Add DrafonFlySelectionCV with sklearn-api

docs/requirement.txt

@@ -6,4 +6,6 @@ mkdocs-meta-descriptions-plugin
 jupyter_contrib_nbextensions
 ipython>=7.16.3 # not directly required, pinned by Snyk to avoid a vulnerability
 pygments>=2.7.4 # not directly required, pinned by Snyk to avoid a vulnerability
-mistune>=2.0.1 # not directly required, pinned by Snyk to avoid a vulnerability
+mistune>=2.0.1 # not directly required, pinned by Snyk to avoid a vulnerability
+setuptools>=65.5.1 # not directly required, pinned by Snyk to avoid a vulnerability
+wheel>=0.38.0 # not directly required, pinned by Snyk to avoid a vulnerability

example/DragonFly.ipynb

@@ -0,0 +1,105 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# from dragon_fly import DragonFlyFeatureSelectionCV\n",
+    "from zoofs.feature_selection import DragonFlySelectionCV\n",
+    "from sklearn.linear_model import Lasso\n",
+    "from sklearn.datasets import load_diabetes, make_regression\n",
+    "from sklearn.pipeline import Pipeline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "selector = DragonFlySelectionCV(Lasso(),\n",
+    "                                n_jobs=-1,\n",
+    "                                min_features_to_select=10,\n",
+    "                                n_population=50,\n",
+    "                                n_iteration=100,\n",
+    "                                verbose=2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X,y = make_regression()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "selector.fit(X,y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_transformed = selector.transform(X)\n",
+    "X_transformed.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pipe = Pipeline([(\"selector\", selector), (\"estimator\", Lasso())])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pipe.fit(X,y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "py310",
+   "language": "python",
+   "name": "py310"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

tests/test_DragonFlySelectionCV.py

@@ -0,0 +1,46 @@
+# Pytest code to test DragonFlySelectionCV class
+# I will use English comments as requested.
+
+import pytest
+from sklearn.ensemble import RandomForestRegressor
+from sklearn.cross_decomposition import PLSRegression
+from sklearn.datasets import make_regression
+
+from zoofs.feature_selection import DragonFlySelectionCV
+
+# Sample dataset
+X, y = make_regression(n_samples=50, n_features=20, noise=0.1, random_state=42)
+
+# Test case parameters
+params = [
+    (RandomForestRegressor(), False),
+    (PLSRegression(), True),
+]
+
+@pytest.mark.parametrize("estimator, auto_n_components", params)
+def test_dragonfly_fit_transform(estimator, auto_n_components):
+    """
+    Test if DragonFlySelectionCV can fit and transform without any errors.
+
+    Parameters
+    ----------
+    estimator : object
+        The base estimator to use for feature selection.
+    auto_n_components : bool
+        Whether or not to automatically adjust the number of components for PLSRegression.
+    """
+    # Initialize DragonFlySelectionCV with the given parameters
+    dragonfly = DragonFlySelectionCV(
+        estimator=estimator,
+        auto_n_components=auto_n_components,
+        n_population=15,
+        n_iteration=15,
+        n_jobs=-1
+    )
+
+    # Test if the 'fit' method works without any errors
+    dragonfly.fit(X, y)
+    # Test if the 'transform' method works without any errors
+    X_transformed = dragonfly.transform(X)
+    # Check if the transformed array has fewer or equal features than the original array
+    assert X_transformed.shape[1] <= X.shape[1]

zoofs/__init__.py

@@ -5,3 +5,5 @@
 from zoofs.gravitationaloptimization import GravitationalOptimization
 from zoofs.baseoptimizationalgorithm import BaseOptimizationAlgorithm
 from zoofs.harrishawkoptimization import HarrisHawkOptimization
+
+__all__ = ["feature_selection"]

zoofs/baseoptimizationalgorithm.py

@@ -33,6 +33,12 @@ def fit(self):
     def sigmoid(self, x):
         return 1 / (1 + np.exp(-x))
 
+    def _get_bestScore(self):
+        if self.minimize:
+            return self.best_score
+        else:
+            return -(self.best_score)
+
     def _evaluate_fitness(
         self, model, x_train, y_train, x_valid, y_valid, particle_swarm_flag=0, dragon_fly_flag=0
     ):

zoofs/feature_selection/DragonFly.ipynb

@@ -0,0 +1,181 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# from dragon_fly import DragonFlyFeatureSelectionCV\n",
+    "from zoofs.feature_selection import DragonFlySelectionCV\n",
+    "from sklearn.linear_model import Lasso\n",
+    "from sklearn.datasets import load_diabetes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "selector = DragonFlySelectionCV(Lasso())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X,y = load_diabetes(return_X_y=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "self.best_features_\n",
+      "[0 1 2 3 4 5 6 7 8 9]\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "DragonFlyFeatureSelectionCV(estimator=Lasso())"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "selector.fit(X,y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "bool_ = selector.transform(X)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[ 0.03807591,  0.05068012,  0.06169621, ..., -0.00259226,\n",
+       "         0.01990842, -0.01764613],\n",
+       "       [-0.00188202, -0.04464164, -0.05147406, ..., -0.03949338,\n",
+       "        -0.06832974, -0.09220405],\n",
+       "       [ 0.08529891,  0.05068012,  0.04445121, ..., -0.00259226,\n",
+       "         0.00286377, -0.02593034],\n",
+       "       ...,\n",
+       "       [ 0.04170844,  0.05068012, -0.01590626, ..., -0.01107952,\n",
+       "        -0.04687948,  0.01549073],\n",
+       "       [-0.04547248, -0.04464164,  0.03906215, ...,  0.02655962,\n",
+       "         0.04452837, -0.02593034],\n",
+       "       [-0.04547248, -0.04464164, -0.0730303 , ..., -0.03949338,\n",
+       "        -0.00421986,  0.00306441]])"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "bool_"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(442, 10)"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "bool_.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.pipeline import Pipeline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "TypeError",
+     "evalue": "Pipeline.__init__() takes 2 positional arguments but 3 were given",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[9], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m pipe \u001b[38;5;241m=\u001b[39m \u001b[43mPipeline\u001b[49m\u001b[43m(\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mselector\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mselector\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mestimator\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mLasso\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\n",
+      "\u001b[1;31mTypeError\u001b[0m: Pipeline.__init__() takes 2 positional arguments but 3 were given"
+     ]
+    }
+   ],
+   "source": [
+    "pipe = Pipeline([\"selector\", selector], [\"estimator\", Lasso()])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "py310",
+   "language": "python",
+   "name": "py310"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

zoofs/feature_selection/__init__.py

@@ -0,0 +1,5 @@
+from .dragonfly import  DragonFlySelectionCV
+
+__all__ = [
+    "DragonFlySelectionCV",
+]