Move utiltiy functions to utils.py and tests accordingly.

copulas/__init__.py

@@ -1,268 +1,16 @@
-# -*- coding: utf-8 -*-
-
 """Top-level package for Copulas."""
 
 __author__ = 'DataCebo, Inc.'
 __email__ = '[email protected]'
 __version__ = '0.11.2.dev0'
 
-import contextlib
-import importlib
 import sys
 import warnings
 from copy import deepcopy
 from importlib.metadata import entry_points
 from operator import attrgetter
 from types import ModuleType
 
-import numpy as np
-import pandas as pd
-
-EPSILON = np.finfo(np.float32).eps
-
-
-class NotFittedError(Exception):
-    """NotFittedError class."""
-
-
-@contextlib.contextmanager
-def set_random_state(random_state, set_model_random_state):
-    """Context manager for managing the random state.
-
-    Args:
-        random_state (int or np.random.RandomState):
-            The random seed or RandomState.
-        set_model_random_state (function):
-            Function to set the random state on the model.
-    """
-    original_state = np.random.get_state()
-
-    np.random.set_state(random_state.get_state())
-
-    try:
-        yield
-    finally:
-        current_random_state = np.random.RandomState()
-        current_random_state.set_state(np.random.get_state())
-        set_model_random_state(current_random_state)
-        np.random.set_state(original_state)
-
-
-def random_state(function):
-    """Set the random state before calling the function.
-
-    Args:
-        function (Callable):
-            The function to wrap around.
-    """
-
-    def wrapper(self, *args, **kwargs):
-        if self.random_state is None:
-            return function(self, *args, **kwargs)
-
-        else:
-            with set_random_state(self.random_state, self.set_random_state):
-                return function(self, *args, **kwargs)
-
-    return wrapper
-
-
-def validate_random_state(random_state):
-    """Validate random state argument.
-
-    Args:
-        random_state (int, numpy.random.RandomState, tuple, or None):
-            Seed or RandomState for the random generator.
-
-    Output:
-        numpy.random.RandomState
-    """
-    if random_state is None:
-        return None
-
-    if isinstance(random_state, int):
-        return np.random.RandomState(seed=random_state)
-    elif isinstance(random_state, np.random.RandomState):
-        return random_state
-    else:
-        raise TypeError(
-            f'`random_state` {random_state} expected to be an int '
-            'or `np.random.RandomState` object.'
-        )
-
-
-def get_instance(obj, **kwargs):
-    """Create new instance of the ``obj`` argument.
-
-    Args:
-        obj (str, type, instance):
-    """
-    instance = None
-    if isinstance(obj, str):
-        package, name = obj.rsplit('.', 1)
-        instance = getattr(importlib.import_module(package), name)(**kwargs)
-    elif isinstance(obj, type):
-        instance = obj(**kwargs)
-    else:
-        if kwargs:
-            instance = obj.__class__(**kwargs)
-        else:
-            args = getattr(obj, '__args__', ())
-            kwargs = getattr(obj, '__kwargs__', {})
-            instance = obj.__class__(*args, **kwargs)
-
-    return instance
-
-
-def store_args(__init__):
-    """Save ``*args`` and ``**kwargs`` used in the ``__init__`` of a copula.
-
-    Args:
-        __init__(callable): ``__init__`` function to store their arguments.
-
-    Returns:
-        callable: Decorated ``__init__`` function.
-    """
-
-    def new__init__(self, *args, **kwargs):
-        args_copy = deepcopy(args)
-        kwargs_copy = deepcopy(kwargs)
-        __init__(self, *args, **kwargs)
-        self.__args__ = args_copy
-        self.__kwargs__ = kwargs_copy
-
-    return new__init__
-
-
-def get_qualified_name(_object):
-    """Return the Fully Qualified Name from an instance or class."""
-    module = _object.__module__
-    if hasattr(_object, '__name__'):
-        _class = _object.__name__
-
-    else:
-        _class = _object.__class__.__name__
-
-    return module + '.' + _class
-
-
-def vectorize(function):
-    """Allow a method that only accepts scalars to accept vectors too.
-
-    This decorator has two different behaviors depending on the dimensionality of the
-    array passed as an argument:
-
-    **1-d array**
-
-    It will work under the assumption that the `function` argument is a callable
-    with signature::
-
-        function(self, X, *args, **kwargs)
-
-    where X is an scalar magnitude.
-
-    In this case the arguments of the input array will be given one at a time, and
-    both the input and output of the decorated function will have shape (n,).
-
-    **2-d array**
-
-    It will work under the assumption that the `function` argument is a callable with signature::
-
-        function(self, X0, ..., Xj, *args, **kwargs)
-
-    where `Xi` are scalar magnitudes.
-
-    It will pass the contents of each row unpacked on each call. The input is espected to have
-    shape (n, j), the output a shape of (n,)
-
-    It will return a function that is guaranteed to return a `numpy.array`.
-
-    Args:
-        function(callable): Function that only accept and return scalars.
-
-    Returns:
-        callable: Decorated function that can accept and return :attr:`numpy.array`.
-
-    """
-
-    def decorated(self, X, *args, **kwargs):
-        if not isinstance(X, np.ndarray):
-            return function(self, X, *args, **kwargs)
-
-        if len(X.shape) == 1:
-            X = X.reshape([-1, 1])
-
-        if len(X.shape) == 2:
-            return np.fromiter(
-                (function(self, *x, *args, **kwargs) for x in X), np.dtype('float64')
-            )
-
-        else:
-            raise ValueError('Arrays of dimensionality higher than 2 are not supported.')
-
-    decorated.__doc__ = function.__doc__
-    return decorated
-
-
-def scalarize(function):
-    """Allow methods that only accepts 1-d vectors to work with scalars.
-
-    Args:
-        function(callable): Function that accepts and returns vectors.
-
-    Returns:
-        callable: Decorated function that accepts and returns scalars.
-    """
-
-    def decorated(self, X, *args, **kwargs):
-        scalar = not isinstance(X, np.ndarray)
-
-        if scalar:
-            X = np.array([X])
-
-        result = function(self, X, *args, **kwargs)
-        if scalar:
-            result = result[0]
-
-        return result
-
-    decorated.__doc__ = function.__doc__
-    return decorated
-
-
-def check_valid_values(function):
-    """Raise an exception if the given values are not supported.
-
-    Args:
-        function(callable): Method whose unique argument is a numpy.array-like object.
-
-    Returns:
-        callable: Decorated function
-
-    Raises:
-        ValueError: If there are missing or invalid values or if the dataset is empty.
-    """
-
-    def decorated(self, X, *args, **kwargs):
-        if isinstance(X, pd.DataFrame):
-            W = X.to_numpy()
-
-        else:
-            W = X
-
-        if not len(W):
-            raise ValueError('Your dataset is empty.')
-
-        if not (np.issubdtype(W.dtype, np.floating) or np.issubdtype(W.dtype, np.integer)):
-            raise ValueError('There are non-numerical values in your data.')
-
-        if np.isnan(W).any().any():
-            raise ValueError('There are nan values in your data.')
-
-        return function(self, X, *args, **kwargs)
-
-    return decorated
-
 
 def _get_addon_target(addon_path_name):
     """Find the target object for the add-on.

copulas/bivariate/__init__.py

@@ -3,7 +3,7 @@
 import numpy as np
 import pandas as pd
 
-from copulas import EPSILON
+from copulas.utils import EPSILON
 from copulas.bivariate.base import Bivariate, CopulaTypes
 from copulas.bivariate.clayton import Clayton
 from copulas.bivariate.frank import Frank

copulas/bivariate/base.py

@@ -8,8 +8,9 @@
 from scipy import stats
 from scipy.optimize import brentq
 
-from copulas import EPSILON, NotFittedError, random_state, validate_random_state
 from copulas.bivariate.utils import split_matrix
+from copulas.errors import NotFittedError
+from copulas.utils import EPSILON, random_state, validate_random_state
 
 
 class CopulaTypes(Enum):

copulas/bivariate/frank.py

@@ -6,9 +6,9 @@
 import scipy.integrate as integrate
 from scipy.optimize import least_squares
 
-from copulas import EPSILON
 from copulas.bivariate.base import Bivariate, CopulaTypes
 from copulas.bivariate.utils import split_matrix
+from copulas.utils import EPSILON
 
 MIN_FLOAT_LOG = np.log(sys.float_info.min)
 MAX_FLOAT_LOG = np.log(sys.float_info.max)

copulas/datasets.py

@@ -4,7 +4,7 @@
 import pandas as pd
 from scipy import stats
 
-from copulas import set_random_state, validate_random_state
+from copulas.utils import set_random_state, validate_random_state
 
 
 def _dummy_fn(state):

copulas/errors.py

@@ -0,0 +1,5 @@
+"""Copulas Exceptions."""
+
+
+class NotFittedError(Exception):
+    """NotFittedError class."""

copulas/multivariate/base.py

@@ -4,7 +4,8 @@
 
 import numpy as np
 
-from copulas import NotFittedError, get_instance, validate_random_state
+from copulas.errors import NotFittedError
+from copulas.utils import get_instance, validate_random_state
 
 
 class Multivariate(object):

copulas/multivariate/gaussian.py

@@ -7,7 +7,9 @@
 import pandas as pd
 from scipy import stats
 
-from copulas import (
+from copulas.multivariate.base import Multivariate
+from copulas.univariate import GaussianUnivariate, Univariate
+from copulas.utils import (
     EPSILON,
     check_valid_values,
     get_instance,
@@ -16,8 +18,6 @@
     store_args,
     validate_random_state,
 )
-from copulas.multivariate.base import Multivariate
-from copulas.univariate import GaussianUnivariate, Univariate
 
 LOGGER = logging.getLogger(__name__)
 DEFAULT_DISTRIBUTION = Univariate

copulas/multivariate/tree.py

@@ -6,9 +6,9 @@
 import numpy as np
 import scipy
 
-from copulas import EPSILON, get_qualified_name
 from copulas.bivariate.base import Bivariate
 from copulas.multivariate.base import Multivariate
+from copulas.utils import EPSILON, get_qualified_name
 
 LOGGER = logging.getLogger(__name__)
 

copulas/multivariate/vine.py

@@ -7,18 +7,18 @@
 import numpy as np
 import pandas as pd
 
-from copulas import (
+from copulas.bivariate.base import Bivariate, CopulaTypes
+from copulas.multivariate.base import Multivariate
+from copulas.multivariate.tree import Tree, get_tree
+from copulas.univariate.gaussian_kde import GaussianKDE
+from copulas.utils import (
     EPSILON,
     check_valid_values,
     get_qualified_name,
     random_state,
     store_args,
     validate_random_state,
 )
-from copulas.bivariate.base import Bivariate, CopulaTypes
-from copulas.multivariate.base import Multivariate
-from copulas.multivariate.tree import Tree, get_tree
-from copulas.univariate.gaussian_kde import GaussianKDE
 
 LOGGER = logging.getLogger(__name__)
 

copulas/univariate/base.py

@@ -6,15 +6,15 @@
 
 import numpy as np
 
-from copulas import (
-    NotFittedError,
+from copulas.errors import NotFittedError
+from copulas.univariate.selection import select_univariate
+from copulas.utils import (
     get_instance,
     get_qualified_name,
     random_state,
     store_args,
     validate_random_state,
 )
-from copulas.univariate.selection import select_univariate
 
 
 class ParametricType(Enum):