lime-ndt 0.1.0__tar.gz

lime_ndt-0.1.0/LICENSE

@@ -0,0 +1,233 @@
+ Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+
+   1. Definitions.
+
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+
+   END OF TERMS AND CONDITIONS
+
+
+   APPENDIX: How to apply the Apache License to your work.
+
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+
+   Copyright 2024 [name of copyright owner]
+
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

lime_ndt-0.1.0/PKG-INFO

@@ -0,0 +1,90 @@
+Metadata-Version: 2.1
+Name: lime_ndt
+Version: 0.1.0
+Summary: Enhancing LIME through Neural Decision Trees
+Home-page: https://github.com/aymen20002005/lime_ndt/tree/main
+Author: Mohamed Aymen BOUYAHIA
+Author-email: mohamed-aymen.bouyahia@ensta-paris.fr
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+License-File: LICENSE
+
+# lime_ndt
+
+lime_ndt is a Python library that introduces an enhanced version of the LIME technique for model explainability, leveraging Neural Decision Trees (NDTs) for improved local and global interpretability of machine learning models.
+
+## Features
+
+- Enhanced LIME explanations using Neural Decision Trees.
+- Support for tabular data.
+- Tools for extracting, analyzing, and comparing decision trees and forests.
+- Utilities for submodular pick and discretization.
+- Integration with Keras and scikit-learn.
+
+## Example Usage
+
+Below is a minimal example showing how to use lime_ndt to explain a regression model on the diabetes dataset:
+
+```python
+from sklearn.datasets import load_diabetes
+from sklearn.model_selection import train_test_split
+from sklearn.ensemble import RandomForestRegressor
+from lime_ndt.lime_tabular import LimeTabularExplainer
+from lime_ndt.utils.ndt_sklearn_wrapper import NDTRegressorWrapper
+import matplotlib.pyplot as plt
+
+# Load the diabetes dataset
+diabetes = load_diabetes()
+X = diabetes.data
+y = diabetes.target
+
+# Split into train/test sets
+X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)
+
+# Train a Random Forest regressor
+rf = RandomForestRegressor(random_state=42)
+rf.fit(X_train, y_train)
+
+# Prediction function
+def predict_fn(X):
+    return rf.predict(X)
+
+# Create the LIME explainer
+explainer = LimeTabularExplainer(
+    X_train,
+    feature_names=diabetes.feature_names,
+    class_names=None,
+    discretize_continuous=True,
+    mode='regression',
+)
+
+# Create the local NDT model
+model_regressor = NDTRegressorWrapper(gammas=[1,1], D=X_train.shape[1], max_depth=4)
+
+# Explain a test instance
+exp = explainer.explain_instance(
+    X_test[0],
+    predict_fn,
+    num_features=10,
+    model_regressor=model_regressor
+)
+
+# Visualize the explanation
+exp.as_pyplot_figure()
+plt.show()
+```
+![image](https://github.com/user-attachments/assets/fbdf4b6e-8c4c-4016-998a-aa71e29e05d9)
+
+## Requirements
+
+- Python 3.7+
+- numpy, pandas, scikit-learn, keras, tensorflow, matplotlib
+
+See [requirements.txt](requirements.txt) for the full list.
+
+## License
+
+This project is licensed under the Apache License 2.0. See the [LICENSE](LICENSE) file for details.

lime_ndt-0.1.0/README.md

@@ -0,0 +1,76 @@
+# lime_ndt
+
+lime_ndt is a Python library that introduces an enhanced version of the LIME technique for model explainability, leveraging Neural Decision Trees (NDTs) for improved local and global interpretability of machine learning models.
+
+## Features
+
+- Enhanced LIME explanations using Neural Decision Trees.
+- Support for tabular data.
+- Tools for extracting, analyzing, and comparing decision trees and forests.
+- Utilities for submodular pick and discretization.
+- Integration with Keras and scikit-learn.
+
+## Example Usage
+
+Below is a minimal example showing how to use lime_ndt to explain a regression model on the diabetes dataset:
+
+```python
+from sklearn.datasets import load_diabetes
+from sklearn.model_selection import train_test_split
+from sklearn.ensemble import RandomForestRegressor
+from lime_ndt.lime_tabular import LimeTabularExplainer
+from lime_ndt.utils.ndt_sklearn_wrapper import NDTRegressorWrapper
+import matplotlib.pyplot as plt
+
+# Load the diabetes dataset
+diabetes = load_diabetes()
+X = diabetes.data
+y = diabetes.target
+
+# Split into train/test sets
+X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)
+
+# Train a Random Forest regressor
+rf = RandomForestRegressor(random_state=42)
+rf.fit(X_train, y_train)
+
+# Prediction function
+def predict_fn(X):
+    return rf.predict(X)
+
+# Create the LIME explainer
+explainer = LimeTabularExplainer(
+    X_train,
+    feature_names=diabetes.feature_names,
+    class_names=None,
+    discretize_continuous=True,
+    mode='regression',
+)
+
+# Create the local NDT model
+model_regressor = NDTRegressorWrapper(gammas=[1,1], D=X_train.shape[1], max_depth=4)
+
+# Explain a test instance
+exp = explainer.explain_instance(
+    X_test[0],
+    predict_fn,
+    num_features=10,
+    model_regressor=model_regressor
+)
+
+# Visualize the explanation
+exp.as_pyplot_figure()
+plt.show()
+```
+![image](https://github.com/user-attachments/assets/fbdf4b6e-8c4c-4016-998a-aa71e29e05d9)
+
+## Requirements
+
+- Python 3.7+
+- numpy, pandas, scikit-learn, keras, tensorflow, matplotlib
+
+See [requirements.txt](requirements.txt) for the full list.
+
+## License
+
+This project is licensed under the Apache License 2.0. See the [LICENSE](LICENSE) file for details.

lime_ndt-0.1.0/lime_ndt/RTF/DT_extraction.py

@@ -0,0 +1,174 @@
+import numpy as np
+from sklearn.ensemble import RandomForestClassifier, RandomForestRegressor
+from sklearn.tree import DecisionTreeClassifier, DecisionTreeRegressor
+
+
+def generateNewDataClassification(oracle, X, y, ratio, replace_labels=False, by_class=True, **params):
+	'''
+	Generate new data using an oracle to label randomly generated examples.
+	The quantity of new data depends on the input ratio
+	'''
+
+	newX = np.copy(X)
+	classes = np.unique(y)
+
+	if hasattr(oracle, "predict_classes"):
+		predict_func = oracle.predict_classes
+	else:
+		predict_func = oracle.predict
+
+	if replace_labels:
+		newY = predict_func(X, **params)
+		if not isinstance(newY, list):
+			newY = np.reshape(newY, (newY.shape[0],))
+
+	else:
+		newY = np.copy(y)
+
+	if ratio > 0:
+
+		if by_class:  #### distinguish between classes when sampling values for new examples
+
+			for c in classes:
+				idx = np.nonzero(y == c)[0]
+				X_cl = X[idx, :]
+
+				size = np.ceil(ratio*X_cl.shape[0]).astype(int)  ### at least one example from each class
+
+				extra_X = np.zeros((size, X_cl.shape[1]))
+
+				idx = np.random.choice(X_cl.shape[0], size=extra_X.shape,
+									   replace=True)
+
+				extra_X = X_cl[idx, np.arange(X_cl.shape[1])[None, :]]
+
+				newX = np.vstack((newX, extra_X))
+				# print(predict_func)
+				preds = predict_func(extra_X, **params)
+				if not isinstance(preds, list):
+					if len(preds.shape) > 1:
+						if preds.shape[1] == 1:
+							preds = preds.reshape((preds.shape[0],))
+					# print(preds.shape)
+					newY = np.concatenate((newY, preds))  ### generate labels for
+														  ### the new examples
+				else:
+					newY = np.concatenate((newY, preds))
+
+		else:
+
+			size = np.ceil(ratio*X.shape[0]).astype(int)  ### at least one example from each class
+
+			extra_X = np.zeros((size, X.shape[1]))
+
+			idx = np.random.choice(X.shape[0], size=extra_X.shape, replace=True)
+
+			extra_X = X[idx, np.arange(X.shape[1])[None, :]]
+
+			newX = np.vstack((newX, extra_X))
+			preds = predict_func(extra_X, **params)
+			preds = np.reshape(preds, (preds.shape[0],))
+			newY = np.concatenate((newY, preds))  ### generate labels for
+												  ### the new examples
+
+	classes_Ynew = np.unique(newY)
+	not_represented = set(classes) - set(classes_Ynew)
+
+	if bool(not_represented):
+		for c in not_represented:
+			idx = np.nonzero(y == c)[0]
+			# rand_idx = np.random.choice(idx, size=1)
+
+			newX = np.vstack((newX, X[idx, :]))
+			newY = np.concatenate((newY, y[idx]))
+
+	idx = np.arange(len(newY))
+	np.random.shuffle(idx)  ### shuffle examples
+	newX = newX[idx, :]
+	newY = np.array([newY[i] for i in idx])
+
+	# print("#################")
+	# print(idx)
+	# print(newX.shape)
+	# print(len(newY))
+
+	return(newX, newY)
+
+
+def generateNewDataRegression(oracle, X, y, ratio, replace_labels=False, by_class=None, **params):
+	'''
+	Generate new data using an oracle to label randomly generated examples.
+	The quantity of new data depends on the input ratio
+	'''
+
+	newX = np.copy(X)
+
+	if replace_labels:
+		newY = oracle.predict(X, **params)
+		newY = np.reshape(newY, (newY.shape[0],))
+
+	else:
+		newY = np.copy(y)
+
+	if ratio > 0:
+
+		size = np.ceil(ratio*X.shape[0]).astype(int)  ### at least one example from each class
+
+		extra_X = np.zeros((size, X.shape[1]))
+
+		idx = np.random.choice(X.shape[0], size=extra_X.shape, replace=True)
+
+		extra_X = X[idx, np.arange(X.shape[1])[None, :]]
+
+		newX = np.vstack((newX, extra_X))
+
+		preds = oracle.predict(extra_X, **params)
+		preds = np.reshape(preds, (preds.shape[0],))
+		newY = np.concatenate((newY, preds))  ### generate labels for
+											  ### the new examples
+
+	idx = np.arange(len(newY))
+	np.random.shuffle(idx)  ### shuffle examples
+	newX = newX[idx, :]
+	newY = newY[idx]
+
+	return(newX, newY)
+
+
+def DT_extraction(oracle, X, Y, ratio, max_depth, n_trees=1,
+				  replace_labels=False, by_class=True,
+				  classification=True, **params):
+
+	if hasattr(oracle, "_estimator_type"):
+		if oracle._estimator_type == "classifier":
+			generateNewData = generateNewDataClassification
+			DecisionTree = DecisionTreeClassifier
+			RandomForest = RandomForestClassifier
+		else:
+			generateNewData = generateNewDataRegression
+			DecisionTree = DecisionTreeRegressor
+			RandomForest = RandomForestRegressor
+
+	else:
+		if classification:
+			generateNewData = generateNewDataClassification
+			DecisionTree = DecisionTreeClassifier
+			RandomForest = RandomForestClassifier
+		else:
+			generateNewData = generateNewDataRegression
+			DecisionTree = DecisionTreeRegressor
+			RandomForest = RandomForestRegressor
+
+	newX, newY = generateNewData(oracle, X, Y, ratio, replace_labels, by_class, **params)
+
+	if n_trees == 1:
+		tree = DecisionTree(max_depth=max_depth, random_state=0)
+		tree.fit(newX, newY)
+
+		return tree
+
+	else:
+		trees = RandomForest(n_estimators=n_trees, max_depth=max_depth, random_state=0)
+		trees.fit(newX, newY)
+
+		return trees