粒子群算法特征选择python

粒子群算法（Particle Swarm Optimization，PSO）是一种基于群体智能的优化算法，常用于特征选择。以下是使用Python实现粒子群算法特征选择的示例代码：

import numpy as np
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier

# 加载数据集
iris = load_iris()
X, y = iris.data, iris.target

# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# 定义目标函数，即分类器的准确率
def fitness_function(position, X_train, y_train, X_test, y_test):
    # 选择特征
    idx = np.where(position == 1)[0]
    if len(idx) == 0:
        return 0
    X_train_selected = X_train[:, idx]
    X_test_selected = X_test[:, idx]
    # 训练分类器
    clf = KNeighborsClassifier()
    clf.fit(X_train_selected, y_train)
    # 计算准确率
    accuracy = clf.score(X_test_selected, y_test)
    return accuracy

# 定义粒子群类
class PSO:
    def __init__(self, n_particles, n_features, max_iter, w, c1, c2):
        self.n_particles = n_particles  # 粒子数
        self.n_features = n_features  # 特征数
        self.max_iter = max_iter  # 最大迭代次数
        self.w = w  # 惯性权重
        self.c1 = c1  # 自我学习因子
        self.c2 = c2  # 社会学习因子
        # 初始化粒子位置和速度
        self.positions = np.random.randint(0, 2, size=(n_particles, n_features))
        self.velocities = np.zeros((n_particles, n_features))
        # 初始化全局最优位置和适应度
        self.global_best_position = None
        self.global_best_fitness = -np.inf
    
    def optimize(self, X_train, y_train, X_test, y_test):
        for i in range(self.max_iter):
            # 计算适应度
            fitness = np.array([fitness_function(p, X_train, y_train, X_test, y_test) for p in self.positions])
            # 更新全局最优位置和适应度
            if fitness.max() > self.global_best_fitness:
                self.global_best_fitness = fitness.max()
                self.global_best_position = self.positions[fitness.argmax(), :]
            # 更新粒子速度和位置
            r1, r2 = np.random.rand(2, self.n_particles, self.n_features)
            self.velocities = self.w * self.velocities + self.c1 * r1 * (self.global_best_position - self.positions) + \
                              self.c2 * r2 * (np.tile(self.global_best_position, (self.n_particles, 1)) - self.positions)
            self.positions = np.round(1 / (1 + np.exp(-self.velocities)))  # sigmoid函数映射到[0, 1]
    
    def get_selected_features(self):
        return np.where(self.global_best_position == 1)[0]

# 设置超参数
n_particles = 20
n_features = X_train.shape[1]
max_iter = 50
w = 0.7
c1 = 1.4
c2 = 1.4

# 运行粒子群算法
pso = PSO(n_particles, n_features, max_iter, w, c1, c2)
pso.optimize(X_train, y_train, X_test, y_test)

# 输出选择的特征
selected_features = pso.get_selected_features()
print('Selected features:', selected_features)

其中，fitness_function是目标函数，PSO是粒子群类，optimize方法用于运行粒子群算法，get_selected_features方法用于获取选择的特征。在本例中，使用的是鸢尾花数据集，特征数为4，分类器为KNN，超参数根据经验设置。最终输出选择的特征。