Merge pull request #167 from rbharath/featurization_fix

  # perform common train/test split across all tasks

  n_samples = df.shape[0]

  n_tasks = len(tasks)

  n_features = None

  y = df[tasks].values

  y = np.reshape(y, (n_samples, n_tasks))

  w = np.ones((n_samples, n_tasks))

  missing = np.zeros_like(y).astype(int)

  tensors = []

  feature_shape = None

  for ind in range(n_samples):

    datapoint = df.iloc[ind]

    feature_list = []

        if features[feature_ind] == "":

          features[feature_ind] = 0.

      features = features.astype(float)

      n_features = features.shape[0]

      if feature_shape is None:

        feature_shape = features.shape

    except ValueError:

      missing[ind, :] = 1

      continue

    for task in range(n_tasks):

      if y[ind, task] == "":

        missing[ind, task] = 1

    if features.shape != feature_shape:

      missing[ind, :] = 1

      continue

    tensors.append(features)

  x = np.stack(tensors)

  sorted_ids = df["mol_id"]

      for i, mol in enumerate(mols):

        if verbosity is not None and i % log_every_n == 0:

          log("Featurizing %d / %d" % (i, len(mols)))

        features = [self._featurize(mol) for mol in mols]

        if mol is not None:

          features.append(self._featurize(mol))

        else:

          features.append(np.array([]))

    if self.conformers:

      features = self.conformer_container(mols, features)

    Returns:

      A numpy array containing metric values for each task.

    """

    print("y_true.shape, y_pred.shape")

    print(y_true.shape, y_pred.shape)

    assert y_true.shape[0] == y_pred.shape[0] == w.shape[0]

    n_samples, n_tasks = y_true.shape[0], y_true.shape[1] 

    if self.mode == "classification":

    Raises:

      NotImplementedError: If metric_str is not in METRICS.

    """

    print("compute_singletask_metric()")

    y_true = np.array(np.squeeze(y_true[w != 0]))

    y_pred = np.array(np.squeeze(y_pred[w != 0]))

    if len(y_true.shape) == 0:

    return tf.name_scope(self._name_scopes[name])

  def add_training_cost(self):

    print(self.output)

    with self.graph.as_default():

      self.require_attributes(['output', 'labels', 'weights'])

      epsilon = 1e-3  # small float to avoid dividing by zero