Better lint (#132)

* Better lint

* fix one unit test

* fix wrong change

* update cp

* warning

* mac

* update mac

.gitignore

@@ -51,6 +51,7 @@ _doc/examples/plot_*.onnx
 _doc/examples/plot_*.xlsx
 _doc/_static/require.js
 _doc/_static/viz.js
+_doc/sg_execution_times.rst
 _unittests/ut__main/*.png
 _unittests/test_constants.h
 mlinsights/_config.py

CHANGELOGS.rst

@@ -1,8 +1,12 @@
-
 ===========
 Change Logs
 ===========
 
+0.5.1
+=====
+
+* :pr:`132` builds against scikit-learn==1.5.0, python 3.12
+
 0.5.0
 =====
 

_doc/examples/plot_constraint_kmeans.py

@@ -62,7 +62,7 @@
 
 colors = "brgy"
 fig, ax = plt.subplots(1, 1, figsize=(4, 4))
-for i in range(0, max(cl) + 1):
+for i in range(max(cl) + 1):
     ax.plot(X[cl == i, 0], X[cl == i, 1], colors[i] + ".", label="cl%d" % i)
     x = [km.cluster_centers_[i, 0], km.cluster_centers_[i, 0]]
     y = [km.cluster_centers_[i, 1], km.cluster_centers_[i, 1]]
@@ -97,7 +97,7 @@
 #
 
 fig, ax = plt.subplots(1, 2, figsize=(10, 4))
-for i in range(0, max(cl1) + 1):
+for i in range(max(cl1) + 1):
     ax[0].plot(X[cl1 == i, 0], X[cl1 == i, 1], colors[i] + ".", label="cl%d" % i)
     ax[1].plot(X[cl2 == i, 0], X[cl2 == i, 1], colors[i] + ".", label="cl%d" % i)
     x = [km1.cluster_centers_[i, 0], km1.cluster_centers_[i, 0]]
@@ -135,7 +135,7 @@ def plot_delaunay(ax, edges, points):
 
 
 fig, ax = plt.subplots(1, 2, figsize=(10, 4))
-for i in range(0, max(cl) + 1):
+for i in range(max(cl) + 1):
     ax[0].plot(X[cl == i, 0], X[cl == i, 1], colors[i] + ".", label="cl%d" % i)
     x = [km.cluster_centers_[i, 0], km.cluster_centers_[i, 0]]
     y = [km.cluster_centers_[i, 1], km.cluster_centers_[i, 1]]
@@ -145,7 +145,7 @@ def plot_delaunay(ax, edges, points):
 
 cls = km.cluster_centers_iter_
 ax[1].plot(X[:, 0], X[:, 1], ".", label="X", color="#AAAAAA", ms=3)
-for i in range(0, max(cl) + 1):
+for i in range(max(cl) + 1):
     ms = numpy.arange(cls.shape[-1]).astype(numpy.float64) / cls.shape[-1] * 50 + 1
     ax[1].scatter(cls[i, 0, :], cls[i, 1, :], color=colors[i], s=ms, label="cl%d" % i)
     plot_delaunay(ax[1], edges, km.cluster_centers_)

_doc/examples/plot_logistic_regression_clustering.py

@@ -23,8 +23,8 @@
 Xs = []
 Ys = []
 n = 20
-for i in range(0, 5):
-    for j in range(0, 4):
+for i in range(5):
+    for j in range(4):
         x1 = numpy.random.rand(n) + i * 1.1
         x2 = numpy.random.rand(n) + j * 1.1
         Xs.append(numpy.vstack([x1, x2]).T)
@@ -41,7 +41,7 @@
 fig, ax = plt.subplots(1, 1, figsize=(6, 4))
 for i in set(Y):
     ax.plot(
-        X[Y == i, 0], X[Y == i, 1], "o", label="cl%d" % i, color=plt.cm.tab20.colors[i]
+        X[i == Y, 0], X[i == Y, 1], "o", label="cl%d" % i, color=plt.cm.tab20.colors[i]
     )
 ax.legend()
 ax.set_title("Classification not convex")

_doc/examples/plot_piecewise_linear_regression_criterion.py

@@ -1,9 +1,9 @@
 """
 Custom DecisionTreeRegressor adapted to a linear regression
 ===========================================================
- 
+
 A :class:`sklearn.tree.DecisionTreeRegressor`
-can be trained with a couple of possible criterions but it is possible 
+can be trained with a couple of possible criterions but it is possible
 to implement a custom one (see `hellinger_distance_criterion
 <https://github.com/EvgeniDubov/hellinger-distance-criterion/blob/master/hellinger_distance_criterion.pyx>`_).
 See also tutorial

_doc/examples/plot_search_images_torch.py

@@ -147,7 +147,7 @@
 imgs = datasets.ImageFolder("simages", trans)
 dataloader = DataLoader(imgs, batch_size=1, shuffle=True, num_workers=1)
 img_seq = iter(dataloader)
-imgs = list(img[0] for i, img in zip(range(2), img_seq))
+imgs = [img[0] for i, img in zip(range(2), img_seq)]
 #######################################
 #
 
@@ -182,7 +182,7 @@
     ConcatDataset([imgs1, imgs2]), batch_size=1, shuffle=True, num_workers=1
 )
 img_seq = iter(dataloader)
-imgs = list(img[0] for i, img in zip(range(10), img_seq))
+imgs = [img[0] for i, img in zip(range(10), img_seq)]
 #######################################
 #
 
@@ -259,7 +259,7 @@
 imgs = datasets.ImageFolder("simages", trans)
 dataloader = DataLoader(imgs, batch_size=1, shuffle=False, num_workers=1)
 img_seq = iter(dataloader)
-imgs = list(img[0] for img in img_seq)
+imgs = [img[0] for img in img_seq]
 
 all_outputs = [model.forward(img).detach().numpy().ravel() for img in imgs]
 

_doc/examples/plot_sklearn_transformed_target.py

@@ -202,7 +202,7 @@ def evaluation():
     rnd = []
     perf_reg = []
     perf_clr = []
-    for rs in range(0, 200):
+    for rs in range(200):
         rnd.append(rs)
         X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=rs)
         reg = LinearRegression()
@@ -247,7 +247,7 @@ def evaluation2():
     perf_clr = []
     acc_reg = []
     acc_clr = []
-    for rs in range(0, 50):
+    for rs in range(50):
         rnd.append(rs)
         X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=rs)
         reg = LinearRegression()
@@ -368,7 +368,7 @@ def permute(y):
 
 
 rows = []
-for i in range(0, 10):
+for _i in range(10):
     regpt = TransformedTargetRegressor2(LinearRegression(), transformer="permute")
     regpt.fit(X_train, y_train)
     logpt = TransformedTargetClassifier2(

_doc/examples/plot_visualize_pipeline.py

@@ -238,6 +238,6 @@
 # Every piece behaves the same way.
 
 
-for coor, model, vars in enumerate_pipeline_models(model):
+for coor, m, _vars in enumerate_pipeline_models(model):
     print(coor)
-    print(model._debug)
+    print(m._debug)

_unittests/ut_helpers/test_debug.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 import numpy.random
 from sklearn.linear_model import LinearRegression, LogisticRegression

_unittests/ut_helpers/test_parameters.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 from mlinsights.ext_test_case import ExtTestCase
 from mlinsights.helpers.parameters import format_value

_unittests/ut_metrics/test_non_linear_correlations.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 import pandas
 from sklearn import datasets
@@ -18,7 +17,7 @@ def test_non_linear_correlations_df(self):
         self.assertEqual(cor.shape, (4, 4))
         self.assertEqual(list(cor.columns), ["X1", "X2", "X3", "X4"])
         self.assertEqual(list(cor.index), ["X1", "X2", "X3", "X4"])
-        self.assertEqual(list(cor.iloc[i, i] for i in range(0, 4)), [1, 1, 1, 1])
+        self.assertEqual(list(cor.iloc[i, i] for i in range(4)), [1, 1, 1, 1])
         self.assertGreater(cor.values.min(), 0)
 
     def test_non_linear_correlations_array(self):
@@ -27,7 +26,7 @@ def test_non_linear_correlations_array(self):
         df = pandas.DataFrame(X).values
         cor = non_linear_correlations(df, LinearRegression(fit_intercept=False))
         self.assertEqual(cor.shape, (4, 4))
-        self.assertEqual(list(cor[i, i] for i in range(0, 4)), [1, 1, 1, 1])
+        self.assertEqual(list(cor[i, i] for i in range(4)), [1, 1, 1, 1])
         self.assertGreater(cor.min(), 0)
 
     def test_non_linear_correlations_df_tree(self):
@@ -39,7 +38,7 @@ def test_non_linear_correlations_df_tree(self):
         self.assertEqual(cor.shape, (4, 4))
         self.assertEqual(list(cor.columns), ["X1", "X2", "X3", "X4"])
         self.assertEqual(list(cor.index), ["X1", "X2", "X3", "X4"])
-        self.assertGreater(max(cor.iloc[i, i] for i in range(0, 4)), 0.98)
+        self.assertGreater(max(cor.iloc[i, i] for i in range(4)), 0.98)
         self.assertGreater(cor.values.min(), 0)
 
     def test_non_linear_correlations_df_minmax(self):
@@ -53,9 +52,9 @@ def test_non_linear_correlations_df_minmax(self):
         self.assertEqual(cor.shape, (4, 4))
         self.assertEqual(list(cor.columns), ["X1", "X2", "X3", "X4"])
         self.assertEqual(list(cor.index), ["X1", "X2", "X3", "X4"])
-        self.assertEqual(list(cor.iloc[i, i] for i in range(0, 4)), [1, 1, 1, 1])
-        self.assertEqual(list(mini.iloc[i, i] for i in range(0, 4)), [1, 1, 1, 1])
-        self.assertEqual(list(maxi.iloc[i, i] for i in range(0, 4)), [1, 1, 1, 1])
+        self.assertEqual(list(cor.iloc[i, i] for i in range(4)), [1, 1, 1, 1])
+        self.assertEqual(list(mini.iloc[i, i] for i in range(4)), [1, 1, 1, 1])
+        self.assertEqual(list(maxi.iloc[i, i] for i in range(4)), [1, 1, 1, 1])
         self.assertGreater(cor.values.min(), 0)
         self.assertEqual(list(mini.columns), ["X1", "X2", "X3", "X4"])
         self.assertEqual(list(mini.index), ["X1", "X2", "X3", "X4"])
@@ -74,9 +73,9 @@ def test_non_linear_correlations_array_minmax(self):
             df, LinearRegression(fit_intercept=False), minmax=True
         )
         self.assertEqual(cor.shape, (4, 4))
-        self.assertEqual(list(cor[i, i] for i in range(0, 4)), [1, 1, 1, 1])
-        self.assertEqual(list(mini[i, i] for i in range(0, 4)), [1, 1, 1, 1])
-        self.assertEqual(list(maxi[i, i] for i in range(0, 4)), [1, 1, 1, 1])
+        self.assertEqual(list(cor[i, i] for i in range(4)), [1, 1, 1, 1])
+        self.assertEqual(list(mini[i, i] for i in range(4)), [1, 1, 1, 1])
+        self.assertEqual(list(maxi[i, i] for i in range(4)), [1, 1, 1, 1])
         self.assertGreater(cor.min(), 0)
         self.assertEqual(mini.shape, (4, 4))
         self.assertLesser(mini.min(), cor.min())

_unittests/ut_metrics/test_scoring_metrics.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 import pandas
 import numpy

_unittests/ut_mlbatch/test_pipeline_cache.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 from sklearn.datasets import make_classification
 from sklearn.decomposition import PCA, TruncatedSVD as SVD

_unittests/ut_mlmodel/test_anmf_predictor.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 import numpy
 from scipy.sparse import csr_matrix

_unittests/ut_mlmodel/test_classification_kmeans.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 import numpy
 from numpy.random import RandomState
@@ -75,8 +74,8 @@ def test_classification_kmeans_relevance(self):
         Xs = []
         Ys = []
         n = 20
-        for i in range(0, 5):
-            for j in range(0, 4):
+        for i in range(5):
+            for j in range(4):
                 x1 = state.rand(n) + i * 1.1
                 x2 = state.rand(n) + j * 1.1
                 Xs.append(numpy.vstack([x1, x2]).T)

_unittests/ut_mlmodel/test_decision_tree_logistic_regression.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 import numpy
 from numpy.random import random

_unittests/ut_mlmodel/test_direct_blas_lapack.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 import numpy
 from scipy.linalg.lapack import dgelss as scipy_dgelss

_unittests/ut_mlmodel/test_extended_features.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 import numpy
 from scipy import sparse
@@ -304,7 +303,7 @@ def test_polynomial_features_bigger(self):
             ext = ExtendedFeatures(poly_degree=deg)
             X_ext = ext.fit_transform(X)
 
-            inames = ["x%d" % i for i in range(0, X.shape[1])]
+            inames = ["x%d" % i for i in range(X.shape[1])]
             names_ext = ext.get_feature_names_out(inames)
 
             self.assertEqual(len(names_sk), len(names_ext))
@@ -329,7 +328,7 @@ def test_polynomial_features_bigger_ionly(self):
             )
             X_ext = ext.fit_transform(X)
 
-            inames = ["x%d" % i for i in range(0, X.shape[1])]
+            inames = ["x%d" % i for i in range(X.shape[1])]
             names_ext = ext.get_feature_names_out(inames)
 
             self.assertEqual(len(names_sk), len(names_ext))

_unittests/ut_mlmodel/test_interval_regressor.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 import numpy
 from sklearn.linear_model import LinearRegression

_unittests/ut_mlmodel/test_kmeans_sklearn.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 import numpy as np
 from scipy import sparse as sp

_unittests/ut_mlmodel/test_piecewise_classifier.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 import numpy
 from numpy.random import random

_unittests/ut_mlmodel/test_piecewise_decision_tree_experiment.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 import warnings
 import packaging.version as pv

_unittests/ut_mlmodel/test_piecewise_decision_tree_experiment_fast.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 import warnings
 import numpy

_unittests/ut_mlmodel/test_piecewise_decision_tree_experiment_linear.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 import warnings
 import numpy

_unittests/ut_mlmodel/test_piecewise_regressor.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 import numpy
 from numpy.random import random

_unittests/ut_mlmodel/test_quantile_mlpregression.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 import numpy
 from numpy.random import random

_unittests/ut_mlmodel/test_quantile_regression.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 import numpy
 from numpy.random import random

_unittests/ut_mlmodel/test_sklearn_text.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 import numpy
 from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer

_unittests/ut_mlmodel/test_sklearn_transform_inv.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 import numpy
 from mlinsights.ext_test_case import ExtTestCase

_unittests/ut_mlmodel/test_target_predictors.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 import numpy
 from sklearn.datasets import load_iris

_unittests/ut_mlmodel/test_transfer_transformer.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 import numpy
 from sklearn.linear_model import LinearRegression, LogisticRegression

_unittests/ut_mlmodel/test_tsne_predictable.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 import numpy
 from numpy.random import RandomState
@@ -63,8 +62,8 @@ def test_predictable_tsne_relevance(self):
         Xs = []
         Ys = []
         n = 20
-        for i in range(0, 5):
-            for j in range(0, 4):
+        for i in range(5):
+            for j in range(4):
                 x1 = state.rand(n) + i * 1.1
                 x2 = state.rand(n) + j * 1.1
                 Xs.append(numpy.vstack([x1, x2]).T)

_unittests/ut_mltree/test_tree_digitize.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 import numpy
 from sklearn.tree import DecisionTreeRegressor

_unittests/ut_mltree/test_tree_structure.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 import numpy
 from sklearn import datasets

_unittests/ut_plotting/test_dot.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import unittest
 from io import StringIO
 from textwrap import dedent
@@ -168,7 +167,7 @@ def test_onehotencoder_dot(self):
             ),
             LinearRegression(),
         )
-        train_cols = cols + ["weekday"]
+        train_cols = [*cols, "weekday"]
         model.fit(df, df[train_cols])
         dot = pipeline2dot(model, df)
         self.assertIn('label="Identity"', dot)