Merge pull request #1407 from vsag96/FIX-#1043

import numpy as np

import tensorflow as tf

import deepchem as dc

from datasets import load_sider_convmol

from deepchem.models.tensorgraph.models.graph_models import GraphConvModel

# 4-fold splits

K = 4

# 10 trials on test-set

n_trials = 20

sider_tasks, dataset, transformers = load_sider_convmol()

sider_tasks, fold_datasets, transformers = dc.molnet.load_sider(

    featurizer='GraphConv', split="task")

# Define metric

metric = dc.metrics.Metric(dc.metrics.roc_auc_score, mode="classification")

task_splitter = dc.splits.TaskSplitter()

fold_datasets = task_splitter.k_fold_split(dataset, K)

train_folds = fold_datasets[:-1]

train_dataset = dc.splits.merge_fold_datasets(train_folds)

test_dataset = fold_datasets[-1]

# Get supports on test-set

support_generator = dc.data.SupportGenerator(test_dataset, n_pos, n_neg,

                                             n_trials)

# Compute accuracies

task_scores = {task: [] for task in range(len(test_dataset.get_task_names()))}

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

  n_feat = 75

  # Batch size of models

  batch_size = 50

  graph_model = dc.nn.SequentialGraph(n_feat)

  graph_model.add(dc.nn.GraphConv(64, n_feat, activation='relu'))

  graph_model.add(dc.nn.GraphPool())

  graph_model.add(dc.nn.GraphConv(128, 64, activation='relu'))

  graph_model.add(dc.nn.GraphPool())

  graph_model.add(dc.nn.GraphConv(64, 128, activation='relu'))

  graph_model.add(dc.nn.GraphPool())

  graph_model.add(dc.nn.Dense(128, 64, activation='tanh'))

  graph_model.add(dc.nn.GraphGather(batch_size, activation="tanh"))

  model = dc.models.MultitaskGraphClassifier(

      graph_model,

      1,

      n_feat,

      batch_size=batch_size,

      learning_rate=1e-3,

      learning_rate_decay_time=1000,

      optimizer_type="adam",

      beta1=.9,

      beta2=.999)

  #graph_model = dc.nn.SequentialGraph(n_feat)

  model = GraphConvModel(

      1, graph_conv_layers=[64, 128, 64], batch_size=batch_size)

  # Fit trained model

  model.fit(support, nb_epoch=10)

print("Standard Deviations")

print(std_task_scores)

print("Median of Mean Scores")

"""

To support both python 3.x and 2.7

dict.values() returns an object of type dict_values

and np.median shouts loudly if this is the case so 

converted it to list before passing it to np.array()

"""

try:

  print(np.median(np.array(mean_task_scores.values())))

except TypeError as e:

  print(np.median(np.array(list(mean_task_scores.values()))))