粒子群优化支持向量机代码(PSO-SVM)

粒子群优化支持向量机代码

数据WFs1

import pandas as pd
import numpy as np
import random
from sklearn.svm import SVC
import matplotlib.pyplot as plt
from sklearn.model_selection import cross_val_predict
from sklearn.metrics import confusion_matrix
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import cross_val_score
from sklearn.ensemble import RandomForestClassifier as RFC
from sklearn.feature_selection import RFE

# 1.读取训练数据集
data = pd.read_csv(r"WFs1.csv")
x = data.iloc[:, 1:]
Y = data.iloc[:, 0]
print(x.shape)

# 2.标准化
scaler = StandardScaler()
X = scaler.fit_transform(x)

# 3.初始化参数
W = 0.5                                 # 惯性因子
c1 = 0.2                                # 学习因子
c2 = 0.5                                # 学习因子
n_iterations = 10                       # 迭代次数
n_particles = 100                       # 种群规模

# 4.设置适应度值
def fitness_function(position):

    svclassifier = SVC(kernel='rbf', gamma=position[0], C=position[1])      # 参数gamma和惩罚参数c以实数向量的形式进行编码作为PSO的粒子的位置
    svclassifier.fit(X, Y)
    score = cross_val_score(svclassifier, X, Y, cv=9).mean()                # 交叉验证
    print(score)                                                            # 分类精度
    Y_pred = cross_val_predict(svclassifier, X, Y, cv=9)                    # 获取预测值

    # 我这里是三分类，下面输出错误分类结果
    return confusion_matrix(Y, Y_pred)[0][1] + confusion_matrix(Y, Y_pred)[0][2] + confusion_matrix(Y, Y_pred)[1][0] + \
           confusion_matrix(Y, Y_pred)[1][2] + confusion_matrix(Y, Y_pred)[2][0] + confusion_matrix(Y, Y_pred)[2][1]\
        ,  confusion_matrix(Y, Y_pred)[0][1] + confusion_matrix(Y, Y_pred)[0][2] + confusion_matrix(Y, Y_pred)[1][0] + \
           confusion_matrix(Y, Y_pred)[1][2] + confusion_matrix(Y, Y_pred)[2][0] + confusion_matrix(Y, Y_pred)[2][1]

# 5.粒子图
def plot(position):
    x = []
    y = []
    for i in range(0, len(particle_position_vector)):
        x.append(particle_position_vector[i][0])
        y.append(particle_position_vector[i][1])
    colors = (0, 0, 0)
    plt.scatter(x, y, c = colors, alpha = 0.1)
    # 设置横纵坐标的名称以及对应字体格式
    #font2 = {'family': 'Times New Roman','weight': 'normal', 'size': 20,}
    plt.xlabel('gamma')
    plt.ylabel('C')
    plt.axis([0, 10, 0, 10],)
    plt.gca().set_aspect('equal', adjustable='box')
    return plt.show()

# 6.初始化粒子位置，进行迭代
particle_position_vector = np.array([np.array([random.random() * 10, random.random() * 10]) for _ in range(n_particles)])
pbest_position = particle_position_vector
pbest_fitness_value = np.array([float('inf') for _ in range(n_particles)])
gbest_fitness_value = np.array([float('inf'), float('inf')])
gbest_position = np.array([float('inf'), float('inf')])
velocity_vector = ([np.array([0, 0]) for _ in range(n_particles)])
iteration = 0
while iteration < n_iterations:
    plot(particle_position_vector)
    for i in range(n_particles):
        fitness_cadidate = fitness_function(particle_position_vector[i])
        print("error of particle-", i, "is (training, test)", fitness_cadidate, " At (gamma, c): ",
              particle_position_vector[i])

        if (pbest_fitness_value[i] > fitness_cadidate[1]):
            pbest_fitness_value[i] = fitness_cadidate[1]
            pbest_position[i] = particle_position_vector[i]

        if (gbest_fitness_value[1] > fitness_cadidate[1]):
            gbest_fitness_value = fitness_cadidate
            gbest_position = particle_position_vector[i]

        elif (gbest_fitness_value[1] == fitness_cadidate[1] and gbest_fitness_value[0] > fitness_cadidate[0]):
            gbest_fitness_value = fitness_cadidate
            gbest_position = particle_position_vector[i]

    for i in range(n_particles):
        new_velocity = (W * velocity_vector[i]) + (c1 * random.random()) * (
                    pbest_position[i] - particle_position_vector[i]) + (c2 * random.random()) * (
                                   gbest_position - particle_position_vector[i])
        new_position = new_velocity + particle_position_vector[i]
        particle_position_vector[i] = new_position

    iteration = iteration + 1

# 7.输出最终结果
print("The best position is ", gbest_position, "in iteration number", iteration, "with error (train, test):",
      fitness_function(gbest_position))