Unverified Commit c099b76b authored by Karl Leswing's avatar Karl Leswing Committed by GitHub
Browse files

Merge pull request #1042 from miaecle/temp3 

MolNet update
parents 9e553fca 29a97407

deepchem/data/datasets.py

+4 −2
Original line number Diff line number Diff line
@@ -789,11 +789,13 @@ class DiskDataset(Dataset): 
        else:

          shard_batch_size = batch_size



        num_local_batches = math.ceil(n_shard_samples / shard_batch_size)



        if n_shard_samples == 0:

          cur_shard += 1

          if batch_size is None:

            cur_global_batch += 1

          continue



        num_local_batches = math.ceil(n_shard_samples / shard_batch_size)

        if not deterministic:

          sample_perm = np.random.permutation(n_shard_samples)

        else:

deepchem/models/tensorgraph/layers.py

+31 −0
Original line number Diff line number Diff line
@@ -1562,6 +1562,37 @@ class ReduceMean(Layer): 
    return out_tensor





class ReduceMax(Layer):



  def __init__(self, in_layers=None, axis=None, **kwargs):

    if axis is not None and not isinstance(axis, Sequence):

      axis = [axis]

    self.axis = axis

    super(ReduceMax, self).__init__(in_layers, **kwargs)

    if axis is None:

      self._shape = tuple()

    else:

      try:

        parent_shape = self.in_layers[0].shape

        self._shape = [

            parent_shape[i] for i in range(len(parent_shape)) if i not in axis

        ]

      except:

        pass



  def create_tensor(self, in_layers=None, set_tensors=True, **kwargs):

    inputs = self._get_input_tensors(in_layers)

    if len(inputs) > 1:

      self.out_tensor = tf.stack(inputs)

    else:

      self.out_tensor = inputs[0]



    out_tensor = tf.reduce_max(self.out_tensor, axis=self.axis)

    if set_tensors:

      self.out_tensor = out_tensor

    return out_tensor





class ToFloat(Layer):



  def __init__(self, in_layers=None, **kwargs):

deepchem/models/tensorgraph/models/graph_models.py

+28 −6
Original line number Diff line number Diff line
@@ -139,7 +139,7 @@ class WeaveTensorGraph(TensorGraph): 
          pad_batches=pad_batches):



        feed_dict = dict()

        if y_b is not None and not predict:

        if y_b is not None:

          for index, label in enumerate(self.labels_fd):

            if self.mode == "classification":

              feed_dict[label] = to_one_hot(y_b[:, index])
@@ -182,6 +182,17 @@ class WeaveTensorGraph(TensorGraph): 
        feed_dict[self.atom_to_pair] = np.concatenate(atom_to_pair, axis=0)

        yield feed_dict



  def predict_on_generator(self, generator, transformers=[], outputs=None):

    out = super(WeaveTensorGraph, self).predict_on_generator(

        generator, transformers=[], outputs=outputs)

    if outputs is None:

      outputs = self.outputs

    if len(outputs) > 1:

      out = np.stack(out, axis=1)



    out = undo_transforms(out, transformers)

    return out





class DTNNTensorGraph(TensorGraph):
@@ -193,7 +204,7 @@ class DTNNTensorGraph(TensorGraph): 
               distance_min=-1,

               distance_max=18,

               output_activation=True,

               mode="classification",

               mode="regression",

               **kwargs):

    """

            Parameters
@@ -294,7 +305,7 @@ class DTNNTensorGraph(TensorGraph): 
          pad_batches=pad_batches):



        feed_dict = dict()

        if y_b is not None and not predict:

        if y_b is not None:

          for index, label in enumerate(self.labels_fd):

            feed_dict[label] = y_b[:, index:index + 1]

        if w_b is not None:
@@ -456,7 +467,7 @@ class DAGTensorGraph(TensorGraph): 
          pad_batches=pad_batches):



        feed_dict = dict()

        if y_b is not None and not predict:

        if y_b is not None:

          for index, label in enumerate(self.labels_fd):

            if self.mode == "classification":

              feed_dict[label] = to_one_hot(y_b[:, index])
@@ -496,6 +507,17 @@ class DAGTensorGraph(TensorGraph): 
        feed_dict[self.n_atoms] = n_atoms

        yield feed_dict



  def predict_on_generator(self, generator, transformers=[], outputs=None):

    out = super(DAGTensorGraph, self).predict_on_generator(

        generator, transformers=[], outputs=outputs)

    if outputs is None:

      outputs = self.outputs

    if len(outputs) > 1:

      out = np.stack(out, axis=1)



    out = undo_transforms(out, transformers)

    return out





class PetroskiSuchTensorGraph(TensorGraph):

  """
@@ -1034,7 +1056,7 @@ class MPNNTensorGraph(TensorGraph): 
          pad_batches=pad_batches):



        feed_dict = dict()

        if y_b is not None and not predict:

        if y_b is not None:

          for index, label in enumerate(self.labels_fd):

            if self.mode == "classification":

              feed_dict[label] = to_one_hot(y_b[:, index])
@@ -1099,7 +1121,7 @@ class MPNNTensorGraph(TensorGraph): 
      results = []

      for feed_dict in generator:

        # Extract number of unique samples in the batch from w_b

        n_valid_samples = len(np.nonzero(feed_dict[self.weights][:, 0])[0])

        n_valid_samples = len(np.nonzero(np.sum(feed_dict[self.weights], 1))[0])

        feed_dict = {

            self.layers[k.name].out_tensor: v

            for k, v in six.iteritems(feed_dict)

deepchem/models/tensorgraph/models/text_cnn.py

+18 −10
Original line number Diff line number Diff line
@@ -10,7 +10,7 @@ import copy 
from deepchem.metrics import to_one_hot, from_one_hot

from deepchem.models.tensorgraph.layers import Dense, Concat, SoftMax, \

  SoftMaxCrossEntropy, BatchNorm, WeightedError, Dropout, BatchNormalization, \

  Conv1D, MaxPool1D, Squeeze, Stack, Highway

  Conv1D, ReduceMax, Squeeze, Stack, Highway

from deepchem.models.tensorgraph.graph_layers import DTNNEmbedding



from deepchem.models.tensorgraph.layers import L2Loss, Label, Weights, Feature
@@ -104,6 +104,8 @@ class TextCNNTensorGraph(TensorGraph): 
      Properties of filters used in the conv net

    num_filters: list of int, optional

      Properties of filters used in the conv net

    dropout: float, optional

      Dropout rate

    mode: str

      Either "classification" or "regression" for type of model.

    """
@@ -174,15 +176,10 @@ class TextCNNTensorGraph(TensorGraph): 
              in_layers=[self.Embedding]))

      # Max-over-time pooling

      self.pooled_outputs.append(

          MaxPool1D(

              window_shape=self.seq_length - filter_size + 1,

              strides=1,

              padding='VALID',

              in_layers=[self.conv_layers[-1]]))

          ReduceMax(axis=1, in_layers=[self.conv_layers[-1]]))

    # Concat features from all filters(one feature per filter)

    concat_outputs = Concat(axis=2, in_layers=self.pooled_outputs)

    outputs = Squeeze(squeeze_dims=1, in_layers=concat_outputs)

    dropout = Dropout(dropout_prob=self.dropout, in_layers=[outputs])

    concat_outputs = Concat(axis=1, in_layers=self.pooled_outputs)

    dropout = Dropout(dropout_prob=self.dropout, in_layers=[concat_outputs])

    dense = Dense(

        out_channels=200, activation_fn=tf.nn.relu, in_layers=[dropout])

    # Highway layer from https://arxiv.org/pdf/1505.00387.pdf
@@ -211,7 +208,7 @@ class TextCNNTensorGraph(TensorGraph): 
        cost = L2Loss(in_layers=[label, regression])

        costs.append(cost)

    if self.mode == "classification":

      all_cost = Concat(in_layers=costs, axis=1)

      all_cost = Stack(in_layers=costs, axis=1)

    elif self.mode == "regression":

      all_cost = Stack(in_layers=costs, axis=1)

    self.weights = Weights(shape=(None, self.n_tasks))
@@ -272,3 +269,14 @@ class TextCNNTensorGraph(TensorGraph): 
      # Padding with '_'

      seq.append(self.char_dict['_'])

    return np.array(seq)



  def predict_on_generator(self, generator, transformers=[], outputs=None):

    out = super(TextCNNTensorGraph, self).predict_on_generator(

        generator, transformers=[], outputs=outputs)

    if outputs is None:

      outputs = self.outputs

    if len(outputs) > 1:

      out = np.stack(out, axis=1)



    out = undo_transforms(out, transformers)

    return out

deepchem/molnet/check_availability.py

+28 −1
Original line number Diff line number Diff line
@@ -9,6 +9,8 @@ CheckFeaturizer = { 
    ('bace_c', 'graphconv'): ['GraphConv', 75],

    ('bace_c', 'dag'): ['GraphConv', 75],

    ('bace_c', 'weave'): ['Weave', 75],

    ('bace_c', 'textcnn'): ['Raw', None],

    ('bace_c', 'mpnn'): ['Weave', [75, 14]],

    ('bbbp', 'logreg'): ['ECFP', 1024],

    ('bbbp', 'tf'): ['ECFP', 1024],

    ('bbbp', 'tf_robust'): ['ECFP', 1024],
@@ -19,6 +21,8 @@ CheckFeaturizer = { 
    ('bbbp', 'graphconv'): ['GraphConv', 75],

    ('bbbp', 'dag'): ['GraphConv', 75],

    ('bbbp', 'weave'): ['Weave', 75],

    ('bbbp', 'textcnn'): ['Raw', None],

    ('bbbp', 'mpnn'): ['Weave', [75, 14]],

    ('clintox', 'logreg'): ['ECFP', 1024],

    ('clintox', 'tf'): ['ECFP', 1024],

    ('clintox', 'tf_robust'): ['ECFP', 1024],
@@ -29,6 +33,8 @@ CheckFeaturizer = { 
    ('clintox', 'graphconv'): ['GraphConv', 75],

    ('clintox', 'dag'): ['GraphConv', 75],

    ('clintox', 'weave'): ['Weave', 75],

    ('clintox', 'textcnn'): ['Raw', None],

    ('clintox', 'mpnn'): ['Weave', [75, 14]],

    ('hiv', 'logreg'): ['ECFP', 1024],

    ('hiv', 'tf'): ['ECFP', 1024],

    ('hiv', 'tf_robust'): ['ECFP', 1024],
@@ -39,6 +45,8 @@ CheckFeaturizer = { 
    ('hiv', 'graphconv'): ['GraphConv', 75],

    ('hiv', 'dag'): ['GraphConv', 75],

    ('hiv', 'weave'): ['Weave', 75],

    ('hiv', 'textcnn'): ['Raw', None],

    ('hiv', 'mpnn'): ['Weave', [75, 14]],

    ('muv', 'logreg'): ['ECFP', 1024],

    ('muv', 'tf'): ['ECFP', 1024],

    ('muv', 'tf_robust'): ['ECFP', 1024],
@@ -51,6 +59,8 @@ CheckFeaturizer = { 
    ('muv', 'attn'): ['GraphConv', 75],

    ('muv', 'res'): ['GraphConv', 75],

    ('muv', 'weave'): ['Weave', 75],

    ('muv', 'textcnn'): ['Raw', None],

    ('muv', 'mpnn'): ['Weave', [75, 14]],

    ('pcba', 'logreg'): ['ECFP', 1024],

    ('pcba', 'tf'): ['ECFP', 1024],

    ('pcba', 'tf_robust'): ['ECFP', 1024],
@@ -58,6 +68,7 @@ CheckFeaturizer = { 
    ('pcba', 'xgb'): ['ECFP', 1024],

    ('pcba', 'graphconv'): ['GraphConv', 75],

    ('pcba', 'weave'): ['Weave', 75],

    ('pcba', 'textcnn'): ['Raw', None],

    ('pcba_146', 'logreg'): ['ECFP', 1024],

    ('pcba_146', 'tf'): ['ECFP', 1024],

    ('pcba_146', 'tf_robust'): ['ECFP', 1024],
@@ -85,6 +96,8 @@ CheckFeaturizer = { 
    ('sider', 'siamese'): ['GraphConv', 75],

    ('sider', 'attn'): ['GraphConv', 75],

    ('sider', 'res'): ['GraphConv', 75],

    ('sider', 'textcnn'): ['Raw', None],

    ('sider', 'mpnn'): ['Weave', [75, 14]],

    ('tox21', 'logreg'): ['ECFP', 1024],

    ('tox21', 'tf'): ['ECFP', 1024],

    ('tox21', 'tf_robust'): ['ECFP', 1024],
@@ -98,6 +111,8 @@ CheckFeaturizer = { 
    ('tox21', 'siamese'): ['GraphConv', 75],

    ('tox21', 'attn'): ['GraphConv', 75],

    ('tox21', 'res'): ['GraphConv', 75],

    ('tox21', 'textcnn'): ['Raw', None],

    ('tox21', 'mpnn'): ['Weave', [75, 14]],

    ('toxcast', 'logreg'): ['ECFP', 1024],

    ('toxcast', 'tf'): ['ECFP', 1024],

    ('toxcast', 'tf_robust'): ['ECFP', 1024],
@@ -107,6 +122,8 @@ CheckFeaturizer = { 
    ('toxcast', 'xgb'): ['ECFP', 1024],

    ('toxcast', 'graphconv'): ['GraphConv', 75],

    ('toxcast', 'weave'): ['Weave', 75],

    ('toxcast', 'textcnn'): ['Raw', None],

    ('toxcast', 'mpnn'): ['Weave', [75, 14]],

    ('bace_r', 'tf_regression'): ['ECFP', 1024],

    ('bace_r', 'rf_regression'): ['ECFP', 1024],

    ('bace_r', 'krr'): ['ECFP', 1024],
@@ -114,6 +131,7 @@ CheckFeaturizer = { 
    ('bace_r', 'graphconvreg'): ['GraphConv', 75],

    ('bace_r', 'dag_regression'): ['GraphConv', 75],

    ('bace_r', 'weave_regression'): ['Weave', 75],

    ('bace_r', 'textcnn_regression'): ['Raw', None],

    ('chembl', 'tf_regression'): ['ECFP', 1024],

    ('chembl', 'rf_regression'): ['ECFP', 1024],

    ('chembl', 'krr'): ['ECFP', 1024],
@@ -135,6 +153,7 @@ CheckFeaturizer = { 
    ('delaney', 'dag_regression'): ['GraphConv', 75],

    ('delaney', 'weave_regression'): ['Weave', 75],

    ('delaney', 'mpnn'): ['Weave', [75, 14]],

    ('delaney', 'textcnn_regression'): ['Raw', None],

    ('hopv', 'tf_regression'): ['ECFP', 1024],

    ('hopv', 'rf_regression'): ['ECFP', 1024],

    ('hopv', 'krr'): ['ECFP', 1024],
@@ -150,6 +169,7 @@ CheckFeaturizer = { 
    ('lipo', 'dag_regression'): ['GraphConv', 75],

    ('lipo', 'weave_regression'): ['Weave', 75],

    ('lipo', 'mpnn'): ['Weave', [75, 14]],

    ('lipo', 'textcnn_regression'): ['Raw', None],

    ('nci', 'tf_regression'): ['ECFP', 1024],

    ('nci', 'rf_regression'): ['ECFP', 1024],

    ('nci', 'krr'): ['ECFP', 1024],
@@ -171,6 +191,7 @@ CheckFeaturizer = { 
    ('sampl', 'dag_regression'): ['GraphConv', 75],

    ('sampl', 'weave_regression'): ['Weave', 75],

    ('sampl', 'mpnn'): ['Weave', [75, 14]],

    ('sampl', 'textcnn_regression'): ['Raw', None],

    ('kaggle', 'tf_regression'): [None, 14293],

    ('kaggle', 'rf_regression'): [None, 14293],

    ('kaggle', 'krr'): [None, 14293],
@@ -182,7 +203,9 @@ CheckFeaturizer = { 
    ('qm7', 'rf_regression'): ['ECFP', 1024],

    ('qm7', 'krr'): ['ECFP', 1024],

    ('qm7', 'krr_ft'): ['CoulombMatrix', 1024],

    ('qm7', 'textcnn_regression'): ['Raw', None],

    ('qm7', 'graphconvreg'): ['GraphConv', 75],

    ('qm7', 'weave_regression'): ['Weave', 75],

    ('qm7', 'tf_regression_ft'): ['CoulombMatrix', [23, 23]],

    ('qm7', 'dtnn'): ['CoulombMatrix', [23, 23]],

    ('qm7', 'ani'): ['BPSymmetryFunction', [23, 4]],
@@ -198,6 +221,8 @@ CheckFeaturizer = { 
    ('qm8', 'dtnn'): ['CoulombMatrix', [26, 26]],

    ('qm8', 'ani'): ['BPSymmetryFunction', [26, 4]],

    ('qm8', 'mpnn'): ['MP', [70, 8]],

    ('qm8', 'weave_regression'): ['Weave', 75],

    ('qm8', 'textcnn_regression'): ['Raw', None],

    ('qm9', 'tf_regression'): ['ECFP', 1024],

    ('qm9', 'rf_regression'): ['ECFP', 1024],

    ('qm9', 'krr'): ['ECFP', 1024],
@@ -206,7 +231,9 @@ CheckFeaturizer = { 
    ('qm9', 'krr_ft'): ['CoulombMatrix', 1024],

    ('qm9', 'dtnn'): ['CoulombMatrix', [29, 29]],

    ('qm9', 'ani'): ['BPSymmetryFunction', [29, 4]],

    ('qm9', 'mpnn'): ['MP', [70, 8]]

    ('qm9', 'mpnn'): ['MP', [70, 8]],

    ('qm9', 'weave_regression'): ['Weave', 75],

    ('qm9', 'textcnn_regression'): ['Raw', None]

}



CheckSplit = {

CRA Git | Maintained and supported by SUSTech CRA and CCSE