Merge pull request #373 from sudo-hannes/update-force-all-finite-to-ensure-all-finite

Replace deprecated force_all_finite parameter and update scikit-learn version requirement

Author: guillermo-navas-palencia

README.rst

@@ -81,7 +81,7 @@ OptBinning requires
 * ortools (>=9.4)
 * pandas
 * ropwr (>=1.0.0)
-* scikit-learn (>=1.0.2)
+* scikit-learn (>=1.6.0)
 * scipy (>=1.6.0)
 
 OptBinning[distributed] requires additional packages

optbinning/binning/binning.py

@@ -793,7 +793,7 @@ def _fit(self, x, y, sample_weight, check_input):
                 if self.dtype == "numerical":
                     user_splits = check_array(
                         self.user_splits, ensure_2d=False, dtype=None,
-                        force_all_finite=True)
+                        ensure_all_finite=True)
 
                     if len(set(user_splits)) != len(user_splits):
                         raise ValueError("User splits are not unique.")

optbinning/binning/binning_process.py

@@ -1085,10 +1085,10 @@ def _fit(self, X, y, sample_weight, check_input):
         # check X and y data
         if check_input:
             X = check_array(X, ensure_2d=False, dtype=None,
-                            force_all_finite='allow-nan')
+                            ensure_all_finite='allow-nan')
 
             y = check_array(y, ensure_2d=False, dtype=None,
-                            force_all_finite=True)
+                            ensure_all_finite=True)
 
             check_consistent_length(X, y)
 

optbinning/binning/continuous_binning.py

@@ -642,7 +642,7 @@ def _fit(self, x, y, sample_weight, check_input):
                 if self.dtype == "numerical":
                     user_splits = check_array(
                         self.user_splits, ensure_2d=False, dtype=None,
-                        force_all_finite=True)
+                        ensure_all_finite=True)
 
                     if len(set(user_splits)) != len(user_splits):
                         raise ValueError("User splits are not unique.")

optbinning/binning/mdlp.py

@@ -99,8 +99,8 @@ def fit(self, x, y):
     def _fit(self, x, y):
         _check_parameters(**self.get_params())
 
-        x = check_array(x, ensure_2d=False, force_all_finite=True)
-        y = check_array(y, ensure_2d=False, force_all_finite=True)
+        x = check_array(x, ensure_2d=False, ensure_all_finite=True)
+        y = check_array(y, ensure_2d=False, ensure_all_finite=True)
 
         idx = np.argsort(x)
         x = x[idx]

optbinning/binning/metrics.py

@@ -14,8 +14,8 @@
 
 
 def _check_x_y(x, y):
-    x = check_array(x, ensure_2d=False, force_all_finite=True)
-    y = check_array(y, ensure_2d=False, force_all_finite=True)
+    x = check_array(x, ensure_2d=False, ensure_all_finite=True)
+    y = check_array(y, ensure_2d=False, ensure_all_finite=True)
 
     check_consistent_length(x, y)
 

optbinning/binning/multiclass_binning.py

@@ -565,7 +565,7 @@ def _fit(self, x, y, check_input):
                             .format(n_splits))
 
             user_splits = check_array(self.user_splits, ensure_2d=False,
-                                      dtype=None, force_all_finite=True)
+                                      dtype=None, ensure_all_finite=True)
 
             if len(set(user_splits)) != len(user_splits):
                 raise ValueError("User splits are not unique.")

optbinning/binning/multidimensional/preprocessing_2d.py

@@ -53,13 +53,13 @@ def split_data_2d(dtype_x, dtype_y, x, y, z, special_codes_x=None,
     """
     if check_input:
         x = check_array(x, ensure_2d=False, dtype=None,
-                        force_all_finite='allow-nan')
+                        ensure_all_finite='allow-nan')
 
         y = check_array(y, ensure_2d=False, dtype=None,
-                        force_all_finite='allow-nan')
+                        ensure_all_finite='allow-nan')
 
         z = check_array(z, ensure_2d=False, dtype=None,
-                        force_all_finite=True)
+                        ensure_all_finite=True)
 
         check_consistent_length(x, y, z)
 

optbinning/binning/multidimensional/transformations_2d.py

@@ -121,10 +121,10 @@ def transform_binary_target(dtype_x, dtype_y, splits_x, splits_y, x, y,
 
     if check_input:
         x = check_array(x, ensure_2d=False, dtype=None,
-                        force_all_finite='allow-nan')
+                        ensure_all_finite='allow-nan')
 
         y = check_array(y, ensure_2d=False, dtype=None,
-                        force_all_finite='allow-nan')
+                        ensure_all_finite='allow-nan')
 
     x = np.asarray(x)
     y = np.asarray(y)
@@ -198,10 +198,10 @@ def transform_continuous_target(dtype_x, dtype_y, splits_x, splits_y, x, y,
 
     if check_input:
         x = check_array(x, ensure_2d=False, dtype=None,
-                        force_all_finite='allow-nan')
+                        ensure_all_finite='allow-nan')
 
         y = check_array(y, ensure_2d=False, dtype=None,
-                        force_all_finite='allow-nan')
+                        ensure_all_finite='allow-nan')
 
     x = np.asarray(x)
     y = np.asarray(y)

optbinning/binning/piecewise/transformations.py

@@ -72,7 +72,7 @@ def transform_binary_target(splits, x, c, lb, ub, n_nonevent, n_event,
 
     if check_input:
         x = check_array(x, ensure_2d=False, dtype=None,
-                        force_all_finite='allow-nan')
+                        ensure_all_finite='allow-nan')
 
     x = np.asarray(x)
 
@@ -144,7 +144,7 @@ def transform_continuous_target(splits, x, c, lb, ub, n_records_special,
 
     if check_input:
         x = check_array(x, ensure_2d=False, dtype=None,
-                        force_all_finite='allow-nan')
+                        ensure_all_finite='allow-nan')
 
     x = np.asarray(x)