psyke 0.9.1.dev12__py3-none-any.whl → 0.9.1.dev43__py3-none-any.whl

psyke/__init__.py

@@ -65,7 +65,7 @@ class EvaluableModel(object):
         raise NotImplementedError('predict')
 
     def __convert(self, ys: Iterable) -> Iterable:
-        if self.normalization is not None and not isinstance([p for p in ys if p is not None][0], str):
+        if self.normalization is not None and len(ys) > 0 and not isinstance([p for p in ys if p is not None][0], str):
             m, s = self.normalization[list(self.normalization.keys())[-1]]
             ys = [prediction if prediction is None else prediction * s + m for prediction in ys]
         return ys
@@ -231,7 +231,7 @@ class Extractor(EvaluableModel, ABC):
 
         for i in range(len(output['labels'])):
             for j in range(len(groups)):
-                plt.gca().text(j, i, f'{abs(int(data[i, j]))}%', ha="center", va="center", color="k")
+                plt.gca().text(j, i, f'{abs(data[i, j]):.2f}%', ha="center", va="center", color="k")
 
         plt.gca().set_xticks([i + .5 for i in range(len(groups))], minor=True)
         plt.gca().set_yticks([i + .5 for i in range(len(output['labels']))], minor=True)
@@ -394,6 +394,19 @@ class Extractor(EvaluableModel, ABC):
         from psyke.extraction.hypercubic.hex import HEx
         return HEx(predictor, grid, min_examples, threshold, output, discretization, normalization, seed)
 
+    @staticmethod
+    def ginger(predictor, features: Iterable[str], sigmas: Iterable[float], max_slices: int, min_rules: int = 1,
+               max_poly: int = 1, alpha: float = 0.5, indpb: float = 0.5, tournsize: int = 3, metric:str = 'R2',
+               n_gen: int = 50, n_pop: int = 50, threshold=None, valid=None,
+               normalization: dict[str, tuple[float, float]] = None,
+               seed: int = get_default_random_seed()) -> Extractor:
+        """
+        Creates a new GInGER extractor.
+        """
+        from psyke.extraction.hypercubic.ginger import GInGER
+        return GInGER(predictor, features, sigmas, max_slices, min_rules, max_poly, alpha, indpb, tournsize, metric,
+                      n_gen, n_pop, threshold, valid, normalization, seed)
+
     @staticmethod
     def gridrex(predictor, grid, min_examples: int = 250, threshold: float = 0.1,
                 normalization: dict[str, tuple[float, float]] = None,

psyke/clustering/__init__.py

@@ -10,6 +10,10 @@ class HyperCubeClustering(HyperCubePredictor, Clustering, ABC):
 
     def __init__(self, output: Target = Target.CONSTANT, discretization=None, normalization=None):
         HyperCubePredictor.__init__(self, output=output, discretization=discretization, normalization=normalization)
+        self._protected_features = []
 
     def get_hypercubes(self) -> Iterable[HyperCube]:
         raise NotImplementedError('get_hypercubes')
+
+    def make_fair(self, features: Iterable[str]):
+        self._protected_features = features

psyke/clustering/cream/__init__.py

@@ -46,11 +46,7 @@ class CREAM(ExACT):
     def _iterate(self, surrounding: Node) -> Iterable[HyperCube]:
         to_split = [(self.error_threshold * 10, 1, 1, surrounding)]
         while len(to_split) > 0:
-            to_split.sort(reverse=True)
-            (_, depth, _, node) = to_split.pop()
-            data = ExACT._remove_string_label(node.dataframe)
-            gauss_params = select_gaussian_mixture(data, self.gauss_components)
-            gauss_pred = gauss_params[2].predict(data)
+            node, depth, gauss_pred, gauss_params = self._get_gauss_predictions(to_split)
             cubes = self.__eligible_cubes(gauss_pred, node, gauss_params[1])
             if len(cubes) < 1:
                 continue
@@ -65,4 +61,4 @@ class CREAM(ExACT):
                     (error, depth + 1, np.random.uniform(), n) for (n, error) in
                     zip(node.children, [right[0].diversity, left[0].diversity]) if error > self.error_threshold
                 ]
-        return self._node_to_cubes(surrounding)
+        return self._node_to_cubes(surrounding)

psyke/clustering/exact/__init__.py

@@ -54,13 +54,13 @@ class ExACT(HyperCubeClustering, ABC):
         dbscan_pred = DBSCAN(eps=select_dbscan_epsilon(data, clusters)).fit_predict(data.iloc[:, :-1])
         return HyperCube.create_surrounding_cube(
             dataframe.iloc[np.where(dbscan_pred == Counter(dbscan_pred).most_common(1)[0][0])],
-            True, self._output
+            True, self._output, self._protected_features
         )
 
     def fit(self, dataframe: pd.DataFrame):
         np.random.seed(self.seed)
         self._predictor.fit(dataframe.iloc[:, :-1], dataframe.iloc[:, -1])
-        self._surrounding = HyperCube.create_surrounding_cube(dataframe, True, self._output)
+        self._surrounding = HyperCube.create_surrounding_cube(dataframe, True, self._output, self._protected_features)
         self._hypercubes = self._iterate(Node(dataframe, self._surrounding))
 
     def get_hypercubes(self) -> Iterable[HyperCube]:
@@ -79,14 +79,17 @@ class ExACT(HyperCubeClustering, ABC):
             enumerate(dataframe.iloc[:, -1].unique())
         ).items()}}) if isinstance(dataframe.iloc[0, -1], str) else dataframe
 
+    def _get_gauss_predictions(self, to_split):
+        to_split.sort(reverse=True)
+        (_, depth, _, node) = to_split.pop()
+        data = ExACT._remove_string_label(node.dataframe)
+        gauss_params = select_gaussian_mixture(data.drop(self._protected_features, axis=1), self.gauss_components)
+        return node, depth, gauss_params[2].predict(data.drop(self._protected_features, axis=1)), gauss_params
+
     def _iterate(self, surrounding: Node) -> Iterable[HyperCube]:
         to_split = [(self.error_threshold * 10, 1, 1, surrounding)]
         while len(to_split) > 0:
-            to_split.sort(reverse=True)
-            (_, depth, _, node) = to_split.pop()
-            data = ExACT._remove_string_label(node.dataframe)
-            gauss_params = select_gaussian_mixture(data, self.gauss_components)
-            gauss_pred = gauss_params[2].predict(data)
+            node, depth, gauss_pred, gauss_params = self._get_gauss_predictions(to_split)
             cubes, indices = self.__eligible_cubes(gauss_pred, node, gauss_params[1])
             cubes = [(c.volume(), len(idx), i, idx, c) for i, (c, idx) in enumerate(zip(cubes, indices))
                      if (idx is not None) and (not node.cube.equal(c))]

psyke/clustering/utils.py

@@ -11,7 +11,6 @@ def select_gaussian_mixture(data: pd.DataFrame, max_components) -> tuple[float,
     try:
         models = [GaussianMixture(n_components=n).fit(data) for n in components if n <= len(data)]
     except ValueError:
-        print(data)
         print(len(data))
     return min([(m.bic(data) / (i + 2), (i + 2), m) for i, m in enumerate(models)])
 

psyke/extraction/cart/FairTree.py

@@ -77,15 +77,16 @@ class FairTree:
         sorted_indices = np.argsort(X)
         X = np.array(X)[sorted_indices]
         y = np.array(y)[sorted_indices]
-        return np.array([(X[i] + X[i - 1]) / 2.0 for i in range(1, len(X)) if y[i] != y[i - 1]])
+        # X = np.array(np.unique(np.unique(list(zip(X, y)), axis=0)[:, 0]), dtype=float)
+        return np.array([(X[:-1][i] + X[1:][i]) / 2.0 for i in range(len(X) - 1) if y[i] != y[i + 1]])
 
     def _best_split(self, X, y):
         best_gain = -float('inf')
         split_idx, split_threshold = None, None
 
         for feature in [feature for feature in X.columns if feature not in self.protected_attr]:
-            # for threshold in np.unique(np.quantile(X[feature], np.linspace(0, 1, num=25))):
-            for threshold in self.generate_thresholds(X[feature], y):
+            # for threshold in self.generate_thresholds(X[feature], y):
+            for threshold in np.unique(np.quantile(X[feature], np.linspace(0, 1, num=25))):
                 left_idxs = X[feature] <= threshold
                 right_idxs = X[feature] > threshold
 

psyke/extraction/hypercubic/__init__.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 from abc import ABC
 from collections import Iterable
+from itertools import combinations
 
 import numpy as np
 import pandas as pd
@@ -25,6 +26,7 @@ class HyperCubeExtractor(HyperCubePredictor, PedagogicalExtractor, ABC):
         HyperCubePredictor.__init__(self, output=output, normalization=normalization)
         PedagogicalExtractor.__init__(self, predictor, discretization=discretization, normalization=normalization)
         self._default_surrounding_cube = False
+        self.threshold = None
 
     def _default_cube(self) -> HyperCube | RegressionCube | ClassificationCube:
         if self._output == Target.CONSTANT:
@@ -33,11 +35,53 @@ class HyperCubeExtractor(HyperCubePredictor, PedagogicalExtractor, ABC):
             return RegressionCube()
         return ClassificationCube()
 
+    @staticmethod
+    def _find_couples(to_split: Iterable[HyperCube], not_in_cache: set[HyperCube],
+                      adjacent_cache: dict[tuple[HyperCube, HyperCube], str | None]) -> \
+            Iterable[tuple[HyperCube, HyperCube, str]]:
+
+        for cube1, cube2 in combinations(to_split, 2):
+            key = (cube1, cube2) if id(cube1) < id(cube2) else (cube2, cube1)
+
+            if (cube1 in not_in_cache) or (cube2 in not_in_cache):
+                adjacent_cache[key] = cube1.is_adjacent(cube2)
+            feature = adjacent_cache.get(key)
+            if feature is not None:
+                yield cube1, cube2, feature
+
+    def _evaluate_merge(self, not_in_cache: Iterable[HyperCube], dataframe: pd.DataFrame, feature: str,
+                        cube: HyperCube, other_cube: HyperCube,
+                        merge_cache: dict[tuple[HyperCube, HyperCube], HyperCube | None]) -> bool:
+        if (cube in not_in_cache) or (other_cube in not_in_cache):
+            merged_cube = cube.merge_along_dimension(other_cube, feature)
+            merged_cube.update(dataframe, self.predictor)
+            merge_cache[(cube, other_cube)] = merged_cube
+        return cube.output == other_cube.output if self._output == Target.CLASSIFICATION else \
+            merge_cache[(cube, other_cube)].diversity < self.threshold
+
     def _sort_cubes(self):
         cubes = [(cube.diversity, i, cube) for i, cube in enumerate(self._hypercubes)]
         cubes.sort()
         self._hypercubes = [cube[2] for cube in cubes]
 
+    def _merge(self, to_split: list[HyperCube], dataframe: pd.DataFrame) -> Iterable[HyperCube]:
+        not_in_cache = set(to_split)
+        adjacent_cache = {}
+        merge_cache = {}
+        while True:
+            to_merge = [([cube, other_cube], merge_cache[(cube, other_cube)]) for cube, other_cube, feature in
+                        HyperCubeExtractor._find_couples(to_split, not_in_cache, adjacent_cache) if
+                        self._evaluate_merge(not_in_cache, dataframe, feature, cube, other_cube, merge_cache)]
+
+            if len(to_merge) == 0:
+                break
+            best = min(to_merge, key=lambda c: c[1].diversity)
+            for cube in best[0]:
+                to_split.remove(cube)
+            to_split.append(best[1])
+            not_in_cache = [best[1]]
+        return to_split
+
     def extract(self, dataframe: pd.DataFrame) -> Theory:
         theory = PedagogicalExtractor.extract(self, dataframe)
         self._surrounding = HyperCube.create_surrounding_cube(dataframe, output=self._output)

psyke/extraction/hypercubic/creepy/__init__.py

@@ -1,7 +1,8 @@
 from __future__ import annotations
 
 from collections import Iterable
-import numpy as np
+from typing import Callable, Any
+
 import pandas as pd
 from sklearn.base import ClassifierMixin
 from tuprolog.theory import Theory
@@ -16,16 +17,23 @@ class CReEPy(HyperCubeExtractor):
     Explanator implementing CReEPy algorithm.
     """
 
-    def __init__(self, predictor, clustering=Clustering.exact, depth: int = 3, error_threshold: float = 0.1,
-                 output: Target = Target.CONSTANT, gauss_components: int = 5, ranks: Iterable[(str, float)] = tuple(),
-                 ignore_threshold: float = 0.0, discretization=None, normalization=None,
-                 seed: int = get_default_random_seed()):
+    ClusteringType = Callable[[int, float, Target, int, Any, Any, int], HyperCubeClustering]
+
+    def __init__(self, predictor, clustering: ClusteringType = Clustering.exact, depth: int = 3,
+                 error_threshold: float = 0.1, output: Target = Target.CONSTANT, gauss_components: int = 5,
+                 ranks: Iterable[(str, float)] = tuple(), ignore_threshold: float = 0.0, discretization=None,
+                 normalization=None, seed: int = get_default_random_seed()):
         super().__init__(predictor, Target.CLASSIFICATION if isinstance(predictor, ClassifierMixin) else output,
                          discretization, normalization)
         self.clustering = clustering(depth, error_threshold, self._output, gauss_components, discretization,
                                      normalization, seed)
         self._default_surrounding_cube = True
         self._dimensions_to_ignore = set([dimension for dimension, relevance in ranks if relevance < ignore_threshold])
+        self._protected_features = []
+
+    def make_fair(self, features: Iterable[str]):
+        self.clustering.make_fair(features)
+        self._dimensions_to_ignore.update(features)
 
     def _extract(self, dataframe: pd.DataFrame) -> Theory:
         if not isinstance(self.clustering, HyperCubeClustering):

psyke/extraction/hypercubic/ginger/__init__.py

@@ -0,0 +1,98 @@
+import itertools
+from typing import Iterable
+
+import numpy as np
+import pandas as pd
+from sklearn.preprocessing import PolynomialFeatures
+from tuprolog.theory import Theory
+
+from psyke import get_default_random_seed
+from psyke.extraction.hypercubic import HyperCubeExtractor, HyperCube, RegressionCube
+
+from deap import base, creator
+
+from psyke.genetic.gin import GIn
+
+
+class GInGER(HyperCubeExtractor):
+    """
+    Explanator implementing GInGER algorithm.
+    """
+
+    def __init__(self, predictor, features, sigmas, max_slices, min_rules=1, max_poly=1, alpha=0.5, indpb=0.5,
+                 tournsize=3, metric='R2', n_gen=50, n_pop=50, threshold=None, valid=None, normalization=None,
+                 seed: int = get_default_random_seed()):
+        super().__init__(predictor, normalization)
+        self.threshold = threshold
+        np.random.seed(seed)
+
+        self.features = features
+        self.max_features = len(features)
+        self.sigmas = sigmas
+        self.max_slices = max_slices
+        self.min_rules = min_rules
+        self.poly = max_poly
+        self.trained_poly = None
+
+        self.alpha = alpha
+        self.indpb = indpb
+        self.tournsize = tournsize
+        self.metric = metric
+
+        self.n_gen = n_gen
+        self.n_pop = n_pop
+        self.valid = valid
+
+        creator.create("FitnessMax", base.Fitness, weights=(1.0,))
+        creator.create("Individual", list, fitness=creator.FitnessMax)
+
+    def __poly_names(self):
+        return [''.join(['' if pp == 0 else f'{n} * ' if pp == 1 else f'{n}**{pp} * '
+                         for pp, n in zip(p, self.trained_poly.feature_names_in_)])[:-3]
+                for p in self.trained_poly.powers_]
+
+    def _predict(self, dataframe: pd.DataFrame) -> Iterable:
+        dataframe = pd.DataFrame(self.trained_poly.fit_transform(dataframe), columns=self.__poly_names())
+        return np.array([self._predict_from_cubes(row.to_dict()) for _, row in dataframe.iterrows()])
+
+    def _extract(self, dataframe: pd.DataFrame) -> Theory:
+        best = {}
+        for poly in range(self.poly):
+            for slices in list(itertools.product(range(1, self.max_slices + 1), repeat=self.max_features)):
+                gr = GIn((dataframe.iloc[:, :-1], dataframe.iloc[:, -1]), self.valid, self.features, self.sigmas,
+                         slices, min_rules=self.min_rules, poly=poly + 1, alpha=self.alpha,
+                         indpb=self.indpb, tournsize=self.tournsize, metric=self.metric, warm=True)
+
+                b, score, _, _ = gr.run(n_gen=self.n_gen, n_pop=self.n_pop)
+                best[(score, poly + 1, slices)] = b
+        m = min(best)
+        poly, slices, best = m[1], m[2], best[m]
+        self.trained_poly = PolynomialFeatures(degree=poly, include_bias=False)
+        transformed = pd.DataFrame(self.trained_poly.fit_transform(dataframe.iloc[:, :-1]), columns=self.__poly_names())
+        transformed[dataframe.columns[-1]] = dataframe.iloc[:, -1].values
+
+        self._surrounding = HyperCube.create_surrounding_cube(transformed, output=self._output)
+
+        cuts = [sorted(best[sum(slices[:i]):sum(slices[:i + 1])]) for i in range(len(slices))]
+
+        intervals = [[(transformed[self.features[i]].min(), cut[0])] +
+                     [(cut[i], cut[i + 1]) for i in range(len(cut) - 1)] +
+                     [(cut[-1], transformed[self.features[i]].max())] for i, cut in enumerate(cuts)]
+
+        hypercubes = [{f: iv for f, iv in zip(self.features, combo)} for combo in itertools.product(*intervals)]
+        mi_ma = {f: (transformed[f].min(), transformed[f].max()) for f in transformed.columns if f not in self.features}
+        self._hypercubes = [RegressionCube({feat: h[feat] if feat in self.features else mi_ma[feat]
+                                            for feat in transformed.columns[:-1]}) for h in hypercubes]
+        self._hypercubes = [c for c in self._hypercubes if c.count(transformed) >= 2]
+        for c in self._hypercubes:
+            for feature in transformed.columns:
+                if feature not in self.features:
+                    for direction in ['+', '-']:
+                        c.set_infinite(feature, direction)
+            c.update(transformed)
+        if self.threshold is not None:
+            self._hypercubes = self._merge(self._hypercubes, transformed)
+        return self._create_theory(transformed)
+
+    def make_fair(self, features: Iterable[str]):
+        self._dimensions_to_ignore.update(features)

psyke/extraction/hypercubic/gridex/__init__.py

@@ -59,7 +59,6 @@ class GridEx(HyperCubeExtractor):
     def _iterate(self, dataframe: pd.DataFrame):
         fake = dataframe.copy()
         prev = [self._surrounding]
-        next_iteration = []
 
         for iteration in self.grid.iterate():
             next_iteration = []
@@ -67,56 +66,12 @@ class GridEx(HyperCubeExtractor):
                 if cube.count(dataframe) == 0:
                     continue
                 if cube.diversity < self.threshold:
-                    self._hypercubes += [cube]
+                    self._hypercubes.append(cube)
                     continue
                 to_split, fake = self._cubes_to_split(cube, iteration, dataframe, fake)
-                next_iteration += [c for c in self._merge(to_split, fake)]
-            prev = next_iteration.copy()
-        self._hypercubes += [cube for cube in next_iteration]
-
-    @staticmethod
-    def _find_couples(to_split: Iterable[HyperCube], not_in_cache: Iterable[HyperCube],
-                      adjacent_cache: dict[tuple[HyperCube, HyperCube], str | None]) -> \
-            Iterable[tuple[HyperCube, HyperCube, str]]:
-        checked = []
-        eligible = []
-        for cube in to_split:
-            checked.append(cube)
-            for other_cube in [c for c in to_split if c not in checked]:
-                if (cube in not_in_cache) or (other_cube in not_in_cache):
-                    adjacent_cache[(cube, other_cube)] = cube.is_adjacent(other_cube)
-                adjacent_feature = adjacent_cache[(cube, other_cube)]
-                eligible.append((cube, other_cube, adjacent_feature))
-        return [couple for couple in eligible if couple[2] is not None]
-
-    def _evaluate_merge(self, not_in_cache: Iterable[HyperCube],
-                        dataframe: pd.DataFrame, feature: str,
-                        cube: HyperCube, other_cube: HyperCube,
-                        merge_cache: dict[(HyperCube, HyperCube), HyperCube | None]) -> bool:
-        if (cube in not_in_cache) or (other_cube in not_in_cache):
-            merged_cube = cube.merge_along_dimension(other_cube, feature)
-            merged_cube.update(dataframe, self.predictor)
-            merge_cache[(cube, other_cube)] = merged_cube
-        return cube.output == other_cube.output if self._output == Target.CLASSIFICATION else \
-            merge_cache[(cube, other_cube)].diversity < self.threshold
-
-    def _merge(self, to_split: Iterable[HyperCube], dataframe: pd.DataFrame) -> Iterable[HyperCube]:
-        not_in_cache = [cube for cube in to_split]
-        adjacent_cache = {}
-        merge_cache = {}
-        cont = True
-        while cont:
-            to_merge = [([cube, other_cube], merge_cache[(cube, other_cube)]) for cube, other_cube, feature in
-                        GridEx._find_couples(to_split, not_in_cache, adjacent_cache) if
-                        self._evaluate_merge(not_in_cache, dataframe, feature, cube, other_cube, merge_cache)]
-            if len(to_merge) == 0:
-                cont = False
-            else:
-                sorted(to_merge, key=lambda c: c[1].diversity)
-                best = to_merge[0]
-                to_split = [cube for cube in to_split if cube not in best[0]] + [best[1]]
-                not_in_cache = [best[1]]
-        return to_split
+                next_iteration.extend(self._merge(to_split, fake))
+            prev = next_iteration
+        self._hypercubes.extend(prev)
 
     def make_fair(self, features: Iterable[str]):
         self.grid.make_fair(features)

psyke/extraction/hypercubic/hypercube.py

@@ -143,10 +143,9 @@ class HyperCube:
         self._default = True
 
     def set_infinite(self, dimension: str, direction: str):
-        if dimension in self._infinite_dimensions:
-            self._infinite_dimensions[dimension].append(direction)
-        else:
-            self._infinite_dimensions[dimension] = [direction]
+        if dimension not in self._infinite_dimensions:
+            self._infinite_dimensions[dimension] = set()
+        self._infinite_dimensions[dimension].add(direction)
 
     def copy_infinite_dimensions(self, dimensions: dict[str, str]):
         self._infinite_dimensions = dimensions.copy()
@@ -260,13 +259,15 @@ class HyperCube:
                 if not self.is_default and value is not None]
 
     @staticmethod
-    def create_surrounding_cube(dataset: pd.DataFrame, closed: bool = False,
-                                output=None) -> GenericCube:
+    def create_surrounding_cube(dataset: pd.DataFrame, closed: bool = False, output=None,
+                                features_to_ignore: Iterable[str] = []) -> GenericCube:
         output = Target.CONSTANT if output is None else output
         dimensions = {
             column: (min(dataset[column]) - HyperCube.EPSILON * 2, max(dataset[column]) + HyperCube.EPSILON * 2)
             for column in dataset.columns[:-1]
         }
+        for column in features_to_ignore:
+            dimensions[column] = (-np.inf, np.inf)
         if closed:
             if output == Target.CONSTANT:
                 return ClosedCube(dimensions)
@@ -432,14 +433,16 @@ class HyperCube:
         else:
             self.update_dimension(feature, (lower, upper))
 
-    def update(self, dataset: pd.DataFrame, predictor) -> None:
-        filtered = self.filter_dataframe(dataset.iloc[:, :-1])
-        predictions = predictor.predict(filtered)
-        self._output = np.mean(predictions)
-        self._diversity = np.std(predictions)
-        self._error = (abs(predictions - self._output)).mean()
-        means = filtered.describe().loc['mean']
-        self._barycenter = Point(means.index.values, means.values)
+    def update(self, dataset: pd.DataFrame, predictor=None) -> None:
+        idx = self.filter_indices(dataset.iloc[:, :-1])
+        filtered = dataset.iloc[idx, :-1]
+        if len(filtered > 0):
+            predictions = dataset.iloc[idx, -1] if predictor is None else predictor.predict(filtered)
+            self._output = np.mean(predictions)
+            self._diversity = np.std(predictions)
+            self._error = (abs(predictions - self._output)).mean()
+            means = filtered.describe().loc['mean']
+            self._barycenter = Point(means.index.values, means.values)
 
     # TODO: why this is not a property?
     def init_diversity(self, std: float) -> None:
@@ -450,10 +453,11 @@ class RegressionCube(HyperCube):
     def __init__(self, dimension: dict[str, tuple] = None, limits: set[Limit] = None, output=None):
         super().__init__(dimension=dimension, limits=limits, output=LinearRegression() if output is None else output)
 
-    def update(self, dataset: pd.DataFrame, predictor) -> None:
-        filtered = self.filter_dataframe(dataset.iloc[:, :-1])
+    def update(self, dataset: pd.DataFrame, predictor=None) -> None:
+        idx = self.filter_indices(dataset.iloc[:, :-1])
+        filtered = dataset.iloc[idx, :-1]
         if len(filtered > 0):
-            predictions = predictor.predict(filtered)
+            predictions = dataset.iloc[idx, -1] if predictor is None else predictor.predict(filtered)
             self._output.fit(filtered, predictions)
             self._diversity = self._error = (abs(self._output.predict(filtered) - predictions)).mean()
             means = filtered.describe().loc['mean']
@@ -489,10 +493,11 @@ class ClassificationCube(HyperCube):
     def __init__(self, dimension: dict[str, tuple] = None, limits: set[Limit] = None, output: str = ""):
         super().__init__(dimension=dimension, limits=limits, output=output)
 
-    def update(self, dataset: pd.DataFrame, predictor) -> None:
-        filtered = self.filter_dataframe(dataset.iloc[:, :-1])
+    def update(self, dataset: pd.DataFrame, predictor=None) -> None:
+        idx = self.filter_indices(dataset.iloc[:, :-1])
+        filtered = dataset.iloc[idx, :-1]
         if len(filtered > 0):
-            predictions = predictor.predict(filtered)
+            predictions = dataset.iloc[idx, -1] if predictor is None else predictor.predict(filtered)
             self._output = mode(predictions)
             self._diversity = self._error = 1 - sum(p == self.output for p in predictions) / len(predictions)
             means = filtered.describe().loc['mean']

psyke/genetic/gin/__init__.py

@@ -0,0 +1,106 @@
+import numpy as np
+from deap import base, creator, tools, algorithms
+import random
+from sklearn.linear_model import LinearRegression
+from sklearn.metrics import mean_absolute_error, r2_score
+from sklearn.preprocessing import PolynomialFeatures
+
+
+class GIn:
+
+    def __init__(self, train, valid, features, sigmas, slices, min_rules=1, poly=1,
+                 alpha=0.5, indpb=0.5, tournsize=3, metric='R2', warm=False):
+        self.X, self.y = train
+        self.valid = valid
+
+        self.features = features
+        self.sigmas = sigmas
+        self.slices = slices
+        self.min_rules = min_rules
+        self.poly = PolynomialFeatures(degree=poly, include_bias=False)
+
+        self.alpha = alpha
+        self.indpb = indpb
+        self.tournsize = tournsize
+        self.metric = metric
+
+        self.toolbox = None
+        self.stats = None
+        self.hof = None
+
+        self.setup(warm)
+
+    def region(self, X, cuts):
+        indices = [np.searchsorted(np.array(cut), X[f].to_numpy(), side='right')
+                   for cut, f in zip(cuts, self.features)]
+
+        regions = np.zeros(len(X), dtype=int)
+        multiplier = 1
+        for idx, n in zip(reversed(indices), reversed([len(cut) + 1 for cut in cuts])):
+            regions += idx * multiplier
+            multiplier *= n
+
+        return regions
+
+    def evaluate(self, individual):
+        to_pred, true = self.valid or (self.X, self.y)
+        boundaries = np.cumsum([0] + list(self.slices))
+        cuts = [sorted(individual[boundaries[i]:boundaries[i + 1]]) for i in range(len(self.slices))]
+
+        regions = self.region(to_pred, cuts)
+        regionsT = self.region(self.X, cuts)
+
+        y_pred = np.zeros(len(to_pred))
+        valid_regions = 0
+
+        for r in range(np.prod([s + 1 for s in self.slices])):
+            mask = regions == r
+            maskT = regionsT == r
+            if min(mask.sum(), maskT.sum()) < 3:
+                y_pred[mask] = np.mean(self.y)
+                continue
+            y_pred[mask] = LinearRegression().fit(self.poly.fit_transform(self.X)[maskT], self.y[maskT]).predict(
+                self.poly.fit_transform(to_pred)[mask])
+            valid_regions += 1
+
+        if valid_regions < self.min_rules:
+            return -9999,
+
+        return (r2_score if self.metric == 'R2' else -mean_absolute_error)(true, y_pred),
+
+    def setup(self, warm=False):
+        if not warm:
+            creator.create("FitnessMax", base.Fitness, weights=(1.0,))
+            creator.create("Individual", list, fitness=creator.FitnessMax)
+
+        self.toolbox = base.Toolbox()
+        for f in self.features:
+            self.toolbox.register(f, random.uniform, self.X[f].min(), self.X[f].max())
+
+        self.toolbox.register("individual", tools.initCycle, creator.Individual,
+                              (sum([[getattr(self.toolbox, f) for i in range(s)]
+                                    for f, s in zip(self.features, self.slices)], [])), n=1)
+
+        self.toolbox.register("population", tools.initRepeat, list, self.toolbox.individual)
+
+        self.toolbox.register("mate", tools.cxBlend, alpha=self.alpha)
+        self.toolbox.register("mutate", tools.mutGaussian, indpb=self.indpb, mu=0,
+                              sigma=sum([[sig] * s for sig, s in zip(self.sigmas, self.slices)], []))
+        self.toolbox.register("select", tools.selTournament, tournsize=self.tournsize)
+        self.toolbox.register("evaluate", self.evaluate)
+
+        self.stats = tools.Statistics(lambda ind: ind.fitness.values[0])
+        self.stats.register("avg", np.mean)
+        # self.stats.register("min", np.min)
+        self.stats.register("max", np.max)
+        # self.stats.register("std", np.std)
+
+        self.hof = tools.HallOfFame(1)
+
+    def run(self, n_pop=30, cxpb=0.8, mutpb=0.5, n_gen=50, seed=123):
+        random.seed(seed)
+        pop = self.toolbox.population(n=n_pop)
+        result, log = algorithms.eaSimple(pop, self.toolbox, cxpb=cxpb, mutpb=mutpb, ngen=n_gen,
+                                          stats=self.stats, halloffame=self.hof, verbose=False)
+        best = tools.selBest(pop, 1)[0]
+        return best, self.evaluate(best)[0], result, log

{psyke-0.9.1.dev12.dist-info → psyke-0.9.1.dev43.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: psyke
-Version: 0.9.1.dev12
+Version: 0.9.1.dev43
 Summary: Python-based implementation of PSyKE, i.e. a Platform for Symbolic Knowledge Extraction
 Home-page: https://github.com/psykei/psyke-python
 Author: Matteo Magnini

{psyke-0.9.1.dev12.dist-info → psyke-0.9.1.dev43.dist-info}/RECORD

@@ -1,22 +1,23 @@
-psyke/__init__.py,sha256=J8lzVDJaGAin9TpDB6cXgAQegopVBuqURaWkkxjptR8,22490
+psyke/__init__.py,sha256=4GYagtqZnAOBz3VKyOgEp-yS5-16J7x2J9PoOkdQ9-U,23282
 psyke/hypercubepredictor.py,sha256=Pg8F2R_NHrNgFHx92s32BorYHMVvaxpEh4GtCsoyB2U,4620
-psyke/clustering/__init__.py,sha256=36MokTVwwWR_-o0mesvXHaYEYVTK2pn2m0ZY4G3Y3qU,581
-psyke/clustering/utils.py,sha256=S0YwCKyHVYp9qUAQVzCMrTwcQFPJ5TD14Jwn10DE-Z4,1616
-psyke/clustering/cream/__init__.py,sha256=W6k7vdjuUdA_azYA4vb5JtpWrofhDJ0DbM2jsnRKzfw,2994
-psyke/clustering/exact/__init__.py,sha256=s4MPvGZ6gle3X9WH3YFHOEdinGcXIXh-7EFRcElWzsQ,5275
+psyke/clustering/__init__.py,sha256=LfLZY2UwHY9xlFT4SMGGbyFY5S6sMXndY-UMaJIJtd8,714
+psyke/clustering/utils.py,sha256=BqMPKJ-r6CdxXwyk-2AvkPV4DBnZF5WUNz2fKiXbhlw,1596
+psyke/clustering/cream/__init__.py,sha256=TtUd5IyfavSUZeSuSAr06ZftVhK30ZLZGUUfH3ZQG2w,2799
+psyke/clustering/exact/__init__.py,sha256=OMMxc_lIKHouZTpbLF7dt4dOA3chL4XFpjOCyc6GTTY,5545
 psyke/extraction/__init__.py,sha256=Q0i6wMzCdU7CkxhzWoD8H_a6XId6bfEx6LZbSJmTqm0,936
 psyke/extraction/cart/CartPredictor.py,sha256=YhEuaENLWixu379sIXZkFeCNc8GBnxLnR6TPCQR7sps,5743
-psyke/extraction/cart/FairTree.py,sha256=49ciVmqgSa6hNL2axYi-oN4DSsqrHdewH76TTYiR8x0,7529
+psyke/extraction/cart/FairTree.py,sha256=mccoLDrSNy6iivqFZ23m33hxIB_kPXa3mNL1ukfb5Ls,7624
 psyke/extraction/cart/FairTreePredictor.py,sha256=7z4oLqflkRMqqVW_UIlrGsQrvROM4sXUfY7LPQJ662g,2321
 psyke/extraction/cart/__init__.py,sha256=SsjAJiL4n6q_GNR6H8PNfhTkAZ67Ka7NRvVRxCULBhQ,3191
-psyke/extraction/hypercubic/__init__.py,sha256=SK-I9IPQEdpYVTkFGa8No803QMwYSqgTTzinry4KLew,10896
-psyke/extraction/hypercubic/hypercube.py,sha256=s1fuGOZfN2ZE21C7f6-b1T3Ta_934c4rwDLD_pBWwFk,25847
+psyke/extraction/hypercubic/__init__.py,sha256=AxvPJxEQzL9Diyi7l2kX3zZESZ9xbh6RFp7ffs0w2ic,13112
+psyke/extraction/hypercubic/hypercube.py,sha256=Pz-F6RkAKLT5e86L29khqLjKTJ7k2TZszdRdxddVFtA,26275
 psyke/extraction/hypercubic/strategy.py,sha256=m9BGSrKc-VadgEQTOPow85hBPFqMIt0J99nCFIh4NUs,1839
 psyke/extraction/hypercubic/utils.py,sha256=D2FN5CCm_T3h23DmLFoTnIcFo7LvIq__ktl4hjUqkcA,1525
 psyke/extraction/hypercubic/cosmik/__init__.py,sha256=XQUvOtMFpR0vMHYtwIVl3G626HMqN8Clt6BqNm4nvFs,1880
-psyke/extraction/hypercubic/creepy/__init__.py,sha256=Cglj1mmj6VM_YBKgfNN0uDIbZb2_YS1RtPc75ftXWP8,1744
+psyke/extraction/hypercubic/creepy/__init__.py,sha256=x8a1ftoYHixGpiDfM3u-6QBEDYmaSlPIRIuAOCx573w,2056
 psyke/extraction/hypercubic/divine/__init__.py,sha256=ClO8CITKKXoo7nhlBJagR1yAachsxLHYQlqggl-9eGE,3665
-psyke/extraction/hypercubic/gridex/__init__.py,sha256=_g_JC6eFKLeg_CtkQawsUpVUAVxiVPQFJbfRVhMaBLg,5632
+psyke/extraction/hypercubic/ginger/__init__.py,sha256=GZOKy_iLmYOuXcRrPhNEDP5ZA2Ez2Cjb6GuervSAD4Y,4476
+psyke/extraction/hypercubic/gridex/__init__.py,sha256=tPPLGRJ-7fCt-OB-qq6W7EV0hqEuQVUGlXs2yyABo98,3161
 psyke/extraction/hypercubic/gridrex/__init__.py,sha256=h9usK5tFqd6ngBmRydsgkfQ1jlcQKj2uG72Tr1puFHk,595
 psyke/extraction/hypercubic/hex/__init__.py,sha256=553AZjOT9thfqDGtVDI6WtgYNex2Y6dg53cEyuf7Q80,4805
 psyke/extraction/hypercubic/iter/__init__.py,sha256=bb0neiPcNlyyr-OUUjgw4vdkehnAsoyJzVJ88jAHtQ8,10233
@@ -24,6 +25,8 @@ psyke/extraction/real/__init__.py,sha256=zAE_syurDqmFiopD5oLeIs9bROiuXy06wxoHmVq
 psyke/extraction/real/utils.py,sha256=4NNL15Eu7cmkG9b29GBP6CKgMTV1cmiJVS0k1MbWpIs,2148
 psyke/extraction/trepan/__init__.py,sha256=H8F_wpFLPcfyx2tgOOno8FwUomxfVxVl1vxlb0ClP1g,6931
 psyke/extraction/trepan/utils.py,sha256=iSUJ1ooNQT_VO1KfBZuIUeUsyUbGdQf_pSEE87vMeQg,2320
+psyke/genetic/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+psyke/genetic/gin/__init__.py,sha256=liRG5kenjPnMlr4pDGIshLDGmwK-GYrFCKFlWUDk1YU,4179
 psyke/schema/__init__.py,sha256=axv4ejZY0ItUwrC9IXb_yAhaQL5f1vwvXXmaIAHJmt0,26063
 psyke/tuning/__init__.py,sha256=yd_ForFmHeYbtRXltY1fOa-mPJvpE6ijzg50M_8Sdxw,3649
 psyke/tuning/crash/__init__.py,sha256=zIHEF75EFy_mRIieqzP04qKLG3GLsSc_mYZHpPfkzxU,2623
@@ -35,8 +38,8 @@ psyke/utils/logic.py,sha256=ioP25WMTYNYEzaRDNDe3kGNWqZ6DA_63t19d-ky_2kM,12227
 psyke/utils/metrics.py,sha256=Oo5BOonOSfo0qYsXWT5dmypZ7jiStByFC2MKEU0uMHg,2250
 psyke/utils/plot.py,sha256=dE8JJ6tQ0Ezosid-r2jqAisREjFe5LqExRzsVi5Ns-c,7785
 psyke/utils/sorted.py,sha256=C3CPW2JisND30BRk5c1sAAHs3Lb_wsRB2qZrYFuRnfM,678
-psyke-0.9.1.dev12.dist-info/licenses/LICENSE,sha256=G3mPaubObvkBXbsgTTeYGLk_pNEW8tc7HZr4u_wLEpU,11398
-psyke-0.9.1.dev12.dist-info/METADATA,sha256=R8bTf2T9Hf2Qc35iVKAINxAm5kiqRpF79HRUFYPwXcc,8395
-psyke-0.9.1.dev12.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-psyke-0.9.1.dev12.dist-info/top_level.txt,sha256=q1HglxOqqoIRukFtyis_ZNHczZg4gANRUPWkD7HAUTU,6
-psyke-0.9.1.dev12.dist-info/RECORD,,
+psyke-0.9.1.dev43.dist-info/licenses/LICENSE,sha256=G3mPaubObvkBXbsgTTeYGLk_pNEW8tc7HZr4u_wLEpU,11398
+psyke-0.9.1.dev43.dist-info/METADATA,sha256=8P6RB9OhVsNHokg8Q1meg5zpigQoaigC58y8EtrQHCo,8395
+psyke-0.9.1.dev43.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+psyke-0.9.1.dev43.dist-info/top_level.txt,sha256=q1HglxOqqoIRukFtyis_ZNHczZg4gANRUPWkD7HAUTU,6
+psyke-0.9.1.dev43.dist-info/RECORD,,