psyke 0.9.0.dev1__py3-none-any.whl → 0.9.1__py3-none-any.whl

psyke/extraction/__init__.py

@@ -24,28 +24,3 @@ class PedagogicalExtractor(Extractor, ABC):
 
     def _extract(self, dataframe: pd.DataFrame) -> Theory:
         raise NotImplementedError('extract')
-
-
-class FairExtractor(PedagogicalExtractor, ABC):
-
-    def __init__(self, extractor: Extractor, features: Iterable):
-        super().__init__(extractor.predictor, extractor.discretization, extractor.normalization)
-        self.features = features
-        self.extractor = extractor
-        # self.make_fair()
-
-#    def extract(self, dataframe: pd.DataFrame) -> Theory:
-#        self.theory = self.extractor.extract(dataframe)
-#        return self.theory
-
-#    def predict_why(self, data: dict[str, float], verbose: bool = True):
-#        self.extractor.predict_why(data, verbose)
-
-#    def predict_counter(self, data: dict[str, float], verbose: bool = True, only_first: bool = True):
-#        self.extractor.predict_counter(data, verbose, only_first)
-
-#    def _predict(self, dataframe: pd.DataFrame) -> Iterable:
-#        return self.extractor.predict(dataframe)
-
-#    def _brute_predict(self, dataframe: pd.DataFrame, criterion: str = 'corner', n: int = 2) -> Iterable:
-#        return self.extractor.brute_predict(dataframe, criterion, n)

psyke/extraction/cart/FairTree.py

@@ -72,12 +72,20 @@ class FairTree:
         right = self._grow_tree(X[right_idxs], y[right_idxs], depth + 1)
         return Node(best_feature, best_threshold, left, right)
 
+    @staticmethod
+    def generate_thresholds(X, y):
+        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]])
+
     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 np.unique(np.quantile(X[feature], np.linspace(0, 1, num=25))):
+            for threshold in self.generate_thresholds(X[feature], y):
                 left_idxs = X[feature] <= threshold
                 right_idxs = X[feature] > threshold
 

psyke/extraction/cart/FairTreePredictor.py

@@ -1,15 +1,9 @@
 import copy
-from collections import Iterable
 from typing import Union, Any
-import pandas as pd
-from sklearn.tree import DecisionTreeClassifier, DecisionTreeRegressor
-from tuprolog.core import clause, Var, Struct
-from tuprolog.theory import Theory, mutable_theory
 
 from psyke.extraction.cart import FairTreeClassifier, FairTreeRegressor, LeafSequence, LeafConstraints
 from psyke.extraction.cart.CartPredictor import CartPredictor
-from psyke.schema import LessThan, GreaterThan, SchemaException, DiscreteFeature, Value
-from psyke.utils.logic import create_variable_list, create_head, create_term
+from psyke.schema import LessThan, GreaterThan, SchemaException, Value
 
 
 class FairTreePredictor(CartPredictor):
@@ -17,7 +11,7 @@ class FairTreePredictor(CartPredictor):
     A wrapper for fair decision and regression trees of psyke.
     """
 
-    def __init__(self, predictor: Union[FairTreeClassifier, FairTreeRegressor] = DecisionTreeClassifier(),
+    def __init__(self, predictor: Union[FairTreeClassifier, FairTreeRegressor] = FairTreeClassifier(),
                  discretization=None, normalization=None):
         super().__init__(predictor, discretization, normalization)
 

psyke/extraction/real/__init__.py

@@ -19,6 +19,7 @@ class REAL(PedagogicalExtractor):
 
     def __init__(self, predictor, discretization: Iterable[DiscreteFeature]):
         super().__init__(predictor, discretization)
+        self._ignore_feature = []
         self._ruleset: IndexedRuleSet = IndexedRuleSet()
 
     @property
@@ -87,13 +88,20 @@ class REAL(PedagogicalExtractor):
         return self._create_ruleset(dataset)
 
     def _internal_predict(self, sample: pd.Series):
-        x = [index for index, rule in self._ruleset.flatten() if REAL._rule_from_example(sample) in rule]
+        x = [index for index, rule in self._ruleset.flatten() if self._rule_from_example(sample) in rule]
         return x[0] if x else None
 
-    @staticmethod
-    def _rule_from_example(sample: pd.Series) -> Rule:
+    def make_fair(self, features: Iterable[str]):
+        self._ignore_feature = [list(i.admissible_values.keys()) for i in self.discretization if i.name in features] \
+            if self.discretization else [features]
+        self._ignore_feature = [feature for features in self._ignore_feature for feature in features]
+        self._get_or_set.cache_clear()
+
+    def _rule_from_example(self, sample: pd.Series) -> Rule:
         true_predicates, false_predicates = [], []
         for feature, value in sample.items():
+            if feature in self._ignore_feature:
+                continue
             true_predicates.append(str(feature)) if value == 1 else false_predicates.append(str(feature))
         return Rule(true_predicates, false_predicates)
 

{psyke-0.9.0.dev1.dist-info → psyke-0.9.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: psyke
-Version: 0.9.0.dev1
+Version: 0.9.1
 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-0.9.0.dev1.dist-info → psyke-0.9.1.dist-info}/RECORD

@@ -4,10 +4,10 @@ psyke/clustering/__init__.py,sha256=36MokTVwwWR_-o0mesvXHaYEYVTK2pn2m0ZY4G3Y3qU,
 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/extraction/__init__.py,sha256=wZxazCtNfJXIebsjma8aAk0dZPyiKHmzeVcqTfZDyFQ,1978
+psyke/extraction/__init__.py,sha256=Q0i6wMzCdU7CkxhzWoD8H_a6XId6bfEx6LZbSJmTqm0,936
 psyke/extraction/cart/CartPredictor.py,sha256=YhEuaENLWixu379sIXZkFeCNc8GBnxLnR6TPCQR7sps,5743
-psyke/extraction/cart/FairTree.py,sha256=69JtbODGi9HN4AhcjuaF3e9csgBOrQoNaf1n6I0YnOY,7187
-psyke/extraction/cart/FairTreePredictor.py,sha256=kGHNLQ_HL2fWMe7g7pye7E0EmfPKPPFILklDHguJGvc,2640
+psyke/extraction/cart/FairTree.py,sha256=49ciVmqgSa6hNL2axYi-oN4DSsqrHdewH76TTYiR8x0,7529
+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
@@ -20,7 +20,7 @@ psyke/extraction/hypercubic/gridex/__init__.py,sha256=_g_JC6eFKLeg_CtkQawsUpVUAV
 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
-psyke/extraction/real/__init__.py,sha256=t3wrY4dEmZK3PhGexxHh1bhlCr4vvZ1IS6vDZoHyZjw,5379
+psyke/extraction/real/__init__.py,sha256=zAE_syurDqmFiopD5oLeIs9bROiuXy06wxoHmVqAhCA,5836
 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
@@ -35,8 +35,8 @@ 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-0.9.0.dev1.dist-info/licenses/LICENSE,sha256=KP9K6Hgezf_xdMFW7ORyKz9uA8Y8k52YJn292wcP-_E,11354
-psyke-0.9.0.dev1.dist-info/METADATA,sha256=YQQ4BWoNe-23RnTWikpxeITjxypGFYQC6pWZmVd1XDA,8394
-psyke-0.9.0.dev1.dist-info/WHEEL,sha256=Nw36Djuh_5VDukK0H78QzOX-_FQEo6V37m3nkm96gtU,91
-psyke-0.9.0.dev1.dist-info/top_level.txt,sha256=q1HglxOqqoIRukFtyis_ZNHczZg4gANRUPWkD7HAUTU,6
-psyke-0.9.0.dev1.dist-info/RECORD,,
+psyke-0.9.1.dist-info/licenses/LICENSE,sha256=KP9K6Hgezf_xdMFW7ORyKz9uA8Y8k52YJn292wcP-_E,11354
+psyke-0.9.1.dist-info/METADATA,sha256=wVhKaa9Y2XGpbwfjuuDFtLCB0LxrK916GmhkmzbLHHU,8389
+psyke-0.9.1.dist-info/WHEEL,sha256=Nw36Djuh_5VDukK0H78QzOX-_FQEo6V37m3nkm96gtU,91
+psyke-0.9.1.dist-info/top_level.txt,sha256=q1HglxOqqoIRukFtyis_ZNHczZg4gANRUPWkD7HAUTU,6
+psyke-0.9.1.dist-info/RECORD,,