Commit 51730d4e authored by Bharath Ramsundar's avatar Bharath Ramsundar
Browse files

First graph-conv example on large dataset.

parent 335545f1

deepchem/__init__.py

+16 −0
Original line number Diff line number Diff line 
"""

Imports all submodules 

"""

from __future__ import print_function

from __future__ import division

from __future__ import unicode_literals



import deepchem.datasets

import deepchem.featurizers

import deepchem.hyperparameters

import deepchem.metrics

import deepchem.models

import deepchem.nn

import deepchem.splits

import deepchem.transformers

import deepchem.utils

deepchem/models/__init__.py

+25 −0
Original line number Diff line number Diff line
@@ -14,6 +14,7 @@ import joblib 
import os

import tempfile

import sklearn



from deepchem.datasets import Dataset, pad_features

from deepchem.transformers import undo_transforms

from deepchem.transformers import undo_grad_transforms
@@ -21,6 +22,7 @@ from deepchem.utils.save import load_from_disk 
from deepchem.utils.save import save_to_disk

from deepchem.utils.save import log

from deepchem.datasets import pad_batch

from deepchem.utils.evaluate import Evaluator





class Model(object):
@@ -175,6 +177,29 @@ class Model(object): 
      y_pred = np.reshape(y_pred, (n_samples,)) 

    return y_pred



  def evaluate(self, dataset, metrics, transformers=[]):

    """

    Evaluates the performance of this model on specified dataset.

  

    Parameters

    ----------

    dataset: deepchem.datasets.Dataset

      Dataset object.

    metric: deepchem.metrics.Metric

      Evaluation metric

    transformers: list

      List of deepchem.transformers.Transformer



    Returns

    -------

    dict

      Maps tasks to scores under metric.

    """

    evaluator = Evaluator(self, dataset, transformers,

                          verbosity=self.verbosity)

    scores = evaluator.compute_model_performance(metrics)

    return scores



  def predict_grad(self, dataset, transformers=[], batch_size=50):

    """

    Uses self to calculate gradient on provided Dataset object.

deepchem/models/tf_keras_models/multitask_classifier.py

+11 −4
Original line number Diff line number Diff line
@@ -176,9 +176,12 @@ class MultitaskGraphClassifier(Model): 
    # Perform the optimization

    log("Training for %d epochs" % nb_epoch, self.verbosity)

  

    # TODO(rbharath): Disabling saving for now to try to debug.

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

    # Save an initial checkpoint.

    saver = tf.train.Saver(max_to_keep=max_checkpoints_to_keep)

    saver.save(self.sess, self._save_path, global_step=0)

    #saver = tf.train.Saver(max_to_keep=max_checkpoints_to_keep)

    #saver.save(self.sess, self._save_path, global_step=0)

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

    for epoch in range(nb_epoch):

      # TODO(rbharath): This decay shouldn't be hard-coded.

      lr = self.learning_rate / (1 + float(epoch) / self.T)
@@ -192,9 +195,13 @@ class MultitaskGraphClassifier(Model): 
        self.sess.run(

            self.train_op,

            feed_dict=self.construct_feed_dict(X_b, y_b, w_b))

      saver.save(self.sess, self._save_path, global_step=epoch)

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

      #saver.save(self.sess, self._save_path, global_step=epoch)

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

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

    # Always save a final checkpoint when complete.

    saver.save(self.sess, self._save_path, global_step=epoch+1)

    #saver.save(self.sess, self._save_path, global_step=epoch+1)

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



  def save(self):

    """

deepchem/nn/__init__.py

0 → 100644
+11 −0
Original line number Diff line number Diff line 
"""

Imports a number of useful deep learning primitives into one place.

"""

from __future__ import print_function

from __future__ import division

from __future__ import unicode_literals



from keras.layers import Dense, BatchNormalization

from deepchem.models.tf_keras_models.keras_layers import GraphConv

from deepchem.models.tf_keras_models.keras_layers import GraphPool

from deepchem.models.tf_keras_models.keras_layers import GraphGather

examples/tox21/tox21_datasets.py

+65 −0
Original line number Diff line number Diff line
@@ -10,6 +10,7 @@ import numpy as np 
import shutil

from deepchem.utils.save import load_from_disk

from deepchem.featurizers.featurize import DataLoader

from deepchem.featurizers.graph_features import ConvMolFeaturizer

from deepchem.featurizers.fingerprints import CircularFingerprint

from deepchem.datasets import DiskDataset

from deepchem.transformers import BalancingTransformer
@@ -78,3 +79,67 @@ def load_tox21(base_dir, reload=True, num_train=7200): 
                                     w_valid, ids_valid, tox21_tasks)

  

  return tox21_tasks, (train_dataset, valid_dataset), transformers



def load_tox21_convmol(base_dir=None, num_train=7200):

  """Load Tox21 datasets with conv feat. Does not do train/test split"""

  # Set some global variables up top

  verbosity = "high"

  if base_dir is None:

    base_dir = tempfile.mkdtemp()



  # Create some directories for analysis

  # The base_dir holds the results of all analysis

  if os.path.exists(base_dir):

    shutil.rmtree(base_dir)

  if not os.path.exists(base_dir):

    os.makedirs(base_dir)

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

  #Make directories to store the raw and featurized datasets.

  data_dir = os.path.join(base_dir, "dataset")

  train_dir = os.path.join(base_dir, "train")

  valid_dir = os.path.join(base_dir, "valid")



  # Load Tox21 dataset

  print("About to load Tox21 dataset.")

  dataset_file = os.path.join(

      current_dir, "../../datasets/tox21.csv.gz")

  dataset = load_from_disk(dataset_file)

  print("Columns of dataset: %s" % str(dataset.columns.values))

  print("Number of examples in dataset: %s" % str(dataset.shape[0]))



  # Featurize Tox21 dataset

  print("About to featurize Tox21 dataset.")

  featurizer = ConvMolFeaturizer()

  tox21_tasks = ['NR-AR', 'NR-AR-LBD', 'NR-AhR', 'NR-Aromatase', 'NR-ER',

                 'NR-ER-LBD', 'NR-PPAR-gamma', 'SR-ARE', 'SR-ATAD5',

                 'SR-HSE', 'SR-MMP', 'SR-p53']



  loader = DataLoader(tasks=tox21_tasks,

                      smiles_field="smiles",

                      featurizer=featurizer,

                      verbosity=verbosity)

  dataset = loader.featurize(

      dataset_file, data_dir, shard_size=8192)



  # Initialize transformers 

  transformers = [

      BalancingTransformer(transform_w=True, dataset=dataset)]



  print("About to transform data")

  for transformer in transformers:

      dataset = transformer.transform(dataset)



  X, y, w, ids = (dataset.X, dataset.y, dataset.w, dataset.ids)

  X_train, X_valid = X[:num_train], X[num_train:]

  y_train, y_valid = y[:num_train], y[num_train:]

  w_train, w_valid = w[:num_train], w[num_train:]

  ids_train, ids_valid = ids[:num_train], ids[num_train:]



  train_dataset = DiskDataset.from_numpy(

      train_dir, X_train, y_train, w_train, ids_train, tox21_tasks,

      compute_feature_statistics=False)

  valid_dataset = DiskDataset.from_numpy(

      valid_dir, X_valid, y_valid, w_valid, ids_valid, tox21_tasks,

      compute_feature_statistics=False)

  

  return tox21_tasks, (train_dataset, valid_dataset), transformers

CRA Git | Maintained and supported by SUSTech CRA and CCSE