categorial → categorical

4 files changed, 36 insertions, 34 deletions

diff --git a/lib/cli.py b/lib/cli.py
index 3da6fce..f289d4a 100644
--- a/lib/cli.py
+++ b/lib/cli.py
@@ -576,7 +576,7 @@ def add_standard_arguments(parser):
     )
     parser.add_argument(
         "--param-shift",
-        metavar="<key>=<+|-|*|/><value>|none-to-0|categorial;...",
+        metavar="<key>=<+|-|*|/><value>|none-to-0|categorical;...",
         type=str,
         help="Adjust parameter values before passing them to model generation",
     )
@@ -695,7 +695,7 @@ def parse_shift_function(param_name, param_shift):
     elif param_shift.startswith("/"):
         param_shift_value = float(param_shift[1:])
         return lambda p: p / param_shift_value
-    elif param_shift == "categorial":
+    elif param_shift == "categorical":
         return lambda p: "=" + str(p)
     elif param_shift == "none-to-0":
         return lambda p: p or 0
diff --git a/lib/functions.py b/lib/functions.py
index 6366f0a..4940956 100644
--- a/lib/functions.py
+++ b/lib/functions.py
@@ -590,7 +590,7 @@ class SKLearnRegressionFunction(ModelFunction):
     always_predictable = True
     has_eval_arr = True
 
-    def __init__(self, value, regressor, categorial_to_index, ignore_index, **kwargs):
+    def __init__(self, value, regressor, categorical_to_index, ignore_index, **kwargs):
         # Needed for JSON export
         self.param_names = kwargs.pop("param_names")
         self.arg_count = kwargs.pop("arg_count")
@@ -601,7 +601,7 @@ class SKLearnRegressionFunction(ModelFunction):
         super().__init__(value, **kwargs)
 
         self.regressor = regressor
-        self.categorial_to_index = categorial_to_index
+        self.categorical_to_index = categorical_to_index
         self.ignore_index = ignore_index
 
         # SKLearnRegressionFunction descendants use self.param_names \ self.ignore_index as features.
@@ -649,15 +649,15 @@ class SKLearnRegressionFunction(ModelFunction):
         actual_param_list = list()
         for i, param in enumerate(param_list):
             if not self.ignore_index[i]:
-                if i in self.categorial_to_index:
+                if i in self.categorical_to_index:
                     try:
-                        actual_param_list.append(self.categorial_to_index[i][param])
+                        actual_param_list.append(self.categorical_to_index[i][param])
                     except KeyError:
                         # param was not part of training data. substitute an unused scalar.
                         # Note that all param values which were not part of training data map to the same scalar this way.
                         # This should be harmless.
                         actual_param_list.append(
-                            max(self.categorial_to_index[i].values()) + 1
+                            max(self.categorical_to_index[i].values()) + 1
                         )
                 else:
                     actual_param_list.append(int(param))
@@ -672,15 +672,17 @@ class SKLearnRegressionFunction(ModelFunction):
             actual_param_list = list()
             for i, param in enumerate(param_tuple):
                 if not self.ignore_index[i]:
-                    if i in self.categorial_to_index:
+                    if i in self.categorical_to_index:
                         try:
-                            actual_param_list.append(self.categorial_to_index[i][param])
+                            actual_param_list.append(
+                                self.categorical_to_index[i][param]
+                            )
                         except KeyError:
                             # param was not part of training data. substitute an unused scalar.
                             # Note that all param values which were not part of training data map to the same scalar this way.
                             # This should be harmless.
                             actual_param_list.append(
-                                max(self.categorial_to_index[i].values()) + 1
+                                max(self.categorical_to_index[i].values()) + 1
                             )
                     else:
                         actual_param_list.append(int(param))
@@ -691,7 +693,7 @@ class SKLearnRegressionFunction(ModelFunction):
     def to_json(self, **kwargs):
         ret = super().to_json(**kwargs)
 
-        # Note: categorial_to_index uses param_names, not feature_names
+        # Note: categorical_to_index uses param_names, not feature_names
         param_names = self.param_names + list(
             map(
                 lambda i: f"arg{i-len(self.param_names)}",
@@ -704,7 +706,7 @@ class SKLearnRegressionFunction(ModelFunction):
         ret["paramValueToIndex"] = dict(
             map(
                 lambda kv: (param_names[kv[0]], kv[1]),
-                self.categorial_to_index.items(),
+                self.categorical_to_index.items(),
             )
         )
 
@@ -958,17 +960,17 @@ class FOLFunction(ModelFunction):
         self.fit_success = False
 
     def fit(self, param_values, data, ignore_param_indexes=None):
-        self.categorial_to_scalar = bool(
-            int(os.getenv("DFATOOL_PARAM_CATEGORIAL_TO_SCALAR", "0"))
+        self.categorical_to_scalar = bool(
+            int(os.getenv("DFATOOL_PARAM_CATEGORICAL_TO_SCALAR", "0"))
         )
         second_order = int(os.getenv("DFATOOL_FOL_SECOND_ORDER", "0"))
-        fit_parameters, categorial_to_index, ignore_index = param_to_ndarray(
+        fit_parameters, categorical_to_index, ignore_index = param_to_ndarray(
             param_values,
             with_nan=False,
-            categorial_to_scalar=self.categorial_to_scalar,
+            categorical_to_scalar=self.categorical_to_scalar,
             ignore_indexes=ignore_param_indexes,
         )
-        self.categorial_to_index = categorial_to_index
+        self.categorical_to_index = categorical_to_index
         self.ignore_index = ignore_index
         fit_parameters = fit_parameters.swapaxes(0, 1)
 
@@ -1052,15 +1054,15 @@ class FOLFunction(ModelFunction):
         actual_param_list = list()
         for i, param in enumerate(param_list):
             if not self.ignore_index[i]:
-                if i in self.categorial_to_index:
+                if i in self.categorical_to_index:
                     try:
-                        actual_param_list.append(self.categorial_to_index[i][param])
+                        actual_param_list.append(self.categorical_to_index[i][param])
                     except KeyError:
                         # param was not part of training data. substitute an unused scalar.
                         # Note that all param values which were not part of training data map to the same scalar this way.
                         # This should be harmless.
                         actual_param_list.append(
-                            max(self.categorial_to_index[i].values()) + 1
+                            max(self.categorical_to_index[i].values()) + 1
                         )
                 else:
                     actual_param_list.append(int(param))
@@ -1105,7 +1107,7 @@ class FOLFunction(ModelFunction):
 
     def hyper_to_dref(self):
         return {
-            "fol/categorial to scalar": int(self.categorial_to_scalar),
+            "fol/categorical to scalar": int(self.categorical_to_scalar),
         }
 
 
diff --git a/lib/parameters.py b/lib/parameters.py
index 2e3878f..f367eb9 100644
--- a/lib/parameters.py
+++ b/lib/parameters.py
@@ -918,7 +918,7 @@ class ModelAttribute:
         :param data: Measurements. [data 1, data 2, data 3, ...]
         :param with_function_leaves: Use fitted function sets to generate function leaves for scalar parameters
         :param with_nonbinary_nodes: Allow non-binary nodes for enum and scalar parameters (i.e., nodes with more than two children)
-        :param with_sklearn_cart: Use `sklearn.tree.DecisionTreeRegressor` CART implementation for tree generation. Does not support categorial (enum)
+        :param with_sklearn_cart: Use `sklearn.tree.DecisionTreeRegressor` CART implementation for tree generation. Does not support categorical (enum)
             and sparse parameters. Both are ignored during fitting. All other options are ignored as well.
         :param with_sklearn_decart: Use `sklearn.tree.DecisionTreeRegressor` CART implementation in DECART mode for tree generation. CART limitations
             apply; additionaly, scalar parameters are ignored during fitting.
@@ -928,8 +928,8 @@ class ModelAttribute:
         :returns: SplitFunction or StaticFunction
         """
 
-        categorial_to_scalar = bool(
-            int(os.getenv("DFATOOL_PARAM_CATEGORIAL_TO_SCALAR", "0"))
+        categorical_to_scalar = bool(
+            int(os.getenv("DFATOOL_PARAM_CATEGORICAL_TO_SCALAR", "0"))
         )
         if with_function_leaves is None:
             with_function_leaves = bool(
@@ -969,13 +969,13 @@ class ModelAttribute:
                 fit_parameters, category_to_index, ignore_index = param_to_ndarray(
                     parameters,
                     with_nan=False,
-                    categorial_to_scalar=categorial_to_scalar,
+                    categorical_to_scalar=categorical_to_scalar,
                 )
             elif with_sklearn_decart:
                 fit_parameters, category_to_index, ignore_index = param_to_ndarray(
                     parameters,
                     with_nan=False,
-                    categorial_to_scalar=categorial_to_scalar,
+                    categorical_to_scalar=categorical_to_scalar,
                     ignore_indexes=self.scalar_param_indexes,
                 )
             if fit_parameters.shape[1] == 0:
@@ -1071,7 +1071,7 @@ class ModelAttribute:
                 reg_lambda=reg_lambda,
             )
             fit_parameters, category_to_index, ignore_index = param_to_ndarray(
-                parameters, with_nan=False, categorial_to_scalar=categorial_to_scalar
+                parameters, with_nan=False, categorical_to_scalar=categorical_to_scalar
             )
             if fit_parameters.shape[1] == 0:
                 logger.warning(
@@ -1159,7 +1159,7 @@ class ModelAttribute:
                 criterion=criterion,
             )
             fit_parameters, category_to_index, ignore_index = param_to_ndarray(
-                parameters, with_nan=False, categorial_to_scalar=categorial_to_scalar
+                parameters, with_nan=False, categorical_to_scalar=categorical_to_scalar
             )
             if fit_parameters.shape[1] == 0:
                 logger.warning(
diff --git a/lib/utils.py b/lib/utils.py
index d6cdfc5..c16e419 100644
--- a/lib/utils.py
+++ b/lib/utils.py
@@ -289,7 +289,7 @@ def partition_by_param(data, param_values, ignore_parameters=list()):
 
 
 def param_to_ndarray(
-    param_tuples, with_nan=True, categorial_to_scalar=False, ignore_indexes=list()
+    param_tuples, with_nan=True, categorical_to_scalar=False, ignore_indexes=list()
 ):
     has_nan = dict()
     has_non_numeric = dict()
@@ -297,7 +297,7 @@ def param_to_ndarray(
     category_to_scalar = dict()
 
     logger.debug(
-        f"converting param_to_ndarray(with_nan={with_nan}, categorial_to_scalar={categorial_to_scalar}, ignore_indexes={ignore_indexes})"
+        f"converting param_to_ndarray(with_nan={with_nan}, categorical_to_scalar={categorical_to_scalar}, ignore_indexes={ignore_indexes})"
     )
 
     for param_tuple in param_tuples:
@@ -307,7 +307,7 @@ def param_to_ndarray(
                     has_nan[i] = True
                 else:
                     has_non_numeric[i] = True
-                if categorial_to_scalar and param is not None:
+                if categorical_to_scalar and param is not None:
                     if not i in distinct_values:
                         distinct_values[i] = set()
                     distinct_values[i].add(param)
@@ -320,7 +320,7 @@ def param_to_ndarray(
 
     ignore_index = dict()
     for i in range(len(param_tuples[0])):
-        if has_non_numeric.get(i, False) and not categorial_to_scalar:
+        if has_non_numeric.get(i, False) and not categorical_to_scalar:
             ignore_index[i] = True
         elif not with_nan and has_nan.get(i, False):
             ignore_index[i] = True
@@ -337,7 +337,7 @@ def param_to_ndarray(
             if not ignore_index[i]:
                 if i in category_to_scalar and not is_numeric(param):
                     ret_tuple.append(category_to_scalar[i][param])
-                elif categorial_to_scalar:
+                elif categorical_to_scalar:
                     ret_tuple.append(soft_cast_int(param))
                 else:
                     ret_tuple.append(param)
@@ -357,7 +357,7 @@ def param_dict_to_list(param_dict, parameter_names, default=None):
 
 def observations_enum_to_bool(observations: list, kconfig=False):
     """
-    Convert enum / categorial observations to boolean-only ones.
+    Convert enum / categorical observations to boolean-only ones.
     'observations' is altered in-place.
 
     DEPRECATED.