Commit 7bdc2a80 authored by Bharath's avatar Bharath
Browse files

Debugging broken tests

parent 1b7140fe

deepchem/datasets/__init__.py

+6 −1
Original line number Diff line number Diff line
@@ -13,6 +13,9 @@ from functools import partial 
from deepchem.utils.save import save_to_disk

from deepchem.utils.save import load_from_disk

from deepchem.utils.save import log

####################################################### DEBUG

import sys

####################################################### DEBUG



__author__ = "Bharath Ramsundar"

__copyright__ = "Copyright 2016, Stanford University"
@@ -77,6 +80,7 @@ class Dataset(object): 
      ids, X, y, w = convert_df_to_numpy(df, feature_type, tasks, mol_id_field)

      ############################################################## DEBUG

      print("convert_df_to_numpy returned successfully")

      sys.stdout.flush()

      ############################################################## DEBUG

    else:

      ids, X, y, w = raw_data
@@ -606,10 +610,11 @@ def convert_df_to_numpy(df, feature_type, tasks, mol_id_field): 
    print("SLKFJD:LSKJF:SLFKJ:SLDFKJSD:LKFJDSLKFJSDKFJSLKFJS:LFJSDLKJ")

    print("feature_type")

    print(feature_type)

    sys.stdout.flush()

    ############################################################## DEBUG



    raise ValueError(

        "Featurized data does not support requested feature_type.")

        "Featurized data does not support requested feature_type %s." % feature_type)

  # perform common train/test split across all tasks

  n_samples = df.shape[0]

  n_tasks = len(tasks)

deepchem/datasets/tests/test_load.py

+15 −16
Original line number Diff line number Diff line
@@ -37,12 +37,11 @@ class TestLoad(TestAPI): 


    featurizer = CircularFingerprint(size=1024)

    tasks = ["log-solubility"]

    featurizer = DataFeaturizer(tasks=tasks,

    loader = DataFeaturizer(tasks=tasks,

                                smiles_field="smiles",

                                featurizer=featurizer,

                                verbosity=verbosity)

    dataset = featurizer.featurize(

        dataset_file, data_dir)

    dataset = loader.featurize(dataset_file, data_dir)



    X, y, w, ids = dataset.to_numpy()

    shutil.move(data_dir, moved_data_dir)
@@ -89,15 +88,15 @@ class TestLoad(TestAPI): 


    # Featurize tox21 dataset

    print("About to featurize dataset.")

    featurizer = [CircularFingerprint(size=1024)]

    featurizer = CircularFingerprint(size=1024)

    all_tasks = ["task%d"%i for i in range(17)] 



    ####### Do featurization

    featurizer = DataFeaturizer(tasks=all_tasks,

    loader = DataFeaturizer(tasks=all_tasks,

                                smiles_field="smiles",

                                featurizer=featurizer,

                                verbosity=verbosity)

    dataset = featurizer.featurize(

    dataset = loader.featurize(

        dataset_file, data_dir)



    # Do train/valid split.
@@ -161,11 +160,11 @@ class TestLoad(TestAPI): 
    tasks = all_tasks[0:n_tasks]



    ####### Do multitask load

    featurizer = DataFeaturizer(tasks=tasks,

    loader = DataFeaturizer(tasks=tasks,

                            smiles_field="smiles",

                            featurizer=featurizer,

                            verbosity=verbosity)

    dataset = featurizer.featurize(dataset_file, data_dir)

    dataset = loader.featurize(dataset_file, data_dir)



    # Do train/valid split.

    X_multi, y_multi, w_multi, ids_multi = dataset.to_numpy()
@@ -177,11 +176,11 @@ class TestLoad(TestAPI): 
      print("Processing task %s" % task)

      if os.path.exists(data_dir):

        shutil.rmtree(data_dir)

      featurizer = DataFeaturizer(tasks=[task],

      loader = DataFeaturizer(tasks=[task],

                              smiles_field="smiles",

                              featurizer=featurizer,

                              verbosity=verbosity)

      dataset = featurizer.featurize(dataset_file, data_dir)

      dataset = loader.featurize(dataset_file, data_dir)



      X_task, y_task, w_task, ids_task = dataset.to_numpy()

      y_tasks.append(y_task)

deepchem/datasets/tests/test_reload.py

+4 −4
Original line number Diff line number Diff line
@@ -40,16 +40,16 @@ class TestReload(TestAPI): 
    print("Number of examples in dataset: %s" % str(raw_dataset.shape[0]))



    print("About to featurize compounds")

    featurizers = [CircularFingerprint(size=1024)]

    featurizer = CircularFingerprint(size=1024)

    MUV_tasks = ['MUV-692', 'MUV-689', 'MUV-846', 'MUV-859', 'MUV-644',

                 'MUV-548', 'MUV-852', 'MUV-600', 'MUV-810', 'MUV-712',

                 'MUV-737', 'MUV-858', 'MUV-713', 'MUV-733', 'MUV-652',

                 'MUV-466', 'MUV-832']

    featurizer = DataFeaturizer(tasks=MUV_tasks,

    loader = DataFeaturizer(tasks=MUV_tasks,

                                smiles_field="smiles",

                                featurizers=featurizers,

                                featurizer=featurizer,

                                verbosity=verbosity)

    dataset = featurizer.featurize(dataset_file, self.data_dir)

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

    assert len(dataset) == len(raw_dataset)



    print("About to split compounds into train/valid/test")

deepchem/datasets/tests/test_shuffle.py

+6 −6
Original line number Diff line number Diff line
@@ -32,13 +32,13 @@ class TestShuffle(TestAPI): 
    dataset_file = os.path.join(

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



    featurizers = [CircularFingerprint(size=1024)]

    featurizer = CircularFingerprint(size=1024)

    tasks = ["log-solubility"]

    featurizer = DataFeaturizer(tasks=tasks,

    loader = DataFeaturizer(tasks=tasks,

                            smiles_field="smiles",

                                featurizers=featurizers,

                            featurizer=featurizer,

                            verbosity=verbosity)

    dataset = featurizer.featurize(

    dataset = loader.featurize(

        dataset_file, data_dir, shard_size=2)



    X_orig, y_orig, w_orig, orig_ids = dataset.to_numpy()

deepchem/featurizers/tests/test_featurized_samples.py

+30 −30
Original line number Diff line number Diff line
@@ -37,15 +37,15 @@ class TestFeaturizedSamples(TestAPI): 
    task_type = "regression"

    task_types = {task: task_type for task in tasks}

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

    featurizers = [CircularFingerprint(size=1024)]

    featurizer = CircularFingerprint(size=1024)



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

    featurizer = DataFeaturizer(tasks=tasks,

    loader = DataFeaturizer(tasks=tasks,

                            smiles_field=self.smiles_field,

                                featurizers=featurizers,

                            featurizer=featurizer,

                            verbosity="low")



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

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



    # Splits featurized samples into train/test

    splitter = ScaffoldSplitter()
@@ -65,15 +65,15 @@ class TestFeaturizedSamples(TestAPI): 
    task_type = "regression"

    task_types = {task: task_type for task in tasks}

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

    featurizers = [CircularFingerprint(size=1024)]

    featurizer = CircularFingerprint(size=1024)



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

    featurizer = DataFeaturizer(tasks=tasks,

    loader = DataFeaturizer(tasks=tasks,

                            smiles_field=self.smiles_field,

                                featurizers=featurizers,

                            featurizer=featurizer,

                            verbosity="low")



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

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



    # Splits featurized samples into train/test

    splitter = ScaffoldSplitter()
@@ -91,15 +91,15 @@ class TestFeaturizedSamples(TestAPI): 
    task_type = "regression"

    task_types = {task: task_type for task in tasks}

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

    featurizers = [CircularFingerprint(size=1024)]

    featurizer = CircularFingerprint(size=1024)



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

    featurizer = DataFeaturizer(tasks=tasks,

    loader = DataFeaturizer(tasks=tasks,

                            smiles_field=self.smiles_field,

                                featurizers=featurizers,

                            featurizer=featurizer,

                            verbosity="low")



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

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



    # Splits featurized samples into train/test

    splitter = RandomSplitter()
@@ -117,13 +117,13 @@ class TestFeaturizedSamples(TestAPI): 
    task_type = "regression"

    task_types = {task: task_type for task in tasks}

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

    featurizers = [CircularFingerprint(size=1024)]

    featurizer = DataFeaturizer(tasks=tasks,

    featurizer = CircularFingerprint(size=1024)

    loader = DataFeaturizer(tasks=tasks,

                            smiles_field=self.smiles_field,

                                featurizers=featurizers,

                            featurizer=featurizer,

                            verbosity="low")



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

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



    # Splits featurized samples into train/test

    splitter = RandomSplitter()
@@ -140,13 +140,13 @@ class TestFeaturizedSamples(TestAPI): 
    dataset_file = os.path.join(

        self.current_dir, "example.csv")



    featurizers = [CircularFingerprint(size=1024)]

    featurizer = CircularFingerprint(size=1024)

    tasks = ["log-solubility"]

    featurizer = DataFeaturizer(tasks=tasks,

    loader = DataFeaturizer(tasks=tasks,

                            smiles_field="smiles",

                                featurizers=featurizers,

                            featurizer=featurizer,

                            verbosity=verbosity)

    featurized_dataset = featurizer.featurize(

    featurized_dataset = loader.featurize(

        dataset_file, data_dir)

    n_dataset = len(featurized_dataset)

CRA Git | Maintained and supported by SUSTech CRA and CCSE