distclassipy 0.1.2__tar.gz → 0.1.4__tar.gz

{distclassipy-0.1.2 → distclassipy-0.1.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: distclassipy
-Version: 0.1.2
+Version: 0.1.4
 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
@@ -679,7 +679,7 @@ License:                     GNU GENERAL PUBLIC LICENSE
         <https://www.gnu.org/licenses/why-not-lgpl.html>.
         
 Project-URL: Repository, https://github.com/sidchaini/DistClassiPy
-Project-URL: Documenation, https://sidchaini.github.io/DistClassiPy/
+Project-URL: Documentation, https://sidchaini.github.io/DistClassiPy/
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Education
@@ -694,9 +694,9 @@ Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: joblib>=1.3.2
-Requires-Dist: numpy>=1.26.3
-Requires-Dist: pandas>=2.2.0
-Requires-Dist: scikit-learn>=1.4.0
+Requires-Dist: numpy>=1.25.2
+Requires-Dist: pandas>=2.0.3
+Requires-Dist: scikit-learn>=1.2.2
 
 <h1 align="center">
 <picture align="center">
@@ -712,6 +712,9 @@ Requires-Dist: scikit-learn>=1.4.0
 [![License - GPL-3](https://img.shields.io/pypi/l/distclassipy.svg)](https://github.com/sidchaini/distclassipy/blob/main/LICENSE)
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 
+[![arXiv](https://img.shields.io/badge/arXiv-astro--ph%2F2403.12120-red)](https://arxiv.org/abs/2403.12120) 
+[![ascl:2403.002](https://img.shields.io/badge/ascl-2403.002-blue.svg?colorB=262255)](https://ascl.net/2403.002)
+
 <!-- [![Paper](https://img.shields.io/badge/DOI-10.1038%2Fs41586--020--2649--2-blue)](
 https://doi.org/10.1038/s41586-020-2649-2) -->
 
@@ -743,9 +746,11 @@ print(clf.predict([[0, 0, 0, 0]]))
 ```
 
 ## Features
-- Multiple distance metrics support
-- Easy integration with existing data processing pipelines
-- Efficient and scalable for large datasets
+- **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
 
 ## Documentation
 
@@ -760,30 +765,28 @@ 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:
-> Light Curve Classification with DistClassiPy: a new distance-based classifier (submitted to A&C)
-
+> 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
 
-<!--
 ### Bibtex
 
 
 ```bibtex
-@ARTICLE{Chaini2024,
-       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 = {Submitted to A&C},
-    %  keywords = {},
-         year = 2024,
-      %   month = ,
-      %  volume = {},
-      %     eid = {},
-      %   pages = {},
-      %     doi = {},
-      %  adsurl = {},
-      % adsnote = {}
+@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},
+       eprint = {2403.12120},
+       primaryClass = {astro-ph.IM},
+       adsurl = {https://ui.adsabs.harvard.edu/abs/2024arXiv240312120C},
+       adsnote = {Provided by the SAO/NASA Astrophysics Data System}
 }
 ```
--->
   
 
 <!-- You can also find citation information in the [CITATION.cff](https://github.com/sidchaini/DistClassiPy/CITATION.cff) file. -->

{distclassipy-0.1.2 → distclassipy-0.1.4}/README.md

@@ -12,6 +12,9 @@
 [![License - GPL-3](https://img.shields.io/pypi/l/distclassipy.svg)](https://github.com/sidchaini/distclassipy/blob/main/LICENSE)
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 
+[![arXiv](https://img.shields.io/badge/arXiv-astro--ph%2F2403.12120-red)](https://arxiv.org/abs/2403.12120) 
+[![ascl:2403.002](https://img.shields.io/badge/ascl-2403.002-blue.svg?colorB=262255)](https://ascl.net/2403.002)
+
 <!-- [![Paper](https://img.shields.io/badge/DOI-10.1038%2Fs41586--020--2649--2-blue)](
 https://doi.org/10.1038/s41586-020-2649-2) -->
 
@@ -43,9 +46,11 @@ print(clf.predict([[0, 0, 0, 0]]))
 ```
 
 ## Features
-- Multiple distance metrics support
-- Easy integration with existing data processing pipelines
-- Efficient and scalable for large datasets
+- **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
 
 ## Documentation
 
@@ -60,30 +65,28 @@ 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:
-> Light Curve Classification with DistClassiPy: a new distance-based classifier (submitted to A&C)
-
+> 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
 
-<!--
 ### Bibtex
 
 
 ```bibtex
-@ARTICLE{Chaini2024,
-       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 = {Submitted to A&C},
-    %  keywords = {},
-         year = 2024,
-      %   month = ,
-      %  volume = {},
-      %     eid = {},
-      %   pages = {},
-      %     doi = {},
-      %  adsurl = {},
-      % adsnote = {}
+@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},
+       eprint = {2403.12120},
+       primaryClass = {astro-ph.IM},
+       adsurl = {https://ui.adsabs.harvard.edu/abs/2024arXiv240312120C},
+       adsnote = {Provided by the SAO/NASA Astrophysics Data System}
 }
 ```
--->
   
 
 <!-- You can also find citation information in the [CITATION.cff](https://github.com/sidchaini/DistClassiPy/CITATION.cff) file. -->

{distclassipy-0.1.2 → distclassipy-0.1.4}/distclassipy/__init__.py

@@ -12,4 +12,5 @@ from .classifier import (
 from .distances import (
     Distance,
 )  # Importing the Distance class from the distances module
-from .version import __version__
+
+__version__ = "0.1.4"

{distclassipy-0.1.2 → distclassipy-0.1.4}/distclassipy/classifier.py

@@ -1,3 +1,7 @@
+"""
+A module which contains the DistanceMetricClassifier introduced by Chaini et al. (2024) in "Light Curve Classification with DistClassiPy: a new distance-based classifier".
+"""
+
 import numpy as np
 import pandas as pd
 import scipy
@@ -94,12 +98,6 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
         self.calculate_kde = calculate_kde
         self.calculate_1d_dist = calculate_1d_dist
 
-        # Hardcoded source packages to check for distance metrics.
-        self.metric_sources_ = {
-            "scipy.spatial.distance": scipy.spatial.distance,
-            "distances.Distance": Distance(),
-        }
-
     def set_metric_fn_(self):
         """
         Set the metric function based on the provided metric.
@@ -107,6 +105,12 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
         If the metric is a string, the function will look for a corresponding function in scipy.spatial.distance or distances.Distance. If the metric is a function, it will be used directly.
         """
 
+        # Hardcoded source packages to check for distance metrics.
+        metric_sources_ = {
+            "scipy.spatial.distance": scipy.spatial.distance,
+            "distances.Distance": Distance(),
+        }
+
         if callable(self.metric):
             self.metric_fn_ = self.metric
             self.metric_arg_ = self.metric
@@ -114,17 +118,26 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
         elif isinstance(self.metric, str):
             metric_str_lowercase = self.metric.lower()
             metric_found = False
-            for package_str, source in self.metric_sources_.items():
+            for package_str, source in metric_sources_.items():
+
+                # Don't use scipy for jaccard as their implementation only works with booleans - use custom jaccard instead
+                if (
+                    package_str == "scipy.spatial.distance"
+                    and metric_str_lowercase == "jaccard"
+                ):
+                    continue
+
                 if hasattr(source, metric_str_lowercase):
                     self.metric_fn_ = getattr(source, metric_str_lowercase)
                     metric_found = True
-                    if package_str == "scipy.spatial.distance":
-                        # Use the string as an argument if it belongs to scipy as it is optimized
-                        self.metric_arg_ = self.metric
-                    else:
-                        self.metric_arg_ = self.metric_fn_
-                    break
 
+                    # Use the string as an argument if it belongs to scipy as it is optimized
+                    self.metric_arg_ = (
+                        self.metric
+                        if package_str == "scipy.spatial.distance"
+                        else self.metric_fn_
+                    )
+                    break
             if not metric_found:
                 raise ValueError(
                     f"{self.metric} metric not found. Please pass a string of the name of a metric in scipy.spatial.distance or distances.Distance, or pass a metric function directly. For a list of available metrics, see: https://sidchaini.github.io/DistClassiPy/distances.html or https://docs.scipy.org/doc/scipy/reference/spatial.distance.html"
@@ -358,9 +371,7 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
                         sum_1d_dists = sum_1d_dists + dists / self.df_iqr_.loc[cl, feat]
                     else:
                         sum_1d_dists = sum_1d_dists + dists
-                confs = 1 / sum_1d_dists
-                # Add epsilon later
-                # confs = 1 / (sum_1d_dists + np.finfo(float).eps)
+                confs = 1 / np.clip(sum_1d_dists, a_min=np.finfo(float).eps, a_max=None)
                 conf_cl.append(confs)
             conf_cl = np.array(conf_cl)
             self.conf_cl_ = conf_cl
@@ -388,7 +399,9 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
 
         # Calculate confidence for each prediction
         if method == "distance_inverse":
-            self.confidence_df_ = 1 / self.centroid_dist_df_
+            self.confidence_df_ = 1 / np.clip(
+                self.centroid_dist_df_, a_min=np.finfo(float).eps, a_max=None
+            )
             self.confidence_df_.columns = [
                 x.replace("_dist", "_conf") for x in self.confidence_df_.columns
             ]

{distclassipy-0.1.2 → distclassipy-0.1.4}/distclassipy/distances.py

@@ -24,6 +24,7 @@ Notes
 
     In addition, the following code was added to all functions for array conversion:
         u,v = np.asarray(u), np.asarray(v)
+-----
 """
 
 import numpy as np
@@ -89,33 +90,33 @@ class Distance:
         with np.errstate(divide="ignore", invalid="ignore"):
             return np.sum(np.where(uvmult != 0, ((u - v) ** 2 * (u + v)) / uvmult, 0))
 
-    def bhattacharyya(self, u, v):
-        """
-        Calculate the Bhattacharyya distance between two vectors.
-
-        Returns a distance value between 0 and 1.
-
-        Parameters
-        ----------
-        - u, v: Input vectors between which the distance is to be calculated.
-
-        Returns
-        -------
-        - The Bhattacharyya distance between the two vectors.
-
-        References
-        ----------
-            1. Bhattacharyya A (1947) On a measure of divergence between two
-               statistical populations defined by probability distributions,
-               Bull. Calcutta Math. Soc., 35, 99–109.
-            2. Sung-Hyuk C. (2007) Comprehensive Survey on Distance/Similarity
-               Measures between Probability Density Functions. International
-               Journal of Mathematical Models and Methods in Applied Sciences.
-               1(4), 300-307.
-            3. https://en.wikipedia.org/wiki/Bhattacharyya_distance
-        """
-        u, v = np.asarray(u), np.asarray(v)
-        return -np.log(np.sum(np.sqrt(u * v)))
+    # def bhattacharyya(self, u, v):
+    #     """
+    #     Calculate the Bhattacharyya distance between two vectors.
+
+    #     Returns a distance value between 0 and 1.
+
+    #     Parameters
+    #     ----------
+    #     - u, v: Input vectors between which the distance is to be calculated.
+
+    #     Returns
+    #     -------
+    #     - The Bhattacharyya distance between the two vectors.
+
+    #     References
+    #     ----------
+    #         1. Bhattacharyya A (1947) On a measure of divergence between two
+    #            statistical populations defined by probability distributions,
+    #            Bull. Calcutta Math. Soc., 35, 99–109.
+    #         2. Sung-Hyuk C. (2007) Comprehensive Survey on Distance/Similarity
+    #            Measures between Probability Density Functions. International
+    #            Journal of Mathematical Models and Methods in Applied Sciences.
+    #            1(4), 300-307.
+    #         3. https://en.wikipedia.org/wiki/Bhattacharyya_distance
+    #     """
+    #     u, v = np.asarray(u), np.asarray(v)
+    #     return -np.log(np.sum(np.sqrt(u * v)))
 
     def braycurtis(self, u, v):
         """
@@ -397,26 +398,26 @@ class Distance:
         u, v = np.asarray(u), np.asarray(v)
         return np.linalg.norm(u - v)
 
-    def fidelity(self, u, v):
-        """
-        Calculate the fidelity distance between two vectors.
+    # def fidelity(self, u, v):
+    #     """
+    #     Calculate the fidelity distance between two vectors.
 
-        The fidelity distance measures the similarity between two probability distributions.
+    #     The fidelity distance measures the similarity between two probability distributions.
 
-        Parameters
-        ----------
-        - u, v: Input vectors between which the distance is to be calculated.
+    #     Parameters
+    #     ----------
+    #     - u, v: Input vectors between which the distance is to be calculated.
 
-        Returns
-        -------
-        - The fidelity distance between the two vectors.
+    #     Returns
+    #     -------
+    #     - The fidelity distance between the two vectors.
 
-        Notes
-        -----
-            Added by SC.
-        """
-        u, v = np.asarray(u), np.asarray(v)
-        return 1 - (np.sum(np.sqrt(u * v)))
+    #     Notes
+    #     -----
+    #         Added by SC.
+    #     """
+    #     u, v = np.asarray(u), np.asarray(v)
+    #     return 1 - (np.sum(np.sqrt(u * v)))
 
     def google(self, u, v):
         """
@@ -515,26 +516,26 @@ class Distance:
         u, v = np.asarray(u), np.asarray(v)
         return np.sqrt(2 * np.sum((np.sqrt(u) - np.sqrt(v)) ** 2))
 
-    def inner(self, u, v):
-        """
-        Calculate the inner product distance between two vectors.
+    # def inner(self, u, v):
+    #     """
+    #     Calculate the inner product distance between two vectors.
 
-        The inner product distance is a measure of similarity between two vectors, based on their inner product.
+    #     The inner product distance is a measure of similarity between two vectors, based on their inner product.
 
-        Parameters
-        ----------
-        - u, v: Input vectors between which the distance is to be calculated.
+    #     Parameters
+    #     ----------
+    #     - u, v: Input vectors between which the distance is to be calculated.
 
-        Returns
-        -------
-        - The inner product distance between the two vectors.
+    #     Returns
+    #     -------
+    #     - The inner product distance between the two vectors.
 
-        Notes
-        -----
-            Added by SC.
-        """
-        u, v = np.asarray(u), np.asarray(v)
-        return 1 - np.dot(u, v)
+    #     Notes
+    #     -----
+    #         Added by SC.
+    #     """
+    #     u, v = np.asarray(u), np.asarray(v)
+    #     return 1 - np.dot(u, v)
 
     def jaccard(self, u, v):
         """
@@ -1032,32 +1033,32 @@ class Distance:
         with np.errstate(divide="ignore", invalid="ignore"):
             return np.sum(np.where(u != 0, (u - v) ** 2 / u, 0))
 
-    def nonintersection(self, u, v):
-        """
-        Calculate the Nonintersection distance between two vectors.
-
-        Parameters
-        ----------
-        - u, v: Input vectors between which the distance is to be calculated.
-
-        Returns
-        -------
-        - The Nonintersection distance between the two vectors.
-
-        References
-        ----------
-            1. Sung-Hyuk C. (2007) Comprehensive Survey on Distance/Similarity
-               Measures between Probability Density Functions. International
-               Journal of Mathematical Models and Methods in Applied Sciences.
-               1(4), 300-307.
-
-        Notes
-        -----
-            When used for comparing two probability density functions (pdfs),
-            Nonintersection distance equals half of Cityblock distance.
-        """
-        u, v = np.asarray(u), np.asarray(v)
-        return 1 - np.sum(np.minimum(u, v))
+    # def nonintersection(self, u, v):
+    #     """
+    #     Calculate the Nonintersection distance between two vectors.
+
+    #     Parameters
+    #     ----------
+    #     - u, v: Input vectors between which the distance is to be calculated.
+
+    #     Returns
+    #     -------
+    #     - The Nonintersection distance between the two vectors.
+
+    #     References
+    #     ----------
+    #         1. Sung-Hyuk C. (2007) Comprehensive Survey on Distance/Similarity
+    #            Measures between Probability Density Functions. International
+    #            Journal of Mathematical Models and Methods in Applied Sciences.
+    #            1(4), 300-307.
+
+    #     Notes
+    #     -----
+    #         When used for comparing two probability density functions (pdfs),
+    #         Nonintersection distance equals half of Cityblock distance.
+    #     """
+    #     u, v = np.asarray(u), np.asarray(v)
+    #     return 1 - np.sum(np.minimum(u, v))
 
     def pearson_chisq(self, u, v):
         """

{distclassipy-0.1.2 → distclassipy-0.1.4}/distclassipy.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: distclassipy
-Version: 0.1.2
+Version: 0.1.4
 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
@@ -679,7 +679,7 @@ License:                     GNU GENERAL PUBLIC LICENSE
         <https://www.gnu.org/licenses/why-not-lgpl.html>.
         
 Project-URL: Repository, https://github.com/sidchaini/DistClassiPy
-Project-URL: Documenation, https://sidchaini.github.io/DistClassiPy/
+Project-URL: Documentation, https://sidchaini.github.io/DistClassiPy/
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Education
@@ -694,9 +694,9 @@ Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: joblib>=1.3.2
-Requires-Dist: numpy>=1.26.3
-Requires-Dist: pandas>=2.2.0
-Requires-Dist: scikit-learn>=1.4.0
+Requires-Dist: numpy>=1.25.2
+Requires-Dist: pandas>=2.0.3
+Requires-Dist: scikit-learn>=1.2.2
 
 <h1 align="center">
 <picture align="center">
@@ -712,6 +712,9 @@ Requires-Dist: scikit-learn>=1.4.0
 [![License - GPL-3](https://img.shields.io/pypi/l/distclassipy.svg)](https://github.com/sidchaini/distclassipy/blob/main/LICENSE)
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 
+[![arXiv](https://img.shields.io/badge/arXiv-astro--ph%2F2403.12120-red)](https://arxiv.org/abs/2403.12120) 
+[![ascl:2403.002](https://img.shields.io/badge/ascl-2403.002-blue.svg?colorB=262255)](https://ascl.net/2403.002)
+
 <!-- [![Paper](https://img.shields.io/badge/DOI-10.1038%2Fs41586--020--2649--2-blue)](
 https://doi.org/10.1038/s41586-020-2649-2) -->
 
@@ -743,9 +746,11 @@ print(clf.predict([[0, 0, 0, 0]]))
 ```
 
 ## Features
-- Multiple distance metrics support
-- Easy integration with existing data processing pipelines
-- Efficient and scalable for large datasets
+- **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
 
 ## Documentation
 
@@ -760,30 +765,28 @@ 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:
-> Light Curve Classification with DistClassiPy: a new distance-based classifier (submitted to A&C)
-
+> 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
 
-<!--
 ### Bibtex
 
 
 ```bibtex
-@ARTICLE{Chaini2024,
-       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 = {Submitted to A&C},
-    %  keywords = {},
-         year = 2024,
-      %   month = ,
-      %  volume = {},
-      %     eid = {},
-      %   pages = {},
-      %     doi = {},
-      %  adsurl = {},
-      % adsnote = {}
+@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},
+       eprint = {2403.12120},
+       primaryClass = {astro-ph.IM},
+       adsurl = {https://ui.adsabs.harvard.edu/abs/2024arXiv240312120C},
+       adsnote = {Provided by the SAO/NASA Astrophysics Data System}
 }
 ```
--->
   
 
 <!-- You can also find citation information in the [CITATION.cff](https://github.com/sidchaini/DistClassiPy/CITATION.cff) file. -->

{distclassipy-0.1.2 → distclassipy-0.1.4}/distclassipy.egg-info/SOURCES.txt

@@ -5,7 +5,6 @@ setup.py
 distclassipy/__init__.py
 distclassipy/classifier.py
 distclassipy/distances.py
-distclassipy/version.py
 distclassipy.egg-info/PKG-INFO
 distclassipy.egg-info/SOURCES.txt
 distclassipy.egg-info/dependency_links.txt

distclassipy-0.1.4/distclassipy.egg-info/requires.txt

@@ -0,0 +1,4 @@
+joblib>=1.3.2
+numpy>=1.25.2
+pandas>=2.0.3
+scikit-learn>=1.2.2

{distclassipy-0.1.2 → distclassipy-0.1.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "distclassipy"
-version = "0.1.2"
+dynamic = ["version"]
 description = "A python package for a distance-based classifier which can use several different distance metrics."
 readme = "README.md"
 requires-python = ">=3.10"
@@ -24,11 +24,14 @@ classifiers = [
 ]
 dependencies = [
     "joblib>=1.3.2",
-    "numpy>=1.26.3",
-    "pandas>=2.2.0",
-    "scikit-learn>=1.4.0"
+    "numpy>=1.25.2",
+    "pandas>=2.0.3",
+    "scikit-learn>=1.2.2"
 ]
 
+[tool.setuptools.dynamic]
+version = {attr = "distclassipy.__version__"}
+
 [project.urls]
 Repository = "https://github.com/sidchaini/DistClassiPy"
-Documenation = "https://sidchaini.github.io/DistClassiPy/"
+Documentation = "https://sidchaini.github.io/DistClassiPy/"

distclassipy-0.1.4/setup.py

@@ -0,0 +1,21 @@
+from setuptools import setup
+import codecs
+import os.path
+
+
+def read(rel_path):
+    here = os.path.abspath(os.path.dirname(__file__))
+    with codecs.open(os.path.join(here, rel_path), "r") as fp:
+        return fp.read()
+
+
+def get_version(rel_path):
+    for line in read(rel_path).splitlines():
+        if line.startswith("__version__"):
+            delim = '"' if '"' in line else "'"
+            return line.split(delim)[1]
+    else:
+        raise RuntimeError("Unable to find version string.")
+
+
+setup(version=get_version("distclassipy/__init__.py"))

{distclassipy-0.1.2 → distclassipy-0.1.4}/tests/test_classifier.py

@@ -1,6 +1,7 @@
 import pytest
 import numpy as np
 from distclassipy.classifier import DistanceMetricClassifier
+from sklearn.utils.estimator_checks import check_estimator
 
 
 # Test initialization of the classifier with specific parameters
@@ -10,12 +11,8 @@ def test_init():
     assert clf.scale is True
 
 
-# Fix later
-# # Test classifier estimator compatibility with scikit-learn
-# def test_estimator_compatibility():
-#     from sklearn.utils.estimator_checks import check_estimator
-
-#     check_estimator(DistanceMetricClassifier())
+def test_sklearn_compatibility():
+    check_estimator(DistanceMetricClassifier())
 
 
 # Test fitting the classifier to a dataset
@@ -105,7 +102,7 @@ def test_metric_invalid():
 def test_central_stat_median():
     X = np.array([[1, 2], [3, 4], [5, 6]])  # Sample feature set
     y = np.array([0, 1, 0])  # Sample target values
-    clf = DistanceMetricClassifier(central_stat="median")
+    clf = DistanceMetricClassifier(central_stat="median", dispersion_stat="iqr")
     clf.fit(X, y)
     assert clf.central_stat == "median"
 

distclassipy-0.1.4/tests/test_distances.py

@@ -0,0 +1,17 @@
+import pytest
+import numpy as np
+from distclassipy.distances import Distance
+
+# Initialize the Distance class to use its methods for testing
+distance = Distance()
+
+
+def test_all_distances():
+    # Define two sample vectors
+    u = np.array([1, 2, 3])
+    v = np.array([1, 2, 3])
+    for func_name in dir(distance):
+        if callable(getattr(distance, func_name)) and not func_name.startswith("__"):
+            func = getattr(distance, func_name)
+            d = func(u, v)
+            assert d >= 0

distclassipy-0.1.2/distclassipy/version.py

@@ -1,16 +0,0 @@
-import os
-import re
-
-
-def get_version_from_pyproject():
-    pyproject_path = os.path.join(os.path.dirname(__file__), "..", "pyproject.toml")
-    with open(pyproject_path, "r") as f:
-        pyproject_content = f.read()
-    version_match = re.search(r'^version\s*=\s*"(.*?)"', pyproject_content, re.M)
-    if version_match:
-        return version_match.group(1)
-    else:
-        raise RuntimeError("Version not found in pyproject.toml")
-
-
-__version__ = get_version_from_pyproject()

distclassipy-0.1.2/distclassipy.egg-info/requires.txt

@@ -1,4 +0,0 @@
-joblib>=1.3.2
-numpy>=1.26.3
-pandas>=2.2.0
-scikit-learn>=1.4.0

distclassipy-0.1.2/setup.py

@@ -1,3 +0,0 @@
-from setuptools import setup
-
-setup()

distclassipy-0.1.2/tests/test_distances.py

@@ -1,35 +0,0 @@
-import pytest
-import numpy as np
-from distclassipy.distances import Distance
-
-# Initialize the Distance class to use its methods for testing
-distance = Distance()
-
-
-# Test for the accuracy distance calculation
-def test_acc_distance():
-    # Define two sample vectors
-    u = np.array([1, 2, 3])
-    v = np.array([2, 4, 6])
-    # Calculate the expected result manually
-    expected = np.mean([np.sum(np.abs(u - v)), np.max(np.abs(u - v))])
-    # Assert that the calculated distance matches the expected result
-    assert distance.acc(u, v) == expected
-
-
-# Test for the Vicis Wave Hedges distance calculation
-def test_vicis_wave_hedges():
-    # Define two sample vectors
-    u = np.array([1, 2, 3])
-    v = np.array([2, 4, 6])
-    # Calculate the minimum of u and v element-wise
-    uvmin = np.minimum(u, v)
-    # Calculate the absolute difference between u and v
-    u_v = np.abs(u - v)
-    # Calculate the expected result manually
-    expected = np.sum(np.where(uvmin != 0, u_v / uvmin, 0))
-    # Assert that the calculated distance matches the expected result
-    assert distance.vicis_wave_hedges(u, v) == expected
-
-
-# HAVE TO ADD MORE TESTS