Merge pull request #407 from sdv-dev/add_ruff

Add ruff for linting, remove flake8, remove isort, remove pylint
sdv-dev · May 2, 2024 · 2f3a2be · 2f3a2be
2 parents d6a3bdc + f19e087
commit 2f3a2be
Show file tree

Hide file tree

Showing 58 changed files with 631 additions and 778 deletions.
diff --git a/Makefile b/Makefile
@@ -67,7 +67,6 @@ clean-test: ## remove test artifacts
 .PHONY: clean
 clean: clean-build clean-pyc clean-test clean-coverage clean-docs ## remove all build, test, coverage, docs and Python artifacts
 
-
 # INSTALL TARGETS
 
 .PHONY: install
@@ -82,23 +81,16 @@ install-test: clean-build clean-pyc ## install the package and test dependencies
 install-develop: clean-build clean-pyc ## install the package in editable mode and dependencies for development
 	pip install -e .[dev]
 
-
 # LINT TARGETS
 
 .PHONY: lint
-lint: ## check style with flake8 and isort
+lint:
 	invoke lint
 
-lint-docs: ## check docs formatting with doc8 and pydocstyle
-	doc8 . docs/
-	pydocstyle copulas/
-
 .PHONY: fix-lint
-fix-lint: ## fix lint issues using autoflake, autopep8, and isort
-	find copulas tests -name '*.py' | xargs autoflake --in-place --remove-all-unused-imports --remove-unused-variables
-	autopep8 --in-place --recursive --aggressive copulas tests
-	isort --apply --atomic copulas tests
-
+fix-lint:
+	ruff check --fix .
+	ruff format .
 
 # TEST TARGETS
 

diff --git a/copulas/__init__.py b/copulas/__init__.py
@@ -86,7 +86,8 @@ def validate_random_state(random_state):
     else:
         raise TypeError(
             f'`random_state` {random_state} expected to be an int '
-            'or `np.random.RandomState` object.')
+            'or `np.random.RandomState` object.'
+        )
 
 
 def get_instance(obj, **kwargs):
@@ -192,8 +193,7 @@ def decorated(self, X, *args, **kwargs):
 
         if len(X.shape) == 2:
             return np.fromiter(
-                (function(self, *x, *args, **kwargs) for x in X),
-                np.dtype('float64')
+                (function(self, *x, *args, **kwargs) for x in X), np.dtype('float64')
             )
 
         else:
@@ -243,7 +243,6 @@ def check_valid_values(function):
     """
 
     def decorated(self, X, *args, **kwargs):
-
         if isinstance(X, pd.DataFrame):
             W = X.to_numpy()
 

diff --git a/copulas/bivariate/__init__.py b/copulas/bivariate/__init__.py
@@ -47,7 +47,6 @@ def _compute_empirical(X):
         right = sum(np.logical_and(U >= base[k], V >= base[k])) / N
 
         if left > 0:
-
             z_left.append(base[k])
             L.append(left / base[k] ** 2)
 
@@ -151,7 +150,8 @@ def select_copula(X):
 
     left_tail, empirical_left_aut, right_tail, empirical_right_aut = _compute_empirical(X)
     candidate_left_auts, candidate_right_auts = _compute_candidates(
-        copula_candidates, left_tail, right_tail)
+        copula_candidates, left_tail, right_tail
+    )
 
     empirical_aut = np.concatenate((empirical_left_aut, empirical_right_aut))
     candidate_auts = [

diff --git a/copulas/bivariate/base.py b/copulas/bivariate/base.py
@@ -96,7 +96,7 @@ def __new__(cls, *args, **kwargs):
             return super(Bivariate, cls).__new__(cls)
 
         if not isinstance(copula_type, CopulaTypes):
-            if (isinstance(copula_type, str) and copula_type.upper() in CopulaTypes.__members__):
+            if isinstance(copula_type, str) and copula_type.upper() in CopulaTypes.__members__:
                 copula_type = CopulaTypes[copula_type.upper()]
             else:
                 raise ValueError(f'Invalid copula type {copula_type}')
@@ -192,11 +192,7 @@ def to_dict(self):
             dict: Parameters of the copula.
 
         """
-        return {
-            'copula_type': self.copula_type.name,
-            'theta': self.theta,
-            'tau': self.tau
-        }
+        return {'copula_type': self.copula_type.name, 'theta': self.theta, 'tau': self.tau}
 
     @classmethod
     def from_dict(cls, copula_dict):
@@ -297,6 +293,7 @@ def percent_point(self, y, V):
         self.check_fit()
         result = []
         for _y, _v in zip(y, V):
+
             def f(u):
                 return self.partial_derivative_scalar(u, _v) - _y
 
@@ -330,7 +327,7 @@ def partial_derivative(self, X):
             np.ndarray
 
         """
-        delta = (-2 * (X[:, 1] > 0.5) + 1)
+        delta = -2 * (X[:, 1] > 0.5) + 1
         delta = 0.0001 * delta
         X_prime = X.copy()
         X_prime[:, 1] += delta
@@ -411,10 +408,11 @@ def select_copula(cls, X):
 
         """
         from copulas.bivariate import select_copula  # noqa
+
         warnings.warn(
             '`Bivariate.select_copula` has been deprecated and will be removed in a later '
             'release. Please use `copulas.bivariate.select_copula` instead',
-            DeprecationWarning
+            DeprecationWarning,
         )
         return select_copula(X)
 

diff --git a/copulas/bivariate/clayton.py b/copulas/bivariate/clayton.py
@@ -84,9 +84,10 @@ def cumulative_distribution(self, X):
             cdfs = [
                 np.power(
                     np.power(U[i], -self.theta) + np.power(V[i], -self.theta) - 1,
-                    -1.0 / self.theta
+                    -1.0 / self.theta,
                 )
-                if (U[i] > 0 and V[i] > 0) else 0
+                if (U[i] > 0 and V[i] > 0)
+                else 0
                 for i in range(len(U))
             ]
 

diff --git a/copulas/bivariate/frank.py b/copulas/bivariate/frank.py
@@ -162,6 +162,7 @@ def compute_theta(self):
 
     def _tau_to_theta(self, alpha):
         """Relationship between tau and theta as a solvable equation."""
+
         def debye(t):
             return t / (np.exp(t) - 1)
 

diff --git a/copulas/datasets.py b/copulas/datasets.py
@@ -33,10 +33,7 @@ def sample_bivariate_age_income(size=1000, seed=42):
         income += np.random.normal(loc=np.log(age) / 100, scale=10, size=size)
         income[np.random.randint(0, 10, size=size) == 0] /= 1000
 
-    return pd.DataFrame({
-        'age': age,
-        'income': income
-    })
+    return pd.DataFrame({'age': age, 'income': income})
 
 
 def sample_trivariate_xyz(size=1000, seed=42):
@@ -61,11 +58,7 @@ def sample_trivariate_xyz(size=1000, seed=42):
     with set_random_state(validate_random_state(seed), _dummy_fn):
         x = stats.beta.rvs(a=0.1, b=0.1, size=size)
         y = stats.beta.rvs(a=0.1, b=0.5, size=size)
-        return pd.DataFrame({
-            'x': x,
-            'y': y,
-            'z': np.random.normal(size=size) + y * 10
-        })
+        return pd.DataFrame({'x': x, 'y': y, 'z': np.random.normal(size=size) + y * 10})
 
 
 def sample_univariate_bernoulli(size=1000, seed=42):

diff --git a/copulas/multivariate/__init__.py b/copulas/multivariate/__init__.py
@@ -5,10 +5,4 @@
 from copulas.multivariate.tree import Tree, TreeTypes
 from copulas.multivariate.vine import VineCopula
 
-__all__ = (
-    'Multivariate',
-    'GaussianMultivariate',
-    'VineCopula',
-    'Tree',
-    'TreeTypes'
-)
+__all__ = ('Multivariate', 'GaussianMultivariate', 'VineCopula', 'Tree', 'TreeTypes')
diff --git a/copulas/multivariate/gaussian.py b/copulas/multivariate/gaussian.py
@@ -8,8 +8,14 @@
 from scipy import stats
 
 from copulas import (
-    EPSILON, check_valid_values, get_instance, get_qualified_name, random_state, store_args,
-    validate_random_state)
+    EPSILON,
+    check_valid_values,
+    get_instance,
+    get_qualified_name,
+    random_state,
+    store_args,
+    validate_random_state,
+)
 from copulas.multivariate.base import Multivariate
 from copulas.univariate import GaussianUnivariate, Univariate
 
@@ -149,8 +155,7 @@ def probability_density(self, X):
         self.check_fit()
         transformed = self._transform_to_normal(X)
 
-        return stats.multivariate_normal.pdf(
-            transformed, cov=self.correlation, allow_singular=True)
+        return stats.multivariate_normal.pdf(transformed, cov=self.correlation, allow_singular=True)
 
     def cumulative_distribution(self, X):
         """Compute the cumulative distribution value for each point in X.

diff --git a/copulas/multivariate/tree.py b/copulas/multivariate/tree.py
@@ -131,7 +131,7 @@ def get_tau_matrix(self):
                     left_parent, right_parent = edge.parents
                     left_u, right_u = Edge.get_conditional_uni(left_parent, right_parent)
 
-                tau[i, j], pvalue = scipy.stats.kendalltau(left_u, right_u)
+                tau[i, j], _pvalue = scipy.stats.kendalltau(left_u, right_u)
 
         return tau
 
@@ -212,8 +212,7 @@ def __str__(self):
         """Produce printable representation of the class."""
         template = 'L:{} R:{} D:{} Copula:{} Theta:{}'
         return '\n'.join([
-            template.format(edge.L, edge.R, edge.D, edge.name, edge.theta)
-            for edge in self.edges
+            template.format(edge.L, edge.R, edge.D, edge.name, edge.theta) for edge in self.edges
         ])
 
     def _serialize_previous_tree(self):
@@ -237,11 +236,7 @@ def to_dict(self):
                 Parameters of this Tree.
         """
         fitted = self.fitted
-        result = {
-            'tree_type': self.tree_type,
-            'type': get_qualified_name(self),
-            'fitted': fitted
-        }
+        result = {'tree_type': self.tree_type, 'type': get_qualified_name(self), 'fitted': fitted}
 
         if not fitted:
             return result
@@ -451,7 +446,7 @@ def get_tree(tree_type):
             Instance of a Tree of the specified type.
     """
     if not isinstance(tree_type, TreeTypes):
-        if (isinstance(tree_type, str) and tree_type.upper() in TreeTypes.__members__):
+        if isinstance(tree_type, str) and tree_type.upper() in TreeTypes.__members__:
             tree_type = TreeTypes[tree_type.upper()]
         else:
             raise ValueError(f'Invalid tree type {tree_type}')
@@ -657,7 +652,7 @@ def to_dict(self):
             'theta': self.theta,
             'tau': self.tau,
             'U': U,
-            'likelihood': self.likelihood
+            'likelihood': self.likelihood,
         }
 
     @classmethod
@@ -674,8 +669,11 @@ def from_dict(cls, edge_dict):
                 Instance of the edge defined on the parameters.
         """
         instance = cls(
-            edge_dict['index'], edge_dict['L'], edge_dict['R'],
-            edge_dict['name'], edge_dict['theta']
+            edge_dict['index'],
+            edge_dict['L'],
+            edge_dict['R'],
+            edge_dict['name'],
+            edge_dict['theta'],
         )
         instance.U = np.array(edge_dict['U'])
         parents = edge_dict['parents']

diff --git a/copulas/multivariate/vine.py b/copulas/multivariate/vine.py
@@ -8,8 +8,13 @@
 import pandas as pd
 
 from copulas import (
-    EPSILON, check_valid_values, get_qualified_name, random_state, store_args,
-    validate_random_state)
+    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
@@ -103,7 +108,7 @@ def to_dict(self):
         result = {
             'type': get_qualified_name(self),
             'vine_type': self.vine_type,
-            'fitted': self.fitted
+            'fitted': self.fitted,
         }
 
         if not self.fitted:
@@ -118,7 +123,7 @@ def to_dict(self):
             'tau_mat': self.tau_mat.tolist(),
             'u_matrix': self.u_matrix.tolist(),
             'unis': [distribution.to_dict() for distribution in self.unis],
-            'columns': self.columns
+            'columns': self.columns,
         })
         return result
 
@@ -293,8 +298,9 @@ def _sample_row(self):
                     # get index of edge to retrieve
                     for edge in current_tree:
                         if i == 0:
-                            if (edge.L == current and edge.R == visited[0]) or\
-                               (edge.R == current and edge.L == visited[0]):
+                            if (edge.L == current and edge.R == visited[0]) or (
+                                edge.R == current and edge.L == visited[0]
+                            ):
                                 current_ind = edge.index
                                 break
                         else:

diff --git a/copulas/optimize/__init__.py b/copulas/optimize/__init__.py
@@ -127,7 +127,7 @@ def chandrupatla(f, xmin, xmax, eps_m=None, eps_a=None, maxiter=50):
         # to determine which method we should use next
         xi = (a - b) / (c - b)
         phi = (fa - fb) / (fc - fb)
-        iqi = np.logical_and(phi**2 < xi, (1 - phi)**2 < 1 - xi)
+        iqi = np.logical_and(phi**2 < xi, (1 - phi) ** 2 < 1 - xi)
 
         if not shape:
             # scalar case
@@ -143,8 +143,9 @@ def chandrupatla(f, xmin, xmax, eps_m=None, eps_a=None, maxiter=50):
             # array case
             t = np.full(shape, 0.5)
             a2, b2, c2, fa2, fb2, fc2 = a[iqi], b[iqi], c[iqi], fa[iqi], fb[iqi], fc[iqi]
-            t[iqi] = fa2 / (fb2 - fa2) * fc2 / (fb2 - fc2) + (c2 - a2) / \
-                (b2 - a2) * fa2 / (fc2 - fa2) * fb2 / (fc2 - fb2)
+            t[iqi] = fa2 / (fb2 - fa2) * fc2 / (fb2 - fc2) + (c2 - a2) / (b2 - a2) * fa2 / (
+                fc2 - fa2
+            ) * fb2 / (fc2 - fb2)
 
         # limit to the range (tlim, 1-tlim)
         t = np.minimum(1 - tlim, np.maximum(tlim, t))

diff --git a/copulas/univariate/__init__.py b/copulas/univariate/__init__.py
@@ -21,5 +21,5 @@
     'ParametricType',
     'BoundedType',
     'UniformUnivariate',
-    'LogLaplace'
+    'LogLaplace',
 )
diff --git a/copulas/univariate/base.py b/copulas/univariate/base.py
@@ -7,8 +7,13 @@
 import numpy as np
 
 from copulas import (
-    NotFittedError, get_instance, get_qualified_name, random_state, store_args,
-    validate_random_state)
+    NotFittedError,
+    get_instance,
+    get_qualified_name,
+    random_state,
+    store_args,
+    validate_random_state,
+)
 from copulas.univariate.selection import select_univariate
 
 
@@ -84,8 +89,14 @@ def _select_candidates(cls, parametric=None, bounded=None):
         return candidates
 
     @store_args
-    def __init__(self, candidates=None, parametric=None, bounded=None, random_state=None,
-                 selection_sample_size=None):
+    def __init__(
+        self,
+        candidates=None,
+        parametric=None,
+        bounded=None,
+        random_state=None,
+        selection_sample_size=None,
+    ):
         self.candidates = candidates or self._select_candidates(parametric, bounded)
         self.random_state = validate_random_state(random_state)
         self.selection_sample_size = selection_sample_size