Commit 2efccdc6 authored by leswing's avatar leswing
Browse files

yapf

parent c17ba162

deepchem/data/datasets.py

+1 −1
Original line number Diff line number Diff line
@@ -18,7 +18,7 @@ import shutil 


__author__ = "Bharath Ramsundar"

__copyright__ = "Copyright 2016, Stanford University"

__license__ = "GPL"

__license__ = "MIT"





def sparsify_features(X):

deepchem/data/tests/__init__.py

+35 −23
Original line number Diff line number Diff line
@@ -7,7 +7,7 @@ from __future__ import unicode_literals 


__author__ = "Bharath Ramsundar"

__copyright__ = "Copyright 2016, Stanford University"

__license__ = "GPL"

__license__ = "MIT"



import unittest

import tempfile
@@ -16,6 +16,7 @@ import shutil 
import numpy as np

import deepchem as dc





def load_solubility_data():

  """Loads solubility dataset"""

  current_dir = os.path.dirname(os.path.abspath(__file__))
@@ -28,39 +29,45 @@ def load_solubility_data(): 


  return loader.featurize(input_file)





def load_butina_data():

  """Loads solubility dataset"""

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

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

  tasks = ["task"]

  # task_type = "regression"

  input_file = os.path.join(current_dir, "../../models/tests/butina_example.csv")

  input_file = os.path.join(current_dir,

                            "../../models/tests/butina_example.csv")

  loader = dc.data.CSVLoader(

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



  return loader.featurize(input_file)





def load_multitask_data():

  """Load example multitask data."""

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

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

  tasks = ["task0", "task1", "task2", "task3", "task4", "task5", "task6",

           "task7", "task8", "task9", "task10", "task11", "task12",

           "task13", "task14", "task15", "task16"]

  input_file = os.path.join(

      current_dir, "../../models/tests/multitask_example.csv")

  tasks = [

      "task0", "task1", "task2", "task3", "task4", "task5", "task6", "task7",

      "task8", "task9", "task10", "task11", "task12", "task13", "task14",

      "task15", "task16"

  ]

  input_file = os.path.join(current_dir,

                            "../../models/tests/multitask_example.csv")

  loader = dc.data.CSVLoader(

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

  return loader.featurize(input_file)





def load_classification_data():

  """Loads classification data from example.csv"""

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

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

  tasks = ["outcome"]

  task_type = "classification"

  input_file = os.path.join(

      current_dir, "../../models/tests/example_classification.csv")

  input_file = os.path.join(current_dir,

                            "../../models/tests/example_classification.csv")

  loader = dc.data.CSVLoader(

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

  return loader.featurize(input_file)
@@ -70,26 +77,30 @@ def load_sparse_multitask_dataset(): 
  """Load sparse tox multitask data, sample dataset."""

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

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

  tasks = ["task1", "task2", "task3", "task4", "task5", "task6",

           "task7", "task8", "task9"]

  input_file = os.path.join(

      current_dir, "../../models/tests/sparse_multitask_example.csv")

  tasks = [

      "task1", "task2", "task3", "task4", "task5", "task6", "task7", "task8",

      "task9"

  ]

  input_file = os.path.join(current_dir,

                            "../../models/tests/sparse_multitask_example.csv")

  loader = dc.data.CSVLoader(

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

  return loader.featurize(input_file)





def load_feat_multitask_data():

  """Load example with numerical features, tasks."""

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

  features = ["feat0", "feat1", "feat2", "feat3", "feat4", "feat5"]

  featurizer = dc.feat.UserDefinedFeaturizer(features)

  tasks = ["task0", "task1", "task2", "task3", "task4", "task5"]

  input_file = os.path.join(

      current_dir, "../../models/tests/feat_multitask_example.csv")

  input_file = os.path.join(current_dir,

                            "../../models/tests/feat_multitask_example.csv")

  loader = dc.data.UserCSVLoader(

      tasks=tasks, featurizer=featurizer, id_field="id")

  return loader.featurize(input_file)





def load_gaussian_cdf_data():

  """Load example with numbers sampled from Gaussian normal distribution.

     Each feature and task is a column of values that is sampled
@@ -98,12 +109,13 @@ def load_gaussian_cdf_data(): 
  features = ["feat0", "feat1"]

  featurizer = dc.feat.UserDefinedFeaturizer(features)

  tasks = ["task0", "task1"]

  input_file = os.path.join(

      current_dir, "../../models/tests/gaussian_cdf_example.csv")

  input_file = os.path.join(current_dir,

                            "../../models/tests/gaussian_cdf_example.csv")

  loader = dc.data.UserCSVLoader(

      tasks=tasks, featurizer=featurizer, id_field="id")

  return loader.featurize(input_file)





def load_unlabelled_data():

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

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

deepchem/data/tests/test_data_loader.py

+26 −30
Original line number Diff line number Diff line
@@ -7,7 +7,7 @@ from __future__ import unicode_literals 


__author__ = "Bharath Ramsundar"

__copyright__ = "Copyright 2016, Stanford University"

__license__ = "GPL"

__license__ = "MIT"



import os

import unittest
@@ -15,21 +15,22 @@ import tempfile 
import shutil

import deepchem as dc





class TestDataLoader(unittest.TestCase):

  """

  Test DataLoader 

  """



  def setUp(self):

    super(TestDataLoader, self).setUp()

    self.current_dir = os.path.dirname(os.path.abspath(__file__))



  def unlabelled_test(self):

    input_file = os.path.join(

        self.current_dir, "../../data/tests/no_labels.csv")

    input_file = os.path.join(self.current_dir,

                              "../../data/tests/no_labels.csv")

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

    loader = dc.data.CSVLoader(

        tasks=[], smiles_field="smiles",

        featurizer=featurizer)

        tasks=[], smiles_field="smiles", featurizer=featurizer)

    loader.featurize(input_file)



  def scaffold_test_train_valid_test_split(self):
@@ -41,14 +42,13 @@ class TestDataLoader(unittest.TestCase): 
    tasks = ["log-solubility"]

    task_type = "regression"

    task_types = {task: task_type for task in tasks}

    input_file = os.path.join(

        self.current_dir, "../../models/tests/example.csv")

    input_file = os.path.join(self.current_dir,

                              "../../models/tests/example.csv")

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



    input_file = os.path.join(self.current_dir, input_file)

    loader = dc.data.CSVLoader(

        tasks=tasks, smiles_field="smiles",

        featurizer=featurizer)

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



    dataset = loader.featurize(input_file)
@@ -69,14 +69,13 @@ class TestDataLoader(unittest.TestCase): 
    tasks = ["log-solubility"]

    task_type = "regression"

    task_types = {task: task_type for task in tasks}

    input_file = os.path.join(

        self.current_dir, "../../models/tests/example.csv")

    input_file = os.path.join(self.current_dir,

                              "../../models/tests/example.csv")

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



    input_file = os.path.join(self.current_dir, input_file)

    loader = dc.data.CSVLoader(

        tasks=tasks, smiles_field="smiles",

        featurizer=featurizer)

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



    dataset = loader.featurize(input_file)
@@ -94,14 +93,13 @@ class TestDataLoader(unittest.TestCase): 
    tasks = ["log-solubility"]

    task_type = "regression"

    task_types = {task: task_type for task in tasks}

    input_file = os.path.join(

        self.current_dir, "../../models/tests/example.csv")

    input_file = os.path.join(self.current_dir,

                              "../../models/tests/example.csv")

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



    input_file = os.path.join(self.current_dir, input_file)

    loader = dc.data.CSVLoader(

        tasks=tasks, smiles_field="smiles",

        featurizer=featurizer)

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



    dataset = loader.featurize(input_file)
@@ -120,12 +118,11 @@ class TestDataLoader(unittest.TestCase): 
    tasks = ["log-solubility"]

    task_type = "regression"

    task_types = {task: task_type for task in tasks}

    input_file = os.path.join(

        self.current_dir, "../../models/tests/example.csv")

    input_file = os.path.join(self.current_dir,

                              "../../models/tests/example.csv")

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

    loader = dc.data.CSVLoader(

        tasks=tasks, smiles_field="smiles",

        featurizer=featurizer)

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



    dataset = loader.featurize(input_file)
@@ -144,7 +141,8 @@ class TestDataLoader(unittest.TestCase): 
    tasks = ["log-solubility"]

    smiles_field = "smiles"

    loader = dc.data.CSVLoader(

        tasks=tasks, smiles_field="smiles",

        tasks=tasks,

        smiles_field="smiles",

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

    dataset = loader.featurize(input_file)
@@ -155,16 +153,14 @@ class TestDataLoader(unittest.TestCase): 
    base_dir = tempfile.mkdtemp()

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

    moved_data_dir = os.path.join(base_dir, "moved_data")

    dataset_file = os.path.join(

        self.current_dir, "../../models/tests/example.csv")

    dataset_file = os.path.join(self.current_dir,

                                "../../models/tests/example.csv")



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

    tasks = ["log-solubility"]

    loader = dc.data.CSVLoader(

        tasks=tasks, smiles_field="smiles",

        featurizer=featurizer)

    featurized_dataset = loader.featurize(

        dataset_file, data_dir)

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

    featurized_dataset = loader.featurize(dataset_file, data_dir)

    n_dataset = len(featurized_dataset)



    # Now perform move

deepchem/data/tests/test_datasets.py

+51 −48
Original line number Diff line number Diff line
@@ -7,7 +7,7 @@ from __future__ import unicode_literals 


__author__ = "Bharath Ramsundar"

__copyright__ = "Copyright 2016, Stanford University"

__license__ = "GPL"

__license__ = "MIT"



import unittest

import tempfile
@@ -16,6 +16,7 @@ import shutil 
import numpy as np

import deepchem as dc





class TestDatasets(unittest.TestCase):

  """

  Test basic top-level API for dataset objects.
@@ -90,7 +91,6 @@ class TestDatasets(unittest.TestCase): 
    X_out = dc.data.pad_features(batch_size, X_b)

    assert len(X_out) == batch_size





  def test_pad_batches(self):

    """Test that pad_batch pads batches correctly."""

    batch_size = 100
@@ -104,8 +104,8 @@ class TestDatasets(unittest.TestCase): 
    w_b = np.zeros((n_samples, num_tasks))

    ids_b = np.zeros((n_samples,))



    X_out, y_out, w_out, ids_out = dc.data.pad_batch(

        batch_size, X_b, y_b, w_b, ids_b)

    X_out, y_out, w_out, ids_out = dc.data.pad_batch(batch_size, X_b, y_b, w_b,

                                                     ids_b)

    assert len(X_out) == len(y_out) == len(w_out) == len(ids_out) == batch_size



    # Test cases where n_samples < batch_size
@@ -115,8 +115,8 @@ class TestDatasets(unittest.TestCase): 
    w_b = np.zeros((n_samples, num_tasks))

    ids_b = np.zeros((n_samples,))



    X_out, y_out, w_out, ids_out = dc.data.pad_batch(

        batch_size, X_b, y_b, w_b, ids_b)

    X_out, y_out, w_out, ids_out = dc.data.pad_batch(batch_size, X_b, y_b, w_b,

                                                     ids_b)

    assert len(X_out) == len(y_out) == len(w_out) == len(ids_out) == batch_size



    # Test case where n_samples == batch_size
@@ -126,8 +126,8 @@ class TestDatasets(unittest.TestCase): 
    w_b = np.zeros((n_samples, num_tasks))

    ids_b = np.zeros((n_samples,))



    X_out, y_out, w_out, ids_out = dc.data.pad_batch(

        batch_size, X_b, y_b, w_b, ids_b)

    X_out, y_out, w_out, ids_out = dc.data.pad_batch(batch_size, X_b, y_b, w_b,

                                                     ids_b)

    assert len(X_out) == len(y_out) == len(w_out) == len(ids_out) == batch_size



    # Test case for object featurization.
@@ -136,8 +136,8 @@ class TestDatasets(unittest.TestCase): 
    y_b = np.zeros((n_samples, num_tasks))

    w_b = np.zeros((n_samples, num_tasks))

    ids_b = np.zeros((n_samples,))

    X_out, y_out, w_out, ids_out = dc.data.pad_batch(

        batch_size, X_b, y_b, w_b, ids_b)

    X_out, y_out, w_out, ids_out = dc.data.pad_batch(batch_size, X_b, y_b, w_b,

                                                     ids_b)

    assert len(X_out) == len(y_out) == len(w_out) == len(ids_out) == batch_size



    # Test case for more complicated object featurization
@@ -146,8 +146,8 @@ class TestDatasets(unittest.TestCase): 
    y_b = np.zeros((n_samples, num_tasks))

    w_b = np.zeros((n_samples, num_tasks))

    ids_b = np.zeros((n_samples,))

    X_out, y_out, w_out, ids_out = dc.data.pad_batch(

        batch_size, X_b, y_b, w_b, ids_b)

    X_out, y_out, w_out, ids_out = dc.data.pad_batch(batch_size, X_b, y_b, w_b,

                                                     ids_b)

    assert len(X_out) == len(y_out) == len(w_out) == len(ids_out) == batch_size



    # Test case with multidimensional data
@@ -159,8 +159,8 @@ class TestDatasets(unittest.TestCase): 
    w_b = np.zeros((n_samples, num_tasks))

    ids_b = np.zeros((n_samples,))



    X_out, y_out, w_out, ids_out = dc.data.pad_batch(

        batch_size, X_b, y_b, w_b, ids_b)

    X_out, y_out, w_out, ids_out = dc.data.pad_batch(batch_size, X_b, y_b, w_b,

                                                     ids_b)

    assert len(X_out) == len(y_out) == len(w_out) == len(ids_out) == batch_size



  def test_get_task_names(self):
@@ -169,10 +169,11 @@ class TestDatasets(unittest.TestCase): 
    assert solubility_dataset.get_task_names() == ["log-solubility"]



    multitask_dataset = dc.data.tests.load_multitask_data()

    assert sorted(multitask_dataset.get_task_names()) == sorted(["task0",

        "task1", "task2", "task3", "task4", "task5", "task6", "task7", "task8",

        "task9", "task10", "task11", "task12", "task13", "task14", "task15",

        "task16"])

    assert sorted(multitask_dataset.get_task_names()) == sorted([

        "task0", "task1", "task2", "task3", "task4", "task5", "task6", "task7",

        "task8", "task9", "task10", "task11", "task12", "task13", "task14",

        "task15", "task16"

    ])



  def test_get_data_shape(self):

    """Test that get_data_shape returns currect data shape"""
@@ -313,6 +314,7 @@ class TestDatasets(unittest.TestCase): 


    def fn(x, y, w):

      return (2 * x, 1.5 * y, w)



    transformed = dataset.transform(fn)

    np.testing.assert_array_equal(X, dataset.X)

    np.testing.assert_array_equal(y, dataset.y)
@@ -334,6 +336,7 @@ class TestDatasets(unittest.TestCase): 
    # Transform it

    def fn(x, y, w):

      return (2 * x, 1.5 * y, w)



    transformed = dataset.transform(fn)

    np.testing.assert_array_equal(X, dataset.X)

    np.testing.assert_array_equal(y, dataset.y)

deepchem/data/tests/test_load.py

+12 −13
Original line number Diff line number Diff line
@@ -7,7 +7,7 @@ from __future__ import unicode_literals 


__author__ = "Bharath Ramsundar"

__copyright__ = "Copyright 2016, Stanford University"

__license__ = "GPL"

__license__ = "MIT"



import os

import shutil
@@ -16,6 +16,7 @@ import tempfile 
import deepchem as dc

import numpy as np





class TestLoad(unittest.TestCase):

  """

  Test singletask/multitask data loading.
@@ -27,8 +28,7 @@ class TestLoad(unittest.TestCase): 
    base_dir = tempfile.mkdtemp()

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

    moved_data_dir = os.path.join(base_dir, "moved_data")

    dataset_file = os.path.join(

        current_dir, "../../models/tests/example.csv")

    dataset_file = os.path.join(current_dir, "../../models/tests/example.csv")



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

    tasks = ["log-solubility"]
@@ -61,8 +61,8 @@ class TestLoad(unittest.TestCase): 


    # Load dataset

    print("About to load dataset.")

    dataset_file = os.path.join(

        current_dir, "../../models/tests/multitask_example.csv")

    dataset_file = os.path.join(current_dir,

                                "../../models/tests/multitask_example.csv")



    # Featurize tox21 dataset

    print("About to featurize dataset.")
@@ -78,7 +78,6 @@ class TestLoad(unittest.TestCase): 
    X_multi, y_multi, w_multi, ids_multi = (dataset.X, dataset.y, dataset.w,

                                            dataset.ids)





    ####### Do singletask load

    y_tasks, w_tasks, = [], []

    dataset = dc.data.DiskDataset(data_dir)
@@ -115,8 +114,8 @@ class TestLoad(unittest.TestCase): 


    # Load dataset

    print("About to load dataset.")

    dataset_file = os.path.join(

        current_dir, "../../models/tests/multitask_example.csv")

    dataset_file = os.path.join(current_dir,

                                "../../models/tests/multitask_example.csv")



    # Featurize tox21 dataset

    print("About to featurize dataset.")

CRA Git | Maintained and supported by SUSTech CRA and CCSE