distclassipy 0.1.5__tar.gz → 0.2.0__tar.gz

{distclassipy-0.1.5 → distclassipy-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: distclassipy
-Version: 0.1.5
+Version: 0.2.0
 Summary: A python package for a distance-based classifier which can use several different distance metrics.
 Author-email: Siddharth Chaini <sidchaini@gmail.com>
 License:                     GNU GENERAL PUBLIC LICENSE
@@ -694,7 +694,7 @@ Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: joblib>=1.3.2
-Requires-Dist: numpy<2,>=1.25.2
+Requires-Dist: numpy>=1.25.2
 Requires-Dist: pandas>=2.0.3
 Requires-Dist: scikit-learn>=1.2.2
 
@@ -740,17 +740,25 @@ X, y = make_classification(
     random_state=0,
     shuffle=False,
 )
-clf = dcpy.DistanceMetricClassifier(metric="canberra")
+# Example usage of DistanceMetricClassifier
+clf = dcpy.DistanceMetricClassifier()
 clf.fit(X, y)
-print(clf.predict([[0, 0, 0, 0]]))
+print(clf.predict([[0, 0, 0, 0]], metric="canberra"))
+
+# Example usage of EnsembleDistanceClassifier
+ensemble_clf = dcpy.EnsembleDistanceClassifier(feat_idx=0)
+ensemble_clf.fit(X, y)
+print(ensemble_clf.predict(X))
 ```
 
 ## Features
 - **Distance Metric-Based Classification**: Utilizes a variety of distance metrics for classification.
 - **Customizable for Scientific Goals**: Allows fine-tuning based on scientific objectives by selecting appropriate distance metrics and features, enhancing both computational efficiency and model performance.
 - **Interpretable Results**: Offers improved interpretability of classification outcomes by directly using distance metrics and feature importance, making it ideal for scientific applications.
-- **Efficient and Scalable**: Demonstrates lower computational requirements compared to traditional methods like Random Forests, making it suitable for large datasets
-- **Open Source and Accessible**: Available as an open-source Python package on PyPI, encouraging broad application in astronomy and beyond
+- **Efficient and Scalable**: Demonstrates lower computational requirements compared to traditional methods like Random Forests, making it suitable for large datasets.
+- **Open Source and Accessible**: Available as an open-source Python package on PyPI, encouraging broad application in astronomy and beyond.
+- **(NEW) Ensemble Distance Classification**: Leverages an ensemble approach to use different distance metrics for each quantile, improving classification performance across diverse data distributions.
+- **(NEW) Expanded Distance Metrics**: DistClassiPy now offers 43 built-in distance metrics, an increase from the previous 18. Additionally, users can still define and use custom distance metrics as needed.
 
 ## Documentation
 
@@ -765,27 +773,30 @@ DistClassiPy is released under the [GNU General Public License v3.0](https://www
 ## Citation
 
 If you use DistClassiPy in your research or project, please consider citing the paper:
-> Chaini, S., Mahabal, A., Kembhavi, A., & Bianco, F. B. (2024). Light Curve Classification with DistClassiPy: a new distance-based classifier. arXiv. https://doi.org/10.48550/arXiv.2403.12120
+> Chaini, S., Mahabal, A., Kembhavi, A., & Bianco, F. B. (2024). Light Curve Classification with DistClassiPy: a new distance-based classifier. Astronomy and Computing. https://doi.org/10.1016/j.ascom.2024.100850.
 
 ### Bibtex
 
 
 ```bibtex
-@ARTICLE{chaini2024light,
-       author = {{Chaini}, Siddharth and {Mahabal}, Ashish and {Kembhavi}, Ajit and {Bianco}, Federica B.},
-       title = "{Light Curve Classification with DistClassiPy: a new distance-based classifier}",
-       journal = {arXiv e-prints},
-       keywords = {Astrophysics - Instrumentation and Methods for Astrophysics, Astrophysics - Solar and Stellar Astrophysics, Computer Science - Machine Learning},
-       year = 2024,
-       month = mar,
-       eid = {arXiv:2403.12120},
-       pages = {arXiv:2403.12120},
-       archivePrefix = {arXiv},
+@ARTICLE{2024A&C....4800850C,
+       author = {{Chaini}, S. and {Mahabal}, A. and {Kembhavi}, A. and {Bianco}, F.~B.},
+        title = "{Light curve classification with DistClassiPy: A new distance-based classifier}",
+      journal = {Astronomy and Computing},
+     keywords = {Variable stars (1761), Astronomy data analysis (1858), Open source software (1866), Astrostatistics (1882), Classification (1907), Light curve classification (1954), Astrophysics - Instrumentation and Methods for Astrophysics, Astrophysics - Solar and Stellar Astrophysics, Computer Science - Machine Learning},
+         year = 2024,
+        month = jul,
+       volume = {48},
+          eid = {100850},
+        pages = {100850},
+          doi = {10.1016/j.ascom.2024.100850},
+archivePrefix = {arXiv},
        eprint = {2403.12120},
-       primaryClass = {astro-ph.IM},
-       adsurl = {https://ui.adsabs.harvard.edu/abs/2024arXiv240312120C},
-       adsnote = {Provided by the SAO/NASA Astrophysics Data System}
+ primaryClass = {astro-ph.IM},
+       adsurl = {https://ui.adsabs.harvard.edu/abs/2024A&C....4800850C},
+      adsnote = {Provided by the SAO/NASA Astrophysics Data System}
 }
+
 ```
   
 

{distclassipy-0.1.5 → distclassipy-0.2.0}/README.md

@@ -40,17 +40,25 @@ X, y = make_classification(
     random_state=0,
     shuffle=False,
 )
-clf = dcpy.DistanceMetricClassifier(metric="canberra")
+# Example usage of DistanceMetricClassifier
+clf = dcpy.DistanceMetricClassifier()
 clf.fit(X, y)
-print(clf.predict([[0, 0, 0, 0]]))
+print(clf.predict([[0, 0, 0, 0]], metric="canberra"))
+
+# Example usage of EnsembleDistanceClassifier
+ensemble_clf = dcpy.EnsembleDistanceClassifier(feat_idx=0)
+ensemble_clf.fit(X, y)
+print(ensemble_clf.predict(X))
 ```
 
 ## Features
 - **Distance Metric-Based Classification**: Utilizes a variety of distance metrics for classification.
 - **Customizable for Scientific Goals**: Allows fine-tuning based on scientific objectives by selecting appropriate distance metrics and features, enhancing both computational efficiency and model performance.
 - **Interpretable Results**: Offers improved interpretability of classification outcomes by directly using distance metrics and feature importance, making it ideal for scientific applications.
-- **Efficient and Scalable**: Demonstrates lower computational requirements compared to traditional methods like Random Forests, making it suitable for large datasets
-- **Open Source and Accessible**: Available as an open-source Python package on PyPI, encouraging broad application in astronomy and beyond
+- **Efficient and Scalable**: Demonstrates lower computational requirements compared to traditional methods like Random Forests, making it suitable for large datasets.
+- **Open Source and Accessible**: Available as an open-source Python package on PyPI, encouraging broad application in astronomy and beyond.
+- **(NEW) Ensemble Distance Classification**: Leverages an ensemble approach to use different distance metrics for each quantile, improving classification performance across diverse data distributions.
+- **(NEW) Expanded Distance Metrics**: DistClassiPy now offers 43 built-in distance metrics, an increase from the previous 18. Additionally, users can still define and use custom distance metrics as needed.
 
 ## Documentation
 
@@ -65,27 +73,30 @@ DistClassiPy is released under the [GNU General Public License v3.0](https://www
 ## Citation
 
 If you use DistClassiPy in your research or project, please consider citing the paper:
-> Chaini, S., Mahabal, A., Kembhavi, A., & Bianco, F. B. (2024). Light Curve Classification with DistClassiPy: a new distance-based classifier. arXiv. https://doi.org/10.48550/arXiv.2403.12120
+> Chaini, S., Mahabal, A., Kembhavi, A., & Bianco, F. B. (2024). Light Curve Classification with DistClassiPy: a new distance-based classifier. Astronomy and Computing. https://doi.org/10.1016/j.ascom.2024.100850.
 
 ### Bibtex
 
 
 ```bibtex
-@ARTICLE{chaini2024light,
-       author = {{Chaini}, Siddharth and {Mahabal}, Ashish and {Kembhavi}, Ajit and {Bianco}, Federica B.},
-       title = "{Light Curve Classification with DistClassiPy: a new distance-based classifier}",
-       journal = {arXiv e-prints},
-       keywords = {Astrophysics - Instrumentation and Methods for Astrophysics, Astrophysics - Solar and Stellar Astrophysics, Computer Science - Machine Learning},
-       year = 2024,
-       month = mar,
-       eid = {arXiv:2403.12120},
-       pages = {arXiv:2403.12120},
-       archivePrefix = {arXiv},
+@ARTICLE{2024A&C....4800850C,
+       author = {{Chaini}, S. and {Mahabal}, A. and {Kembhavi}, A. and {Bianco}, F.~B.},
+        title = "{Light curve classification with DistClassiPy: A new distance-based classifier}",
+      journal = {Astronomy and Computing},
+     keywords = {Variable stars (1761), Astronomy data analysis (1858), Open source software (1866), Astrostatistics (1882), Classification (1907), Light curve classification (1954), Astrophysics - Instrumentation and Methods for Astrophysics, Astrophysics - Solar and Stellar Astrophysics, Computer Science - Machine Learning},
+         year = 2024,
+        month = jul,
+       volume = {48},
+          eid = {100850},
+        pages = {100850},
+          doi = {10.1016/j.ascom.2024.100850},
+archivePrefix = {arXiv},
        eprint = {2403.12120},
-       primaryClass = {astro-ph.IM},
-       adsurl = {https://ui.adsabs.harvard.edu/abs/2024arXiv240312120C},
-       adsnote = {Provided by the SAO/NASA Astrophysics Data System}
+ primaryClass = {astro-ph.IM},
+       adsurl = {https://ui.adsabs.harvard.edu/abs/2024A&C....4800850C},
+      adsnote = {Provided by the SAO/NASA Astrophysics Data System}
 }
+
 ```
   
 

{distclassipy-0.1.5 → distclassipy-0.2.0}/distclassipy/__init__.py

@@ -22,7 +22,17 @@ You should have received a copy of the GNU General Public License
 along with this program.  If not, see <https://www.gnu.org/licenses/>.
 """
 
-from .classifier import DistanceMetricClassifier  # noqa
-from .distances import Distance  # noqa
+from .classifier import (
+    DistanceMetricClassifier,
+    EnsembleDistanceClassifier,
+)
+from .distances import Distance, _ALL_METRICS
 
-__version__ = "0.1.5"
+__version__ = "0.2.0"
+
+__all__ = [
+    "DistanceMetricClassifier",
+    "EnsembleDistanceClassifier",
+    "Distance",
+    "_ALL_METRICS",
+]