Commit 92dc0b88 authored by Bharath Ramsundar's avatar Bharath Ramsundar
Browse files

More test fixes

parent b4d052fd

deepchem/featurizers/__init__.py

+1 −0
Original line number Diff line number Diff line
@@ -15,3 +15,4 @@ from deepchem.featurizers.featurize import DataLoader 
from deepchem.featurizers.graph_features import ConvMolFeaturizer

from deepchem.featurizers.fingerprints import CircularFingerprint

from deepchem.featurizers.basic import RDKitDescriptors

from deepchem.featurizers.coulomb_matrices import CoulombMatrixEig

deepchem/featurizers/tests/test_data_featurizer.py

+7 −9
Original line number Diff line number Diff line
@@ -13,11 +13,9 @@ import os 
import unittest

import tempfile

import shutil

from deepchem.models.tests import TestAPI

from deepchem.featurizers.featurize import DataLoader

from deepchem.featurizers.fingerprints import CircularFingerprint

import deepchem as dc



class TestDataLoader(TestAPI):

class TestDataLoader(unittest.TestCase):

  """

  Test Data Featurizer class.

  """
@@ -29,10 +27,10 @@ class TestDataLoader(TestAPI): 


    tasks = ["log-solubility"]

    smiles_field = "smiles"

    loader = DataLoader(tasks=tasks,

                        smiles_field=self.smiles_field,

                        featurizer=CircularFingerprint(size=1024),

    loader = dc.loaders.DataLoader(

        tasks=tasks, smiles_field="smiles",

        featurizer=dc.featurizers.CircularFingerprint(size=1024),

        verbosity="low")

    dataset = loader.featurize(input_file, self.data_dir)

    dataset = loader.featurize(input_file)

    

    assert len(dataset) == 10

deepchem/featurizers/tests/test_featurized_samples.py

+51 −57
Original line number Diff line number Diff line
@@ -13,19 +13,15 @@ import os 
import unittest

import tempfile

import shutil

from deepchem.datasets import DiskDataset

from deepchem.models.tests import TestAPI

from deepchem.splits import RandomSplitter

from deepchem.splits import ScaffoldSplitter

from deepchem.splits import SpecifiedSplitter

from deepchem.featurizers.featurize import DataLoader

from deepchem.featurizers.fingerprints import CircularFingerprint

#from deepchem.featurizers.featurize import FeaturizedSamples



class TestFeaturizedSamples(TestAPI):

import deepchem as dc



class TestFeaturizedSamples(unittest.TestCase):

  """

  Test Featurized Samples class.

  """

  def setUp(self):

    super(TestFeaturizedSamples, self).setUp()

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



  def scaffold_test_train_valid_test_split(self):

    """Test of singletask RF ECFP regression API."""
@@ -36,21 +32,21 @@ class TestFeaturizedSamples(TestAPI): 
    tasks = ["log-solubility"]

    task_type = "regression"

    task_types = {task: task_type for task in tasks}

    input_file = os.path.join(self.current_dir, "example.csv")

    featurizer = CircularFingerprint(size=1024)

    input_file = os.path.join(

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

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



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

    loader = DataLoader(tasks=tasks,

                        smiles_field=self.smiles_field,

                        featurizer=featurizer,

                        verbosity="low")

    loader = dc.loaders.DataLoader(

        tasks=tasks, smiles_field="smiles",

        featurizer=featurizer, verbosity="low")



    dataset = loader.featurize(input_file, self.data_dir)

    dataset = loader.featurize(input_file)



    # Splits featurized samples into train/test

    splitter = ScaffoldSplitter()

    splitter = dc.splits.ScaffoldSplitter()

    train_dataset, valid_dataset, test_dataset = splitter.train_valid_test_split(

        dataset, self.train_dir, self.valid_dir, self.test_dir)

        dataset)

    assert len(train_dataset) == 8

    assert len(valid_dataset) == 1

    assert len(test_dataset) == 1
@@ -64,21 +60,20 @@ class TestFeaturizedSamples(TestAPI): 
    tasks = ["log-solubility"]

    task_type = "regression"

    task_types = {task: task_type for task in tasks}

    input_file = os.path.join(self.current_dir, "example.csv")

    featurizer = CircularFingerprint(size=1024)

    input_file = os.path.join(

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

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



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

    loader = DataLoader(tasks=tasks,

                        smiles_field=self.smiles_field,

                        featurizer=featurizer,

                        verbosity="low")

    loader = dc.loaders.DataLoader(

        tasks=tasks, smiles_field="smiles",

        featurizer=featurizer, verbosity="low")



    dataset = loader.featurize(input_file, self.data_dir)

    dataset = loader.featurize(input_file)



    # Splits featurized samples into train/test

    splitter = ScaffoldSplitter()

    train_dataset, test_dataset = splitter.train_test_split(

        dataset, self.train_dir, self.test_dir)

    splitter = dc.splits.ScaffoldSplitter()

    train_dataset, test_dataset = splitter.train_test_split(dataset)

    assert len(train_dataset) == 8

    assert len(test_dataset) == 2
@@ -90,21 +85,21 @@ class TestFeaturizedSamples(TestAPI): 
    tasks = ["log-solubility"]

    task_type = "regression"

    task_types = {task: task_type for task in tasks}

    input_file = os.path.join(self.current_dir, "example.csv")

    featurizer = CircularFingerprint(size=1024)

    input_file = os.path.join(

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

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



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

    loader = DataLoader(tasks=tasks,

                        smiles_field=self.smiles_field,

                        featurizer=featurizer,

                        verbosity="low")

    loader = dc.loaders.DataLoader(

        tasks=tasks, smiles_field="smiles",

        featurizer=featurizer, verbosity="low")



    dataset = loader.featurize(input_file, self.data_dir)

    dataset = loader.featurize(input_file)



    # Splits featurized samples into train/test

    splitter = RandomSplitter()

    splitter = dc.splits.RandomSplitter()

    train_dataset, valid_dataset, test_dataset = splitter.train_valid_test_split(

        dataset, self.train_dir, self.valid_dir, self.test_dir)

        dataset)

    assert len(train_dataset) == 8

    assert len(valid_dataset) == 1

    assert len(test_dataset) == 1
@@ -116,36 +111,35 @@ class TestFeaturizedSamples(TestAPI): 
    tasks = ["log-solubility"]

    task_type = "regression"

    task_types = {task: task_type for task in tasks}

    input_file = os.path.join(self.current_dir, "example.csv")

    featurizer = CircularFingerprint(size=1024)

    loader = DataLoader(tasks=tasks,

                        smiles_field=self.smiles_field,

                        featurizer=featurizer,

                        verbosity="low")

    input_file = os.path.join(

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

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

    loader = dc.loaders.DataLoader(

        tasks=tasks, smiles_field="smiles",

        featurizer=featurizer, verbosity="low")



    dataset = loader.featurize(input_file, self.data_dir)

    dataset = loader.featurize(input_file)



    # Splits featurized samples into train/test

    splitter = RandomSplitter()

    train_dataset, test_dataset = splitter.train_test_split(

        dataset, self.train_dir, self.test_dir)

    splitter = dc.splits.RandomSplitter()

    train_dataset, test_dataset = splitter.train_test_split(dataset)

    assert len(train_dataset) == 8

    assert len(test_dataset) == 2



  def test_samples_move(self):

    """Test that featurized samples can be moved and reloaded."""

    verbosity = "high"

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

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

    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, "example.csv")

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



    featurizer = CircularFingerprint(size=1024)

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

    tasks = ["log-solubility"]

    loader = DataLoader(tasks=tasks,

                        smiles_field="smiles",

                        featurizer=featurizer,

                        verbosity=verbosity)

    loader = dc.loaders.DataLoader(

        tasks=tasks, smiles_field="smiles",

        featurizer=featurizer, verbosity=verbosity)

    featurized_dataset = loader.featurize(

        dataset_file, data_dir)

    n_dataset = len(featurized_dataset)
@@ -153,7 +147,7 @@ class TestFeaturizedSamples(TestAPI): 
    # Now perform move

    shutil.move(data_dir, moved_data_dir)



    moved_featurized_dataset = DiskDataset(

    moved_featurized_dataset = dc.datasets.DiskDataset(

        data_dir=moved_data_dir, reload=True)



    assert len(moved_featurized_dataset) == n_dataset

deepchem/featurizers/tests/test_sdf_reader.py

+11 −18
Original line number Diff line number Diff line
@@ -13,12 +13,9 @@ import os 
import unittest

import tempfile

import shutil

from deepchem.splits import RandomSplitter

from deepchem.featurizers.featurize import DataLoader

from deepchem.featurizers.coulomb_matrices import CoulombMatrixEig

from deepchem.models.tests import TestAPI

import deepchem as dc



class TestFeaturizedSamples(TestAPI):

class TestFeaturizedSamples(unittest.TestCase):

  """

  Test Featurized Samples class.

  """
@@ -35,22 +32,18 @@ class TestFeaturizedSamples(TestAPI): 
    current_dir = os.path.dirname(os.path.abspath(__file__))

    input_file = os.path.join(current_dir, "data/water.sdf")



    featurizer = CoulombMatrixEig(6, remove_hydrogens=False)



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

    loader = DataLoader(tasks=tasks,

                        smiles_field=self.smiles_field,

                        mol_field="mol",

                        featurizer=featurizer,

    featurizer = dc.featurizers.CoulombMatrixEig(6, remove_hydrogens=False)

    loader = dc.loaders.DataLoader(

        tasks=tasks, smiles_field="smiles",

        mol_field="mol", featurizer=featurizer,

        verbosity="low")



    dataset = loader.featurize(input_file, self.data_dir)

    dataset = loader.featurize(input_file)



    # Splits featurized samples into train/test

    splitter = RandomSplitter()

    train_dataset, valid_dataset, test_dataset = splitter.train_valid_test_split(

        dataset, self.train_dir, self.valid_dir, self.test_dir)

    splitter = dc.splits.RandomSplitter()

    train_dataset, valid_dataset, test_dataset = \

        splitter.train_valid_test_split(dataset)

    assert len(train_dataset) == 8

    assert len(valid_dataset) == 1

    assert len(test_dataset) == 1

deepchem/models/tests/test_generalize.py

+4 −8
Original line number Diff line number Diff line
@@ -112,10 +112,8 @@ class TestGeneralization(unittest.TestCase): 
    n_train = int(frac_train*n_samples)

    X_train, y_train = X[:n_train], y[:n_train]

    X_test, y_test = X[n_train:], y[n_train:]

    train_dataset = dc.datasets.DiskDataset.from_numpy(

        tempfile.mkdtemp(), X_train, y_train)

    test_dataset = dc.datasets.DiskDataset.from_numpy(

        tempfile.mkdtemp(), X_test, y_test)

    train_dataset = dc.datasets.DiskDataset.from_numpy(X_train, y_train)

    test_dataset = dc.datasets.DiskDataset.from_numpy(X_test, y_test)



    verbosity = "high"

    regression_metric = dc.metrics.Metric(dc.metrics.r2_score)
@@ -174,10 +172,8 @@ class TestGeneralization(unittest.TestCase): 
    n_train = int(frac_train*n_samples)

    X_train, y_train = X[:n_train], y[:n_train]

    X_test, y_test = X[n_train:], y[n_train:]

    train_dataset = dc.datasets.DiskDataset.from_numpy(

        tempfile.mkdtemp(), X_train, y_train)

    test_dataset = dc.datasets.DiskDataset.from_numpy(

        tempfile.mkdtemp(), X_test, y_test)

    train_dataset = dc.datasets.DiskDataset.from_numpy(X_train, y_train)

    test_dataset = dc.datasets.DiskDataset.from_numpy(X_test, y_test)



    classification_metric = dc.metrics.Metric(dc.metrics.roc_auc_score)

    def model_builder(model_dir):

CRA Git | Maintained and supported by SUSTech CRA and CCSE