distclassipy 0.1.3__py3-none-any.whl → 0.1.5__py3-none-any.whl

distclassipy/__init__.py

@@ -1,16 +1,28 @@
-"""
-A module for using distance metrics for classification.
+"""A module for using distance metrics for classification.
 
 Classes:
-    DistanceMetricClassifier - A classifier that uses a specified distance metric for classification.
+    DistanceMetricClassifier - A classifier that uses a specified distance metric for
+                               classification.
     Distance - A class that provides various distance metrics for use in classification.
+
+
+Copyright (C) 2024  Siddharth Chaini
+-----
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+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,
-)  # Importing the DistanceMetricClassifier from the classifier module
-from .distances import (
-    Distance,
-)  # Importing the Distance class from the distances module
+from .classifier import DistanceMetricClassifier  # noqa
+from .distances import Distance  # noqa
 
-__version__ = "0.1.3"
+__version__ = "0.1.5"

distclassipy/classifier.py

@@ -1,34 +1,72 @@
+"""A module containing the distance metric classifier.
+
+This module contains the DistanceMetricClassifier introduced by Chaini et al. (2024)
+in "Light Curve Classification with DistClassiPy: a new distance-based classifier"
+
+Copyright (C) 2024  Siddharth Chaini
+-----
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program.  If not, see <https://www.gnu.org/licenses/>.
 """
-A module which contains the DistanceMetricClassifier introduced by Chaini et al. (2024) in "Light Curve Classification with DistClassiPy: a new distance-based classifier".
-"""
+
+from typing import Callable
 
 import numpy as np
+
 import pandas as pd
+
 import scipy
-from .distances import Distance
+
 from sklearn.base import BaseEstimator, ClassifierMixin
-from sklearn.utils.validation import check_X_y, check_array, check_is_fitted
-from sklearn.utils.multiclass import unique_labels
 from sklearn.neighbors import KernelDensity
-from typing import Callable
+from sklearn.utils.multiclass import unique_labels
+from sklearn.utils.validation import check_X_y, check_array, check_is_fitted
+
+from .distances import Distance
+
+# Hardcoded source packages to check for distance metrics.
+METRIC_SOURCES_ = {
+    "scipy.spatial.distance": scipy.spatial.distance,
+    "distances.Distance": Distance(),
+}
 
 
 class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
-    """
-    A distance-based classifier that supports the use of various distance metrics.
+    """A distance-based classifier that supports different distance metrics.
 
-    The distance metric classifier determines the similarity between features in a dataset by leveraging the use of different distance metrics to. A specified distance metric is used to compute the distance between a given object and a centroid for every training class in the feature space. The classifier supports the use of different statistical measures for constructing the centroid and scaling the computed distance. Additionally, the distance metric classifier also optionally provides an estimate of the confidence of the classifier's predictions.
+    The distance metric classifier determines the similarity between features in a
+    dataset by leveraging the use of different distance metrics to. A specified
+    distance metric is used to compute the distance between a given object and a
+    centroid for every training class in the feature space. The classifier supports
+    the use of different statistical measures for constructing the centroid and scaling
+    the computed distance. Additionally, the distance metric classifier also
+    optionally provides an estimate of the confidence of the classifier's predictions.
 
     Parameters
     ----------
     metric : str or callable, default="euclidean"
         The distance metric to use for calculating the distance between features.
     scale : bool, default=True
-        Whether to scale the distance between the test object and the centroid for a class in the feature space. If True, the data will be scaled based on the specified dispersion statistic.
+        Whether to scale the distance between the test object and the centroid for a
+        class in the feature space. If True, the data will be scaled based on the
+        specified dispersion statistic.
     central_stat : {"mean", "median"}, default="median"
-        The statistic used to calculate the central tendency of the data to construct the feature-space centroid. Supported statistics are "mean" and "median".
+        The statistic used to calculate the central tendency of the data to construct
+        the feature-space centroid. Supported statistics are "mean" and "median".
     dispersion_stat : {"std", "iqr"}, default="std"
-        The statistic used to calculate the dispersion of the data for scaling the distance. Supported  statistics are "std" for standard deviation and "iqr" for inter-quartile range.
+        The statistic used to calculate the dispersion of the data for scaling the
+        distance. Supported  statistics are "std" for standard deviation and "iqr"
+        for inter-quartile range.
 
         .. versionadded:: 0.1.0
 
@@ -59,11 +97,14 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
 
     Notes
     -----
-    If using distance metrics supported by SciPy, it is desirable to pass a string, which allows SciPy to use an optimized C version of the code instead of the slower Python version.
+    If using distance metrics supported by SciPy, it is desirable to pass a string,
+    which allows SciPy to use an optimized C version of the code instead of the slower
+    Python version.
 
     References
     ----------
-    .. [1] "Light Curve Classification with DistClassiPy: a new distance-based classifier"
+    .. [1] "Light Curve Classification with DistClassiPy: a new distance-based
+            classifier"
 
     Examples
     --------
@@ -88,9 +129,7 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
         calculate_kde: bool = True,
         calculate_1d_dist: bool = True,
     ):
-        """
-        Initialize the classifier with specified parameters.
-        """
+        """Initialize the classifier with specified parameters."""
         self.metric = metric
         self.scale = scale
         self.central_stat = central_stat
@@ -98,19 +137,13 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
         self.calculate_kde = calculate_kde
         self.calculate_1d_dist = calculate_1d_dist
 
-    def set_metric_fn_(self):
-        """
-        Set the metric function based on the provided metric.
+    def initialize_metric_function(self):
+        """Set the metric function based on the provided metric.
 
-        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.
+        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
@@ -118,9 +151,10 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
         elif isinstance(self.metric, str):
             metric_str_lowercase = self.metric.lower()
             metric_found = False
-            for package_str, source in 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
+                # 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"
@@ -131,7 +165,8 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
                     self.metric_fn_ = getattr(source, metric_str_lowercase)
                     metric_found = True
 
-                    # Use the string as an argument if it belongs to scipy as it is optimized
+                    # 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"
@@ -140,14 +175,22 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
                     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"
+                    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"
                 )
 
     def fit(self, X: np.array, y: np.array, feat_labels: list[str] = None):
-        """
-        Calculate the feature space centroid for all classes in the training set (X,y) using the central statistic. If scaling is enabled, also calculate the appropriate dispersion statistic.
+        """Calculate the feature space centroid for all classes.
 
-        This involves computing the centroid for every class in the feature space and optionally calculating the kernel density estimate and 1-dimensional distance.
+        This function calculates the feature space centroid in the training
+        set (X, y) for all classes using the central statistic. If scaling
+        is enabled, it also calculates the appropriate dispersion statistic.
+        This involves computing the centroid for every class in the feature space and
+        optionally calculating the kernel density estimate and 1-dimensional distance.
 
         Parameters
         ----------
@@ -156,7 +199,8 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
         y : array-like of shape (n_samples,)
             The target values (class labels).
         feat_labels : list of str, optional, default=None
-            The feature labels. If not provided, default labels representing feature number will be used.
+            The feature labels. If not provided, default labels representing feature
+            number will be used.
 
         Returns
         -------
@@ -167,7 +211,7 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
         self.classes_ = unique_labels(y)
         self.n_features_in_ = X.shape[1]
 
-        self.set_metric_fn_()
+        self.initialize_metric_function()
 
         if feat_labels is None:
             feat_labels = [f"Feature_{x}" for x in range(X.shape[1])]
@@ -188,7 +232,8 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
             std_list = []
             for cur_class in self.classes_:
                 cur_X = X[y == cur_class]
-                # Note we're using ddof=1 because we're dealing with a sample. See more: https://stackoverflow.com/a/46083501/10743245
+                # Note we're using ddof=1 because we're dealing with a sample.
+                # See more: https://stackoverflow.com/a/46083501/10743245
                 std_list.append(np.std(cur_X, axis=0, ddof=1).ravel())
             df_std = pd.DataFrame(
                 data=np.array(std_list), index=self.classes_, columns=feat_labels
@@ -200,7 +245,8 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
 
             for cur_class in self.classes_:
                 cur_X = X[y == cur_class]
-                # Note we're using ddof=1 because we're dealing with a sample. See more: https://stackoverflow.com/a/46083501/10743245
+                # Note we're using ddof=1 because we're dealing with a sample.
+                # See more: https://stackoverflow.com/a/46083501/10743245
                 iqr_list.append(
                     np.quantile(cur_X, q=0.75, axis=0).ravel()
                     - np.quantile(cur_X, q=0.25, axis=0).ravel()
@@ -233,7 +279,9 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
     def predict(self, X: np.array):
         """Predict the class labels for the provided X.
 
-        The prediction is based on the distance of each data point in the input sample to the centroid for each class in the feature space. The predicted class is the one whose centroid is the closest to the input sample.
+        The prediction is based on the distance of each data point in the input sample
+        to the centroid for each class in the feature space. The predicted class is the
+        one whose centroid is the closest to the input sample.
 
         Parameters
         ----------
@@ -277,12 +325,14 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
         return y_pred
 
     def predict_and_analyse(self, X: np.array):
-        """
-        Predict the class labels for the provided X and perform analysis.
+        """Predict the class labels for the provided X and perform analysis.
 
-        The prediction is based on the distance of each data point in the input sample to the centroid for each class in the feature space. The predicted class is the one whose centroid is the closest to the input sample.
+        The prediction is based on the distance of each data point in the input sample
+        to the centroid for each class in the feature space. The predicted class is the
+        one whose centroid is the closest to the input sample.
 
-        The analysis involves saving all calculated distances and confidences as an attribute for inspection and analysis later.
+        The analysis involves saving all calculated distances and confidences as an
+        attribute for inspection and analysis later.
 
         Parameters
         ----------
@@ -381,20 +431,24 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
         return y_pred
 
     def calculate_confidence(self, method: str = "distance_inverse"):
-        """
-        Calculate the confidence for each prediction.
+        """Calculate the confidence for each prediction.
 
-        The confidence is calculated based on either the distance of each data point to the centroids of the training data, optionally the kernel density estimate or 1-dimensional distance.
+        The confidence is calculated based on either the distance of each data point to
+        the centroids of the training data, optionally the kernel density estimate or
+        1-dimensional distance.
 
         Parameters
         ----------
-        method : {"distance_inverse", "1d_distance_inverse", "kde_likelihood"}, default="distance_inverse"
-            The method to use for calculating confidence. Default is 'distance_inverse'.
+        method : {"distance_inverse", "1d_distance_inverse","kde_likelihood"},
+                 default="distance_inverse"
+            The method to use for calculating confidence. Default is
+            'distance_inverse'.
         """
         check_is_fitted(self, "is_fitted_")
         if not hasattr(self, "analyis_"):
             raise ValueError(
-                "Use predict_and_analyse() instead of predict() for confidence calculation."
+                "Use predict_and_analyse() instead of predict() for "
+                "confidence calculation."
             )
 
         # Calculate confidence for each prediction
@@ -409,7 +463,8 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
         elif method == "1d_distance_inverse":
             if not self.calculate_1d_dist:
                 raise ValueError(
-                    "method='1d_distance_inverse' is only valid if calculate_1d_dist is set to True"
+                    "method='1d_distance_inverse' is only valid if calculate_1d_dist "
+                    "is set to True"
                 )
             self.confidence_df_ = pd.DataFrame(
                 data=self.conf_cl_.T, columns=[f"{x}_conf" for x in self.classes_]
@@ -418,7 +473,8 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
         elif method == "kde_likelihood":
             if not self.calculate_kde:
                 raise ValueError(
-                    "method='kde_likelihood' is only valid if calculate_kde is set to True"
+                    "method='kde_likelihood' is only valid if calculate_kde is set "
+                    "to True"
                 )
 
             self.confidence_df_ = pd.DataFrame(