Commit ba82f3b3 authored by Bharath Ramsundar's avatar Bharath Ramsundar
Browse files

Cleanup and test fix

parent d2aa9a97

deepchem/data/supports.py

+0 −4
Original line number Diff line number Diff line
@@ -174,10 +174,6 @@ def get_task_support(dataset, n_episodes, n_pos, n_neg, task, log_every_n=50): 
    if episode % log_every_n == 0:

      print("Sampling support %d" % episode)

    # No replacement allowed for supports

    ############################################################# DEBUG

    print("len(pos_mols), n_pos, len(neg_mols), n_neg")

    print(len(pos_mols), n_pos, len(neg_mols), n_neg)

    ############################################################# DEBUG

    pos_ids = np.random.choice(len(pos_mols), (n_pos,), replace=False)

    neg_ids = np.random.choice(len(neg_mols), (n_neg,), replace=False)

    pos_inds, neg_inds = pos_mols[pos_ids], neg_mols[neg_ids]

deepchem/models/tests/test_overfit.py

+12 −18
Original line number Diff line number Diff line
@@ -667,9 +667,8 @@ class TestOverfit(test_util.TensorFlowTestCase): 
      n_pos = 6

      n_neg = 4

      test_batch_size = 10

      n_train_trials = 60

      n_train_trials = 80

      support_batch_size = n_pos + n_neg

      replace = False

      

      # Load mini log-solubility dataset.

      featurizer = dc.feat.ConvMolFeaturizer()
@@ -705,10 +704,9 @@ class TestOverfit(test_util.TensorFlowTestCase): 
          verbosity="high")



        # Fit trained model. Dataset has 6 positives and 4 negatives, so set

        # n_pos/n_neg accordingly.  Set replace to false to ensure full dataset

        # is always passed in to support.

        model.fit(dataset, n_trials=n_train_trials, n_pos=n_pos,

                  n_neg=n_neg, replace=False)

        # n_pos/n_neg accordingly.

        model.fit(dataset, n_episodes_per_epoch=n_train_trials, n_pos=n_pos,

                  n_neg=n_neg)

        model.save()



        # Eval model on train. Dataset has 6 positives and 4 negatives, so set
@@ -738,8 +736,7 @@ class TestOverfit(test_util.TensorFlowTestCase): 
      n_neg = 4

      test_batch_size = 10

      support_batch_size = n_pos + n_neg

      n_train_trials = 60

      replace = False

      n_train_trials = 80

      

      # Load mini log-solubility dataset.

      featurizer = dc.feat.ConvMolFeaturizer()
@@ -780,10 +777,9 @@ class TestOverfit(test_util.TensorFlowTestCase): 
          verbosity="high")



        # Fit trained model. Dataset has 6 positives and 4 negatives, so set

        # n_pos/n_neg accordingly.  Set replace to false to ensure full dataset

        # is always passed in to support.

        model.fit(dataset, n_trials=n_train_trials, n_pos=n_pos, n_neg=n_neg,

                  replace=False)

        # n_pos/n_neg accordingly.

        model.fit(dataset, n_episodes_per_epoch=n_train_trials, n_pos=n_pos,

                  n_neg=n_neg)

        model.save()



        # Eval model on train. Dataset has 6 positives and 4 negatives, so set
@@ -811,8 +807,7 @@ class TestOverfit(test_util.TensorFlowTestCase): 
      n_neg = 4

      test_batch_size = 10

      support_batch_size = n_pos + n_neg

      n_train_trials = 60

      replace = False

      n_train_trials = 80

      

      # Load mini log-solubility dataset.

      featurizer = dc.feat.ConvMolFeaturizer()
@@ -853,11 +848,10 @@ class TestOverfit(test_util.TensorFlowTestCase): 
          verbosity="high")



        # Fit trained model. Dataset has 6 positives and 4 negatives, so set

        # n_pos/n_neg accordingly.  Set replace to false to ensure full dataset

        # is always passed in to support.

        # n_pos/n_neg accordingly.



        model.fit(dataset, n_trials=n_train_trials, n_pos=n_pos, n_neg=n_neg,

                  replace=False)

        model.fit(dataset, n_episodes_per_epoch=n_train_trials, n_pos=n_pos,

                  n_neg=n_neg)

        model.save()



        # Eval model on train. Dataset has 6 positives and 4 negatives, so set

deepchem/models/tf_keras_models/support_classifier.py

+1 −23
Original line number Diff line number Diff line
@@ -134,7 +134,7 @@ class SupportGraphClassifier(Model): 
    feed_total, run_total, test_total = 0, 0, 0

    # Create different support sets

    support_generator = SupportGenerator(dataset, range(n_tasks),

        n_pos, n_neg, n_trials, replace)

        n_pos, n_neg, n_trials)

    recent_losses = []

    for ind, (task, support) in enumerate(support_generator):

      if ind % log_every_n_samples == 0:
@@ -204,10 +204,6 @@ class SupportGraphClassifier(Model): 
      for ind, (task, support, test) in enumerate(episode_generator):

        if ind % log_every_n_samples == 0:

          print("Epoch %d, Sample %d from task %s" % (epoch, ind, str(task)))

          ############################################################### DEBUG

          print("task, len(support), len(test)")

          print(task, len(support), len(test))

          ############################################################### DEBUG

        # Get batch to try it out on

        feed_start = time.time()

        feed_dict = self.construct_feed_dict(test, support)
@@ -402,8 +398,6 @@ class SupportGraphClassifier(Model): 
      Number of negative samples per support.

    exclude_support: bool, optional

      Whether support set should be excluded when computing model accuracy.

    replace: bool, optional

      Whether or not to use replacement when sampling supports.

    """

    # Get batches

    test_tasks = range(len(dataset.get_task_names()))
@@ -420,22 +414,6 @@ class SupportGraphClassifier(Model): 
        print("Keeping support datapoints for eval.")

        task_dataset = get_task_dataset(dataset, task)

      y_pred = self.predict_proba(support, task_dataset)

      ################################################################ DEBUG

      task_y = dataset.y[:, task]

      task_w = dataset.w[:, task]

      print("Number of y elements (including missing data)")

      print(len(task_y))

      task_y = task_y[task_w != 0]

      print("Number of y elements (excluding missing data)")

      print(len(task_y))

      print("Verifying that no elements were dropped.")

      print("len(task_y), len(support), len(task_dataset)")

      print(len(task_y), len(support), len(task_dataset))

      assert len(task_y) == len(support) + len(task_dataset)

      print("Verifying that task_dataset doesn't overlap with support.")

      for task_id in task_dataset.ids:

        assert task_id not in set(support.ids)

      ################################################################ DEBUG

      task_scores[task].append(metric.compute_metric(

          task_dataset.y, y_pred, task_dataset.w))

CRA Git | Maintained and supported by SUSTech CRA and CCSE