qsprpred.data.sampling package

Submodules

qsprpred.data.sampling.folds module

A module that provides a class that creates folds from a given data set.

class qsprpred.data.sampling.folds.FoldGenerator

Bases: ABC

A generator that creates folds from a given data set.

getFolds(dataset: QSPRDataset)

Directly converts the output of iterFolds to a list.

abstract iterFolds(dataset: QSPRDataset, concat=False) → Generator[tuple[pandas.core.frame.DataFrame, pandas.core.frame.DataFrame, pandas.core.frame.DataFrame | pandas.core.series.Series, pandas.core.frame.DataFrame | pandas.core.series.Series, list[int], list[int]], None, None]

Returns the generator of folds to iterate over.

Parameters:

• dataset (QSPRDataset) – the data set to generate the splits for

• concat (bool, optional) – whether to concatenate the features in the test and training set of the data set (default: False)

Returns:

a generator that yields a tuple of (X_train, X_test, y_train, y_test, train_index, test_index)

Return type:

generator

class qsprpred.data.sampling.folds.FoldsFromDataSplit(split: DataSplit, feature_standardizer=None)

Bases: FoldGenerator

This generator takes a scikit-learn or scikit-learn-like splitter and creates folds from it. It is possible to pass a standardizer to make sure features in the splits are properly standardized.

Variables:

• split (DataSplit) – the splitter to use to create the folds (this can also just be a raw scikit-learn splitter)

• featureStandardizer – the standardizer to use to standardize the features (this can also just be a raw scikit-learn standardizer)

Initialize the generator with a splitter and a standardizer.

Parameters:

• split (DataSplit) – the splitter to use to create the folds (this can also just be a raw scikit-learn splitter)

• feature_standardizer – the standardizer to use to standardize the features (this can also just be a raw scikit-learn standardizer)

getFolds(dataset: QSPRDataset)

Directly converts the output of iterFolds to a list.

iterFolds(dataset: QSPRDataset, concat=False) → Generator[tuple[pandas.core.frame.DataFrame, pandas.core.frame.DataFrame, pandas.core.frame.DataFrame | pandas.core.series.Series, pandas.core.frame.DataFrame | pandas.core.series.Series, list[int], list[int]], None, None]

Create folds from X and y. Can be used either for cross-validation, bootstrapping or train-test split.

Each split in the resulting generator is represented by a tuple: (

X_train, # feature matrix of the training set X_test, # feature matrix of the test set y_train, # target values of the training set y_test, # target values of the test set train_index, # indices of the training set in the original data set test_index # indices of the test set in the original data set

)

Parameters:

dataset (QSPRDataset) – the data set to generate the splits for

Returns:

a generator that yields a tuple of (X_train, X_test, y_train, y_test, train_index, test_index)

Return type:

generator

qsprpred.data.sampling.splits module

Different splitters to create train and tests for evalutating QSPR model performance.

To add a new data splitter: * Add a DataSplit subclass for your new splitter

class qsprpred.data.sampling.splits.BootstrapSplit(split: DataSplit, n_bootstraps=5, seed=None)

Bases: DataSplit, Randomized

Splits dataset in random train and test subsets (bootstraps). Unlike cross-validation, bootstrapping allows for repeated samples in the test set.

Variables:

• nBootstraps (int) – number of bootstraps to perform

• seed (int) – Random state to use for shuffling and other random operations.

Initialize a BootstrapSplit object.

Parameters:

• split (DataSplit) – the splitter to use for the bootstraps

• n_bootstraps (int) – number of bootstraps to perform

• seed (int) – random seed to use for random operations

getDataSet()

Get the data set attached to this object.

Raises:

ValueError – If no data set is attached to this object.

getSeed()

Get the seed used to randomize the action.

property hasDataSet: bool

Indicates if this object has a data set attached to it.

setDataSet(dataset: MoleculeDataTable)

setSeed(seed: int | None = None)

split(X: ndarray | DataFrame, y: ndarray | DataFrame | Series) → Iterable[tuple[list[int], list[int]]]

Split the given data into nBootstraps training and test sets.

Parameters:

• X (np.ndarray | pd.DataFrame) – the input data matrix

• y (np.ndarray | pd.DataFrame | pd.Series) – the target variable(s)

Returns:

an generator over nBootstraps tuples generated by the underlying splitter

splitDataset(dataset: QSPRDataset)

class qsprpred.data.sampling.splits.ClusterSplit(dataset: QSPRDataset = None, test_fraction: float = 0.1, n_folds: int = 1, custom_test_list: list[str] | None = None, seed: int | None = None, clustering: MoleculeClusters | None = None, **split_kwargs)

Bases: GBMTDataSplit

Splits dataset into balanced train and test subsets based on clusters of similar molecules.

Variables:

• dataset (QSPRDataset) – dataset that this splitter will be acting on

• testFraction (float) – fraction of total dataset to testset

• customTestList (list) – list of molecule indexes to force in test set

• seed (int) – Random state to use for shuffling and other random operations.

• split_kwargs (dict) – additional arguments to be passed to the GloballyBalancedSplit

getDataSet()

Get the data set attached to this object.

Raises:

ValueError – If no data set is attached to this object.

getSeed()

Get the seed for this instance.

Returns:

the seed for this instance or None if no seed is set.

Return type:

int

property hasDataSet: bool

Indicates if this object has a data set attached to it.

setDataSet(dataset: MoleculeDataTable)

setSeed(seed: int | None)

Set the seed for this instance.

Parameters:

seed (int) – Random state to use for shuffling and other random operations.

split(X: ndarray | DataFrame, y: ndarray | DataFrame | Series) → Iterable[tuple[list[int], list[int]]]

Split dataset into balanced train and test subsets based on an initial clustering algorithm.

Parameters:

• X (np.ndarray | pd.DataFrame) – the input data matrix

• y (np.ndarray | pd.DataFrame | pd.Series) – the target variable(s)

Returns:

an generator over the generated subsets represented as a tuple of (train_indices, test_indices) where the indices are the row indices of the input data matrix

splitDataset(dataset: QSPRDataset)

class qsprpred.data.sampling.splits.DataSplit(dataset: MoleculeDataTable | None = None)

Bases: DataSetDependant, ABC

Defines a function split a dataframe into train and test set.

Variables:

dataset (MoleculeDataTable) – The dataset to split.

getDataSet()

Get the data set attached to this object.

Raises:

ValueError – If no data set is attached to this object.

property hasDataSet: bool

Indicates if this object has a data set attached to it.

setDataSet(dataset: MoleculeDataTable)

abstract split(X: ndarray | DataFrame, y: ndarray | DataFrame | Series) → Iterable[tuple[list[int], list[int]]]

Split the given data into one or multiple train/test subsets.

These classes handle partitioning of a feature matrix by returning an generator of train and test indices. It is compatible with the approach taken in the sklearn package (see sklearn.model_selection._BaseKFold). This can be used for both cross-validation or a one time train/test split.

Parameters:

• X (np.ndarray | pd.DataFrame) – the input data matrix

• y (np.ndarray | pd.DataFrame | pd.Series) – the target variable(s)

Returns:

an generator over the generated subsets represented as a tuple of (train_indices, test_indices) where the indices are the row indices of the input data matrix X (note that these are integer indices, rather than a pandas index!)

splitDataset(dataset: QSPRDataset)

class qsprpred.data.sampling.splits.GBMTDataSplit(dataset: ~qsprpred.data.tables.qspr.QSPRDataset = None, clustering: ~qsprpred.data.chem.clustering.MoleculeClusters = <qsprpred.data.chem.clustering.FPSimilarityMaxMinClusters object>, test_fraction: float = 0.1, n_folds: int = 1, custom_test_list: list[str] | None = None, **split_kwargs)

Bases: DataSplit

Splits dataset into balanced train and test subsets based on an initial clustering algorithm. If nFolds is specified, the determined clusters will be split into nFolds groups of approximately equal size, and the splits will be generated by leaving out one group at a time.

Variables:

• dataset (QSPRDataset) – dataset that this splitter will be acting on

• clustering (MoleculeClusters) – clustering algorithm to use

• testFraction (float) – fraction of total dataset to testset

• nFolds (int) – number of folds to split the dataset into (this overrides testFraction and customTestList)

• customTestList (list) – list of molecule indexes to force in test set

• split_kwargs (dict) – additional arguments to be passed to the GloballyBalancedSplit

getDataSet()

Get the data set attached to this object.

Raises:

ValueError – If no data set is attached to this object.

property hasDataSet: bool

Indicates if this object has a data set attached to it.

setDataSet(dataset: MoleculeDataTable)

split(X: ndarray | DataFrame, y: ndarray | DataFrame | Series) → Iterable[tuple[list[int], list[int]]]

Split dataset into balanced train and test subsets based on an initial clustering algorithm.

Parameters:

• X (np.ndarray | pd.DataFrame) – the input data matrix

• y (np.ndarray | pd.DataFrame | pd.Series) – the target variable(s)

Returns:

an generator over the generated subsets represented as a tuple of (train_indices, test_indices) where the indices are the row indices of the input data matrix

splitDataset(dataset: QSPRDataset)

class qsprpred.data.sampling.splits.GBMTRandomSplit(dataset: QSPRDataset | None = None, test_fraction: float = 0.1, n_folds: int = 1, seed: int | None = None, n_initial_clusters: int | None = None, custom_test_list: list[str] | None = None, **split_kwargs)

Bases: GBMTDataSplit

Splits dataset into balanced random train and test subsets.

Variables:

• dataset (QSPRDataset) – dataset that this splitter will be acting on

• testFraction (float) – fraction of total dataset to testset

• seed (int) – Random state to use for shuffling and other random operations.

• customTestList (list) – list of molecule indexes to force in test set

• split_kwargs (dict) – additional arguments to be passed to the GloballyBalancedSplit

getDataSet()

Get the data set attached to this object.

Raises:

ValueError – If no data set is attached to this object.

property hasDataSet: bool

Indicates if this object has a data set attached to it.

setDataSet(dataset: MoleculeDataTable)

split(X: ndarray | DataFrame, y: ndarray | DataFrame | Series) → Iterable[tuple[list[int], list[int]]]

Split dataset into balanced train and test subsets based on an initial clustering algorithm.

Parameters:

• X (np.ndarray | pd.DataFrame) – the input data matrix

• y (np.ndarray | pd.DataFrame | pd.Series) – the target variable(s)

Returns:

an generator over the generated subsets represented as a tuple of (train_indices, test_indices) where the indices are the row indices of the input data matrix

splitDataset(dataset: QSPRDataset)

class qsprpred.data.sampling.splits.ManualSplit(splitcol: Series, trainval: str, testval: str)

Bases: DataSplit

Splits dataset in train and test subsets based on a column in the dataframe.

Variables:

• splitCol (pd.Series) – pandas series with split information

• trainVal (str) – value in splitcol that will be used for training

• testVal (str) – value in splitcol that will be used for testing

Raises:

ValueError – if there are more values in splitcol than trainval and testval

Initialize the ManualSplit object with the splitcol, trainval and testval attributes.

Parameters:

• splitCol (pd.Series) – pandas series with split information

• trainVal (str) – value in splitcol that will be used for training

• testVal (str) – value in splitcol that will be used for testing

Raises:

ValueError – if there are more values in splitcol than trainval and testval

getDataSet()

Get the data set attached to this object.

Raises:

ValueError – If no data set is attached to this object.

property hasDataSet: bool

Indicates if this object has a data set attached to it.

setDataSet(dataset: MoleculeDataTable)

split(X, y)

Split the given data into one or multiple train/test subsets based on the predefined splitcol.

Parameters:

• X (np.ndarray | pd.DataFrame) – the input data matrix

• y (np.ndarray | pd.DataFrame | pd.Series) – the target variable(s)

Returns:

an generator over the generated subsets represented as a tuple of (train_indices, test_indices) where the indices are the row indices of the input data matrix

splitDataset(dataset: QSPRDataset)

class qsprpred.data.sampling.splits.RandomSplit(test_fraction=0.1, dataset: QSPRDataset | None = None, seed: int | None = None)

Bases: DataSplit, Randomized

Splits dataset in random train and test subsets.

Variables:

• testFraction (float) – fraction of total dataset to testset

• seed (int) – Random state to use for shuffling and other random operations.

getDataSet()

Get the data set attached to this object.

Raises:

ValueError – If no data set is attached to this object.

getSeed()

Get the seed used to randomize the action.

property hasDataSet: bool

Indicates if this object has a data set attached to it.

setDataSet(dataset: MoleculeDataTable)

setSeed(seed: int | None = None)

split(X, y)

Split the given data into one or multiple train/test subsets.

These classes handle partitioning of a feature matrix by returning an generator of train and test indices. It is compatible with the approach taken in the sklearn package (see sklearn.model_selection._BaseKFold). This can be used for both cross-validation or a one time train/test split.

Parameters:

• X (np.ndarray | pd.DataFrame) – the input data matrix

• y (np.ndarray | pd.DataFrame | pd.Series) – the target variable(s)

Returns:

an generator over the generated subsets represented as a tuple of (train_indices, test_indices) where the indices are the row indices of the input data matrix X (note that these are integer indices, rather than a pandas index!)

splitDataset(dataset: QSPRDataset)

class qsprpred.data.sampling.splits.ScaffoldSplit(dataset: ~qsprpred.data.tables.qspr.QSPRDataset | None = None, scaffold: ~qsprpred.data.chem.scaffolds.Scaffold = <qsprpred.data.chem.scaffolds.BemisMurckoRDKit object>, test_fraction: float = 0.1, n_folds: int = 1, custom_test_list: list | None = None, **split_kwargs)

Bases: GBMTDataSplit

Splits dataset into balanced train and test subsets based on molecular scaffolds.

Variables:

• dataset (QSPRDataset) – dataset that this splitter will be acting on

• testFraction (float) – fraction of total dataset to testset

• customTestList (list) – list of molecule indexes to force in test set

• split_kwargs (dict) – additional arguments to be passed to the GloballyBalancedSplit

getDataSet()

Get the data set attached to this object.

Raises:

ValueError – If no data set is attached to this object.

property hasDataSet: bool

Indicates if this object has a data set attached to it.

setDataSet(dataset: MoleculeDataTable)

split(X: ndarray | DataFrame, y: ndarray | DataFrame | Series) → Iterable[tuple[list[int], list[int]]]

Split dataset into balanced train and test subsets based on an initial clustering algorithm.

Parameters:

• X (np.ndarray | pd.DataFrame) – the input data matrix

• y (np.ndarray | pd.DataFrame | pd.Series) – the target variable(s)

Returns:

an generator over the generated subsets represented as a tuple of (train_indices, test_indices) where the indices are the row indices of the input data matrix

splitDataset(dataset: QSPRDataset)

class qsprpred.data.sampling.splits.TemporalSplit(timesplit: float | list[float], timeprop: str, dataset: QSPRDataset | None = None)

Bases: DataSplit

Splits dataset train and test subsets based on a threshold in time.

Variables:

• dataset (QSPRDataset) – dataset that this splitter will be acting on

• timeSplit (float) – time point after which sample to test set

• timeCol (str) – name of the column within the dataframe with timepoints

Initialize a TemporalSplit object.

Parameters:

• dataset (QSPRDataset) – dataset that this splitter will be acting on

• timesplit (float | list[float]) – time point after which sample is moved to test set. If a list is provided, the splitter will split the dataset into multiple subsets based on the timepoints in the list.

• timeprop (str) – name of the column within the dataframe with timepoints

getDataSet()

Get the data set attached to this object.

Raises:

ValueError – If no data set is attached to this object.

property hasDataSet: bool

Indicates if this object has a data set attached to it.

setDataSet(dataset: MoleculeDataTable)

split(X, y)

Split single-task dataset based on a time threshold.

Returns:

an generator over the generated subsets represented as a tuple of (train_indices, test_indices) where the indices are the row indices of the input data matrix

splitDataset(dataset: QSPRDataset)

qsprpred.data.sampling.tests module

class qsprpred.data.sampling.tests.TestDataSplitters(methodName='runTest')

Bases: DataSetsPathMixIn, QSPRTestCase

Small tests to only check if the data splitters work on their own.

The tests here should be used to check for all their specific parameters and edge cases.

Create an instance of the class that will use the named test method when executed. Raises a ValueError if the instance does not have a method with the specified name.

classmethod addClassCleanup(function, /, *args, **kwargs)

Same as addCleanup, except the cleanup items are called even if setUpClass fails (unlike tearDownClass).

addCleanup(function, /, *args, **kwargs)

Add a function, with arguments, to be called when the test is completed. Functions added are called on a LIFO basis and are called after tearDown on test failure or success.

Cleanup items are called even if setUp fails (unlike tearDown).

addTypeEqualityFunc(typeobj, function)

Add a type specific assertEqual style function to compare a type.

This method is for use by TestCase subclasses that need to register their own type equality functions to provide nicer error messages.

Parameters:

• typeobj – The data type to call this function on when both values are of the same type in assertEqual().

• function – The callable taking two arguments and an optional msg= argument that raises self.failureException with a useful error message when the two arguments are not equal.

assertAlmostEqual(first, second, places=None, msg=None, delta=None)

Fail if the two objects are unequal as determined by their difference rounded to the given number of decimal places (default 7) and comparing to zero, or by comparing that the difference between the two objects is more than the given delta.

Note that decimal places (from zero) are usually not the same as significant digits (measured from the most significant digit).

If the two objects compare equal then they will automatically compare almost equal.

assertCountEqual(first, second, msg=None)

Asserts that two iterables have the same elements, the same number of times, without regard to order.

self.assertEqual(Counter(list(first)),

Counter(list(second)))

Example:

• [0, 1, 1] and [1, 0, 1] compare equal.

• [0, 0, 1] and [0, 1] compare unequal.

assertDictEqual(d1, d2, msg=None)

assertEqual(first, second, msg=None)

Fail if the two objects are unequal as determined by the ‘==’ operator.

assertFalse(expr, msg=None)

Check that the expression is false.

assertGreater(a, b, msg=None)

Just like self.assertTrue(a > b), but with a nicer default message.

assertGreaterEqual(a, b, msg=None)

Just like self.assertTrue(a >= b), but with a nicer default message.

assertIn(member, container, msg=None)

Just like self.assertTrue(a in b), but with a nicer default message.

assertIs(expr1, expr2, msg=None)

Just like self.assertTrue(a is b), but with a nicer default message.

assertIsInstance(obj, cls, msg=None)

Same as self.assertTrue(isinstance(obj, cls)), with a nicer default message.

assertIsNone(obj, msg=None)

Same as self.assertTrue(obj is None), with a nicer default message.

assertIsNot(expr1, expr2, msg=None)

Just like self.assertTrue(a is not b), but with a nicer default message.

assertIsNotNone(obj, msg=None)

Included for symmetry with assertIsNone.

assertLess(a, b, msg=None)

Just like self.assertTrue(a < b), but with a nicer default message.

assertLessEqual(a, b, msg=None)

Just like self.assertTrue(a <= b), but with a nicer default message.

assertListEqual(list1, list2, msg=None)

A list-specific equality assertion.

Parameters:

• list1 – The first list to compare.

• list2 – The second list to compare.

• msg – Optional message to use on failure instead of a list of differences.

assertLogs(logger=None, level=None)

Fail unless a log message of level level or higher is emitted on logger_name or its children. If omitted, level defaults to INFO and logger defaults to the root logger.

This method must be used as a context manager, and will yield a recording object with two attributes: output and records. At the end of the context manager, the output attribute will be a list of the matching formatted log messages and the records attribute will be a list of the corresponding LogRecord objects.

Example:

with self.assertLogs('foo', level='INFO') as cm:
    logging.getLogger('foo').info('first message')
    logging.getLogger('foo.bar').error('second message')
self.assertEqual(cm.output, ['INFO:foo:first message',
                             'ERROR:foo.bar:second message'])

assertMultiLineEqual(first, second, msg=None)

Assert that two multi-line strings are equal.

assertNoLogs(logger=None, level=None)

Fail unless no log messages of level level or higher are emitted on logger_name or its children.

This method must be used as a context manager.

assertNotAlmostEqual(first, second, places=None, msg=None, delta=None)

Fail if the two objects are equal as determined by their difference rounded to the given number of decimal places (default 7) and comparing to zero, or by comparing that the difference between the two objects is less than the given delta.

Note that decimal places (from zero) are usually not the same as significant digits (measured from the most significant digit).

Objects that are equal automatically fail.

assertNotEqual(first, second, msg=None)

Fail if the two objects are equal as determined by the ‘!=’ operator.

assertNotIn(member, container, msg=None)

Just like self.assertTrue(a not in b), but with a nicer default message.

assertNotIsInstance(obj, cls, msg=None)

Included for symmetry with assertIsInstance.

assertNotRegex(text, unexpected_regex, msg=None)

Fail the test if the text matches the regular expression.

assertRaises(expected_exception, *args, **kwargs)

Fail unless an exception of class expected_exception is raised by the callable when invoked with specified positional and keyword arguments. If a different type of exception is raised, it will not be caught, and the test case will be deemed to have suffered an error, exactly as for an unexpected exception.

If called with the callable and arguments omitted, will return a context object used like this:

with self.assertRaises(SomeException):
    do_something()

An optional keyword argument ‘msg’ can be provided when assertRaises is used as a context object.

The context manager keeps a reference to the exception as the ‘exception’ attribute. This allows you to inspect the exception after the assertion:

with self.assertRaises(SomeException) as cm:
    do_something()
the_exception = cm.exception
self.assertEqual(the_exception.error_code, 3)

assertRaisesRegex(expected_exception, expected_regex, *args, **kwargs)

Asserts that the message in a raised exception matches a regex.

Parameters:

• expected_exception – Exception class expected to be raised.

• expected_regex – Regex (re.Pattern object or string) expected to be found in error message.

• args – Function to be called and extra positional args.

• kwargs – Extra kwargs.

• msg – Optional message used in case of failure. Can only be used when assertRaisesRegex is used as a context manager.

assertRegex(text, expected_regex, msg=None)

Fail the test unless the text matches the regular expression.

assertSequenceEqual(seq1, seq2, msg=None, seq_type=None)

An equality assertion for ordered sequences (like lists and tuples).

For the purposes of this function, a valid ordered sequence type is one which can be indexed, has a length, and has an equality operator.

Parameters:

• seq1 – The first sequence to compare.

• seq2 – The second sequence to compare.

• seq_type – The expected datatype of the sequences, or None if no datatype should be enforced.

• msg – Optional message to use on failure instead of a list of differences.

assertSetEqual(set1, set2, msg=None)

A set-specific equality assertion.

Parameters:

• set1 – The first set to compare.

• set2 – The second set to compare.

• msg – Optional message to use on failure instead of a list of differences.

assertSetEqual uses ducktyping to support different types of sets, and is optimized for sets specifically (parameters must support a difference method).

assertTrue(expr, msg=None)

Check that the expression is true.

assertTupleEqual(tuple1, tuple2, msg=None)

A tuple-specific equality assertion.

Parameters:

• tuple1 – The first tuple to compare.

• tuple2 – The second tuple to compare.

• msg – Optional message to use on failure instead of a list of differences.

assertWarns(expected_warning, *args, **kwargs)

Fail unless a warning of class warnClass is triggered by the callable when invoked with specified positional and keyword arguments. If a different type of warning is triggered, it will not be handled: depending on the other warning filtering rules in effect, it might be silenced, printed out, or raised as an exception.

If called with the callable and arguments omitted, will return a context object used like this:

with self.assertWarns(SomeWarning):
    do_something()

An optional keyword argument ‘msg’ can be provided when assertWarns is used as a context object.

The context manager keeps a reference to the first matching warning as the ‘warning’ attribute; similarly, the ‘filename’ and ‘lineno’ attributes give you information about the line of Python code from which the warning was triggered. This allows you to inspect the warning after the assertion:

with self.assertWarns(SomeWarning) as cm:
    do_something()
the_warning = cm.warning
self.assertEqual(the_warning.some_attribute, 147)

assertWarnsRegex(expected_warning, expected_regex, *args, **kwargs)

Asserts that the message in a triggered warning matches a regexp. Basic functioning is similar to assertWarns() with the addition that only warnings whose messages also match the regular expression are considered successful matches.

Parameters:

• expected_warning – Warning class expected to be triggered.

• expected_regex – Regex (re.Pattern object or string) expected to be found in error message.

• args – Function to be called and extra positional args.

• kwargs – Extra kwargs.

• msg – Optional message used in case of failure. Can only be used when assertWarnsRegex is used as a context manager.

clearGenerated()

Remove the directories that are used for testing.

countTestCases()

createLargeMultitaskDataSet(name='QSPRDataset_multi_test', target_props=[{'name': 'HBD', 'task': <TargetTasks.MULTICLASS: 'MULTICLASS'>, 'th': [-1, 1, 2, 100]}, {'name': 'CL', 'task': <TargetTasks.REGRESSION: 'REGRESSION'>}], preparation_settings=None, random_state=42)

Create a large dataset for testing purposes.

Parameters:

• name (str) – name of the dataset

• target_props (List of dicts or TargetProperty) – list of target properties

• preparation_settings (dict) – dictionary containing preparation settings

• random_state (int) – random state to use for splitting and shuffling

Returns:

a QSPRDataset object

Return type:

QSPRDataset

createLargeTestDataSet(name='QSPRDataset_test_large', target_props=[{'name': 'CL', 'task': <TargetTasks.REGRESSION: 'REGRESSION'>}], preparation_settings=None, random_state=42, n_jobs=1, chunk_size=None)

Create a large dataset for testing purposes.

Parameters:

• name (str) – name of the dataset

• target_props (List of dicts or TargetProperty) – list of target properties

• random_state (int) – random state to use for splitting and shuffling

• preparation_settings (dict) – dictionary containing preparation settings

Returns:

a QSPRDataset object

Return type:

QSPRDataset

createSmallTestDataSet(name='QSPRDataset_test_small', target_props=[{'name': 'CL', 'task': <TargetTasks.REGRESSION: 'REGRESSION'>}], preparation_settings=None, random_state=42)

Create a small dataset for testing purposes.

Parameters:

• name (str) – name of the dataset

• target_props (List of dicts or TargetProperty) – list of target properties

• random_state (int) – random state to use for splitting and shuffling

• preparation_settings (dict) – dictionary containing preparation settings

Returns:

a QSPRDataset object

Return type:

QSPRDataset

createTestDataSetFromFrame(df, name='QSPRDataset_test', target_props=[{'name': 'CL', 'task': <TargetTasks.REGRESSION: 'REGRESSION'>}], random_state=None, prep=None, n_jobs=1, chunk_size=None)

Create a dataset for testing purposes from the given data frame.

Parameters:

• df (pd.DataFrame) – data frame containing the dataset

• name (str) – name of the dataset

• target_props (List of dicts or TargetProperty) – list of target properties

• random_state (int) – random state to use for splitting and shuffling

• prep (dict) – dictionary containing preparation settings

Returns:

a QSPRDataset object

Return type:

QSPRDataset

debug()

Run the test without collecting errors in a TestResult

defaultTestResult()

classmethod doClassCleanups()

Execute all class cleanup functions. Normally called for you after tearDownClass.

doCleanups()

Execute all cleanup functions. Normally called for you after tearDown.

classmethod enterClassContext(cm)

Same as enterContext, but class-wide.

enterContext(cm)

Enters the supplied context manager.

If successful, also adds its __exit__ method as a cleanup function and returns the result of the __enter__ method.

fail(msg=None)

Fail immediately, with the given message.

failureException

alias of AssertionError

classmethod getAllDescriptors()

Return a list of (ideally) all available descriptor sets. For now they need to be added manually to the list below.

TODO: would be nice to create the list automatically by implementing a descriptor set registry that would hold all installed descriptor sets.

Returns:

list of DescriptorCalculator objects

Return type:

list

getBigDF()

Get a large data frame for testing purposes.

Returns:

a pandas.DataFrame containing the dataset

Return type:

pd.DataFrame

classmethod getDataPrepGrid()

Return a list of many possible combinations of descriptor calculators, splits, feature standardizers, feature filters and data filters. Again, this is not exhaustive, but should cover a lot of cases.

Returns:

a generator that yields tuples of all possible combinations as stated above, each tuple is defined as: (descriptor_calculator, split, feature_standardizer, feature_filters, data_filters)

Return type:

grid

classmethod getDefaultCalculatorCombo()

Makes a list of default descriptor calculators that can be used in tests. It creates a calculator with only morgan fingerprints and rdkit descriptors, but also one with them both to test behaviour with multiple descriptor sets. Override this method if you want to test with other descriptor sets and calculator combinations.

Returns:

list of created DescriptorCalculator objects

Return type:

list

static getDefaultPrep()

Return a dictionary with default preparation settings.

classmethod getPrepCombos()

Return a list of all possible preparation combinations as generated by getDataPrepGrid as well as their names. The generated list can be used to parameterize tests with the given named combinations.

Returns:

list of `list`s of all possible combinations of preparation

Return type:

list

getSmallDF()

Get a small data frame for testing purposes.

Returns:

a pandas.DataFrame containing the dataset

Return type:

pd.DataFrame

id()

longMessage = True

maxDiff = 640

run(result=None)

setUp()

Hook method for setting up the test fixture before exercising it.

classmethod setUpClass()

Hook method for setting up class fixture before running tests in the class.

setUpPaths()

Create the directories that are used for testing.

shortDescription()

Returns a one-line description of the test, or None if no description has been provided.

The default implementation of this method returns the first line of the specified test method’s docstring.

skipTest(reason)

Skip this test.

subTest(msg=<object object>, **params)

Return a context manager that will return the enclosed block of code in a subtest identified by the optional message and keyword parameters. A failure in the subtest marks the test case as failed but resumes execution at the end of the enclosed block, allowing further test code to be executed.

tearDown()

Remove all files and directories that are used for testing.

classmethod tearDownClass()

Hook method for deconstructing the class fixture after running all tests in the class.

testClusterSplit = None

testClusterSplit_0(**kw)

Test the cluster split function [with multitask=False, clustering_algorithm=<qsprpred.data.chem.clustering.F…usters object at 0x7efffb2fef60>, custom_test_list=None].

testClusterSplit_1(**kw)

Test the cluster split function [with multitask=False, clustering_algorithm=<qsprpred.data.chem.clustering.F…usters object at 0x7efffb2fea20>, custom_test_list=[‘ClusterSplit_000’, ‘ClusterSplit_001’]].

testClusterSplit_2(**kw)

Test the cluster split function [with multitask=True, clustering_algorithm=<qsprpred.data.chem.clustering.F…usters object at 0x7efffb2ff050>, custom_test_list=None].

testClusterSplit_3(**kw)

Test the cluster split function [with multitask=True, clustering_algorithm=<qsprpred.data.chem.clustering.F…usters object at 0x7efffb2fc890>, custom_test_list=[‘ClusterSplit_000’, ‘ClusterSplit_001’]].

testManualSplit()

Test the manual split function, where the split is done manually.

testRandomSplit = None

testRandomSplit_0(**kw)

Test the random split function [with multitask=False].

testRandomSplit_1(**kw)

Test the random split function [with multitask=True].

testScaffoldSplit = None

testScaffoldSplit_0(**kw)

Test the scaffold split function [with multitask=False, scaffold=<qsprpred.data.chem.scaffolds.Be…oRDKit object at 0x7efffb2fe8a0>, custom_test_list=None].

testScaffoldSplit_1(**kw)

Test the scaffold split function [with multitask=False, scaffold=<qsprpred.data.chem.scaffolds.Be…Murcko object at 0x7efffb2fe930>, custom_test_list=[‘ScaffoldSplit_000’, ‘ScaffoldSplit_001’]].

testScaffoldSplit_2(**kw)

Test the scaffold split function [with multitask=True, scaffold=<qsprpred.data.chem.scaffolds.Be…oRDKit object at 0x7efffb2fea50>, custom_test_list=None].

testSerialization()

Test the serialization of dataset with datasplit.

testTemporalSplit = None

testTemporalSplit_0(**kw)

Test the temporal split function, where the split is done based on a time [with multitask=False] property.

testTemporalSplit_1(**kw)

Test the temporal split function, where the split is done based on a time [with multitask=True] property.

validate_split(dataset)

Check if the split has the data it should have after splitting.

class qsprpred.data.sampling.tests.TestFoldSplitters(methodName='runTest')

Bases: DataSetsPathMixIn, QSPRTestCase

Small tests to only check if the fold splitters work on their own.

The tests here should be used to check for all their specific parameters and edge cases.

Create an instance of the class that will use the named test method when executed. Raises a ValueError if the instance does not have a method with the specified name.

classmethod addClassCleanup(function, /, *args, **kwargs)

Same as addCleanup, except the cleanup items are called even if setUpClass fails (unlike tearDownClass).

addCleanup(function, /, *args, **kwargs)

Add a function, with arguments, to be called when the test is completed. Functions added are called on a LIFO basis and are called after tearDown on test failure or success.

Cleanup items are called even if setUp fails (unlike tearDown).

addTypeEqualityFunc(typeobj, function)

Add a type specific assertEqual style function to compare a type.

This method is for use by TestCase subclasses that need to register their own type equality functions to provide nicer error messages.

Parameters:

• typeobj – The data type to call this function on when both values are of the same type in assertEqual().

• function – The callable taking two arguments and an optional msg= argument that raises self.failureException with a useful error message when the two arguments are not equal.

assertAlmostEqual(first, second, places=None, msg=None, delta=None)

Fail if the two objects are unequal as determined by their difference rounded to the given number of decimal places (default 7) and comparing to zero, or by comparing that the difference between the two objects is more than the given delta.

Note that decimal places (from zero) are usually not the same as significant digits (measured from the most significant digit).

If the two objects compare equal then they will automatically compare almost equal.

assertCountEqual(first, second, msg=None)

Asserts that two iterables have the same elements, the same number of times, without regard to order.

self.assertEqual(Counter(list(first)),

Counter(list(second)))

Example:

• [0, 1, 1] and [1, 0, 1] compare equal.

• [0, 0, 1] and [0, 1] compare unequal.

assertDictEqual(d1, d2, msg=None)

assertEqual(first, second, msg=None)

Fail if the two objects are unequal as determined by the ‘==’ operator.

assertFalse(expr, msg=None)

Check that the expression is false.

assertGreater(a, b, msg=None)

Just like self.assertTrue(a > b), but with a nicer default message.

assertGreaterEqual(a, b, msg=None)

Just like self.assertTrue(a >= b), but with a nicer default message.

assertIn(member, container, msg=None)

Just like self.assertTrue(a in b), but with a nicer default message.

assertIs(expr1, expr2, msg=None)

Just like self.assertTrue(a is b), but with a nicer default message.

assertIsInstance(obj, cls, msg=None)

Same as self.assertTrue(isinstance(obj, cls)), with a nicer default message.

assertIsNone(obj, msg=None)

Same as self.assertTrue(obj is None), with a nicer default message.

assertIsNot(expr1, expr2, msg=None)

Just like self.assertTrue(a is not b), but with a nicer default message.

assertIsNotNone(obj, msg=None)

Included for symmetry with assertIsNone.

assertLess(a, b, msg=None)

Just like self.assertTrue(a < b), but with a nicer default message.

assertLessEqual(a, b, msg=None)

Just like self.assertTrue(a <= b), but with a nicer default message.

assertListEqual(list1, list2, msg=None)

A list-specific equality assertion.

Parameters:

• list1 – The first list to compare.

• list2 – The second list to compare.

• msg – Optional message to use on failure instead of a list of differences.

assertLogs(logger=None, level=None)

Fail unless a log message of level level or higher is emitted on logger_name or its children. If omitted, level defaults to INFO and logger defaults to the root logger.

This method must be used as a context manager, and will yield a recording object with two attributes: output and records. At the end of the context manager, the output attribute will be a list of the matching formatted log messages and the records attribute will be a list of the corresponding LogRecord objects.

Example:

with self.assertLogs('foo', level='INFO') as cm:
    logging.getLogger('foo').info('first message')
    logging.getLogger('foo.bar').error('second message')
self.assertEqual(cm.output, ['INFO:foo:first message',
                             'ERROR:foo.bar:second message'])

assertMultiLineEqual(first, second, msg=None)

Assert that two multi-line strings are equal.

assertNoLogs(logger=None, level=None)

Fail unless no log messages of level level or higher are emitted on logger_name or its children.

This method must be used as a context manager.

assertNotAlmostEqual(first, second, places=None, msg=None, delta=None)

Fail if the two objects are equal as determined by their difference rounded to the given number of decimal places (default 7) and comparing to zero, or by comparing that the difference between the two objects is less than the given delta.

Note that decimal places (from zero) are usually not the same as significant digits (measured from the most significant digit).

Objects that are equal automatically fail.

assertNotEqual(first, second, msg=None)

Fail if the two objects are equal as determined by the ‘!=’ operator.

assertNotIn(member, container, msg=None)

Just like self.assertTrue(a not in b), but with a nicer default message.

assertNotIsInstance(obj, cls, msg=None)

Included for symmetry with assertIsInstance.

assertNotRegex(text, unexpected_regex, msg=None)

Fail the test if the text matches the regular expression.

assertRaises(expected_exception, *args, **kwargs)

Fail unless an exception of class expected_exception is raised by the callable when invoked with specified positional and keyword arguments. If a different type of exception is raised, it will not be caught, and the test case will be deemed to have suffered an error, exactly as for an unexpected exception.

If called with the callable and arguments omitted, will return a context object used like this:

with self.assertRaises(SomeException):
    do_something()

An optional keyword argument ‘msg’ can be provided when assertRaises is used as a context object.

The context manager keeps a reference to the exception as the ‘exception’ attribute. This allows you to inspect the exception after the assertion:

with self.assertRaises(SomeException) as cm:
    do_something()
the_exception = cm.exception
self.assertEqual(the_exception.error_code, 3)

assertRaisesRegex(expected_exception, expected_regex, *args, **kwargs)

Asserts that the message in a raised exception matches a regex.

Parameters:

• expected_exception – Exception class expected to be raised.

• expected_regex – Regex (re.Pattern object or string) expected to be found in error message.

• args – Function to be called and extra positional args.

• kwargs – Extra kwargs.

• msg – Optional message used in case of failure. Can only be used when assertRaisesRegex is used as a context manager.

assertRegex(text, expected_regex, msg=None)

Fail the test unless the text matches the regular expression.

assertSequenceEqual(seq1, seq2, msg=None, seq_type=None)

An equality assertion for ordered sequences (like lists and tuples).

For the purposes of this function, a valid ordered sequence type is one which can be indexed, has a length, and has an equality operator.

Parameters:

• seq1 – The first sequence to compare.

• seq2 – The second sequence to compare.

• seq_type – The expected datatype of the sequences, or None if no datatype should be enforced.

• msg – Optional message to use on failure instead of a list of differences.

assertSetEqual(set1, set2, msg=None)

A set-specific equality assertion.

Parameters:

• set1 – The first set to compare.

• set2 – The second set to compare.

• msg – Optional message to use on failure instead of a list of differences.

assertSetEqual uses ducktyping to support different types of sets, and is optimized for sets specifically (parameters must support a difference method).

assertTrue(expr, msg=None)

Check that the expression is true.

assertTupleEqual(tuple1, tuple2, msg=None)

A tuple-specific equality assertion.

Parameters:

• tuple1 – The first tuple to compare.

• tuple2 – The second tuple to compare.

• msg – Optional message to use on failure instead of a list of differences.

assertWarns(expected_warning, *args, **kwargs)

Fail unless a warning of class warnClass is triggered by the callable when invoked with specified positional and keyword arguments. If a different type of warning is triggered, it will not be handled: depending on the other warning filtering rules in effect, it might be silenced, printed out, or raised as an exception.

If called with the callable and arguments omitted, will return a context object used like this:

with self.assertWarns(SomeWarning):
    do_something()

An optional keyword argument ‘msg’ can be provided when assertWarns is used as a context object.

The context manager keeps a reference to the first matching warning as the ‘warning’ attribute; similarly, the ‘filename’ and ‘lineno’ attributes give you information about the line of Python code from which the warning was triggered. This allows you to inspect the warning after the assertion:

with self.assertWarns(SomeWarning) as cm:
    do_something()
the_warning = cm.warning
self.assertEqual(the_warning.some_attribute, 147)

assertWarnsRegex(expected_warning, expected_regex, *args, **kwargs)

Asserts that the message in a triggered warning matches a regexp. Basic functioning is similar to assertWarns() with the addition that only warnings whose messages also match the regular expression are considered successful matches.

Parameters:

• expected_warning – Warning class expected to be triggered.

• expected_regex – Regex (re.Pattern object or string) expected to be found in error message.

• args – Function to be called and extra positional args.

• kwargs – Extra kwargs.

• msg – Optional message used in case of failure. Can only be used when assertWarnsRegex is used as a context manager.

clearGenerated()

Remove the directories that are used for testing.

countTestCases()

createLargeMultitaskDataSet(name='QSPRDataset_multi_test', target_props=[{'name': 'HBD', 'task': <TargetTasks.MULTICLASS: 'MULTICLASS'>, 'th': [-1, 1, 2, 100]}, {'name': 'CL', 'task': <TargetTasks.REGRESSION: 'REGRESSION'>}], preparation_settings=None, random_state=42)

Create a large dataset for testing purposes.

Parameters:

• name (str) – name of the dataset

• target_props (List of dicts or TargetProperty) – list of target properties

• preparation_settings (dict) – dictionary containing preparation settings

• random_state (int) – random state to use for splitting and shuffling

Returns:

a QSPRDataset object

Return type:

QSPRDataset

createLargeTestDataSet(name='QSPRDataset_test_large', target_props=[{'name': 'CL', 'task': <TargetTasks.REGRESSION: 'REGRESSION'>}], preparation_settings=None, random_state=42, n_jobs=1, chunk_size=None)

Create a large dataset for testing purposes.

Parameters:

• name (str) – name of the dataset

• target_props (List of dicts or TargetProperty) – list of target properties

• random_state (int) – random state to use for splitting and shuffling

• preparation_settings (dict) – dictionary containing preparation settings

Returns:

a QSPRDataset object

Return type:

QSPRDataset

createSmallTestDataSet(name='QSPRDataset_test_small', target_props=[{'name': 'CL', 'task': <TargetTasks.REGRESSION: 'REGRESSION'>}], preparation_settings=None, random_state=42)

Create a small dataset for testing purposes.

Parameters:

• name (str) – name of the dataset

• target_props (List of dicts or TargetProperty) – list of target properties

• random_state (int) – random state to use for splitting and shuffling

• preparation_settings (dict) – dictionary containing preparation settings

Returns:

a QSPRDataset object

Return type:

QSPRDataset

createTestDataSetFromFrame(df, name='QSPRDataset_test', target_props=[{'name': 'CL', 'task': <TargetTasks.REGRESSION: 'REGRESSION'>}], random_state=None, prep=None, n_jobs=1, chunk_size=None)

Create a dataset for testing purposes from the given data frame.

Parameters:

• df (pd.DataFrame) – data frame containing the dataset

• name (str) – name of the dataset

• target_props (List of dicts or TargetProperty) – list of target properties

• random_state (int) – random state to use for splitting and shuffling

• prep (dict) – dictionary containing preparation settings

Returns:

a QSPRDataset object

Return type:

QSPRDataset

debug()

Run the test without collecting errors in a TestResult

defaultTestResult()

classmethod doClassCleanups()

Execute all class cleanup functions. Normally called for you after tearDownClass.

doCleanups()

Execute all cleanup functions. Normally called for you after tearDown.

classmethod enterClassContext(cm)

Same as enterContext, but class-wide.

enterContext(cm)

Enters the supplied context manager.

If successful, also adds its __exit__ method as a cleanup function and returns the result of the __enter__ method.

fail(msg=None)

Fail immediately, with the given message.

failureException

alias of AssertionError

classmethod getAllDescriptors()

Return a list of (ideally) all available descriptor sets. For now they need to be added manually to the list below.

TODO: would be nice to create the list automatically by implementing a descriptor set registry that would hold all installed descriptor sets.

Returns:

list of DescriptorCalculator objects

Return type:

list

getBigDF()

Get a large data frame for testing purposes.

Returns:

a pandas.DataFrame containing the dataset

Return type:

pd.DataFrame

classmethod getDataPrepGrid()

Return a list of many possible combinations of descriptor calculators, splits, feature standardizers, feature filters and data filters. Again, this is not exhaustive, but should cover a lot of cases.

Returns:

a generator that yields tuples of all possible combinations as stated above, each tuple is defined as: (descriptor_calculator, split, feature_standardizer, feature_filters, data_filters)

Return type:

grid

classmethod getDefaultCalculatorCombo()

Makes a list of default descriptor calculators that can be used in tests. It creates a calculator with only morgan fingerprints and rdkit descriptors, but also one with them both to test behaviour with multiple descriptor sets. Override this method if you want to test with other descriptor sets and calculator combinations.

Returns:

list of created DescriptorCalculator objects

Return type:

list

static getDefaultPrep()

Return a dictionary with default preparation settings.

classmethod getPrepCombos()

Return a list of all possible preparation combinations as generated by getDataPrepGrid as well as their names. The generated list can be used to parameterize tests with the given named combinations.

Returns:

list of `list`s of all possible combinations of preparation

Return type:

list

getSmallDF()

Get a small data frame for testing purposes.

Returns:

a pandas.DataFrame containing the dataset

Return type:

pd.DataFrame

id()

longMessage = True

maxDiff = 640

run(result=None)

setUp()

Hook method for setting up the test fixture before exercising it.

classmethod setUpClass()

Hook method for setting up class fixture before running tests in the class.

setUpPaths()

Create the directories that are used for testing.

shortDescription()

Returns a one-line description of the test, or None if no description has been provided.

The default implementation of this method returns the first line of the specified test method’s docstring.

skipTest(reason)

Skip this test.

subTest(msg=<object object>, **params)

Return a context manager that will return the enclosed block of code in a subtest identified by the optional message and keyword parameters. A failure in the subtest marks the test case as failed but resumes execution at the end of the enclosed block, allowing further test code to be executed.

tearDown()

Remove all files and directories that are used for testing.

classmethod tearDownClass()

Hook method for deconstructing the class fixture after running all tests in the class.

testBootstrappedFold()

testStandardFolds()

Test the default fold generator, which is a 5-fold cross validation.

validateFolds(folds, more=None)

Check if the folds have the data they should have after splitting.

validate_split(dataset)

Check if the split has the data it should have after splitting.

Module contents