Fixes #95, PiecewiseRegressor, makes sure target are vectors

Fixes #95, PiecewiseRegressor, makes sure target are vectors

Author: sdpython

.travis.yml

@@ -7,7 +7,7 @@ matrix:
   - python: 3.9
     name: "Py39-024+"
     env:
-      - sklver=">=0.24.0"
+      - sklver=">=0.24.2"
       - jlver=">=1.0"
   - python: 3.8
     name: "Py38-023"

_doc/sphinxdoc/source/conf.py

@@ -5,7 +5,7 @@
 import sys
 import os
 import alabaster
-from pyquickhelper.helpgen.default_conf import set_sphinx_variables, get_default_stylesheet
+from pyquickhelper.helpgen.default_conf import set_sphinx_variables
 
 
 sys.path.insert(0, os.path.abspath(os.path.join(os.path.split(__file__)[0])))
@@ -20,8 +20,9 @@
                      title="mlinsights", book=True)
 
 blog_root = "http://www.xavierdupre.fr/app/mlinsights/helpsphinx/"
-html_context = {'css_files': get_default_stylesheet() +
-                ['_static/my-styles.css']}
+
+html_css_files = ['my-styles.css']
+
 html_logo = "phdoc_static/project_ico.png"
 html_sidebars = {}
 language = "en"

_doc/pipeline.png renamed to _doc/sphinxdoc/source/pipeline.png

@@ -119,10 +119,11 @@ def test_categories_to_integers_grid_search(self):
                              LogisticRegression())
         self.assertRaise(lambda: test_sklearn_grid_search_cv(
             lambda: pipe, df), ValueError)
-        self.assertRaise(
-            lambda: test_sklearn_grid_search_cv(
-                lambda: pipe, X, y, categoriestointegers__single=[True, False]),
-            ValueError, "Unable to find category value")
+        if compare_module_version(sklver, "0.24") >= 0:
+            self.assertRaise(
+                lambda: test_sklearn_grid_search_cv(
+                    lambda: pipe, X, y, categoriestointegers__single=[True, False]),
+                ValueError, "Unable to find category value")
         pipe = make_pipeline(CategoriesToIntegers(),
                              Imputer(strategy='most_frequent'),
                              LogisticRegression(n_jobs=1))

_unittests/ut_mlmodel/test_categories_to_integers.py

@@ -57,7 +57,12 @@ def test_classification_kmeans_intercept_weights(self):
     def test_classification_kmeans_pickle(self):
         iris = datasets.load_iris()
         X, y = iris.data, iris.target
-        test_sklearn_pickle(lambda: ClassifierAfterKMeans(), X, y)
+        try:
+            test_sklearn_pickle(lambda: ClassifierAfterKMeans(), X, y)
+        except AttributeError as e:
+            if compare_module_version(sklver, "0.24") < 0:
+                return
+            raise e
 
     def test_classification_kmeans_clone(self):
         self.maxDiff = None

_unittests/ut_mlmodel/test_classification_kmeans.py

@@ -7,6 +7,8 @@
 from numpy.random import random
 import pandas
 from sklearn.linear_model import LinearRegression
+from sklearn.datasets import make_regression
+from sklearn.tree import DecisionTreeRegressor
 from pyquickhelper.pycode import ExtTestCase, ignore_warnings
 from mlinsights.mlmodel import test_sklearn_pickle, test_sklearn_clone, test_sklearn_grid_search_cv
 from mlinsights.mlmodel.piecewise_estimator import PiecewiseRegressor
@@ -148,6 +150,23 @@ def test_piecewise_regressor_grid_search(self):
         self.assertGreater(res['score'], 0)
         self.assertLesser(res['score'], 1)
 
+    def test_piecewise_regressor_issue(self):
+        X, y = make_regression(10000, n_features=1, n_informative=1,  # pylint: disable=W0632
+                               n_targets=1)
+        y = y.reshape((-1, 1))
+        model = PiecewiseRegressor(
+            binner=DecisionTreeRegressor(min_samples_leaf=300))
+        model.fit(X, y)
+        vvc = model.predict(X)
+        self.assertEqual(vvc.shape, (X.shape[0], ))
+
+    def test_piecewise_regressor_raise(self):
+        X, y = make_regression(10000, n_features=2, n_informative=2,  # pylint: disable=W0632
+                               n_targets=2)
+        model = PiecewiseRegressor(
+            binner=DecisionTreeRegressor(min_samples_leaf=300))
+        self.assertRaise(lambda: model.fit(X, y), RuntimeError)
+
 
 if __name__ == "__main__":
     unittest.main()

_unittests/ut_mlmodel/test_piecewise_regressor.py

@@ -9,7 +9,7 @@
 from sklearn.utils.sparsefuncs_fast import assign_rows_csr  # pylint: disable=W0611,E0611
 try:
     from sklearn.cluster._kmeans import _check_sample_weight
-except ImportError:
+except ImportError:  # pragma: no cover
     from sklearn.cluster._kmeans import (
         _check_normalize_sample_weight as _check_sample_weight)
 from sklearn.metrics.pairwise import pairwise_distances_argmin_min

mlinsights/mlmodel/_kmeans_022.py

@@ -234,7 +234,8 @@ def _compute_strategy_coefficient(distances, strategy, labels):
         ar = numpy.arange(distances.shape[0])
         dist = distances[ar, labels]
         return distances - dist[:, numpy.newaxis]
-    raise ValueError("Unknwon strategy '{0}'.".format(strategy))
+    raise ValueError(  # pragma: no cover
+        "Unknwon strategy '{0}'.".format(strategy))
 
 
 def _randomize_index(index, weights):

mlinsights/mlmodel/_kmeans_constraint_.py

@@ -422,7 +422,7 @@ def _fit_parallel(self, X, y, sample_weight):
 
     def _fit_perpendicular(self, X, y, sample_weight):
         "Implements the perpendicular strategy."
-        raise NotImplementedError()
+        raise NotImplementedError()  # pragma: no cover
 
     def predict(self, X):
         """

mlinsights/mlmodel/decision_tree_logreg.py

@@ -71,7 +71,7 @@ def _get_feature_names_poly(self, input_features=None):
             input_features = ["x%d" %
                               i for i in range(0, self.n_input_features_)]
         elif len(input_features) != self.n_input_features_:
-            raise ValueError(
+            raise ValueError(  # pragma: no cover
                 "input_features should contain {} strings.".format(
                     self.n_input_features_))
 
@@ -125,7 +125,7 @@ def fit(self, X, y=None):
             return self._fit_poly(X, y)
         elif self.kind == 'poly-slow':
             return self._fit_poly(X, y)
-        raise ValueError(
+        raise ValueError(  # pragma: no cover
             "Unknown extended features '{}'.".format(self.kind))
 
     def _fit_poly(self, X, y=None):
@@ -148,7 +148,8 @@ def transform(self, X):
         """
         n_features = X.shape[1]
         if n_features != self.n_input_features_:
-            raise ValueError("X shape does not match training shape")
+            raise ValueError(  # pragma: no cover
+                "X shape does not match training shape")
         if self.kind == 'poly':
             return self._transform_poly(X)
         if self.kind == 'poly-slow':