Updates CI for scikit-learn==1.1

.circleci/config.yml

@@ -18,8 +18,8 @@ jobs:
           name: Install pandoc
           command: |
                     sudo apt-get update 
-                    wget https://github.com/jgm/pandoc/releases/download/2.14.1/pandoc-2.14.1-1-amd64.deb
-                    sudo dpkg -i pandoc-2.14.1-1-amd64.deb
+                    wget https://github.com/jgm/pandoc/releases/download/2.18/pandoc-2.18-1-amd64.deb
+                    sudo dpkg -i pandoc-2.18-1-amd64.deb
 
       - run:
           name: Install tex

.travis.yml

@@ -9,11 +9,6 @@ matrix:
     env:
       - sklver=">=0.24.2"
       - jlver=">=1.0"
-  - python: 3.8
-    name: "Py38-023"
-    env:
-      - sklver="==0.23.2"
-      - jlver="==0.17.0"
 
 before_install:
     - sudo apt-get install libgeos-dev libproj-dev proj-data graphviz libblas-dev liblapack-dev

README.rst

@@ -76,4 +76,4 @@ Function ``pipeline2dot`` converts a pipeline into a graph:
     from mlinsights.plotting import pipeline2dot
     dot = pipeline2dot(clf, df)
 
-.. image:: https://github.com/sdpython/mlinsights/raw/master/_doc/pipeline.png
+.. image:: https://raw.githubusercontent.com/sdpython/mlinsights/master/_doc/sphinxdoc/source/pipeline.png

_unittests/ut_mlmodel/test_kmeans_l1.py

@@ -72,8 +72,9 @@ def test_kmeans_l2_iris(self):
         self.assertEqual({0, 1, 2, 3}, cls)
 
     def test_kmeans_l1_check(self):
-        X = numpy.array([[-10, 1, 2, 3, 4, 10],
-                         [-10, 1, 2, 3, 4, 10]]).T
+        X = numpy.ascontiguousarray(
+            numpy.array([[-10, 1, 2, 3, 4, 10],
+                         [-10, 1, 2, 3, 4, 10]]).T)
         clr = KMeansL1L2(2, norm='L1')
         clr.fit(X)
         cls = set(clr.predict(X))

_unittests/ut_mlmodel/test_piecewise_decision_tree_experiment.py

@@ -26,7 +26,7 @@ def test_criterions(self):
         X = numpy.array([[1., 2.]]).T
         y = numpy.array([1., 2.])
         c1 = MSE(1, X.shape[0])
-        c2 = SimpleRegressorCriterion(X)
+        c2 = SimpleRegressorCriterion(1, X.shape[0])
         self.assertNotEmpty(c1)
         self.assertNotEmpty(c2)
         w = numpy.ones((y.shape[0],))
@@ -49,7 +49,7 @@ def test_criterions(self):
         X = numpy.array([[1., 2., 3.]]).T
         y = numpy.array([1., 2., 3.])
         c1 = MSE(1, X.shape[0])
-        c2 = SimpleRegressorCriterion(X)
+        c2 = SimpleRegressorCriterion(1, X.shape[0])
         w = numpy.ones((y.shape[0],))
         ind = numpy.arange(y.shape[0]).astype(numpy.int64)
         ys = y.astype(float).reshape((y.shape[0], 1))
@@ -68,7 +68,7 @@ def test_criterions(self):
         X = numpy.array([[1., 2., 10., 11.]]).T
         y = numpy.array([0.9, 1.1, 1.9, 2.1])
         c1 = MSE(1, X.shape[0])
-        c2 = SimpleRegressorCriterion(X)
+        c2 = SimpleRegressorCriterion(1, X.shape[0])
         w = numpy.ones((y.shape[0],))
         ind = numpy.arange(y.shape[0]).astype(numpy.int64)
         ys = y.astype(float).reshape((y.shape[0], 1))
@@ -121,7 +121,7 @@ def test_criterions(self):
         X = numpy.array([[1., 2., 10., 11.]]).T
         y = numpy.array([0.9, 1.1, 1.9, 2.1])
         c1 = MSE(1, X.shape[0])
-        c2 = SimpleRegressorCriterion(X)
+        c2 = SimpleRegressorCriterion(1, X.shape[0])
         w = numpy.ones((y.shape[0],))
         ind = numpy.array([0, 3, 2, 1], dtype=ind.dtype)
         ys = y.astype(float).reshape((y.shape[0], 1))
@@ -166,7 +166,8 @@ def test_decision_tree_criterion(self):
         clr1.fit(X, y)
         p1 = clr1.predict(X)
 
-        crit = SimpleRegressorCriterion(X)
+        crit = SimpleRegressorCriterion(
+            1 if len(y.shape) <= 1 else y.shape[1], X.shape[0])
         clr2 = DecisionTreeRegressor(criterion=crit, max_depth=1)
         clr2.fit(X, y)
         p2 = clr2.predict(X)
@@ -179,7 +180,9 @@ def test_decision_tree_criterion_iris(self):
         clr1 = DecisionTreeRegressor()
         clr1.fit(X, y)
         p1 = clr1.predict(X)
-        clr2 = DecisionTreeRegressor(criterion=SimpleRegressorCriterion(X))
+        clr2 = DecisionTreeRegressor(
+            criterion=SimpleRegressorCriterion(
+                1 if len(y.shape) <= 1 else y.shape[1], X.shape[0]))
         clr2.fit(X, y)
         p2 = clr2.predict(X)
         self.assertEqual(p1[:10], p2[:10])

_unittests/ut_mlmodel/test_piecewise_decision_tree_experiment_fast.py

@@ -27,7 +27,7 @@ def test_criterions(self):
         X = numpy.array([[1., 2.]]).T
         y = numpy.array([1., 2.])
         c1 = MSE(1, X.shape[0])
-        c2 = SimpleRegressorCriterionFast(X)
+        c2 = SimpleRegressorCriterionFast(1, X.shape[0])
         self.assertNotEmpty(c1)
         self.assertNotEmpty(c2)
         w = numpy.ones((y.shape[0],))
@@ -51,7 +51,7 @@ def test_criterions(self):
         X = numpy.array([[1., 2., 3.]]).T
         y = numpy.array([1., 2., 3.])
         c1 = MSE(1, X.shape[0])
-        c2 = SimpleRegressorCriterionFast(X)
+        c2 = SimpleRegressorCriterionFast(1, X.shape[0])
         w = numpy.ones((y.shape[0],))
         ind = numpy.arange(y.shape[0]).astype(numpy.int64)
         ys = y.astype(float).reshape((y.shape[0], 1))
@@ -71,7 +71,7 @@ def test_criterions(self):
         X = numpy.array([[1., 2., 10., 11.]]).T
         y = numpy.array([0.9, 1.1, 1.9, 2.1])
         c1 = MSE(1, X.shape[0])
-        c2 = SimpleRegressorCriterionFast(X)
+        c2 = SimpleRegressorCriterionFast(1, X.shape[0])
         w = numpy.ones((y.shape[0],))
         ind = numpy.arange(y.shape[0]).astype(numpy.int64)
         ys = y.astype(float).reshape((y.shape[0], 1))
@@ -115,7 +115,7 @@ def test_criterions(self):
         X = numpy.array([[1., 2., 10., 11.]]).T
         y = numpy.array([0.9, 1.1, 1.9, 2.1])
         c1 = MSE(1, X.shape[0])
-        c2 = SimpleRegressorCriterionFast(X)
+        c2 = SimpleRegressorCriterionFast(1, X.shape[0])
         w = numpy.ones((y.shape[0],))
         ind = numpy.array([0, 3, 2, 1], dtype=ind.dtype)
         ys = y.astype(float).reshape((y.shape[0], 1))
@@ -162,7 +162,7 @@ def test_decision_tree_criterion(self):
         clr1.fit(X, y)
         p1 = clr1.predict(X)
 
-        crit = SimpleRegressorCriterionFast(X)
+        crit = SimpleRegressorCriterionFast(1, X.shape[0])
         clr2 = DecisionTreeRegressor(criterion=crit, max_depth=1)
         clr2.fit(X, y)
         p2 = clr2.predict(X)
@@ -175,7 +175,7 @@ def test_decision_tree_criterion_iris(self):
         clr1 = DecisionTreeRegressor()
         clr1.fit(X, y)
         p1 = clr1.predict(X)
-        clr2 = DecisionTreeRegressor(criterion=SimpleRegressorCriterionFast(X))
+        clr2 = DecisionTreeRegressor(criterion=SimpleRegressorCriterionFast(1, X.shape[0]))
         clr2.fit(X, y)
         p2 = clr2.predict(X)
         self.assertEqual(p1[:10], p2[:10])

_unittests/ut_mlmodel/test_piecewise_decision_tree_experiment_linear.py

@@ -25,7 +25,7 @@ def test_criterions(self):
         X = numpy.array([[10., 12., 13.]]).T
         y = numpy.array([20., 22., 23.])
         c1 = MSE(1, X.shape[0])
-        c2 = LinearRegressorCriterion(X)
+        c2 = LinearRegressorCriterion(1, X)
         self.assertNotEmpty(c1)
         self.assertNotEmpty(c2)
         w = numpy.ones((y.shape[0],))
@@ -49,7 +49,7 @@ def test_criterions(self):
         X = numpy.array([[1., 2., 3.]]).T
         y = numpy.array([1., 2., 3.])
         c1 = MSE(1, X.shape[0])
-        c2 = LinearRegressorCriterion(X)
+        c2 = LinearRegressorCriterion(1, X)
         w = numpy.ones((y.shape[0],))
         ind = numpy.arange(y.shape[0]).astype(numpy.int64)
         ys = y.astype(float).reshape((y.shape[0], 1))
@@ -68,7 +68,7 @@ def test_criterions(self):
         X = numpy.array([[1., 2., 10., 11.]]).T
         y = numpy.array([0.9, 1.1, 1.9, 2.1])
         c1 = MSE(1, X.shape[0])
-        c2 = LinearRegressorCriterion(X)
+        c2 = LinearRegressorCriterion(1, X)
         w = numpy.ones((y.shape[0],))
         ind = numpy.arange(y.shape[0]).astype(numpy.int64)
         ys = y.astype(float).reshape((y.shape[0], 1))
@@ -87,7 +87,7 @@ def test_criterions(self):
         X = numpy.array([[1., 2., 10., 11.]]).T
         y = numpy.array([0.9, 1.1, 1.9, 2.1])
         c1 = MSE(1, X.shape[0])
-        c2 = LinearRegressorCriterion(X)
+        c2 = LinearRegressorCriterion(1, X)
         w = numpy.ones((y.shape[0],))
         ind = numpy.array([0, 3, 2, 1], dtype=ind.dtype)
         ys = y.astype(float).reshape((y.shape[0], 1))
@@ -145,7 +145,7 @@ def test_decision_tree_criterion(self):
         clr1.fit(X, y)
         p1 = clr1.predict(X)
 
-        crit = LinearRegressorCriterion(X)
+        crit = LinearRegressorCriterion(1, X)
         clr2 = DecisionTreeRegressor(criterion=crit, max_depth=1)
         clr2.fit(X, y)
         p2 = clr2.predict(X)
@@ -158,7 +158,7 @@ def test_decision_tree_criterion_iris(self):
         clr1 = DecisionTreeRegressor()
         clr1.fit(X, y)
         p1 = clr1.predict(X)
-        clr2 = DecisionTreeRegressor(criterion=LinearRegressorCriterion(X))
+        clr2 = DecisionTreeRegressor(criterion=LinearRegressorCriterion(1, X))
         clr2.fit(X, y)
         p2 = clr2.predict(X)
         self.assertEqual(p1.shape, p2.shape)

_unittests/ut_timeseries/test_plot_timeseries.py

@@ -3,6 +3,8 @@
 """
 import unittest
 import datetime
+import warnings
+import sys
 from pyquickhelper.pycode import ExtTestCase
 from mlinsights.timeseries.datasets import artificial_data
 from mlinsights.timeseries.agg import aggregate_timeseries
@@ -11,8 +13,17 @@
 
 class TestPlotTimeSeries(ExtTestCase):
 
+    @unittest.skipIf(
+        sys.platform == "win32" and __name__ != "__main__",
+        reason="issue with matplotlib")
     def test_plot_data(self):
-        import matplotlib.pyplot as plt  # pylint: disable=C0415
+        try:
+            import matplotlib.pyplot as plt  # pylint: disable=C0415
+        except Exception as e:
+            if 'generated new fontManager' in str(e):
+                warnings.warn(e)
+                return
+            raise e
         dt1 = datetime.datetime(2019, 8, 1)
         dt2 = datetime.datetime(2019, 8, 15)
         data = artificial_data(dt1, dt2, minutes=15)

appveyor.yml

@@ -10,10 +10,6 @@ environment:
       PYTHON_VERSION: "3.9.x"
       PYTHON_ARCH: "64"
       SKL: '==0.24.2'
-    - PYTHON: "C:\\Python38-x64"
-      PYTHON_VERSION: "3.8.x"
-      PYTHON_ARCH: "64"
-      SKL: '==0.23.2'
 init:
   - "ECHO %PYTHON% %PYTHON_VERSION% %PYTHON_ARCH%"
 

azure-pipelines.yml

@@ -18,8 +18,8 @@ jobs:
     displayName: 'Install Inkscape'
   - script: sudo apt-get install -y pandoc
     displayName: 'Install Pandoc'
-  - script: sudo apt-get install -y texlive texlive-latex-extra texlive-xetex dvipng
-    displayName: 'Install Latex'
+  # - script: sudo apt-get install -y texlive texlive-latex-extra texlive-xetex dvipng
+  #   displayName: 'Install Latex'
   - script: sudo apt-get install -y libgeos-dev libproj-dev proj-data graphviz libblas-dev liblapack-dev
     displayName: 'Install Geos packages'
   - script: |
@@ -37,7 +37,7 @@ jobs:
     displayName: 'Install tools'
   - script: pip install numpy
     displayName: 'Install numpy'
-  - script: pip install torch==1.7.1+cpu torchvision==0.8.2+cpu torchaudio==0.7.2 -f https://download.pytorch.org/whl/torch_stable.html
+  - script: pip install install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
     displayName: 'Install pytorch'
   - script: |
           export LLVM_CONFIG=/usr/bin/llvm-config-10

mlinsights/mlmodel/_kmeans_022.py

@@ -21,7 +21,7 @@ def _labels_inertia_precompute_dense(norm, X, sample_weight, centers, distances)
 
     This will overwrite the 'distances' array in-place.
 
-    :param norm: 'l1' or 'l2'
+    :param norm: 'L1' or 'L2'
     :param X:  numpy array, shape (n_sample, n_features)
         Input data.
     :param sample_weight: array-like, shape (n_samples,)
@@ -37,10 +37,10 @@ def _labels_inertia_precompute_dense(norm, X, sample_weight, centers, distances)
         cluster center.
     """
     n_samples = X.shape[0]
-    if norm == 'l2':
+    if norm == 'L2':
         labels, mindist = pairwise_distances_argmin_min(
             X=X, Y=centers, metric='euclidean', metric_kwargs={'squared': True})
-    elif norm == 'l1':
+    elif norm == 'L1':
         labels, mindist = pairwise_distances_argmin_min(
             X=X, Y=centers, metric='manhattan')
     else:  # pragma no cover

mlinsights/mlmodel/_piecewise_tree_regression_common.pxd

@@ -9,8 +9,6 @@ from sklearn.tree._criterion cimport SIZE_t, DOUBLE_t
 
 cdef class CommonRegressorCriterion(Criterion):
 
-    cdef const DOUBLE_t[:, ::1] sample_X
-
     cdef void _update_weights(self, SIZE_t start, SIZE_t end,
                               SIZE_t old_pos, SIZE_t new_pos) nogil