model_dir):

    keras_model = MultiTaskDNN(

        len(bace_tasks),

        n_features,

        "classification",

        dropout=.5,

        len(bace_tasks), n_features, "classification", dropout=.5,

        **model_params)

    return KerasModel(keras_model, model_dir)



  optimizer = HyperparamOpt(model_builder, verbosity="low")

  best_dnn, best_hyperparams, all_results = optimizer.hyperparam_search(

      params_dict, train_dataset, valid_dataset, transformers, metric=metric)

      params_dict, train_dataset, valid_dataset, transformers,

      metric=metric)



  if len(train_dataset) > 0:

    dnn_train_evaluator = Evaluator(best_dnn, train_dataset, transformers)
@@ -92,7 +86,6 @@ def bace_dnn_model(mode="classification", verbosity="high", split="20-80"): 
        all_metrics, csv_out=csv_out, stats_out=stats_out)

    print("DNN Crystal set %s: %s" % (metric.name, str(dnn_crystal_score)))





if __name__ == "__main__":

  print("Classifier DNN 20-80:")

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

examples/bace/bace_features.py

+1 −222

File changed.

Preview size limit exceeded, changes collapsed.

examples/bace/bace_rf.py

+9 −13
Original line number Diff line number Diff line
@@ -11,12 +11,10 @@ from deepchem import metrics 
from deepchem.metrics import Metric

from deepchem.utils.evaluate import Evaluator





def bace_rf_model(mode="classification", verbosity="high", split="20-80"):

  """Train random forests on BACE dataset."""

  (bace_tasks, train_dataset, valid_dataset, test_dataset, crystal_dataset,

   transformers) = load_bace(

       mode=mode, transform=False, split=split)

   transformers) = load_bace(mode=mode, transform=False, split=split)



  if mode == "regression":

    r2_metric = Metric(metrics.r2_score, verbosity=verbosity)
@@ -25,7 +23,6 @@ def bace_rf_model(mode="classification", verbosity="high", split="20-80"): 
    all_metrics = [r2_metric, rms_metric, mae_metric]

    metric = r2_metric

    model_class = RandomForestRegressor



    def rf_model_builder(model_params, model_dir):

      sklearn_model = RandomForestRegressor(**model_params)

      return SklearnModel(sklearn_model, model_dir)
@@ -38,7 +35,6 @@ def bace_rf_model(mode="classification", verbosity="high", split="20-80"): 
    model_class = RandomForestClassifier

    all_metrics = [accuracy_metric, mcc_metric, recall_metric, roc_auc_metric]

    metric = roc_auc_metric 



    def rf_model_builder(model_params, model_dir):

      sklearn_model = RandomForestClassifier(**model_params)

      return SklearnModel(sklearn_model, model_dir)
@@ -52,11 +48,12 @@ def bace_rf_model(mode="classification", verbosity="high", split="20-80"): 


  optimizer = HyperparamOpt(rf_model_builder, verbosity="low")

  best_rf, best_rf_hyperparams, all_rf_results = optimizer.hyperparam_search(

      params_dict, train_dataset, valid_dataset, transformers, metric=metric)

      params_dict, train_dataset, valid_dataset, transformers,

      metric=metric)



  if len(train_dataset) > 0:

    rf_train_evaluator = Evaluator(

        best_rf, train_dataset, transformers, verbosity=verbosity)

    rf_train_evaluator = Evaluator(best_rf, train_dataset, transformers,

                                   verbosity=verbosity)

    csv_out = "rf_%s_%s_train.csv" % (mode, split)

    stats_out = "rf_%s_%s_train_stats.txt" % (mode, split)

    rf_train_score = rf_train_evaluator.compute_model_performance(
@@ -64,8 +61,8 @@ def bace_rf_model(mode="classification", verbosity="high", split="20-80"): 
    print("RF Train set scores: %s" % (str(rf_train_score)))



  if len(valid_dataset) > 0:

    rf_valid_evaluator = Evaluator(

        best_rf, valid_dataset, transformers, verbosity=verbosity)

    rf_valid_evaluator = Evaluator(best_rf, valid_dataset, transformers,

                                   verbosity=verbosity)

    csv_out = "rf_%s_%s_valid.csv" % (mode, split)

    stats_out = "rf_%s_%s_valid_stats.txt" % (mode, split)

    rf_valid_score = rf_valid_evaluator.compute_model_performance(
@@ -73,8 +70,8 @@ def bace_rf_model(mode="classification", verbosity="high", split="20-80"): 
    print("RF Valid set scores: %s" % (str(rf_valid_score)))



  if len(test_dataset) > 0:

    rf_test_evaluator = Evaluator(

        best_rf, test_dataset, transformers, verbosity=verbosity)

    rf_test_evaluator = Evaluator(best_rf, test_dataset, transformers,

                                  verbosity=verbosity)

    csv_out = "rf_%s_%s_test.csv" % (mode, split)

    stats_out = "rf_%s_%s_test_stats.txt" % (mode, split)

    rf_test_score = rf_test_evaluator.compute_model_performance(
@@ -90,7 +87,6 @@ def bace_rf_model(mode="classification", verbosity="high", split="20-80"): 
        all_metrics, csv_out=csv_out, stats_out=stats_out)

    print("RF Crystal set: %s" % (str(rf_crystal_score)))





if __name__ == "__main__":

  print("Classifier RF 20-80:")

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

examples/benchmark.py

+3 −6
Original line number Diff line number Diff line
@@ -228,8 +228,7 @@ def benchmark_loading_datasets(hyper_parameters, 
      if mode == 'classification':

        for i in train_score:

          output_line = [

              count, dataset,

              str(split), mode, 'train', i,

              count, dataset, str(split), mode, 'train', i,

              train_score[i]['mean-roc_auc_score'], 'valid', i,

              valid_score[i]['mean-roc_auc_score']

          ]
@@ -242,8 +241,7 @@ def benchmark_loading_datasets(hyper_parameters, 
        for i in train_score:

          if metric == 'r2':

            output_line = [

                count, dataset,

                str(split), mode, 'train', i,

                count, dataset, str(split), mode, 'train', i,

                train_score[i]['mean-pearson_r2_score'], 'valid', i,

                valid_score[i]['mean-pearson_r2_score']

            ]
@@ -254,8 +252,7 @@ def benchmark_loading_datasets(hyper_parameters, 
                ['time_for_running', time_finish_fitting - time_start_fitting])

          elif metric == 'mae':

            output_line = [

                count, dataset,

                str(split), mode, 'train', i,

                count, dataset, str(split), mode, 'train', i,

                train_score[i]['mean-mean_absolute_error'], 'valid', i,

                valid_score[i]['mean-mean_absolute_error']

            ]

CRA Git | Maintained and supported by SUSTech CRA and CCSE