MPNN debug

              feed_dict[label] = to_one_hot(y_b[:, index])

            if self.mode == "regression":

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

        if w_b is not None and not predict:

        if w_b is not None:

          feed_dict[self.weights] = w_b

        atom_feat = []

        yield feed_dict

  def predict(self, dataset, transformers=[], batch_size=None):

    length_dataset = dataset.y.shape[0]

    generator = self.default_generator(dataset, predict=True, pad_batches=True)

    y_pred = self.predict_on_generator(generator, transformers)

    return y_pred[:length_dataset]

    return self.predict_on_generator(generator, transformers)

  def predict_proba(self, dataset, transformers=[], batch_size=None):

    length_dataset = dataset.y.shape[0]

    generator = self.default_generator(dataset, predict=True, pad_batches=True)

    y_pred = self.predict_proba_on_generator(generator, transformers)

    return y_pred[:length_dataset]

 No newline at end of file

    return self.predict_proba_on_generator(generator, transformers)

  def predict_proba_on_generator(self, generator, transformers=[]):

    """

    Returns:

      y_pred: numpy ndarray of shape (n_samples, n_classes*n_tasks)

    """

    if not self.built:

      self.build()

    with self._get_tf("Graph").as_default():

      with tf.Session() as sess:

        saver = tf.train.Saver()

        self._initialize_weights(sess, saver)

        out_tensors = [x.out_tensor for x in self.outputs]

        results = []

        for feed_dict in generator:

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

          feed_dict = {

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

              for k, v in six.iteritems(feed_dict)

          }

          feed_dict[self._training_placeholder] = 0.0

          result = np.array(sess.run(out_tensors, feed_dict=feed_dict))

          if len(result.shape) == 3:

            result = np.transpose(result, axes=[1, 0, 2])

          result = undo_transforms(result, transformers)

          results.append(result[:n_valid_samples])

        return np.concatenate(results, axis=0)

 No newline at end of file

#!/usr/bin/env python2

# -*- coding: utf-8 -*-

"""

Created on Sat Jul 29 23:49:02 2017

@author: zqwu

"""

from __future__ import print_function

from __future__ import division

from __future__ import unicode_literals

import numpy as np

np.random.seed(123)

import tensorflow as tf

tf.set_random_seed(123)

import deepchem as dc

# Load Delaney dataset

delaney_tasks, delaney_datasets, transformers = dc.molnet.load_delaney(

    featurizer='Weave', split='index')

train_dataset, valid_dataset, test_dataset = delaney_datasets

# Fit models

metric = dc.metrics.Metric(dc.metrics.pearson_r2_score, np.mean)

n_atom_feat = 75

n_pair_feat = 14

# Batch size of models

batch_size = 64

model = dc.models.MPNNTensorGraph(

    len(delaney_tasks),

    n_atom_feat=n_atom_feat,

    n_pair_feat=n_pair_feat,

    T=3,

    M=5,

    batch_size=batch_size,

    learning_rate=0.0001,

    use_queue=False,

    mode="regression")

# Fit trained model

model.fit(train_dataset, nb_epoch=50, checkpoint_interval=100)

print("Evaluating model")

train_scores = model.evaluate(train_dataset, [metric], transformers)

valid_scores = model.evaluate(valid_dataset, [metric], transformers)

print("Train scores")

print(train_scores)

print("Validation scores")

print(valid_scores)