Introduction

Usage

from FS.pso import jfs

from FS.de import jfs

Input

Output

Example 1 : Particle Swarm Optimization ( PSO )

import numpy as npimport pandas as pdfrom sklearn.neighbors import KNeighborsClassifierfrom sklearn.model_selection import train_test_splitfrom FS.pso import jfs   # change this to switch algorithm import matplotlib.pyplot as plt# load datadata  = pd.read_csv('ionosphere.csv')data  = data.valuesfeat  = np.asarray(data[:, 0:-1])   # feature vectorlabel = np.asarray(data[:, -1])     # label vector# split data into train & validation (70 -- 30)xtrain, xtest, ytrain, ytest = train_test_split(feat, label, test_size=0.3, stratify=label)fold = {'xt':xtrain, 'yt':ytrain, 'xv':xtest, 'yv':ytest}# parameterk    = 5     # k-value in KNNN    = 10    # number of particlesT    = 100   # maximum number of iterationsw    = 0.9c1   = 2c2   = 2opts = {'k':k, 'fold':fold, 'N':N, 'T':T, 'w':w, 'c1':c1, 'c2':c2}# perform feature selectionfmdl = jfs(feat, label, opts)sf   = fmdl['sf']# model with selected featuresnum_train = np.size(xtrain, 0)num_valid = np.size(xtest, 0)x_train   = xtrain[:, sf]y_train   = ytrain.reshape(num_train)  # Solve bugx_valid   = xtest[:, sf]y_valid   = ytest.reshape(num_valid)  # Solve bugmdl       = KNeighborsClassifier(n_neighbors = k) mdl.fit(x_train, y_train)# accuracyy_pred    = mdl.predict(x_valid)Acc       = np.sum(y_valid == y_pred)  / num_validprint("Accuracy:", 100 * Acc)# number of selected featuresnum_feat = fmdl['nf']print("Feature Size:", num_feat)# plot convergencecurve   = fmdl['c']curve   = curve.reshape(np.size(curve,1))x       = np.arange(0, opts['T'], 1.0) + 1.0fig, ax = plt.subplots()ax.plot(x, curve, 'o-')ax.set_xlabel('Number of Iterations')ax.set_ylabel('Fitness')ax.set_title('PSO')ax.grid()plt.show()

Example 2 : Genetic Algorithm ( GA )

import numpy as npimport pandas as pdfrom sklearn.neighbors import KNeighborsClassifierfrom sklearn.model_selection import train_test_splitfrom FS.ga import jfs   # change this to switch algorithm import matplotlib.pyplot as plt# load datadata  = pd.read_csv('ionosphere.csv')data  = data.valuesfeat  = np.asarray(data[:, 0:-1])label = np.asarray(data[:, -1])# split data into train & validation (70 -- 30)xtrain, xtest, ytrain, ytest = train_test_split(feat, label, test_size=0.3, stratify=label)fold = {'xt':xtrain, 'yt':ytrain, 'xv':xtest, 'yv':ytest}# parameterk    = 5     # k-value in KNNN    = 10    # number of chromosomesT    = 100   # maximum number of generationsCR   = 0.8MR   = 0.01opts = {'k':k, 'fold':fold, 'N':N, 'T':T, 'CR':CR, 'MR':MR}# perform feature selectionfmdl = jfs(feat, label, opts)sf   = fmdl['sf']# model with selected featuresnum_train = np.size(xtrain, 0)num_valid = np.size(xtest, 0)x_train   = xtrain[:, sf]y_train   = ytrain.reshape(num_train)  # Solve bugx_valid   = xtest[:, sf]y_valid   = ytest.reshape(num_valid)  # Solve bugmdl       = KNeighborsClassifier(n_neighbors = k) mdl.fit(x_train, y_train)# accuracyy_pred    = mdl.predict(x_valid)Acc       = np.sum(y_valid == y_pred)  / num_validprint("Accuracy:", 100 * Acc)# number of selected featuresnum_feat = fmdl['nf']print("Feature Size:", num_feat)# plot convergencecurve   = fmdl['c']curve   = curve.reshape(np.size(curve,1))x       = np.arange(0, opts['T'], 1.0) + 1.0fig, ax = plt.subplots()ax.plot(x, curve, 'o-')ax.set_xlabel('Number of Iterations')ax.set_ylabel('Fitness')ax.set_title('GA')ax.grid()plt.show()

Requirement

List of available wrapper feature selection methods