Update version and notebooks

notebooks/gridsearch.ipynb

@@ -66,7 +66,8 @@
         "id": "z9Q-YUfBDZEq",
         "colab_type": "code",
         "colab": {},
-        "outputId": "afc822fb-f16a-4302-8a67-2b9e2880159b"
+        "outputId": "afc822fb-f16a-4302-8a67-2b9e2880159b",
+        "tags": []
       },
       "source": [
         "random_state=1\n",
@@ -112,7 +113,7 @@
         {
           "output_type": "stream",
           "name": "stdout",
-          "text": "Fraud: 0.173% 492\nValid: 99.827% 284315\nX.shape (1492, 28)  y.shape (1492,)\nFraud: 33.244% 496\nValid: 66.756% 996\n"
+          "text": "Fraud: 0.173% 492\nValid: 99.827% 284315\nX.shape (1492, 28)  y.shape (1492,)\nFraud: 32.976% 492\nValid: 67.024% 1000\n"
         }
       ]
     },
@@ -137,25 +138,25 @@
         "    'learning_rate': [.5, 1],\n",
         "    'base_estimator__tol': [.1,  1e-02],\n",
         "    'base_estimator__max_depth': [3, 5],\n",
-        "    'base_estimator__C': [1, 3],\n",
+        "    'base_estimator__C': [7, 55],\n",
         "    'base_estimator__kernel': ['linear', 'poly', 'rbf']\n",
         "}"
       ],
-      "execution_count": 9,
+      "execution_count": 5,
       "outputs": []
     },
     {
       "cell_type": "code",
-      "execution_count": 14,
+      "execution_count": 6,
       "metadata": {},
       "outputs": [
         {
           "output_type": "execute_result",
           "data": {
-            "text/plain": "{'C': 1.0,\n 'degree': 3,\n 'gamma': 'scale',\n 'kernel': 'linear',\n 'max_depth': None,\n 'max_iter': 1000,\n 'min_samples_split': 0,\n 'random_state': None,\n 'tol': 0.0001}"
+            "text/plain": "{'C': 1.0,\n 'criterion': 'gini',\n 'degree': 3,\n 'gamma': 'scale',\n 'kernel': 'linear',\n 'max_depth': None,\n 'max_features': None,\n 'max_iter': 1000,\n 'min_samples_split': 0,\n 'random_state': None,\n 'split_criteria': 'max_samples',\n 'splitter': 'random',\n 'tol': 0.0001}"
           },
           "metadata": {},
-          "execution_count": 14
+          "execution_count": 6
         }
       ],
       "source": [
@@ -168,28 +169,29 @@
         "id": "CrcB8o6EDZE5",
         "colab_type": "code",
         "colab": {},
-        "outputId": "7703413a-d563-4289-a13b-532f38f82762"
+        "outputId": "7703413a-d563-4289-a13b-532f38f82762",
+        "tags": []
       },
       "source": [
         "random_state=2020\n",
-        "clf = AdaBoostClassifier(random_state=random_state)\n",
+        "clf = AdaBoostClassifier(random_state=random_state, algorithm=\"SAMME\")\n",
         "grid = GridSearchCV(clf, parameters, verbose=10, n_jobs=-1, return_train_score=True)\n",
         "grid.fit(Xtrain, ytrain)"
       ],
-      "execution_count": 11,
+      "execution_count": 7,
       "outputs": [
         {
           "output_type": "stream",
           "name": "stdout",
-          "text": "Fitting 5 folds for each of 96 candidates, totalling 480 fits\n[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n[Parallel(n_jobs=-1)]: Done   2 tasks      | elapsed:    3.6s\n[Parallel(n_jobs=-1)]: Done   9 tasks      | elapsed:    4.2s\n[Parallel(n_jobs=-1)]: Done  16 tasks      | elapsed:    4.8s\n[Parallel(n_jobs=-1)]: Done  25 tasks      | elapsed:    5.3s\n[Parallel(n_jobs=-1)]: Done  34 tasks      | elapsed:    6.2s\n[Parallel(n_jobs=-1)]: Done  45 tasks      | elapsed:    7.2s\n[Parallel(n_jobs=-1)]: Done  56 tasks      | elapsed:    8.9s\n[Parallel(n_jobs=-1)]: Done  69 tasks      | elapsed:   10.7s\n[Parallel(n_jobs=-1)]: Done  82 tasks      | elapsed:   12.7s\n[Parallel(n_jobs=-1)]: Done  97 tasks      | elapsed:   16.7s\n[Parallel(n_jobs=-1)]: Done 112 tasks      | elapsed:   19.4s\n[Parallel(n_jobs=-1)]: Done 129 tasks      | elapsed:   24.4s\n[Parallel(n_jobs=-1)]: Done 146 tasks      | elapsed:   29.3s\n[Parallel(n_jobs=-1)]: Done 165 tasks      | elapsed:   32.7s\n[Parallel(n_jobs=-1)]: Done 184 tasks      | elapsed:   36.4s\n[Parallel(n_jobs=-1)]: Done 205 tasks      | elapsed:   39.7s\n[Parallel(n_jobs=-1)]: Done 226 tasks      | elapsed:   43.7s\n[Parallel(n_jobs=-1)]: Done 249 tasks      | elapsed:   46.6s\n[Parallel(n_jobs=-1)]: Done 272 tasks      | elapsed:   48.8s\n[Parallel(n_jobs=-1)]: Done 297 tasks      | elapsed:   52.0s\n[Parallel(n_jobs=-1)]: Done 322 tasks      | elapsed:   55.9s\n[Parallel(n_jobs=-1)]: Done 349 tasks      | elapsed:  1.0min\n[Parallel(n_jobs=-1)]: Done 376 tasks      | elapsed:  1.2min\n[Parallel(n_jobs=-1)]: Done 405 tasks      | elapsed:  1.3min\n[Parallel(n_jobs=-1)]: Done 434 tasks      | elapsed:  1.3min\n[Parallel(n_jobs=-1)]: Done 465 tasks      | elapsed:  1.4min\n[Parallel(n_jobs=-1)]: Done 480 out of 480 | elapsed:  1.5min finished\n"
+          "text": "Fitting 5 folds for each of 96 candidates, totalling 480 fits\n[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n[Parallel(n_jobs=-1)]: Done   2 tasks      | elapsed:    2.0s\n[Parallel(n_jobs=-1)]: Done   9 tasks      | elapsed:    2.4s\n[Parallel(n_jobs=-1)]: Done  16 tasks      | elapsed:    2.7s\n[Parallel(n_jobs=-1)]: Done  25 tasks      | elapsed:    3.3s\n[Parallel(n_jobs=-1)]: Done  34 tasks      | elapsed:    4.3s\n[Parallel(n_jobs=-1)]: Done  45 tasks      | elapsed:    5.3s\n[Parallel(n_jobs=-1)]: Done  56 tasks      | elapsed:    6.6s\n[Parallel(n_jobs=-1)]: Done  69 tasks      | elapsed:    8.1s\n[Parallel(n_jobs=-1)]: Done  82 tasks      | elapsed:    9.4s\n[Parallel(n_jobs=-1)]: Done  97 tasks      | elapsed:   10.1s\n[Parallel(n_jobs=-1)]: Done 112 tasks      | elapsed:   11.1s\n[Parallel(n_jobs=-1)]: Done 129 tasks      | elapsed:   12.3s\n[Parallel(n_jobs=-1)]: Done 146 tasks      | elapsed:   13.6s\n[Parallel(n_jobs=-1)]: Done 165 tasks      | elapsed:   14.9s\n[Parallel(n_jobs=-1)]: Done 184 tasks      | elapsed:   16.2s\n[Parallel(n_jobs=-1)]: Done 205 tasks      | elapsed:   17.6s\n[Parallel(n_jobs=-1)]: Done 226 tasks      | elapsed:   19.1s\n[Parallel(n_jobs=-1)]: Done 249 tasks      | elapsed:   21.6s\n[Parallel(n_jobs=-1)]: Done 272 tasks      | elapsed:   25.9s\n[Parallel(n_jobs=-1)]: Done 297 tasks      | elapsed:   30.4s\n[Parallel(n_jobs=-1)]: Done 322 tasks      | elapsed:   36.7s\n[Parallel(n_jobs=-1)]: Done 349 tasks      | elapsed:   38.1s\n[Parallel(n_jobs=-1)]: Done 376 tasks      | elapsed:   39.6s\n[Parallel(n_jobs=-1)]: Done 405 tasks      | elapsed:   41.9s\n[Parallel(n_jobs=-1)]: Done 434 tasks      | elapsed:   44.9s\n[Parallel(n_jobs=-1)]: Done 465 tasks      | elapsed:   48.2s\n[Parallel(n_jobs=-1)]: Done 480 out of 480 | elapsed:   49.2s finished\n"
         },
         {
           "output_type": "execute_result",
           "data": {
-            "text/plain": "GridSearchCV(estimator=AdaBoostClassifier(random_state=2020), n_jobs=-1,\n             param_grid={'base_estimator': [Stree(C=1, max_depth=3, tol=0.1)],\n                         'base_estimator__C': [1, 3],\n                         'base_estimator__kernel': ['linear', 'poly', 'rbf'],\n                         'base_estimator__max_depth': [3, 5],\n                         'base_estimator__tol': [0.1, 0.01],\n                         'learning_rate': [0.5, 1], 'n_estimators': [10, 25]},\n             return_train_score=True, verbose=10)"
+            "text/plain": "GridSearchCV(estimator=AdaBoostClassifier(algorithm='SAMME', random_state=2020),\n             n_jobs=-1,\n             param_grid={'base_estimator': [Stree(C=55, max_depth=3, tol=0.01)],\n                         'base_estimator__C': [7, 55],\n                         'base_estimator__kernel': ['linear', 'poly', 'rbf'],\n                         'base_estimator__max_depth': [3, 5],\n                         'base_estimator__tol': [0.1, 0.01],\n                         'learning_rate': [0.5, 1], 'n_estimators': [10, 25]},\n             return_train_score=True, verbose=10)"
           },
           "metadata": {},
-          "execution_count": 11
+          "execution_count": 7
         }
       ]
     },
@@ -199,19 +201,20 @@
         "id": "ZjX88NoYDZE8",
         "colab_type": "code",
         "colab": {},
-        "outputId": "285163c8-fa33-4915-8ae7-61c4f7844344"
+        "outputId": "285163c8-fa33-4915-8ae7-61c4f7844344",
+        "tags": []
       },
       "source": [
         "print(\"Best estimator: \", grid.best_estimator_)\n",
         "print(\"Best hyperparameters: \", grid.best_params_)\n",
         "print(\"Best accuracy: \", grid.best_score_)"
       ],
-      "execution_count": 16,
+      "execution_count": 8,
       "outputs": [
         {
           "output_type": "stream",
           "name": "stdout",
-          "text": "Best estimator:  AdaBoostClassifier(base_estimator=Stree(C=1, max_depth=3, tol=0.1),\n                   learning_rate=0.5, n_estimators=10, random_state=2020)\nBest hyperparameters:  {'base_estimator': Stree(C=1, max_depth=3, tol=0.1), 'base_estimator__C': 1, 'base_estimator__kernel': 'linear', 'base_estimator__max_depth': 3, 'base_estimator__tol': 0.1, 'learning_rate': 0.5, 'n_estimators': 10}\nBest accuracy:  0.9492316893632683\n"
+          "text": "Best estimator:  AdaBoostClassifier(algorithm='SAMME',\n                   base_estimator=Stree(C=55, max_depth=3, tol=0.01),\n                   learning_rate=0.5, n_estimators=25, random_state=2020)\nBest hyperparameters:  {'base_estimator': Stree(C=55, max_depth=3, tol=0.01), 'base_estimator__C': 55, 'base_estimator__kernel': 'linear', 'base_estimator__max_depth': 3, 'base_estimator__tol': 0.01, 'learning_rate': 0.5, 'n_estimators': 25}\nBest accuracy:  0.9559440559440558\n"
         }
       ]
     }

setup.py

@@ -1,6 +1,6 @@
 import setuptools
 
-__version__ = "0.9rc4"
+__version__ = "0.9rc5"
 __author__ = "Ricardo Montañana Gómez"
 
 

stree/Strees.py

@@ -6,24 +6,25 @@ __version__ = "0.9"
 Build an oblique tree classifier based on SVM Trees
 """
 
-from __future__ import annotations
 import os
+import numbers
 import random
 import warnings
-from typing import Optional, List, Union, Tuple
 from math import log
 from itertools import combinations
-import numpy as np  # type: ignore
-from sklearn.base import BaseEstimator, ClassifierMixin  # type: ignore
-from sklearn.svm import SVC, LinearSVC  # type: ignore
-from sklearn.utils.multiclass import (  # type: ignore
-    check_classification_targets,
-)
-from sklearn.exceptions import ConvergenceWarning  # type: ignore
-from sklearn.utils.validation import (  # type: ignore
+import numpy as np
+from sklearn.base import BaseEstimator, ClassifierMixin
+from sklearn.svm import SVC, LinearSVC
+from sklearn.utils import check_consistent_length
+from sklearn.utils.multiclass import check_classification_targets
+from sklearn.exceptions import ConvergenceWarning
+from sklearn.utils.validation import (
+    check_X_y,
+    check_array,
     check_is_fitted,
     _check_sample_weight,
 )
+from sklearn.metrics._classification import _weighted_sum, _check_targets
 
 
 class Snode:
@@ -33,7 +34,7 @@ class Snode:
 
     def __init__(
         self,
-        clf: Union[SVC, LinearSVC],
+        clf: SVC,
         X: np.ndarray,
         y: np.ndarray,
         features: np.array,
@@ -41,25 +42,24 @@ class Snode:
         title: str,
         weight: np.ndarray = None,
     ):
-        self._clf: Union[SVC, LinearSVC] = clf
-        self._title: str = title
-        self._belief: float = 0.0
+        self._clf = clf
+        self._title = title
+        self._belief = 0.0
         # Only store dataset in Testing
-        self._X: Optional[np.array] = X if os.environ.get(
-            "TESTING", "NS"
-        ) != "NS" else None
-        self._y: np.array = y
-        self._down: Optional[Snode] = None
-        self._up: Optional[Snode] = None
+        self._X = X if os.environ.get("TESTING", "NS") != "NS" else None
+        self._y = y
+        self._down = None
+        self._up = None
         self._class = None
-        self._sample_weight: Optional[np.array] = (
+        self._feature = None
+        self._sample_weight = (
             weight if os.environ.get("TESTING", "NS") != "NS" else None
         )
-        self._features: Tuple[int, ...] = features
-        self._impurity: float = impurity
+        self._features = features
+        self._impurity = impurity
 
     @classmethod
-    def copy(cls, node: Snode) -> Snode:
+    def copy(cls, node: "Snode") -> "Snode":
         return cls(
             node._clf,
             node._X,
@@ -69,22 +69,22 @@ class Snode:
             node._title,
         )
 
-    def set_down(self, son: Snode) -> None:
+    def set_down(self, son):
         self._down = son
 
-    def set_up(self, son: Snode) -> None:
+    def set_up(self, son):
         self._up = son
 
     def is_leaf(self) -> bool:
         return self._up is None and self._down is None
 
-    def get_down(self) -> Optional[Snode]:
+    def get_down(self) -> "Snode":
         return self._down
 
-    def get_up(self) -> Optional[Snode]:
+    def get_up(self) -> "Snode":
         return self._up
 
-    def make_predictor(self) -> None:
+    def make_predictor(self):
         """Compute the class of the predictor and its belief based on the
         subdataset of the node only if it is a leaf
         """
@@ -123,11 +123,11 @@ class Siterator:
     """Stree preorder iterator
     """
 
-    def __init__(self, tree: Optional[Snode]):
-        self._stack: List[Snode] = []
+    def __init__(self, tree: Snode):
+        self._stack = []
         self._push(tree)
 
-    def _push(self, node: Optional[Snode]) -> None:
+    def _push(self, node: Snode):
         if node is not None:
             self._stack.append(node)
 
@@ -143,21 +143,21 @@ class Siterator:
 class Splitter:
     def __init__(
         self,
-        clf: Union[SVC, LinearSVC] = None,
-        criterion: str = "",
-        splitter_type: str = "",
-        criteria: str = "",
-        min_samples_split: int = 0,
-        random_state: Optional[int] = None,
+        clf: SVC = None,
+        criterion: str = None,
+        splitter_type: str = None,
+        criteria: str = None,
+        min_samples_split: int = None,
+        random_state=None,
     ):
-        self._clf: Union[SVC, LinearSVC] = clf
-        self._random_state: Optional[int] = random_state
+        self._clf = clf
+        self._random_state = random_state
         if random_state is not None:
             random.seed(random_state)
-        self._criterion: str = criterion
-        self._min_samples_split: int = min_samples_split
-        self._criteria: str = criteria
-        self._splitter_type: str = splitter_type
+        self._criterion = criterion
+        self._min_samples_split = min_samples_split
+        self._criteria = criteria
+        self._splitter_type = splitter_type
 
         if clf is None:
             raise ValueError(f"clf has to be a sklearn estimator, got({clf})")
@@ -186,7 +186,7 @@ class Splitter:
     @staticmethod
     def _gini(y: np.array) -> float:
         _, count = np.unique(y, return_counts=True)
-        return float(1 - np.sum(np.square(count / np.sum(count))))
+        return 1 - np.sum(np.square(count / np.sum(count)))
 
     @staticmethod
     def _entropy(y: np.array) -> float:
@@ -220,7 +220,7 @@ class Splitter:
         if samples == 0:
             return 0.0
         else:
-            result = float(
+            result = (
                 imp_prev
                 - (card_up / samples) * imp_up
                 - (card_dn / samples) * imp_dn
@@ -228,13 +228,10 @@ class Splitter:
             return result
 
     def _select_best_set(
-        self,
-        dataset: np.array,
-        labels: np.array,
-        features_sets: List[Tuple[int, ...]],
-    ) -> Tuple[int, ...]:
-        max_gain: float = 0.0
-        selected: Union[Tuple[int, ...], None] = None
+        self, dataset: np.array, labels: np.array, features_sets: list
+    ) -> list:
+        max_gain = 0
+        selected = None
         warnings.filterwarnings("ignore", category=ConvergenceWarning)
         for feature_set in features_sets:
             self._clf.fit(dataset[:, feature_set], labels)
@@ -268,14 +265,14 @@ class Splitter:
 
     def get_subspace(
         self, dataset: np.array, labels: np.array, max_features: int
-    ) -> Tuple[np.array, np.array]:
+    ) -> list:
         """Return the best subspace to make a split
         """
         indices = self._get_subspaces_set(dataset, labels, max_features)
         return dataset[:, indices], indices
 
     @staticmethod
-    def _min_distance(data: np.array, _: np.array) -> np.array:
+    def _min_distance(data: np.array, _) -> np.array:
         """Assign class to min distances
 
         return a vector of classes so partition can separate class 0 from
@@ -291,7 +288,7 @@ class Splitter:
         return np.argmin(data, axis=1)
 
     @staticmethod
-    def _max_distance(data: np.array, _: np.array) -> np.array:
+    def _max_distance(data: np.array, _) -> np.array:
         """Assign class to max distances
 
         return a vector of classes so partition can separate class 0 from
@@ -323,7 +320,7 @@ class Splitter:
         selected = np.argmax(samples)
         return data[:, selected]
 
-    def partition(self, samples: np.array, node: Snode) -> None:
+    def partition(self, samples: np.array, node: Snode):
         """Set the criteria to split arrays. Compute the indices of the samples
         that should go to one side of the tree (down)
 
@@ -351,7 +348,7 @@ class Splitter:
         """
         return node._clf.decision_function(data[:, node._features])
 
-    def part(self, origin: np.array) -> Tuple[np.array, np.array]:
+    def part(self, origin: np.array) -> list:
         """Split an array in two based on indices (down) and its complement
 
         :param origin: dataset to split
@@ -362,13 +359,13 @@ class Splitter:
         :rtype: list
         """
         up = ~self._down
-        return (
+        return [
             origin[up] if any(up) else None,
             origin[self._down] if any(self._down) else None,
-        )
+        ]
 
 
-class Stree(BaseEstimator, ClassifierMixin):  # type: ignore
+class Stree(BaseEstimator, ClassifierMixin):
     """Estimator that is based on binary trees of svm nodes
     can deal with sample_weights in predict, used in boosting sklearn methods
     inheriting from BaseEstimator implements get_params and set_params methods
@@ -381,34 +378,42 @@ class Stree(BaseEstimator, ClassifierMixin):  # type: ignore
         C: float = 1.0,
         kernel: str = "linear",
         max_iter: int = 1000,
-        random_state: Optional[int] = None,
-        max_depth: Optional[int] = None,
+        random_state: int = None,
+        max_depth: int = None,
         tol: float = 1e-4,
         degree: int = 3,
-        gamma: Union[float, str] = "scale",
+        gamma="scale",
         split_criteria: str = "max_samples",
         criterion: str = "gini",
         min_samples_split: int = 0,
-        max_features: Optional[Union[str, int, float]] = None,
+        max_features=None,
         splitter: str = "random",
     ):
         self.max_iter = max_iter
-        self.C: float = C
-        self.kernel: str = kernel
-        self.random_state: Optional[int] = random_state
-        self.max_depth: Optional[int] = max_depth
-        self.tol: float = tol
-        self.gamma: Union[float, str] = gamma
-        self.degree: int = degree
-        self.min_samples_split: int = min_samples_split
-        self.split_criteria: str = split_criteria
-        self.max_features: Union[str, int, float, None] = max_features
-        self.criterion: str = criterion
-        self.splitter: str = splitter
+        self.C = C
+        self.kernel = kernel
+        self.random_state = random_state
+        self.max_depth = max_depth
+        self.tol = tol
+        self.gamma = gamma
+        self.degree = degree
+        self.min_samples_split = min_samples_split
+        self.split_criteria = split_criteria
+        self.max_features = max_features
+        self.criterion = criterion
+        self.splitter = splitter
+
+    def _more_tags(self) -> dict:
+        """Required by sklearn to supply features of the classifier
+
+        :return: the tag required
+        :rtype: dict
+        """
+        return {"requires_y": True}
 
     def fit(
         self, X: np.ndarray, y: np.ndarray, sample_weight: np.array = None
-    ) -> Stree:
+    ) -> "Stree":
         """Build the tree based on the dataset of samples and its labels
 
         :param X: dataset of samples to make predictions
@@ -437,11 +442,13 @@ class Stree(BaseEstimator, ClassifierMixin):  # type: ignore
                 f"Maximum depth has to be greater than 1... got (max_depth=\
                     {self.max_depth})"
             )
+
         check_classification_targets(y)
-        X, y = self._validate_data(X, y)
+        X, y = check_X_y(X, y)
         sample_weight = _check_sample_weight(
             sample_weight, X, dtype=np.float64
         )
+        check_classification_targets(y)
         # Initialize computed parameters
         self.splitter_ = Splitter(
             clf=self._build_clf(),
@@ -457,6 +464,8 @@ class Stree(BaseEstimator, ClassifierMixin):  # type: ignore
         self.n_classes_ = self.classes_.shape[0]
         self.n_iter_ = self.max_iter
         self.depth_ = 0
+        self.n_features_ = X.shape[1]
+        self.n_features_in_ = X.shape[1]
         self.max_features_ = self._initialize_max_features()
         self.tree_ = self.train(X, y, sample_weight, 1, "root")
         self._build_predictor()
@@ -469,7 +478,7 @@ class Stree(BaseEstimator, ClassifierMixin):  # type: ignore
         sample_weight: np.ndarray,
         depth: int,
         title: str,
-    ) -> Optional[Snode]:
+    ) -> Snode:
         """Recursive function to split the original dataset into predictor
         nodes (leaves)
 
@@ -530,25 +539,15 @@ class Stree(BaseEstimator, ClassifierMixin):  # type: ignore
                 title=title + ", <cgaf>",
                 weight=sample_weight,
             )
-        node.set_up(
-            self.train(  # type: ignore
-                X_U, y_u, sw_u, depth + 1, title + " - Up"
-            )
-        )
-        node.set_down(
-            self.train(  # type: ignore
-                X_D, y_d, sw_d, depth + 1, title + " - Down"
-            )
-        )
+        node.set_up(self.train(X_U, y_u, sw_u, depth + 1, title + " - Up"))
+        node.set_down(self.train(X_D, y_d, sw_d, depth + 1, title + " - Down"))
         return node
 
-    def _build_predictor(self) -> None:
+    def _build_predictor(self):
         """Process the leaves to make them predictors
         """
 
-        def run_tree(node: Optional[Snode]) -> None:
-            if node is None:
-                raise ValueError("Can't build predictors on None")
+        def run_tree(node: Snode):
             if node.is_leaf():
                 node.make_predictor()
                 return
@@ -557,7 +556,7 @@ class Stree(BaseEstimator, ClassifierMixin):  # type: ignore
 
         run_tree(self.tree_)
 
-    def _build_clf(self) -> Union[LinearSVC, SVC]:
+    def _build_clf(self):
         """ Build the correct classifier for the node
         """
         return (
@@ -606,30 +605,30 @@ class Stree(BaseEstimator, ClassifierMixin):  # type: ignore
         """
 
         def predict_class(
-            xp: np.array, indices: np.array, node: Optional[Snode]
+            xp: np.array, indices: np.array, node: Snode
         ) -> np.array:
             if xp is None:
                 return [], []
-            if node.is_leaf():  # type: ignore
+            if node.is_leaf():
                 # set a class for every sample in dataset
-                prediction = np.full(
-                    (xp.shape[0], 1), node._class  # type: ignore
-                )
+                prediction = np.full((xp.shape[0], 1), node._class)
                 return prediction, indices
-            self.splitter_.partition(xp, node)  # type: ignore
+            self.splitter_.partition(xp, node)
             x_u, x_d = self.splitter_.part(xp)
             i_u, i_d = self.splitter_.part(indices)
-            prx_u, prin_u = predict_class(
-                x_u, i_u, node.get_up()  # type: ignore
-            )
-            prx_d, prin_d = predict_class(
-                x_d, i_d, node.get_down()  # type: ignore
-            )
+            prx_u, prin_u = predict_class(x_u, i_u, node.get_up())
+            prx_d, prin_d = predict_class(x_d, i_d, node.get_down())
             return np.append(prx_u, prx_d), np.append(prin_u, prin_d)
 
-        check_is_fitted(self, "n_features_in_")
+        # sklearn check
+        check_is_fitted(self, ["tree_"])
         # Input validation
-        X = self._validate_data(X, reset=False)
+        X = check_array(X)
+        if X.shape[1] != self.n_features_:
+            raise ValueError(
+                f"Expected {self.n_features_} features but got "
+                f"({X.shape[1]})"
+            )
         # setup prediction & make it happen
         indices = np.arange(X.shape[0])
         result = (
@@ -639,6 +638,32 @@ class Stree(BaseEstimator, ClassifierMixin):  # type: ignore
         )
         return self.classes_[result]
 
+    def score(
+        self, X: np.array, y: np.array, sample_weight: np.array = None
+    ) -> float:
+        """Compute accuracy of the prediction
+
+        :param X: dataset of samples to make predictions
+        :type X: np.array
+        :param y_true: samples labels
+        :type y_true: np.array
+        :param sample_weight: weights of the samples. Rescale C per sample.
+        Hi' weights force the classifier to put more emphasis on these points
+        :type sample_weight: np.array optional
+        :return: accuracy of the prediction
+        :rtype: float
+        """
+        # sklearn check
+        check_is_fitted(self)
+        check_classification_targets(y)
+        X, y = check_X_y(X, y)
+        y_pred = self.predict(X).reshape(y.shape)
+        # Compute accuracy for each possible representation
+        _, y_true, y_pred = _check_targets(y, y_pred)
+        check_consistent_length(y_true, y_pred, sample_weight)
+        score = y_true == y_pred
+        return _weighted_sum(score, sample_weight, normalize=True)
+
     def __iter__(self) -> Siterator:
         """Create an iterator to be able to visit the nodes of the tree in
         preorder, can make a list with all the nodes in preorder
@@ -666,11 +691,11 @@ class Stree(BaseEstimator, ClassifierMixin):  # type: ignore
     def _initialize_max_features(self) -> int:
         if isinstance(self.max_features, str):
             if self.max_features == "auto":
-                max_features = max(1, int(np.sqrt(self.n_features_in_)))
+                max_features = max(1, int(np.sqrt(self.n_features_)))
             elif self.max_features == "sqrt":
-                max_features = max(1, int(np.sqrt(self.n_features_in_)))
+                max_features = max(1, int(np.sqrt(self.n_features_)))
             elif self.max_features == "log2":
-                max_features = max(1, int(np.log2(self.n_features_in_)))
+                max_features = max(1, int(np.log2(self.n_features_)))
             else:
                 raise ValueError(
                     "Invalid value for max_features. "
@@ -678,13 +703,13 @@ class Stree(BaseEstimator, ClassifierMixin):  # type: ignore
                     "'sqrt' or 'log2'."
                 )
         elif self.max_features is None:
-            max_features = self.n_features_in_
-        elif isinstance(self.max_features, int):
+            max_features = self.n_features_
+        elif isinstance(self.max_features, numbers.Integral):
             max_features = self.max_features
         else:  # float
             if self.max_features > 0.0:
                 max_features = max(
-                    1, int(self.max_features * self.n_features_in_)
+                    1, int(self.max_features * self.n_features_)
                 )
             else:
                 raise ValueError(

stree/tests/Snode_test.py

@@ -1,4 +1,3 @@
-# type: ignore
 import os
 import unittest
 

stree/tests/Splitter_test.py

@@ -1,4 +1,3 @@
-# type: ignore
 import os
 import unittest
 import random

stree/tests/Stree_test.py

@@ -1,4 +1,3 @@
-# type: ignore
 import os
 import unittest
 import warnings
@@ -240,7 +239,7 @@ class Stree_test(unittest.TestCase):
             (None, 16),
         ]
         clf = Stree()
-        clf.n_features_in_ = n_features
+        clf.n_features_ = n_features
         for max_features, expected in expected_values:
             clf.set_params(**dict(max_features=max_features))
             computed = clf._initialize_max_features()
@@ -415,24 +414,3 @@ class Stree_test(unittest.TestCase):
         # zero weights are ok when they don't erase a class
         _ = clf.train(X, y, weights_no_zero, 1, "test")
         self.assertListEqual(weights_no_zero.tolist(), original.tolist())
-
-    def test_build_predictor(self):
-        X, y = load_dataset(self._random_state)
-        clf = Stree(random_state=self._random_state)
-        with self.assertRaises(ValueError):
-            clf.tree_ = None
-            clf._build_predictor()
-        clf.fit(X, y)
-        node = clf.tree_.get_down().get_down()
-        expected_impurity = 0.04686951386893923
-        expected_class = 1
-        expected_belief = 0.9759887005649718
-        self.assertAlmostEqual(expected_impurity, node._impurity)
-        self.assertAlmostEqual(expected_belief, node._belief)
-        self.assertEqual(expected_class, node._class)
-        node._belief = 0.0
-        node._class = None
-        clf._build_predictor()
-        node = clf.tree_.get_down().get_down()
-        self.assertAlmostEqual(expected_belief, node._belief)
-        self.assertEqual(expected_class, node._class)

stree/tests/__init__.py

@@ -1,4 +1,3 @@
-# type: ignore
 from .Stree_test import Stree_test
 from .Snode_test import Snode_test
 from .Splitter_test import Splitter_test

stree/tests/utils.py

@@ -1,4 +1,3 @@
-# type: ignore
 from sklearn.datasets import make_classification