Fixing linting

Author: cajchristian

src/skmatter/decomposition/_pcov.py

@@ -3,14 +3,12 @@
 
 import numpy as np
 from numpy.linalg import LinAlgError
-
-from scipy.linalg import sqrtm as MatrixSqrt
 from scipy import linalg
+from scipy.linalg import sqrtm as MatrixSqrt
 from scipy.sparse.linalg import svds
-
 from sklearn.decomposition._base import _BasePCA
-from sklearn.linear_model._base import LinearModel
 from sklearn.decomposition._pca import _infer_dimension
+from sklearn.linear_model._base import LinearModel
 from sklearn.utils import check_random_state
 from sklearn.utils._arpack import _init_arpack_v0
 from sklearn.utils.extmath import randomized_svd, stable_cumsum, svd_flip

src/skmatter/decomposition/_pcovc.py

@@ -2,18 +2,18 @@
 from sklearn import clone
 from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
 from sklearn.linear_model import (
+    LogisticRegression,
+    LogisticRegressionCV,
     Perceptron,
     RidgeClassifier,
     RidgeClassifierCV,
-    LogisticRegression,
-    LogisticRegressionCV,
     SGDClassifier,
 )
 from sklearn.linear_model._base import LinearClassifierMixin
 from sklearn.svm import LinearSVC
 from sklearn.utils import check_array
-from sklearn.utils.validation import check_is_fitted, validate_data
 from sklearn.utils.multiclass import check_classification_targets, type_of_target
+from sklearn.utils.validation import check_is_fitted, validate_data
 
 from skmatter.decomposition import _BasePCov
 from skmatter.utils import check_cl_fit
@@ -218,29 +218,28 @@ def __init__(
         self.classifier = classifier
 
     def fit(self, X, Y, W=None):
-        r"""Fit the model with X and Y. Depending on the dimensions of X, calls either
-        `_fit_feature_space` or `_fit_sample_space`
+        r"""Fit the model with X and Y. Depending on the dimensions of X,
+        calls either `_fit_feature_space` or `_fit_sample_space`.
 
         Parameters
         ----------
         X : numpy.ndarray, shape (n_samples, n_features)
-            Training data, where n_samples is the number of samples and n_features is
-            the number of features.
+            Training data, where n_samples is the number of samples and
+            n_features is the number of features.
 
             It is suggested that :math:`\mathbf{X}` be centered by its column-
-            means and scaled. If features are related, the matrix should be scaled
-            to have unit variance, otherwise :math:`\mathbf{X}` should be
-            scaled so that each feature has a variance of 1 / n_features.
+            means and scaled. If features are related, the matrix should be
+            scaled to have unit variance, otherwise :math:`\mathbf{X}` should
+            be scaled so that each feature has a variance of 1 / n_features.
 
         Y : numpy.ndarray, shape (n_samples,)
             Training data, where n_samples is the number of samples.
 
         W : numpy.ndarray, shape (n_features, n_properties)
-            Classification weights, optional when classifier=`precomputed`. If not
-            passed, it is assumed that the weights will be taken from a linear classifier
-            fit between X and Y
+            Classification weights, optional when classifier=`precomputed`. If
+            not passed, it is assumed that the weights will be taken from a
+            linear classifier fit between X and Y
         """
-
         X, Y = validate_data(self, X, Y, y_numeric=False)
         check_classification_targets(Y)
         self.classes_ = np.unique(Y)
@@ -280,7 +279,8 @@ def fit(self, X, Y, W=None):
             # If precomputed, use default classifier to predict Y from T
             classifier = LogisticRegression()
             if W is None:
-                W = LogisticRegression().fit(X, Y).coef_.T.reshape(X.shape[1], -1)
+                W = LogisticRegression().fit(X, Y).coef_.T
+                W = W.reshape(X.shape[1], -1)
 
         Z = X @ W
 
@@ -289,8 +289,8 @@ def fit(self, X, Y, W=None):
         else:
             self._fit_sample_space(X, Y, Z, W)
 
-        # instead of using linear regression solution, refit with the classifier
-        # and steal weights to get pxz and ptz
+        # instead of using linear regression solution, refit with the
+        # classifier and steal weights to get pxz and ptz
 
         self.classifier_ = clone(classifier).fit(X @ self.pxt_, Y)
 
@@ -404,8 +404,8 @@ def predict(self, X=None, T=None):
     def transform(self, X=None):
         """Apply dimensionality reduction to X.
 
-        ``X`` is projected on the first principal components as determined by the
-        modified PCovC distances.
+        ``X`` is projected on the first principal components as determined by
+        the modified PCovC distances.
 
         Parameters
         ----------

src/skmatter/decomposition/_pcovr.py

@@ -1,9 +1,8 @@
 import numpy as np
-
-from sklearn.utils import check_array
+from sklearn.base import MultiOutputMixin, RegressorMixin
 from sklearn.linear_model import LinearRegression, Ridge, RidgeCV
+from sklearn.utils import check_array
 from sklearn.utils.validation import check_is_fitted, validate_data
-from sklearn.base import MultiOutputMixin, RegressorMixin
 
 from skmatter.decomposition import _BasePCov
 from skmatter.utils import check_lr_fit

src/skmatter/utils/_pcovc_utils.py

@@ -1,8 +1,9 @@
 from copy import deepcopy
+
+import numpy as np
 from sklearn import clone
-from sklearn.utils.validation import check_is_fitted, validate_data
 from sklearn.exceptions import NotFittedError
-import numpy as np
+from sklearn.utils.validation import check_is_fitted, validate_data
 
 
 def check_cl_fit(classifier, X, y):
@@ -22,8 +23,8 @@ def check_cl_fit(classifier, X, y):
     Returns
     -------
     fitted_classifier : object
-        The fitted classifier. If input classifier was already fitted and compatible with
-        the data, returns a deep copy. Otherwise returns a newly fitted classifier.
+        The fitted classifier. If input classifier was already fitted and compatible
+        with the data, returns a deep copy. Otherwise returns a newly fitted classifier.
 
     Raises
     ------
@@ -65,4 +66,4 @@ def check_cl_fit(classifier, X, y):
         fitted_classifier = clone(classifier)
         fitted_classifier.fit(X, y)
 
-    return fitted_classifier
+    return fitted_classifier

tests/test_check_estimators.py

@@ -1,6 +1,6 @@
 from sklearn.utils.estimator_checks import parametrize_with_checks
 
-from skmatter.decomposition import KernelPCovR, PCovR, PCovC
+from skmatter.decomposition import KernelPCovR, PCovC, PCovR
 from skmatter.feature_selection import CUR as fCUR
 from skmatter.feature_selection import FPS as fFPS
 from skmatter.feature_selection import PCovCUR as fPCovCUR

tests/test_pcovc.py

@@ -6,7 +6,6 @@
 from sklearn.datasets import load_breast_cancer as get_dataset
 from sklearn.decomposition import PCA
 from sklearn.linear_model import LogisticRegression
-
 from sklearn.naive_bayes import GaussianNB
 from sklearn.preprocessing import StandardScaler
 from sklearn.utils.validation import check_X_y
@@ -231,18 +230,6 @@ def test_spaces_equivalent(self):
                     n_components=2, mixing=alpha, tol=1e-12, space="feature"
                 )
                 pcovc_fs.fit(self.X, self.Y)
-
-                # if(alpha > 0.5):
-                #     print(np.isclose(
-                #             pcovc_ss.transform(self.X),
-                #             pcovc_fs.transform(self.X),
-                #             self.error_tol
-                #         ))
-
-                # failing for all alpha values
-                # so these are similar (within approximately 0.001), but not exactly the same.
-                # I think this is because transform and inverse_transform depend on Pxt and Ptx,
-                # which in turn depend on Z, which is a matrix of class likelihoods (so maybe there is some rounding problems)
                 self.assertTrue(
                     np.allclose(
                         pcovc_ss.inverse_transform(pcovc_ss.transform(self.X)),
@@ -301,8 +288,6 @@ def test_bad_n_components(self):
             pcovc = self.model(
                 n_components="mle", classifier=LogisticRegression(), svd_solver="full"
             )
-            # changed X[:2], Y[:2] to X[:20], Y[:20] since first two rows of classes only had class 1 as target,
-            # thus error was thrown
             pcovc.fit(self.X[:20], self.Y[:20])
         self.assertEqual(
             str(cm.exception),
@@ -401,13 +386,13 @@ def test_centering(self):
             pcovc.fit(X, self.Y)
             self.assertEqual(
                 str(w[0].message),
-                "This class does not automatically center data, and your data mean is "
-                "greater than the supplied tolerance.",
+                "This class does not automatically center data, and your data "
+                "mean is greater than the supplied tolerance.",
             )
 
     def test_T_shape(self):
-        """Check that PCovC returns a latent space projection consistent with the shape
-        of the input matrix.
+        """Check that PCovC returns a latent space projection consistent with
+        the shape of the input matrix.
         """
         n_components = 5
         pcovc = self.model(n_components=n_components, tol=1e-12)
@@ -417,8 +402,8 @@ def test_T_shape(self):
         self.assertTrue(T.shape[-1] == n_components)
 
     def test_Z_shape(self):
-        """Check that PCovC returns an evidence matrix consistent with the number of samples
-        and the number of classes.
+        """Check that PCovC returns an evidence matrix consistent with the
+        number of samples and the number of classes.
         """
         n_components = 5
         pcovc = self.model(n_components=n_components, tol=1e-12)