Commit 707c2592 authored by peastman's avatar peastman
Browse files

Cleanup to examples

parent b9b35840

examples/chembl/chembl_datasets.py

deleted100644 → 0
+0 −89
Original line number Diff line number Diff line 
"""

ChEMBL dataset loader.

"""

from __future__ import division

from __future__ import print_function

from __future__ import unicode_literals



import os

import sys

import time



import deepchem as dc



sys.path.append(os.path.dirname(os.path.abspath(__file__)))

from chembl_tasks import chembl_tasks





# Set shard size low to avoid memory problems.

def load_chembl(shard_size=2000, featurizer="ECFP", set="5thresh", split="random"):

    ############################################################## TIMING

    time1 = time.time()

    ############################################################## TIMING

    # Set some global variables up top

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



    # Load dataset

    print("About to load ChEMBL dataset.")

    if split == "year":

        train_datasets, valid_datasets, test_datasets = [], [], []

        train_files = os.path.join(current_dir,

                                   "year_sets/chembl_%s_ts_train.csv.gz" % set)

        valid_files = os.path.join(current_dir,

                                   "year_sets/chembl_%s_ts_valid.csv.gz" % set)

        test_files = os.path.join(current_dir,

                                  "year_sets/chembl_%s_ts_test.csv.gz" % set)

    else:

        dataset_path = os.path.join(

            current_dir, "../../datasets/chembl_%s.csv.gz" % set)



    # Featurize ChEMBL dataset

    print("About to featurize ChEMBL dataset.")

    if featurizer == 'ECFP':

        featurizer = dc.feat.CircularFingerprint(size=1024)

    elif featurizer == 'GraphConv':

        featurizer = dc.feat.ConvMolFeaturizer()



    loader = dc.data.CSVLoader(

        tasks=chembl_tasks, smiles_field="smiles", featurizer=featurizer)



    if split == "year":

        print("Featurizing train datasets")

        train_dataset = loader.featurize(

            train_files, shard_size=shard_size)



        print("Featurizing valid datasets")

        valid_dataset = loader.featurize(

            valid_files, shard_size=shard_size)



        print("Featurizing test datasets")

        test_dataset = loader.featurize(

            test_files, shard_size=shard_size)

    else:

        dataset = loader.featurize(dataset_path, shard_size=shard_size)



    # Initialize transformers

    print("About to transform data")

    if split == "year":

        transformers = [

            dc.trans.NormalizationTransformer(transform_y=True, dataset=train_dataset)]

        for transformer in transformers:

            train = transformer.transform(train_dataset)

            valid = transformer.transform(valid_dataset)

            test = transformer.transform(test_dataset)

    else:

        transformers = [

            dc.trans.NormalizationTransformer(transform_y=True, dataset=dataset)]

        for transformer in transformers:

            dataset = transformer.transform(dataset)



    splitters = {'index': dc.splits.IndexSplitter(),

                 'random': dc.splits.RandomSplitter(),

                 'scaffold': dc.splits.ScaffoldSplitter()}

    if split in splitters:

        splitter = splitters[split]

        print("Performing new split.")

        train, valid, test = splitter.train_valid_test_split(dataset)





    return chembl_tasks, (train, valid, test), transformers

examples/chembl/chembl_graph_conv.py

+1 −1
Original line number Diff line number Diff line
@@ -10,7 +10,7 @@ np.random.seed(123) 
import tensorflow as tf

tf.set_random_seed(123)

import deepchem as dc

from chembl_datasets import load_chembl

from deepchem.molnet import load_chembl



# Load ChEMBL dataset

chembl_tasks, datasets, transformers = load_chembl(

examples/chembl/chembl_tf_models.py

+15 −10
Original line number Diff line number Diff line
@@ -11,7 +11,7 @@ import tempfile 
import shutil

import numpy as np

import deepchem as dc

from chembl_datasets import load_chembl

from deepchem.molnet import load_chembl



# Set numpy seed

np.random.seed(123)
@@ -19,8 +19,8 @@ np.random.seed(123) 
###Load data###

shard_size = 2000

print("About to load ChEMBL data.")

chembl_tasks, datasets, transformers = load_chembl(shard_size=shard_size,

                                                   featurizer="ECFP", set="5thresh", split="random")

chembl_tasks, datasets, transformers = load_chembl(

    shard_size=shard_size, featurizer="ECFP", set="5thresh", split="random")

train_dataset, valid_dataset, test_dataset = datasets



print("ChEMBL_tasks")
@@ -35,13 +35,18 @@ print(len(test_dataset)) 
###Create model###

n_layers = 3

nb_epoch = 10

model = dc.models.TensorflowMultiTaskRegressor(

    len(chembl_tasks), train_dataset.get_data_shape()[0],

    layer_sizes=[1000]*n_layers, dropouts=[.25]*n_layers,

model = dc.models.TensorGraphMultiTaskRegressor(

    len(chembl_tasks),

    train_dataset.get_data_shape()[0],

    layer_sizes=[1000] * n_layers,

    dropouts=[.25] * n_layers,

    weight_init_stddevs=[.02] * n_layers,

    bias_init_consts=[1.]*n_layers, learning_rate=.0003,

    penalty=.0001, penalty_type="l2", optimizer="adam", batch_size=100,

    seed=123, verbosity="high")

    bias_init_consts=[1.] * n_layers,

    learning_rate=.0003,

    weight_decay_penalty=.0001,

    batch_size=100,

    seed=123,

    verbosity="high")



#Use R2 classification metric

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

examples/clintox/clintox_datasets.py

deleted100644 → 0
+0 −52
Original line number Diff line number Diff line 
"""

Clinical Toxicity (clintox) dataset loader.

@author Caleb Geniesse

"""



from __future__ import print_function

from __future__ import division

from __future__ import unicode_literals



import os

import deepchem as dc





def load_clintox(featurizer='ECFP', split='index'):

  """Load clintox datasets."""



  # Load clintox dataset

  print("About to load clintox dataset.")

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

  dataset_file = os.path.join(

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

  dataset = dc.utils.save.load_from_disk(dataset_file)

  clintox_tasks = dataset.columns.values[1:].tolist()

  print("Tasks in dataset: %s" % (clintox_tasks))

  print("Number of tasks in dataset: %s" % str(len(clintox_tasks)))

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



  # Featurize clintox dataset

  print("About to featurize clintox dataset.")

  featurizers = {'ECFP': dc.feat.CircularFingerprint(size=1024),

                 'GraphConv': dc.feat.ConvMolFeaturizer()}

  featurizer = featurizers[featurizer]

  loader = dc.data.CSVLoader(

      tasks=clintox_tasks, smiles_field="smiles", featurizer=featurizer)

  dataset = loader.featurize(dataset_file, shard_size=8192)



  # Transform clintox dataset

  print("About to transform clintox dataset.")

  transformers = [

      dc.trans.BalancingTransformer(transform_w=True, dataset=dataset)]

  for transformer in transformers:

    dataset = transformer.transform(dataset)



  # Split clintox dataset

  print("About to split clintox dataset.")

  splitters = {'index': dc.splits.IndexSplitter(),

               'random': dc.splits.RandomSplitter(),

               'scaffold': dc.splits.ScaffoldSplitter()}

  splitter = splitters[split]

  train, valid, test = splitter.train_valid_test_split(dataset)



  return clintox_tasks, (train, valid, test), transformers

examples/clintox/clintox_graph_conv.py

+1 −1
Original line number Diff line number Diff line
@@ -11,7 +11,7 @@ np.random.seed(123) 
import tensorflow as tf

tf.set_random_seed(123)

import deepchem as dc

from clintox_datasets import load_clintox

from deepchem.molnet import load_clintox



# Load clintox dataset

clintox_tasks, clintox_datasets, transformers = load_clintox(

CRA Git | Maintained and supported by SUSTech CRA and CCSE