rename functions

xadupre · xadupre · commit 79da5b5653fb · 2023-10-30T14:33:19.000+01:00
diff --git a/_unittests/ut_mlmodel/test_piecewise_decision_tree_experiment.py b/_unittests/ut_mlmodel/test_piecewise_decision_tree_experiment.py
@@ -86,6 +86,7 @@ def test_criterions(self):
         _test_criterion_init(c2, ys, w, 1.0, ind, 0, y.shape[0])
         _test_criterion_check(c1)
         _test_criterion_check(c2)
+        self.assertStartsWith("SimpleRegressorCriterion(", str(c2))
         i1 = _test_criterion_node_impurity(c1)
         i2 = _test_criterion_node_impurity(c2)
         _test_criterion_check(c1)
@@ -109,21 +110,18 @@ def test_criterions(self):
             _test_criterion_update(c2, i)
             _test_criterion_check(c2)
             assert_criterion_equal(c1, c2)
+            self.assertIsInstance(c2.printd(), str)
             left1, right1 = _test_criterion_node_impurity_children(c1)
             left2, right2 = _test_criterion_node_impurity_children(c2)
             self.assertAlmostEqual(left1, left2)
             self.assertAlmostEqual(right1, right2, atol=1e-10)
             v1 = _test_criterion_node_value(c1)
             v2 = _test_criterion_node_value(c2)
             self.assertEqual(v1, v2)
-            try:
-                # scikit-learn >= 0.24
-                p1 = _test_criterion_impurity_improvement(c1, 0.0, left1, right1)
-                p2 = _test_criterion_impurity_improvement(c2, 0.0, left2, right2)
-            except TypeError:
-                # scikit-learn < 0.24
-                p1 = _test_criterion_impurity_improvement(c1, 0.0)
-                p2 = _test_criterion_impurity_improvement(c2, 0.0)
+            p1 = _test_criterion_impurity_improvement(c1, 0.0, left1, right1)
+            p2 = _test_criterion_impurity_improvement(c2, 0.0, left2, right2)
+            # print(left1, right1, "*", left2, right2)
+            # print(c2.printd())
             self.assertAlmostEqual(p1, p2, atol=1e-10)
 
         X = numpy.array([[1.0, 2.0, 10.0, 11.0]]).T
@@ -155,14 +153,8 @@ def test_criterions(self):
             v1 = _test_criterion_node_value(c1)
             v2 = _test_criterion_node_value(c2)
             self.assertEqual(v1, v2)
-            try:
-                # scikit-learn >= 0.24
-                p1 = _test_criterion_impurity_improvement(c1, 0.0, left1, right1)
-                p2 = _test_criterion_impurity_improvement(c2, 0.0, left2, right2)
-            except TypeError:
-                # scikit-learn < 0.24
-                p1 = _test_criterion_impurity_improvement(c1, 0.0)
-                p2 = _test_criterion_impurity_improvement(c2, 0.0)
+            p1 = _test_criterion_impurity_improvement(c1, 0.0, left1, right1)
+            p2 = _test_criterion_impurity_improvement(c2, 0.0, left2, right2)
             self.assertAlmostEqual(p1, p2)
 
     def test_decision_tree_criterion(self):
diff --git a/_unittests/ut_mlmodel/test_piecewise_decision_tree_experiment_fast.py b/_unittests/ut_mlmodel/test_piecewise_decision_tree_experiment_fast.py
@@ -104,15 +104,8 @@ def test_criterions(self):
             v2 = _test_criterion_node_value(c2)
             self.assertEqual(v1, v2)
             assert_criterion_equal(c1, c2)
-            try:
-                # scikit-learn >= 0.24
-                p1 = _test_criterion_impurity_improvement(c1, 0.0, left1, right1)
-                p2 = _test_criterion_impurity_improvement(c2, 0.0, left2, right2)
-            except TypeError:
-                # scikit-learn < 0.23
-                p1 = _test_criterion_impurity_improvement(c1, 0.0)
-                p2 = _test_criterion_impurity_improvement(c2, 0.0)
-
+            p1 = _test_criterion_impurity_improvement(c1, 0.0, left1, right1)
+            p2 = _test_criterion_impurity_improvement(c2, 0.0, left2, right2)
             self.assertAlmostEqual(p1, p2)
 
         X = numpy.array([[1.0, 2.0, 10.0, 11.0]]).T
@@ -144,17 +137,11 @@ def test_criterions(self):
             v1 = _test_criterion_node_value(c1)
             v2 = _test_criterion_node_value(c2)
             self.assertEqual(v1, v2)
-            try:
-                # scikit-learn >= 0.24
-                p1 = _test_criterion_impurity_improvement(c1, 0.0, left1, right1)
-                p2 = _test_criterion_impurity_improvement(c2, 0.0, left2, right2)
-            except TypeError:
-                # scikit-learn < 0.23
-                p1 = _test_criterion_impurity_improvement(c1, 0.0)
-                p2 = _test_criterion_impurity_improvement(c2, 0.0)
+            p1 = _test_criterion_impurity_improvement(c1, 0.0, left1, right1)
+            p2 = _test_criterion_impurity_improvement(c2, 0.0, left2, right2)
             self.assertAlmostEqual(p1, p2)
 
-    def test_decision_tree_criterion(self):
+    def test_decision_tree_criterion_fast(self):
         X = numpy.array([[1.0, 2.0, 10.0, 11.0]]).T
         y = numpy.array([0.9, 1.1, 1.9, 2.1])
         clr1 = DecisionTreeRegressor(max_depth=1)
diff --git a/_unittests/ut_mlmodel/test_piecewise_decision_tree_experiment_linear.py b/_unittests/ut_mlmodel/test_piecewise_decision_tree_experiment_linear.py
@@ -118,14 +118,8 @@ def test_criterions(self):
             v1 = _test_criterion_node_value(c1)
             v2 = _test_criterion_node_value(c2)
             self.assertEqual(v1, v2)
-            try:
-                # scikit-learn >= 0.24
-                p1 = _test_criterion_impurity_improvement(c1, 0.0, left1, right1)
-                p2 = _test_criterion_impurity_improvement(c2, 0.0, left2, right2)
-            except TypeError:
-                # scikit-learn < 0.23
-                p1 = _test_criterion_impurity_improvement(c1, 0.0)
-                p2 = _test_criterion_impurity_improvement(c2, 0.0)
+            p1 = _test_criterion_impurity_improvement(c1, 0.0, left1, right1)
+            p2 = _test_criterion_impurity_improvement(c2, 0.0, left2, right2)
             self.assertGreater(p1, p2 - 1.0)
 
             dest = numpy.empty((2,))
@@ -145,7 +139,7 @@ def test_criterions_check_value(self):
         c2.node_beta(coef)
         self.assertEqual(coef[:2], numpy.array([1, 10]))
 
-    def test_decision_tree_criterion(self):
+    def test_decision_tree_criterion_linear(self):
         X = numpy.array([[1.0, 2.0, 10.0, 11.0]]).T
         y = numpy.array([0.9, 1.1, 1.9, 2.1])
         clr1 = DecisionTreeRegressor(max_depth=1)
diff --git a/mlinsights/mlmodel/piecewise_tree_regression_criterion.pyx b/mlinsights/mlmodel/piecewise_tree_regression_criterion.pyx
@@ -6,7 +6,6 @@ cimport numpy as cnp
 cnp.import_array()
 
 from sklearn.tree._criterion cimport SIZE_t, DOUBLE_t
-from sklearn.tree._criterion cimport Criterion
 from ._piecewise_tree_regression_common cimport CommonRegressorCriterion
 
 
@@ -68,6 +67,13 @@ cdef class SimpleRegressorCriterion(CommonRegressorCriterion):
         if self.sample_i == NULL:
             self.sample_i = <SIZE_t*> calloc(n_samples, sizeof(SIZE_t))
 
+    def __str__(self):
+        "usual"
+        return (
+            f"SimpleRegressorCriterion(n_outputs={self.n_outputs}, "
+            f"n_samples={self.n_samples})"
+        )
+
     @cython.boundscheck(False)
     cdef int init(self, const DOUBLE_t[:, ::1] y,
                   const DOUBLE_t[:] sample_weight,
@@ -84,6 +90,21 @@ cdef class SimpleRegressorCriterion(CommonRegressorCriterion):
         return self.init_with_X(y, sample_weight, weighted_n_samples,
                                 sample_indices, start, end)
 
+    def printd(self):
+        "debug print"
+        rows = [str(self)]
+        rows.append(f"  start={self.start}, pos={self.pos}, end={self.end}")
+        rows.append(f"  weighted_n_samples={self.weighted_n_samples}")
+        rows.append(f"  weighted_n_node_samples={self.weighted_n_node_samples}")
+        rows.append(f"  sample_sum_w={self.sample_sum_w}")
+        rows.append(f"  sample_sum_wy={self.sample_sum_wy}")
+        rows.append(f"  weighted_n_left={self.weighted_n_left} "
+                    f"weighted_n_right={self.weighted_n_right}")
+        for ki in range(self.start, self.end):
+            rows.append(f"  ki={ki}, sample_i={self.sample_i[ki]}, "
+                        f"sample_w={self.sample_w[ki]}, sample_wy={self.sample_wy[ki]}")
+        return "\n".join(rows)
+
     @cython.boundscheck(False)
     cdef int init_with_X(self,
                          const DOUBLE_t[:, ::1] y,
diff --git a/mlinsights/mlmodel/quantile_regression.py b/mlinsights/mlmodel/quantile_regression.py
@@ -59,19 +59,13 @@ def __init__(
         positive=False,
         verbose=False,
     ):
-        try:
-            LinearRegression.__init__(
-                self,
-                fit_intercept=fit_intercept,
-                copy_X=copy_X,
-                n_jobs=n_jobs,
-                positive=positive,
-            )
-        except TypeError:
-            # scikit-learn<0.24
-            LinearRegression.__init__(
-                self, fit_intercept=fit_intercept, copy_X=copy_X, n_jobs=n_jobs
-            )
+        LinearRegression.__init__(
+            self,
+            fit_intercept=fit_intercept,
+            copy_X=copy_X,
+            n_jobs=n_jobs,
+            positive=positive,
+        )
         self.max_iter = max_iter
         self.verbose = verbose
         self.delta = delta
@@ -138,18 +132,12 @@ def compute_z(Xm, beta, Y, W, delta=0.0001):
         else:
             Xm = X
 
-        try:
-            clr = LinearRegression(
-                fit_intercept=False,
-                copy_X=self.copy_X,
-                n_jobs=self.n_jobs,
-                positive=self.positive,
-            )
-        except AttributeError:
-            # scikit-learn<0.24
-            clr = LinearRegression(
-                fit_intercept=False, copy_X=self.copy_X, n_jobs=self.n_jobs
-            )
+        clr = LinearRegression(
+            fit_intercept=False,
+            copy_X=self.copy_X,
+            n_jobs=self.n_jobs,
+            positive=self.positive,
+        )
 
         W = numpy.ones(X.shape[0]) if sample_weight is None else sample_weight
         self.n_iter_ = 0
diff --git a/mlinsights/mltree/tree_digitize.py b/mlinsights/mltree/tree_digitize.py
@@ -137,15 +137,5 @@ def add_nodes(parent, i, j, is_left):
     cl.tree_.value[:, 0, 0] = numpy.array(values, dtype=numpy.float64)
     cl.n_outputs = 1
     cl.n_outputs_ = 1
-    try:
-        # scikit-learn >= 0.24
-        cl.n_features_in_ = 1
-    except AttributeError:
-        # scikit-learn < 0.24
-        cl.n_features_ = 1
-    try:
-        # for scikit-learn<=0.23.2
-        cl.n_features_ = 1
-    except AttributeError:
-        pass
+    cl.n_features_in_ = 1
     return cl
