scikit-learn · Nebula1230 · Jan 12, 2023 · Jan 12, 2023 · Jan 12, 2023
diff --git a/benchmarks/bench_hist_gradient_boosting_threading.py b/benchmarks/bench_hist_gradient_boosting_threading.py
@@ -239,7 +239,7 @@ def one_run(n_threads, n_samples):
 
 
 max_threads = os.cpu_count()
-n_threads_list = [2**i for i in range(8) if (2**i) < max_threads]
+n_threads_list = [2 ** i for i in range(8) if (2 ** i) < max_threads]
 n_threads_list.append(max_threads)
 
 sklearn_scores = []

diff --git a/benchmarks/bench_isotonic.py b/benchmarks/bench_isotonic.py
@@ -86,7 +86,7 @@ def bench_isotonic_regression(Y):
 
     timings = []
     for exponent in range(args.log_min_problem_size, args.log_max_problem_size):
-        n = 10**exponent
+        n = 10 ** exponent
         Y = DATASET_GENERATORS[args.dataset](n)
         time_per_iteration = [
             bench_isotonic_regression(Y) for i in range(args.iterations)

diff --git a/benchmarks/bench_lasso.py b/benchmarks/bench_lasso.py
@@ -39,7 +39,7 @@ def compute_bench(alpha, n_samples, n_features, precompute):
                 coef=True,
             )
 
-            X /= np.sqrt(np.sum(X**2, axis=0))  # Normalize data
+            X /= np.sqrt(np.sum(X ** 2, axis=0))  # Normalize data
 
             gc.collect()
             print("- benchmarking Lasso")

diff --git a/benchmarks/bench_plot_nmf.py b/benchmarks/bench_plot_nmf.py
@@ -162,7 +162,7 @@ def _fit_projected_gradient(X, W, H, tol, max_iter, nls_max_iter, alpha, l1_rati
         proj_grad_W = squared_norm(gradW * np.logical_or(gradW < 0, W > 0))
         proj_grad_H = squared_norm(gradH * np.logical_or(gradH < 0, H > 0))
 
-        if (proj_grad_W + proj_grad_H) / init_grad < tol**2:
+        if (proj_grad_W + proj_grad_H) / init_grad < tol ** 2:
             break
 
         # update W
@@ -261,8 +261,7 @@ def _fit_transform(self, X, y=None, W=None, H=None, update_H=True):
         if not isinstance(self.max_iter, numbers.Integral) or self.max_iter < 0:
             raise ValueError(
                 "Maximum number of iterations must be a positive "
-                "integer; got (max_iter=%r)"
-                % self.max_iter
+                "integer; got (max_iter=%r)" % self.max_iter
             )
         if not isinstance(self.tol, numbers.Number) or self.tol < 0:
             raise ValueError(
@@ -308,8 +307,7 @@ def _fit_transform(self, X, y=None, W=None, H=None, update_H=True):
         if n_iter == self.max_iter and self.tol > 0:
             warnings.warn(
                 "Maximum number of iteration %d reached. Increase it"
-                " to improve convergence."
-                % self.max_iter,
+                " to improve convergence." % self.max_iter,
                 ConvergenceWarning,
             )
 

diff --git a/benchmarks/bench_random_projections.py b/benchmarks/bench_random_projections.py
@@ -38,7 +38,7 @@ def type_auto_or_int(val):
 
 
 def compute_time(t_start, delta):
-    mu_second = 0.0 + 10**6  # number of microseconds in a second
+    mu_second = 0.0 + 10 ** 6  # number of microseconds in a second
 
     return delta.seconds + delta.microseconds / mu_second
 
@@ -109,7 +109,7 @@ def print_row(clf_type, time_fit, time_transform):
     op.add_option(
         "--n-features",
         dest="n_features",
-        default=10**4,
+        default=10 ** 4,
         type=int,
         help="Number of features in the benchmarks",
     )
@@ -124,7 +124,7 @@ def print_row(clf_type, time_fit, time_transform):
     op.add_option(
         "--ratio-nonzeros",
         dest="ratio_nonzeros",
-        default=10**-3,
+        default=10 ** -3,
         type=float,
         help="Number of features in the benchmarks",
     )

diff --git a/benchmarks/bench_rcv1_logreg_convergence.py b/benchmarks/bench_rcv1_logreg_convergence.py
@@ -149,7 +149,7 @@ def plot_dloss(clfs):
 
 def get_max_squared_sum(X):
     """Get the maximum row-wise sum of squares"""
-    return np.sum(X**2, axis=1).max()
+    return np.sum(X ** 2, axis=1).max()
 
 
 rcv1 = fetch_rcv1()

diff --git a/benchmarks/bench_saga.py b/benchmarks/bench_saga.py
@@ -119,7 +119,7 @@ def fit_single(
                 # Lightning predict_proba is not implemented for n_classes > 2
                 y_pred = _predict_proba(lr, X)
             score = log_loss(y, y_pred, normalize=False) / n_samples
-            score += 0.5 * alpha * np.sum(lr.coef_**2) + beta * np.sum(
+            score += 0.5 * alpha * np.sum(lr.coef_ ** 2) + beta * np.sum(
                 np.abs(lr.coef_)
             )
             scores.append(score)

diff --git a/benchmarks/bench_sample_without_replacement.py b/benchmarks/bench_sample_without_replacement.py
@@ -16,7 +16,7 @@
 
 
 def compute_time(t_start, delta):
-    mu_second = 0.0 + 10**6  # number of microseconds in a second
+    mu_second = 0.0 + 10 ** 6  # number of microseconds in a second
 
     return delta.seconds + delta.microseconds / mu_second
 

diff --git a/benchmarks/bench_tree.py b/benchmarks/bench_tree.py
@@ -22,7 +22,7 @@
 scikit_classifier_results = []
 scikit_regressor_results = []
 
-mu_second = 0.0 + 10**6  # number of microseconds in a second
+mu_second = 0.0 + 10 ** 6  # number of microseconds in a second
 
 
 def bench_scikit_tree_classifier(X, Y):

diff --git a/examples/applications/plot_model_complexity_influence.py b/examples/applications/plot_model_complexity_influence.py
@@ -184,7 +184,7 @@ def _count_nonzero_coefficients(estimator):
     },
     {
         "estimator": NuSVR,
-        "tuned_params": {"C": 1e3, "gamma": 2**-15},
+        "tuned_params": {"C": 1e3, "gamma": 2 ** -15},
         "changing_param": "nu",
         "changing_param_values": [0.05, 0.1, 0.2, 0.35, 0.5],
         "complexity_label": "n_support_vectors",

diff --git a/examples/applications/plot_out_of_core_classification.py b/examples/applications/plot_out_of_core_classification.py
@@ -194,7 +194,7 @@ def progress(blocknum, bs, size):
 # maximum
 
 vectorizer = HashingVectorizer(
-    decode_error="ignore", n_features=2**18, alternate_sign=False
+    decode_error="ignore", n_features=2 ** 18, alternate_sign=False
 )
 
 

diff --git a/examples/applications/plot_species_distribution_modeling.py b/examples/applications/plot_species_distribution_modeling.py
@@ -214,15 +214,15 @@ def plot_species_distribution(
         plt.scatter(
             species.pts_train["dd long"],
             species.pts_train["dd lat"],
-            s=2**2,
+            s=2 ** 2,
             c="black",
             marker="^",
             label="train",
         )
         plt.scatter(
             species.pts_test["dd long"],
             species.pts_test["dd lat"],
-            s=2**2,
+            s=2 ** 2,
             c="black",
             marker="x",
             label="test",

diff --git a/examples/applications/plot_stock_market.py b/examples/applications/plot_stock_market.py
@@ -208,7 +208,7 @@
 
 # Plot the nodes using the coordinates of our embedding
 plt.scatter(
-    embedding[0], embedding[1], s=100 * d**2, c=labels, cmap=plt.cm.nipy_spectral
+    embedding[0], embedding[1], s=100 * d ** 2, c=labels, cmap=plt.cm.nipy_spectral
 )
 
 # Plot the edges

diff --git a/examples/applications/plot_tomography_l1_reconstruction.py b/examples/applications/plot_tomography_l1_reconstruction.py
@@ -81,7 +81,7 @@ def build_projection_operator(l_x, n_dir):
     X, Y = _generate_center_coordinates(l_x)
     angles = np.linspace(0, np.pi, n_dir, endpoint=False)
     data_inds, weights, camera_inds = [], [], []
-    data_unravel_indices = np.arange(l_x**2)
+    data_unravel_indices = np.arange(l_x ** 2)
     data_unravel_indices = np.hstack((data_unravel_indices, data_unravel_indices))
     for i, angle in enumerate(angles):
         Xrot = np.cos(angle) * X - np.sin(angle) * Y

diff --git a/examples/cluster/plot_feature_agglomeration_vs_univariate_selection.py b/examples/cluster/plot_feature_agglomeration_vs_univariate_selection.py
@@ -48,7 +48,7 @@
 coef[0:roi_size, 0:roi_size] = -1.0
 coef[-roi_size:, -roi_size:] = 1.0
 
-X = np.random.randn(n_samples, size**2)
+X = np.random.randn(n_samples, size ** 2)
 for x in X:  # smooth data
     x[:] = ndimage.gaussian_filter(x.reshape(size, size), sigma=1.0).ravel()
 X -= X.mean(axis=0)

diff --git a/examples/cluster/plot_kmeans_stability_low_dim_dense.py b/examples/cluster/plot_kmeans_stability_low_dim_dense.py
@@ -49,7 +49,7 @@
 n_samples_per_center = 100
 grid_size = 3
 scale = 0.1
-n_clusters = grid_size**2
+n_clusters = grid_size ** 2
 
 
 def make_data(random_state, n_samples_per_center, grid_size, scale):

diff --git a/examples/cluster/plot_segmentation_toy.py b/examples/cluster/plot_segmentation_toy.py
@@ -45,10 +45,10 @@
 
 radius1, radius2, radius3, radius4 = 16, 14, 15, 14
 
-circle1 = (x - center1[0]) ** 2 + (y - center1[1]) ** 2 < radius1**2
-circle2 = (x - center2[0]) ** 2 + (y - center2[1]) ** 2 < radius2**2
-circle3 = (x - center3[0]) ** 2 + (y - center3[1]) ** 2 < radius3**2
-circle4 = (x - center4[0]) ** 2 + (y - center4[1]) ** 2 < radius4**2
+circle1 = (x - center1[0]) ** 2 + (y - center1[1]) ** 2 < radius1 ** 2
+circle2 = (x - center2[0]) ** 2 + (y - center2[1]) ** 2 < radius2 ** 2
+circle3 = (x - center3[0]) ** 2 + (y - center3[1]) ** 2 < radius3 ** 2
+circle4 = (x - center4[0]) ** 2 + (y - center4[1]) ** 2 < radius4 ** 2
 
 # %%
 # Plotting four circles

diff --git a/examples/covariance/plot_robust_vs_empirical_covariance.py b/examples/covariance/plot_robust_vs_empirical_covariance.py
@@ -99,7 +99,7 @@
         # fit a Minimum Covariance Determinant (MCD) robust estimator to data
         mcd = MinCovDet().fit(X)
         # compare raw robust estimates with the true location and covariance
-        err_loc_mcd[i, j] = np.sum(mcd.location_**2)
+        err_loc_mcd[i, j] = np.sum(mcd.location_ ** 2)
         err_cov_mcd[i, j] = mcd.error_norm(np.eye(n_features))
 
         # compare estimators learned from the full data set with true
@@ -114,7 +114,7 @@
         pure_X = X[inliers_mask]
         pure_location = pure_X.mean(0)
         pure_emp_cov = EmpiricalCovariance().fit(pure_X)
-        err_loc_emp_pure[i, j] = np.sum(pure_location**2)
+        err_loc_emp_pure[i, j] = np.sum(pure_location ** 2)
         err_cov_emp_pure[i, j] = pure_emp_cov.error_norm(np.eye(n_features))
 
 # Display results

diff --git a/examples/datasets/plot_random_multilabel_dataset.py b/examples/datasets/plot_random_multilabel_dataset.py
@@ -55,7 +55,7 @@
 
 # Use same random seed for multiple calls to make_multilabel_classification to
 # ensure same distributions
-RANDOM_SEED = np.random.randint(2**10)
+RANDOM_SEED = np.random.randint(2 ** 10)
 
 
 def plot_2d(ax, n_labels=1, n_classes=3, length=50):
@@ -79,7 +79,7 @@ def plot_2d(ax, n_labels=1, n_classes=3, length=50):
         marker="*",
         linewidth=0.5,
         edgecolor="black",
-        s=20 + 1500 * p_c**2,
+        s=20 + 1500 * p_c ** 2,
         color=COLORS.take([1, 2, 4]),
     )
     ax.set_xlabel("Feature 0 count")

diff --git a/examples/decomposition/plot_image_denoising.py b/examples/decomposition/plot_image_denoising.py
@@ -82,7 +82,7 @@ def show_with_diff(image, reference, title):
     plt.subplot(1, 2, 2)
     difference = image - reference
 
-    plt.title("Difference (norm: %.2f)" % np.sqrt(np.sum(difference**2)))
+    plt.title("Difference (norm: %.2f)" % np.sqrt(np.sum(difference ** 2)))
     plt.imshow(
         difference, vmin=-0.5, vmax=0.5, cmap=plt.cm.PuOr, interpolation="nearest"
     )

diff --git a/examples/decomposition/plot_sparse_coding.py b/examples/decomposition/plot_sparse_coding.py
@@ -26,9 +26,9 @@ def ricker_function(resolution, center, width):
     """Discrete sub-sampled Ricker (Mexican hat) wavelet"""
     x = np.linspace(0, resolution - 1, resolution)
     x = (
-        (2 / (np.sqrt(3 * width) * np.pi**0.25))
-        * (1 - (x - center) ** 2 / width**2)
-        * np.exp(-((x - center) ** 2) / (2 * width**2))
+        (2 / (np.sqrt(3 * width) * np.pi ** 0.25))
+        * (1 - (x - center) ** 2 / width ** 2)
+        * np.exp(-((x - center) ** 2) / (2 * width ** 2))
     )
     return x
 
@@ -39,7 +39,7 @@ def ricker_matrix(width, resolution, n_components):
     D = np.empty((n_components, resolution))
     for i, center in enumerate(centers):
         D[i] = ricker_function(resolution, center, width)
-    D /= np.sqrt(np.sum(D**2, axis=1))[:, np.newaxis]
+    D /= np.sqrt(np.sum(D ** 2, axis=1))[:, np.newaxis]
     return D
 
 

diff --git a/examples/ensemble/plot_bias_variance.py b/examples/ensemble/plot_bias_variance.py
@@ -95,7 +95,7 @@
 def f(x):
     x = x.ravel()
 
-    return np.exp(-(x**2)) + 1.5 * np.exp(-((x - 2) ** 2))
+    return np.exp(-(x ** 2)) + 1.5 * np.exp(-((x - 2) ** 2))
 
 
 def generate(n_samples, noise, n_repeat=1):

diff --git a/examples/ensemble/plot_gradient_boosting_quantile.py b/examples/ensemble/plot_gradient_boosting_quantile.py
@@ -35,7 +35,7 @@ def f(x):
 # The lognormal distribution is non-symmetric and long tailed: observing large
 # outliers is likely but it is impossible to observe small outliers.
 sigma = 0.5 + X.ravel() / 10
-noise = rng.lognormal(sigma=sigma) - np.exp(sigma**2 / 2)
+noise = rng.lognormal(sigma=sigma) - np.exp(sigma ** 2 / 2)
 y = expected_y + noise
 
 # %%

diff --git a/examples/gaussian_process/plot_gpr_co2.py b/examples/gaussian_process/plot_gpr_co2.py
@@ -100,7 +100,7 @@
 # specific length-scale and the amplitude are free hyperparameters.
 from sklearn.gaussian_process.kernels import RBF
 
-long_term_trend_kernel = 50.0**2 * RBF(length_scale=50.0)
+long_term_trend_kernel = 50.0 ** 2 * RBF(length_scale=50.0)
 
 # %%
 # The seasonal variation is explained by the periodic exponential sine squared
@@ -113,7 +113,7 @@
 from sklearn.gaussian_process.kernels import ExpSineSquared
 
 seasonal_kernel = (
-    2.0**2
+    2.0 ** 2
     * RBF(length_scale=100.0)
     * ExpSineSquared(length_scale=1.0, periodicity=1.0, periodicity_bounds="fixed")
 )
@@ -126,7 +126,7 @@
 # better accommodate the different irregularities.
 from sklearn.gaussian_process.kernels import RationalQuadratic
 
-irregularities_kernel = 0.5**2 * RationalQuadratic(length_scale=1.0, alpha=1.0)
+irregularities_kernel = 0.5 ** 2 * RationalQuadratic(length_scale=1.0, alpha=1.0)
 
 # %%
 # Finally, the noise in the dataset can be accounted with a kernel consisting
@@ -136,8 +136,8 @@
 # further free parameters.
 from sklearn.gaussian_process.kernels import WhiteKernel
 
-noise_kernel = 0.1**2 * RBF(length_scale=0.1) + WhiteKernel(
-    noise_level=0.1**2, noise_level_bounds=(1e-5, 1e5)
+noise_kernel = 0.1 ** 2 * RBF(length_scale=0.1) + WhiteKernel(
+    noise_level=0.1 ** 2, noise_level_bounds=(1e-5, 1e5)
 )
 
 # %%

diff --git a/examples/gaussian_process/plot_gpr_noisy_targets.py b/examples/gaussian_process/plot_gpr_noisy_targets.py
@@ -114,7 +114,7 @@
 # time, we specify the parameter `alpha` which can be interpreted as the
 # variance of a Gaussian noise.
 gaussian_process = GaussianProcessRegressor(
-    kernel=kernel, alpha=noise_std**2, n_restarts_optimizer=9
+    kernel=kernel, alpha=noise_std ** 2, n_restarts_optimizer=9
 )
 gaussian_process.fit(X_train, y_train_noisy)
 mean_prediction, std_prediction = gaussian_process.predict(X, return_std=True)

diff --git a/examples/gaussian_process/plot_gpr_on_structured_data.py b/examples/gaussian_process/plot_gpr_on_structured_data.py
@@ -114,7 +114,7 @@ def clone_with_theta(self, theta):
 D = kernel.diag(X)
 
 plt.figure(figsize=(8, 5))
-plt.imshow(np.diag(D**-0.5).dot(K).dot(np.diag(D**-0.5)))
+plt.imshow(np.diag(D ** -0.5).dot(K).dot(np.diag(D ** -0.5)))
 plt.xticks(np.arange(len(X)), X)
 plt.yticks(np.arange(len(X)), X)
 plt.title("Sequence similarity under the kernel")

diff --git a/examples/linear_model/plot_sgd_penalties.py b/examples/linear_model/plot_sgd_penalties.py
@@ -21,7 +21,7 @@
 line = np.linspace(-1.5, 1.5, 1001)
 xx, yy = np.meshgrid(line, line)
 
-l2 = xx**2 + yy**2
+l2 = xx ** 2 + yy ** 2
 l1 = np.abs(xx) + np.abs(yy)
 rho = 0.5
 elastic_net = rho * l1 + (1 - rho) * l2

diff --git a/examples/manifold/plot_mds.py b/examples/manifold/plot_mds.py
@@ -63,8 +63,8 @@
 npos = nmds.fit_transform(similarities, init=pos)
 
 # Rescale the data
-pos *= np.sqrt((X_true**2).sum()) / np.sqrt((pos**2).sum())
-npos *= np.sqrt((X_true**2).sum()) / np.sqrt((npos**2).sum())
+pos *= np.sqrt((X_true ** 2).sum()) / np.sqrt((pos ** 2).sum())
+npos *= np.sqrt((X_true ** 2).sum()) / np.sqrt((npos ** 2).sum())
 
 # Rotate the data
 clf = PCA(n_components=2)

diff --git a/examples/svm/plot_svm_margin.py b/examples/svm/plot_svm_margin.py
@@ -47,9 +47,9 @@
     # support vectors (margin away from hyperplane in direction
     # perpendicular to hyperplane). This is sqrt(1+a^2) away vertically in
     # 2-d.
-    margin = 1 / np.sqrt(np.sum(clf.coef_**2))
-    yy_down = yy - np.sqrt(1 + a**2) * margin
-    yy_up = yy + np.sqrt(1 + a**2) * margin
+    margin = 1 / np.sqrt(np.sum(clf.coef_ ** 2))
+    yy_down = yy - np.sqrt(1 + a ** 2) * margin
+    yy_up = yy + np.sqrt(1 + a ** 2) * margin
 
     # plot the line, the points, and the nearest vectors to the plane
     plt.figure(fignum, figsize=(4, 3))