psyke 0.8.7__py3-none-any.whl → 0.8.9__py3-none-any.whl

psyke/__init__.py

@@ -256,14 +256,14 @@ class Extractor(EvaluableModel, ABC):
                           [Extractor.ClassificationScore.F1])[Extractor.ClassificationScore.F1][-1]
 
     @staticmethod
-    def cart(predictor, max_depth: int = 3, max_leaves: int = 3,
+    def cart(predictor, max_depth: int = 3, max_leaves: int = 3, max_features=None,
              discretization: Iterable[DiscreteFeature] = None, normalization=None, simplify: bool = True) -> Extractor:
         """
         Creates a new Cart extractor.
         """
         from psyke.extraction.cart import Cart
-        return Cart(predictor, max_depth, max_leaves, discretization=discretization, normalization=normalization,
-                    simplify=simplify)
+        return Cart(predictor, max_depth, max_leaves, max_features,
+                    discretization=discretization, normalization=normalization, simplify=simplify)
 
     @staticmethod
     def divine(predictor, k: int = 5, patience: int = 15, close_to_center: bool = True,

psyke/extraction/cart/__init__.py

@@ -1,3 +1,5 @@
+from abc import ABC
+
 from sklearn.tree import DecisionTreeClassifier, DecisionTreeRegressor
 
 from psyke.extraction import PedagogicalExtractor
@@ -14,26 +16,28 @@ import pandas as pd
 TREE_SEED = get_default_random_seed()
 
 
-class Cart(PedagogicalExtractor):
+class Cart(PedagogicalExtractor, ABC):
 
-    def __init__(self, predictor, max_depth: int = 3, max_leaves: int = None,
+    def __init__(self, predictor, max_depth: int = 3, max_leaves: int = None, max_features=None,
                  discretization: Iterable[DiscreteFeature] = None,
                  normalization=None, simplify: bool = True):
         super().__init__(predictor, discretization, normalization)
         self._cart_predictor = CartPredictor(normalization=normalization)
         self.depth = max_depth
         self.leaves = max_leaves
+        self.max_features = max_features
         self._simplify = simplify
 
-    def _create_body(self, variables: dict[str, Var], constraints: LeafConstraints) -> Iterable[Struct]:
+    def _create_body(self, variables: dict[str, Var], conditions: LeafConstraints) -> Iterable[Struct]:
         results = []
-        for feature_name, constraint, value in constraints:
-            features = [d for d in self.discretization if feature_name in d.admissible_values]
-            feature: DiscreteFeature = features[0] if len(features) > 0 else None
-            results.append(create_term(variables[feature_name], constraint) if feature is None else
-                           create_term(variables[feature.name],
-                                       feature.admissible_values[feature_name],
-                                       isinstance(constraint, GreaterThan)))
+        for feature_name, cond_list in conditions.items():
+            for condition in cond_list:
+                features = [d for d in self.discretization if feature_name in d.admissible_values]
+                feature: DiscreteFeature = features[0] if len(features) > 0 else None
+                results.append(create_term(variables[feature_name], condition) if feature is None else
+                               create_term(variables[feature.name],
+                                           feature.admissible_values[feature_name],
+                                           isinstance(condition, GreaterThan)))
         return results
 
     @staticmethod
@@ -41,11 +45,12 @@ class Cart(PedagogicalExtractor):
         simplified = [nodes.pop(0)]
         while len(nodes) > 0:
             first_node = nodes[0][0]
-            for condition in first_node:
-                if all([condition in [node[0] for node in nodes][i] for i in range(len(nodes))]):
-                    [node[0].remove(condition) for node in nodes]
+            for k, conditions in first_node.items():
+                for condition in conditions:
+                    if all(k in node[0] and condition in node[0][k] for node in nodes):
+                        [node[0][k].remove(condition) for node in nodes]
             simplified.append(nodes.pop(0))
-        return simplified
+        return [({k: v for k, v in rule.items() if v != []}, prediction) for rule, prediction in simplified]
 
     def _create_theory(self, data: pd.DataFrame) -> Theory:
         new_theory = mutable_theory()
@@ -66,13 +71,26 @@ class Cart(PedagogicalExtractor):
 
     def _extract(self, data: pd.DataFrame) -> Theory:
         tree = DecisionTreeClassifier if isinstance(data.iloc[0, -1], str) else DecisionTreeRegressor
-        self._cart_predictor.predictor = tree(random_state=TREE_SEED, max_depth=self.depth, max_leaf_nodes=self.leaves)
+        self._cart_predictor.predictor = tree(random_state=TREE_SEED, max_depth=self.depth,
+                                              max_leaf_nodes=self.leaves, max_features=self.max_features)
         self._cart_predictor.predictor.fit(data.iloc[:, :-1], data.iloc[:, -1])
         return self._create_theory(data)
 
     def _predict(self, dataframe: pd.DataFrame) -> Iterable:
         return self._cart_predictor.predict(dataframe)
 
+    def predict_why(self, data: dict[str, float], verbose=True):
+        prediction = None
+        conditions = {}
+        if self.normalization is not None:
+            data = {k: v * self.normalization[k][1] + self.normalization[k][0] if k in self.normalization else v
+                    for k, v in data.items()}
+        for conditions, prediction in self._cart_predictor:
+            if all(all(interval.is_in(data[variable]) for interval in intervals)
+                   for variable, intervals in conditions.items()):
+                break
+        return prediction, conditions
+
     @property
     def n_rules(self) -> int:
         return self._cart_predictor.n_leaves

psyke/extraction/cart/predictor.py

@@ -2,9 +2,9 @@ from collections import Iterable
 from typing import Union, Any
 import numpy as np
 from sklearn.tree import DecisionTreeClassifier, DecisionTreeRegressor
-from psyke.schema import Value, LessThan, GreaterThan
+from psyke.schema import Value, LessThan, GreaterThan, SchemaException
 
-LeafConstraints = list[tuple[str, Value, bool]]
+LeafConstraints = dict[str, list[Value]]
 LeafSequence = Iterable[tuple[LeafConstraints, Any]]
 
 
@@ -25,8 +25,17 @@ class CartPredictor:
         if self.normalization is not None:
             thresholds = [threshold * self.normalization[feature][1] + self.normalization[feature][0]
                           for feature, threshold in zip(features, thresholds)]
-        return [(feature, LessThan(threshold) if condition else GreaterThan(threshold), condition)
-                for feature, condition, threshold in zip(features, conditions, thresholds)]
+        cond_dict = {}
+        for feature, condition, threshold in zip(features, conditions, thresholds):
+            cond = LessThan(threshold) if condition else GreaterThan(threshold)
+            if feature in cond_dict:
+                try:
+                    cond_dict[feature][-1] *= cond
+                except SchemaException:
+                    cond_dict[feature].append(cond)
+            else:
+                cond_dict[feature] = [cond]
+        return cond_dict
 
     def __get_leaves(self) -> Iterable[int]:
         return [i for i, (left_child, right_child) in enumerate(zip(
@@ -39,7 +48,8 @@ class CartPredictor:
         else:
             return self._predictor.tree_.value[node]
 
-    def __path(self, node: int, path=[]) -> Iterable[(int, bool)]:
+    def __path(self, node: int, path=None) -> Iterable[(int, bool)]:
+        path = [] if path is None else path
         if node == 0:
             return path
         father = list(self._left_children if node in self._left_children else self._right_children).index(node)

psyke/schema/__init__.py

@@ -3,20 +3,27 @@ import math
 from typing import Callable
 from psyke.utils import get_int_precision
 
+
+class SchemaException(Exception):
+
+    def __init__(self, message: str):
+        super().__init__(message)
+
+
 _EMPTY_INTERSECTION_EXCEPTION: Callable = lambda x, y: \
-    Exception(f"Empty intersection between two Value: {str(x)} and {str(y)}")
+    SchemaException(f"Empty intersection between two Value: {str(x)} and {str(y)}")
 
 _NOT_IMPLEMENTED_INTERSECTION: Callable = lambda x, y: \
-    Exception("Not implemented intersection between: " + str(x) + ' and ' + str(y))
+    SchemaException(f"Not implemented intersection between: {str(x)} and {str(y)}")
 
 _OPERATION_WITH_WRONG_TYPE: Callable = lambda x, y: \
-    Exception("Calling method with wrong type argument: " + str(x) + ' and ' + str(y))
+    SchemaException("Calling method with wrong type argument: " + str(x) + ' and ' + str(y))
 
 _EMPTY_UNION_EXCEPTION: Callable = lambda x, y: \
-    Exception(f"Empty union between two Value: {str(x)} and {str(y)}")
+    SchemaException(f"Empty union between two Value: {str(x)} and {str(y)}")
 
 _NOT_IMPLEMENTED_UNION: Callable = lambda x, y: \
-    Exception("Not implemented union between: " + str(x) + ' and ' + str(y))
+    SchemaException("Not implemented union between: " + str(x) + ' and ' + str(y))
 
 PRECISION = get_int_precision()
 STRING_PRECISION = str(PRECISION)

{psyke-0.8.7.dist-info → psyke-0.8.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: psyke
-Version: 0.8.7
+Version: 0.8.9
 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-0.8.7.dist-info → psyke-0.8.9.dist-info}/RECORD

@@ -1,12 +1,12 @@
-psyke/__init__.py,sha256=_Gm4C_o9AifRNXjsPVe0znQy-kTfGxDih7O1YeO3KlY,18601
+psyke/__init__.py,sha256=V_sOXKt_5fYmNABwpveJd10u7Wy7A6wlLECBJY_ra_E,18634
 psyke/hypercubepredictor.py,sha256=MlSRLky6J1I07qKcH98c9WvEjFHGyBiz_LU9W_oDnqs,4572
 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/extraction/__init__.py,sha256=ziZ8T9eAOZjKipepE5_j1zfZgyFPONjW8MGERSk83nI,743
-psyke/extraction/cart/__init__.py,sha256=LzocPLpZVGGVgUu4bh9Bu4GlzD1HuFQh795GgxV2Gys,3622
-psyke/extraction/cart/predictor.py,sha256=2-2mv5fI0lTwwfTaEonxKh0ZUdhxuIEE6OP_rJxgmqc,3019
+psyke/extraction/cart/__init__.py,sha256=r2mDULg7oTHrIMPw9lqD6MyXhkkymP4r9PoGUKjAWCM,4569
+psyke/extraction/cart/predictor.py,sha256=_YBedfyz4rGIBeNpN7OaL2BKWdF_5nuq8AlXkVfCtvk,3359
 psyke/extraction/hypercubic/__init__.py,sha256=w_NmfSjh8fCWLDXVXpRLiAApq697cvUSPTgju-jtZCA,10620
 psyke/extraction/hypercubic/hypercube.py,sha256=GKjplRl34BegrA3JclvlkrL7hXftdUUMXndmRFFoJic,25697
 psyke/extraction/hypercubic/strategy.py,sha256=X-roIsfcpJyMdo2px5JtbhP7-XE-zUNkaEK7XGXoWA8,1636
@@ -22,7 +22,7 @@ psyke/extraction/real/__init__.py,sha256=fFqiwgWTpu5Jx9lz5CdSfs1QyqWYFLQDG7tc5M6
 psyke/extraction/real/utils.py,sha256=eHGU-Y0inn_8jrk9lMcuRUKXpsTkI-s_myXSWz4bALQ,2190
 psyke/extraction/trepan/__init__.py,sha256=KpZpk0btCWV4bS-DOmpgpYscSQ5FEMyP54ekm7ZedME,6583
 psyke/extraction/trepan/utils.py,sha256=iSUJ1ooNQT_VO1KfBZuIUeUsyUbGdQf_pSEE87vMeQg,2320
-psyke/schema/__init__.py,sha256=GjT4Wyw008pS8WuuGz5-YC4iQphvk83B8dtkzL-3a_g,25929
+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
 psyke/tuning/orchid/__init__.py,sha256=s64iABbteik27CrRPHSVHNZX25JKlDu7YYjhseOizxw,3618
@@ -33,8 +33,8 @@ psyke/utils/logic.py,sha256=7bbW6qcKof5PlqoQ0n5Kt3Obcot-KqGAvpE8rMXvEPE,12419
 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-0.8.7.dist-info/LICENSE,sha256=KP9K6Hgezf_xdMFW7ORyKz9uA8Y8k52YJn292wcP-_E,11354
-psyke-0.8.7.dist-info/METADATA,sha256=DefC2-n4FXf0UlT6xFToHNOUuCbPGQZwrKrkjnYwX8k,8102
-psyke-0.8.7.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-psyke-0.8.7.dist-info/top_level.txt,sha256=q1HglxOqqoIRukFtyis_ZNHczZg4gANRUPWkD7HAUTU,6
-psyke-0.8.7.dist-info/RECORD,,
+psyke-0.8.9.dist-info/LICENSE,sha256=KP9K6Hgezf_xdMFW7ORyKz9uA8Y8k52YJn292wcP-_E,11354
+psyke-0.8.9.dist-info/METADATA,sha256=KDPbq3WrDph3KhEDTTNaFuHawsgeDl2XQ24K4lZLx-4,8102
+psyke-0.8.9.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+psyke-0.8.9.dist-info/top_level.txt,sha256=q1HglxOqqoIRukFtyis_ZNHczZg4gANRUPWkD7HAUTU,6
+psyke-0.8.9.dist-info/RECORD,,