molnet valid

from __future__ import print_function

from __future__ import division

from __future__ import unicode_literals

import deepchem

import numpy as np

import tensorflow as tf

seed = 123

np.random.seed(seed)

tasks, datasets, transformers = deepchem.molnet.load_delaney(featurizer='GraphConv', split='random', reload=False)

train_dataset, valid_dataset, test_dataset = datasets

metric = [deepchem.metrics.Metric(deepchem.metrics.rms_score, np.mean)]

max_atoms_train = max([mol.get_num_atoms() for mol in train_dataset.X])

max_atoms_valid = max([mol.get_num_atoms() for mol in valid_dataset.X])

max_atoms_test = max([mol.get_num_atoms() for mol in test_dataset.X])

max_atoms = max([max_atoms_train, max_atoms_valid, max_atoms_test])

reshard_size = 512

transformer = deepchem.trans.DAGTransformer(max_atoms=max_atoms)

train_dataset.reshard(reshard_size)

train_dataset = transformer.transform(train_dataset)

valid_dataset.reshard(reshard_size)

valid_dataset = transformer.transform(valid_dataset)

test_dataset.reshard(reshard_size)

test_dataset = transformer.transform(test_dataset)

batch_size = 128

nb_epoch = 1000

learning_rate = 0.0005

n_graph_feat = 23

tf.set_random_seed(seed)

model = deepchem.models.DAGTensorGraph(

               1, 

               max_atoms=55,

               n_atom_feat=75,

               n_graph_feat=n_graph_feat,

               mode='regression',

               batch_size=batch_size,

               leanring_rate=learning_rate,

               use_queue=False)

model.fit(train_dataset, nb_epoch=nb_epoch)

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

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

test_scores = model.evaluate(test_dataset, metric, transformers)

""" Expected Results:

  train_scores: {'mean-rms_score': 0.029829638487211169}

  valid_scores: {'mean-rms_score': 0.75142478279661051}

  test_scores: {'mean-rms_score': 0.53192168238754678}

"""

 No newline at end of file

from __future__ import print_function

from __future__ import division

from __future__ import unicode_literals

import deepchem

import numpy as np

import tensorflow as tf

seed = 123

np.random.seed(seed)

tasks, datasets, transformers = deepchem.molnet.load_delaney(featurizer='GraphConv', split='random', reload=False)

train_dataset, valid_dataset, test_dataset = datasets

metric = [deepchem.metrics.Metric(deepchem.metrics.rms_score, np.mean)]

batch_size = 150

nb_epoch = 1000

learning_rate = 0.0008

tf.set_random_seed(seed)

model = deepchem.models.GraphConvTensorGraph(1, mode='regression',

                                             batch_size=batch_size,

                                             leanring_rate=learning_rate)

model.fit(train_dataset, nb_epoch=nb_epoch)

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

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

test_scores = model.evaluate(test_dataset, metric, transformers)

""" Expected Results:

  train_scores: {'mean-rms_score': 0.058672648022210311}

  valid_scores: {'mean-rms_score': 0.3635136142334261}

  test_scores: {'mean-rms_score': 0.35664025829369983}

"""

 No newline at end of file

from __future__ import print_function

from __future__ import division

from __future__ import unicode_literals

import os

import deepchem

import numpy as np

import tensorflow as tf

import tempfile

data_dir = deepchem.utils.get_data_dir()

dataset_file = os.path.join(data_dir, "gdb9.sdf")

qm9_tasks = ["u0_atom"]

featurizer = deepchem.feat.CoulombMatrix(29)

loader = deepchem.data.SDFLoader(

        tasks=qm9_tasks,

        smiles_field="smiles",

        mol_field="mol",

        featurizer=featurizer)

dataset = loader.featurize(dataset_file)

splitter = deepchem.splits.RandomSplitter()

train_dataset, valid_dataset, test_dataset = splitter.train_valid_test_split(

      dataset)

transformers = [

      deepchem.trans.NormalizationTransformer(

          transform_y=True, dataset=train_dataset)

]

for transformer in transformers:

  train_dataset = transformer.transform(train_dataset)

  valid_dataset = transformer.transform(valid_dataset)

  test_dataset = transformer.transform(test_dataset)

metric = [deepchem.metrics.Metric(deepchem.metrics.mean_absolute_error, np.mean)]

batch_size = 49

nb_epoch = 100

learning_rate = 0.0003

n_embedding = 42

n_distance = 173

seed = 123

np.random.seed(seed)

tf.set_random_seed(seed)

model_dir = tempfile.mkdtemp()

model = deepchem.models.DTNNTensorGraph(

    len(qm9_tasks),

    n_embedding=n_embedding,

    n_hidden=60,

    n_distance=n_distance,

    distance_min=-1.,

    distance_max=18.,

    output_activation=False,

    batch_size=batch_size,

    learning_rate=learning_rate,

    use_queue=False,

    mode="regression",

    model_dir=model_dir)

model.fit(train_dataset, nb_epoch=nb_epoch)

for rate in [learning_rate/5, learning_rate/20, learning_rate/100]:

  model = deepchem.models.DTNNTensorGraph(

      len(qm9_tasks),

      n_embedding=n_embedding,

      n_hidden=60,

      n_distance=n_distance,

      distance_min=-1.,

      distance_max=18.,

      output_activation=False,

      batch_size=batch_size,

      learning_rate=learning_rate/5,

      use_queue=False,

      mode="regression",

      model_dir=model_dir)

  model.restore()

  model.fit(train_dataset, nb_epoch=10)

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

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

test_scores = model.evaluate(test_dataset, metric, transformers)

model.fit(train_dataset, nb_epoch=10)

'''

computed_metrics: [0.95282979862675088]

computed_metrics: [1.1501283330568968]

computed_metrics: [1.2601717317672092]

'''

 No newline at end of file

from __future__ import print_function

from __future__ import division

from __future__ import unicode_literals

import os

import deepchem

import numpy as np

import tensorflow as tf

import tempfile

seed = 123

data_dir = deepchem.utils.get_data_dir()

dataset_file = os.path.join(data_dir, "gdb9.sdf")

qm9_tasks = ["gap"]

featurizer = deepchem.feat.WeaveFeaturizer(graph_distance=False, explicit_H=True)

loader = deepchem.data.SDFLoader(

        tasks=qm9_tasks,

        smiles_field="smiles",

        mol_field="mol",

        featurizer=featurizer)

dataset = loader.featurize(dataset_file)

np.random.seed(seed)

splitter = deepchem.splits.RandomSplitter()

train_dataset, valid_dataset, test_dataset = splitter.train_valid_test_split(

      dataset)

transformers = [

      deepchem.trans.NormalizationTransformer(

          transform_y=True, dataset=train_dataset)

]

for transformer in transformers:

  train_dataset = transformer.transform(train_dataset)

  valid_dataset = transformer.transform(valid_dataset)

  test_dataset = transformer.transform(test_dataset)

metric = [deepchem.metrics.Metric(deepchem.metrics.mean_absolute_error, np.mean)]

batch_size = 64

nb_epoch = 100

learning_rate = 0.0003

n_hidden = 70

T = 2

M = 5

tf.set_random_seed(seed)

model_dir = tempfile.mkdtemp()

model = deepchem.models.DTNNTensorGraph(

    len(qm9_tasks),

    n_hidden=n_hidden,

    T=T,

    M=M,

    batch_size=batch_size,

    learning_rate=learning_rate,

    use_queue=False,

    mode="regression",

    model_dir=model_dir)

model.fit(train_dataset, nb_epoch=nb_epoch)

for rate in [learning_rate/5, learning_rate/20, learning_rate/100]:

  model = deepchem.models.DTNNTensorGraph(

      len(qm9_tasks),

      n_hidden=n_hidden,

      T=T,

      M=M,

      batch_size=batch_size,

      learning_rate=rate,

      use_queue=False,

      mode="regression",

      model_dir=model_dir)

  model.restore()

  model.fit(train_dataset, nb_epoch=10)

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

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

test_scores = model.evaluate(test_dataset, metric, transformers)

model.fit(train_dataset, nb_epoch=10)

'''

'''

 No newline at end of file