copulas 0.11.1__tar.gz → 0.12.0__tar.gz

{copulas-0.11.1 → copulas-0.12.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: copulas
-Version: 0.11.1
+Version: 0.12.0
 Summary: Create tabular synthetic data using copulas-based modeling.
 Author-email: "DataCebo, Inc." <info@sdv.dev>
 License: BSL-1.1

copulas-0.12.0/copulas/__init__.py

@@ -0,0 +1,91 @@
+"""Top-level package for Copulas."""
+
+__author__ = 'DataCebo, Inc.'
+__email__ = 'info@sdv.dev'
+__version__ = '0.12.0'
+
+import sys
+import warnings
+from copy import deepcopy
+from importlib.metadata import entry_points
+from operator import attrgetter
+from types import ModuleType
+
+
+def _get_addon_target(addon_path_name):
+    """Find the target object for the add-on.
+
+    Args:
+        addon_path_name (str):
+            The add-on's name. The add-on's name should be the full path of valid Python
+            identifiers (i.e. importable.module:object.attr).
+
+    Returns:
+        tuple:
+            * object:
+                The base module or object the add-on should be added to.
+            * str:
+                The name the add-on should be added to under the module or object.
+    """
+    module_path, _, object_path = addon_path_name.partition(':')
+    module_path = module_path.split('.')
+
+    if module_path[0] != __name__:
+        msg = f"expected base module to be '{__name__}', found '{module_path[0]}'"
+        raise AttributeError(msg)
+
+    target_base = sys.modules[__name__]
+    for submodule in module_path[1:-1]:
+        target_base = getattr(target_base, submodule)
+
+    addon_name = module_path[-1]
+    if object_path:
+        if len(module_path) > 1 and not hasattr(target_base, module_path[-1]):
+            msg = f"cannot add '{object_path}' to unknown submodule '{'.'.join(module_path)}'"
+            raise AttributeError(msg)
+
+        if len(module_path) > 1:
+            target_base = getattr(target_base, module_path[-1])
+
+        split_object = object_path.split('.')
+        addon_name = split_object[-1]
+
+        if len(split_object) > 1:
+            target_base = attrgetter('.'.join(split_object[:-1]))(target_base)
+
+    return target_base, addon_name
+
+
+def _find_addons():
+    """Find and load all copulas add-ons."""
+    group = 'copulas_modules'
+    try:
+        eps = entry_points(group=group)
+    except TypeError:
+        # Load-time selection requires Python >= 3.10 or importlib_metadata >= 3.6
+        eps = entry_points().get(group, [])
+
+    for entry_point in eps:
+        try:
+            addon = entry_point.load()
+        except Exception as e:  # pylint: disable=broad-exception-caught
+            msg = f'Failed to load "{entry_point.name}" from "{entry_point.value}" with error:\n{e}'
+            warnings.warn(msg)
+            continue
+
+        try:
+            addon_target, addon_name = _get_addon_target(entry_point.name)
+        except AttributeError as error:
+            msg = f"Failed to set '{entry_point.name}': {error}."
+            warnings.warn(msg)
+            continue
+
+        if isinstance(addon, ModuleType):
+            addon_module_name = f'{addon_target.__name__}.{addon_name}'
+            if addon_module_name not in sys.modules:
+                sys.modules[addon_module_name] = addon
+
+        setattr(addon_target, addon_name, addon)
+
+
+_find_addons()

{copulas-0.11.1 → copulas-0.12.0}/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-0.11.1 → copulas-0.12.0}/copulas/bivariate/base.py

@@ -8,8 +8,9 @@ import numpy as np
 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-0.11.1 → copulas-0.12.0}/copulas/bivariate/frank.py

@@ -6,9 +6,9 @@ import numpy as np
 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-0.11.1 → copulas-0.12.0}/copulas/datasets.py

@@ -4,7 +4,7 @@ import numpy as np
 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-0.12.0/copulas/errors.py

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

{copulas-0.11.1 → copulas-0.12.0}/copulas/multivariate/base.py

@@ -4,7 +4,8 @@ import pickle
 
 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-0.11.1 → copulas-0.12.0}/copulas/multivariate/gaussian.py

@@ -7,7 +7,9 @@ import numpy as np
 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 @@ from copulas import (
     store_args,
     validate_random_state,
 )
-from copulas.multivariate.base import Multivariate
-from copulas.univariate import GaussianUnivariate, Univariate
 
 LOGGER = logging.getLogger(__name__)
 DEFAULT_DISTRIBUTION = Univariate
@@ -70,26 +70,6 @@ class GaussianMultivariate(Multivariate):
 
         return stats.norm.ppf(np.column_stack(U))
 
-    def _get_correlation(self, X):
-        """Compute correlation matrix with transformed data.
-
-        Args:
-            X (numpy.ndarray):
-                Data for which the correlation needs to be computed.
-
-        Returns:
-            numpy.ndarray:
-                computed correlation matrix.
-        """
-        result = self._transform_to_normal(X)
-        correlation = pd.DataFrame(data=result).corr().to_numpy()
-        correlation = np.nan_to_num(correlation, nan=0.0)
-        # If singular, add some noise to the diagonal
-        if np.linalg.cond(correlation) > 1.0 / sys.float_info.epsilon:
-            correlation = correlation + np.identity(correlation.shape[0]) * EPSILON
-
-        return pd.DataFrame(correlation, index=self.columns, columns=self.columns)
-
     @check_valid_values
     def fit(self, X):
         """Compute the distribution for each variable and then its correlation matrix.
@@ -100,42 +80,88 @@ class GaussianMultivariate(Multivariate):
         """
         LOGGER.info('Fitting %s', self)
 
+        # Validate the input data
+        X = self._validate_input(X)
+        columns, univariates = self._fit_columns(X)
+
+        self.columns = columns
+        self.univariates = univariates
+
+        LOGGER.debug('Computing correlation.')
+        self.correlation = self._get_correlation(X)
+        self.fitted = True
+        LOGGER.debug('GaussianMultivariate fitted successfully')
+
+    def _validate_input(self, X):
+        """Validate the input data."""
         if not isinstance(X, pd.DataFrame):
             X = pd.DataFrame(X)
 
+        return X
+
+    def _fit_columns(self, X):
+        """Fit each column to its distribution."""
         columns = []
         univariates = []
         for column_name, column in X.items():
-            if isinstance(self.distribution, dict):
-                distribution = self.distribution.get(column_name, DEFAULT_DISTRIBUTION)
-            else:
-                distribution = self.distribution
-
+            distribution = self._get_distribution_for_column(column_name)
             LOGGER.debug('Fitting column %s to %s', column_name, distribution)
 
-            univariate = get_instance(distribution)
-            try:
-                univariate.fit(column)
-            except BaseException:
-                log_message = (
-                    f'Unable to fit to a {distribution} distribution for column {column_name}. '
-                    'Using a Gaussian distribution instead.'
-                )
-                LOGGER.info(log_message)
-                univariate = GaussianUnivariate()
-                univariate.fit(column)
-
+            univariate = self._fit_column(column, distribution, column_name)
             columns.append(column_name)
             univariates.append(univariate)
 
-        self.columns = columns
-        self.univariates = univariates
+        return columns, univariates
+
+    def _get_distribution_for_column(self, column_name):
+        """Retrieve the distribution for a given column name."""
+        if isinstance(self.distribution, dict):
+            return self.distribution.get(column_name, DEFAULT_DISTRIBUTION)
+
+        return self.distribution
+
+    def _fit_column(self, column, distribution, column_name):
+        """Fit a single column to its distribution with exception handling."""
+        univariate = get_instance(distribution)
+        try:
+            univariate.fit(column)
+        except Exception as error:
+            univariate = self._fit_with_fallback_distribution(
+                column, distribution, column_name, error
+            )
+
+        return univariate
+
+    def _fit_with_fallback_distribution(self, column, distribution, column_name, error):
+        """Fall back to fitting a Gaussian distribution and log the error."""
+        log_message = (
+            f'Unable to fit to a {distribution} distribution for column {column_name}. '
+            'Using a Gaussian distribution instead.'
+        )
+        LOGGER.info(log_message)
+        univariate = GaussianUnivariate()
+        univariate.fit(column)
+        return univariate
 
-        LOGGER.debug('Computing correlation')
-        self.correlation = self._get_correlation(X)
-        self.fitted = True
+    def _get_correlation(self, X):
+        """Compute correlation matrix with transformed data.
 
-        LOGGER.debug('GaussianMultivariate fitted successfully')
+        Args:
+            X (numpy.ndarray):
+                Data for which the correlation needs to be computed.
+
+        Returns:
+            numpy.ndarray:
+                computed correlation matrix.
+        """
+        result = self._transform_to_normal(X)
+        correlation = pd.DataFrame(data=result).corr().to_numpy()
+        correlation = np.nan_to_num(correlation, nan=0.0)
+        # If singular, add some noise to the diagonal
+        if np.linalg.cond(correlation) > 1.0 / sys.float_info.epsilon:
+            correlation = correlation + np.identity(correlation.shape[0]) * EPSILON
+
+        return pd.DataFrame(correlation, index=self.columns, columns=self.columns)
 
     def probability_density(self, X):
         """Compute the probability density for each point in X.

{copulas-0.11.1 → copulas-0.12.0}/copulas/multivariate/tree.py

@@ -6,9 +6,9 @@ from enum import Enum
 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-0.11.1 → copulas-0.12.0}/copulas/multivariate/vine.py

@@ -7,7 +7,11 @@ import warnings
 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,
@@ -15,10 +19,6 @@ from copulas import (
     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__)
 
@@ -76,8 +76,7 @@ class VineCopula(Multivariate):
     def __init__(self, vine_type, random_state=None):
         if sys.version_info > (3, 8):
             warnings.warn(
-                'Vines have not been fully tested on Python >= 3.8 and might '
-                'produce wrong results.'
+                'Vines have not been fully tested on Python >= 3.8 and might produce wrong results.'
             )
 
         self.random_state = validate_random_state(random_state)

{copulas-0.11.1 → copulas-0.12.0}/copulas/univariate/base.py

@@ -6,15 +6,15 @@ from enum import Enum
 
 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):

{copulas-0.11.1 → copulas-0.12.0}/copulas/univariate/gaussian_kde.py

@@ -4,9 +4,9 @@ import numpy as np
 from scipy.special import ndtr
 from scipy.stats import gaussian_kde
 
-from copulas import EPSILON, random_state, store_args, validate_random_state
 from copulas.optimize import bisect, chandrupatla
 from copulas.univariate.base import BoundedType, ParametricType, ScipyModel
+from copulas.utils import EPSILON, random_state, store_args, validate_random_state
 
 
 class GaussianKDE(ScipyModel):

{copulas-0.11.1 → copulas-0.12.0}/copulas/univariate/selection.py

@@ -3,7 +3,7 @@
 import numpy as np
 from scipy.stats import kstest
 
-from copulas import get_instance
+from copulas.utils import get_instance
 
 
 def select_univariate(X, candidates):

{copulas-0.11.1 → copulas-0.12.0}/copulas/univariate/truncated_gaussian.py

@@ -6,8 +6,8 @@ import numpy as np
 from scipy.optimize import fmin_slsqp
 from scipy.stats import truncnorm
 
-from copulas import EPSILON, store_args, validate_random_state
 from copulas.univariate.base import BoundedType, ParametricType, ScipyModel
+from copulas.utils import EPSILON, store_args, validate_random_state
 
 
 class TruncatedGaussian(ScipyModel):

copulas-0.11.1/copulas/__init__.py → copulas-0.12.0/copulas/utils.py

@@ -1,18 +1,9 @@
-# -*- coding: utf-8 -*-
-
-"""Top-level package for Copulas."""
-
-__author__ = 'DataCebo, Inc.'
-__email__ = 'info@sdv.dev'
-__version__ = '0.11.1'
+"""Utils module."""
 
 import contextlib
 import importlib
-import sys
-import warnings
 from copy import deepcopy
-from importlib.metadata import entry_points
-from operator import attrgetter
+from functools import wraps
 
 import numpy as np
 import pandas as pd
@@ -20,10 +11,6 @@ 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.
@@ -35,7 +22,6 @@ def set_random_state(random_state, set_model_random_state):
             Function to set the random state on the model.
     """
     original_state = np.random.get_state()
-
     np.random.set_state(random_state.get_state())
 
     try:
@@ -55,10 +41,10 @@ def random_state(function):
             The function to wrap around.
     """
 
+    @wraps(function)
     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)
@@ -123,6 +109,7 @@ def store_args(__init__):
         callable: Decorated ``__init__`` function.
     """
 
+    @wraps(__init__)
     def new__init__(self, *args, **kwargs):
         args_copy = deepcopy(args)
         kwargs_copy = deepcopy(kwargs)
@@ -138,7 +125,6 @@ def get_qualified_name(_object):
     module = _object.__module__
     if hasattr(_object, '__name__'):
         _class = _object.__name__
-
     else:
         _class = _object.__class__.__name__
 
@@ -184,6 +170,7 @@ def vectorize(function):
 
     """
 
+    @wraps(function)
     def decorated(self, X, *args, **kwargs):
         if not isinstance(X, np.ndarray):
             return function(self, X, *args, **kwargs)
@@ -195,11 +182,9 @@ def vectorize(function):
             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
 
 
@@ -213,6 +198,7 @@ def scalarize(function):
         callable: Decorated function that accepts and returns scalars.
     """
 
+    @wraps(function)
     def decorated(self, X, *args, **kwargs):
         scalar = not isinstance(X, np.ndarray)
 
@@ -225,7 +211,6 @@ def scalarize(function):
 
         return result
 
-    decorated.__doc__ = function.__doc__
     return decorated
 
 
@@ -242,10 +227,10 @@ def check_valid_values(function):
         ValueError: If there are missing or invalid values or if the dataset is empty.
     """
 
+    @wraps(function)
     def decorated(self, X, *args, **kwargs):
         if isinstance(X, pd.DataFrame):
             W = X.to_numpy()
-
         else:
             W = X
 
@@ -261,77 +246,3 @@ def check_valid_values(function):
         return function(self, X, *args, **kwargs)
 
     return decorated
-
-
-def _get_addon_target(addon_path_name):
-    """Find the target object for the add-on.
-
-    Args:
-        addon_path_name (str):
-            The add-on's name. The add-on's name should be the full path of valid Python
-            identifiers (i.e. importable.module:object.attr).
-
-    Returns:
-        tuple:
-            * object:
-                The base module or object the add-on should be added to.
-            * str:
-                The name the add-on should be added to under the module or object.
-    """
-    module_path, _, object_path = addon_path_name.partition(':')
-    module_path = module_path.split('.')
-
-    if module_path[0] != __name__:
-        msg = f"expected base module to be '{__name__}', found '{module_path[0]}'"
-        raise AttributeError(msg)
-
-    target_base = sys.modules[__name__]
-    for submodule in module_path[1:-1]:
-        target_base = getattr(target_base, submodule)
-
-    addon_name = module_path[-1]
-    if object_path:
-        if len(module_path) > 1 and not hasattr(target_base, module_path[-1]):
-            msg = f"cannot add '{object_path}' to unknown submodule '{'.'.join(module_path)}'"
-            raise AttributeError(msg)
-
-        if len(module_path) > 1:
-            target_base = getattr(target_base, module_path[-1])
-
-        split_object = object_path.split('.')
-        addon_name = split_object[-1]
-
-        if len(split_object) > 1:
-            target_base = attrgetter('.'.join(split_object[:-1]))(target_base)
-
-    return target_base, addon_name
-
-
-def _find_addons():
-    """Find and load all copulas add-ons."""
-    group = 'copulas_modules'
-    try:
-        eps = entry_points(group=group)
-    except TypeError:
-        # Load-time selection requires Python >= 3.10 or importlib_metadata >= 3.6
-        eps = entry_points().get(group, [])
-
-    for entry_point in eps:
-        try:
-            addon = entry_point.load()
-        except Exception:  # pylint: disable=broad-exception-caught
-            msg = f'Failed to load "{entry_point.name}" from "{entry_point.value}".'
-            warnings.warn(msg)
-            continue
-
-        try:
-            addon_target, addon_name = _get_addon_target(entry_point.name)
-        except AttributeError as error:
-            msg = f"Failed to set '{entry_point.name}': {error}."
-            warnings.warn(msg)
-            continue
-
-        setattr(addon_target, addon_name, addon)
-
-
-_find_addons()

{copulas-0.11.1 → copulas-0.12.0}/copulas.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: copulas
-Version: 0.11.1
+Version: 0.12.0
 Summary: Create tabular synthetic data using copulas-based modeling.
 Author-email: "DataCebo, Inc." <info@sdv.dev>
 License: BSL-1.1

{copulas-0.11.1 → copulas-0.12.0}/copulas.egg-info/SOURCES.txt

@@ -3,6 +3,8 @@ README.md
 pyproject.toml
 copulas/__init__.py
 copulas/datasets.py
+copulas/errors.py
+copulas/utils.py
 copulas/visualization.py
 copulas.egg-info/PKG-INFO
 copulas.egg-info/SOURCES.txt

{copulas-0.11.1 → copulas-0.12.0}/pyproject.toml

@@ -149,7 +149,7 @@ namespaces = false
 ]
 
 [tool.bumpversion]
-current_version = "0.11.1"
+current_version = "0.12.0"
 commit = true
 tag = true
 parse = '(?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\.(?P<release>[a-z]+)(?P<candidate>\d+))?'
@@ -182,7 +182,8 @@ exclude = [
     ".git",
     "__pycache__",
     ".ipynb_checkpoints",
-    "*.ipynb"
+    "*.ipynb",
+    "tasks.py",
 ]
 
 [tool.ruff.lint]
@@ -192,14 +193,23 @@ select = [
     # Pycodestyle
     "E",
     "W",
-    "D200",
+    # pydocstyle
+    "D",
     # isort
     "I001",
+    # print statements
+    "T201",
+    # pandas-vet
+    "PD",
+    # numpy 2.0
+    "NPY201"
 ]
 ignore = [
-    "E501",
+    # pydocstyle
     "D107",  # Missing docstring in __init__
     "D417",   # Missing argument descriptions in the docstring, this is a bug from pydocstyle: https://github.com/PyCQA/pydocstyle/issues/449
+    "PD901",
+    "PD101",
 ]
 
 [tool.ruff.format]
@@ -209,14 +219,18 @@ preview = true
 docstring-code-format = true
 docstring-code-line-length = "dynamic"
 
-[tool.ruff.lint.pep8-naming]
-extend-ignore-names = ["X", "C", "X_padded", "Y", "Y_padded"]
-
 [tool.ruff.lint.isort]
 known-first-party = ["copulas"]
+lines-between-types = 0
 
 [tool.ruff.lint.per-file-ignores]
 "__init__.py" = ["F401", "E402", "F403", "F405", "E501", "I001"]
+"errors.py" = ["D105"]
+"tests/**.py" = ["D"]
 
 [tool.ruff.lint.pydocstyle]
 convention = "google"
+
+[tool.ruff.lint.pycodestyle]
+max-doc-length = 100
+max-line-length = 100