sklearn上的svm

# coding: utf-8
"""
svm 四个核在iris上的测试
"""
import time

import matplotlib as mpl
import matplotlib.pyplot as plt
from keras.utils import to_categorical
import numpy as np
import pandas as pd
# 训练测试数据分割
# 准确率
from sklearn.metrics import accuracy_score
# from keras.utils import to_categorical
from sklearn.model_selection import train_test_split
# SVC向量机
from sklearn.preprocessing import LabelEncoder, LabelBinarizer
from sklearn.svm import SVC

encoder = LabelEncoder()
lb = LabelBinarizer()
# 乱码设置
# 设置属性防止中文乱码
mpl.rcParams[‘font.sans-serif‘] = [u‘SimHei‘]
mpl.rcParams[‘axes.unicode_minus‘] = False


def load_data():
    raw_data = np.loadtxt("./iris.txt", dtype=‘str‘, encoding=‘utf-8‘)
    x, y = list(), list()
    for index in range(len(raw_data)):
        x.append([float(i) for i in raw_data[index].split(",")[:-1]])
        y.append(raw_data[index].split(",")[-1])
    x = np.array(x)
    # y = encoder.fit_transform(_y)
    print(lb.fit_transform(y))
    y = pd.Categorical(y).codes
    x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=33)
    return x_train, x_test, y_train, y_test


if __name__ == ‘__main__‘:
    x_train, x_test, y_train, y_test = load_data()
    print(y_test)
    # 构建分类器/
    # kernel是不同的方法
    svm1 = SVC(C=1, kernel=‘linear‘)
    svm2 = SVC(C=1, kernel=‘rbf‘)
    svm3 = SVC(C=1, kernel=‘poly‘)  # 表现的更好

    svm4 = SVC(C=1, kernel=‘sigmoid‘)
    # 分类器的训练
    t0 = time.time()
    svm1.fit(x_train, y_train)
    t1 = time.time()
    svm2.fit(x_train, y_train)
    t2 = time.time()
    svm3.fit(x_train, y_train)
    t3 = time.time()
    svm4.fit(x_train, y_train)
    t4 = time.time()
    # 训练完后做什么呢？当然是画图测试准确率
    print(svm3.predict(x_train))
    svm1_train_score = accuracy_score(y_train, svm1.predict(x_train))
    svm1_test_score = accuracy_score(y_test, svm1.predict(x_test))
    svm2_train_score = accuracy_score(y_train, svm2.predict(x_train))
    svm2_test_score = accuracy_score(y_test, svm2.predict(x_test))
    svm3_train_score = accuracy_score(y_train, svm3.predict(x_train))
    svm3_test_score = accuracy_score(y_test, svm3.predict(x_test))
    svm4_train_score = accuracy_score(y_train, svm4.predict(x_train))
    svm4_test_score = accuracy_score(y_test, svm4.predict(x_test))
    # 画图
    # 设置X轴，y轴
    x_tmp = [0, 1, 2, 3]
    y_train_tmp = [svm1_train_score, svm2_train_score, svm3_train_score, svm4_train_score]
    y_test_tmp = [svm1_test_score, svm2_test_score, svm3_test_score, svm4_test_score]
    y_score = [t1 - t0, t2 - t1, t3 - t2, t4 - t3]
    # 设置尺寸和颜色
    plt.figure(facecolor=‘w‘, figsize=(12, 6))
    # subplot是用来分割画布，分割成一行两列，用第一列的来画图
    a = plt.subplot(121)
    # 绘图
    plt.plot(x_tmp, y_train_tmp, ‘r-‘, lw=2, label=u‘训练集准确率‘)
    plt.plot(x_tmp, y_test_tmp, ‘g-‘, lw=2, label=u‘测试集准确率‘)
    # 设置两个图形的解释
    plt.legend(loc=‘lower left‘)
    # plt.title(u‘模型预测准确率‘, fontsize=13)
    plt.xticks(x_tmp, [u‘linear-SVM‘, u‘rbf-SVM‘, u‘poly-SVM‘, u‘sigmoid-SVM‘], rotation=0)
    # 开启网格线
    plt.grid(b=True)

    # 第二个图，分割成一行两列，第二列来画图
    b = plt.subplot(122)

    plt.plot(x_tmp, y_score, ‘b-‘, lw=2, label=u‘模型训练时间‘)
    # plt.title(u‘模型训练耗时‘, fontsize=13)
    # 给x赋予标签
    plt.xticks(x_tmp, [u‘linear-SVM‘, u‘rbf-SVM‘, u‘poly-SVM‘, u‘sigmoid-SVM‘], rotation=0)
    plt.legend(loc=‘lower left‘)
    plt.grid(b=True)
    # 大标题suptitle
    plt.suptitle(u‘鸢尾花数据SVM分类器不同内核函数模型比较‘, fontsize=16)
    a.set_title(u‘预测准确率‘)
    b.set_title(u‘模型运行时间‘)
    plt.show()

sklearn上的svm

原文：https://www.cnblogs.com/xiennnnn/p/12155354.html