机器学习算法加强——SVM实践

 

 

 

首选——高斯核函数

import numpy as np
import pandas as pd
import matplotlib as mpl
import matplotlib.pyplot as plt
from sklearn import svm
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

# 'sepal length', 'sepal width', 'petal length', 'petal width'
iris_feature = u'花萼长度', u'花萼宽度', u'花瓣长度', u'花瓣宽度'

if __name__ == "__main__":
    path = '/Users/zhucan/Desktop/iris.csv'  # 数据文件路径
    data = pd.read_csv(path, header=None)
    x, y = data[range(4)], data[4]
    #字符串映射为0，1，2三个类别
    y = pd.Categorical(y).codes
    x = x[[0, 1]]
    x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=1, train_size=0.6)

    # 分类器 SVC classification   ovr用若干个二分类得到一个三分类
    clf = svm.SVC(C=0.1, kernel='linear', decision_function_shape='ovr')
    # clf = svm.SVC(C=0.8, kernel='rbf', gamma=20, decision_function_shape='ovr')
    clf.fit(x_train, y_train.ravel())

    # 准确率
    print(clf.score(x_train, y_train))  # 精度
    print('训练集准确率：', accuracy_score(y_train, clf.predict(x_train)))
    print(clf.score(x_test, y_test))
    print('测试集准确率：', accuracy_score(y_test, clf.predict(x_test)))

    # decision_function
    print('decision_function:\n', clf.decision_function(x_train))
    print('\npredict:\n', clf.predict(x_train))

0.8777777777777778
训练集准确率： 0.8777777777777778
0.7377049180327869
测试集准确率： 0.7377049180327869

到三个分类器的距离
decision_function:
 [[ 0.77012025  2.22752333  3.25141611 -0.24994564]
 [ 0.72449894  2.2375207   3.27995319 -0.24915267]
 [ 3.25675197  2.19909745  0.78766834 -0.25165556]
 [ 3.2365702   2.22433941  0.80405863 -0.25157315]
 [ 0.82102496  2.23135422  3.21875372 -0.25038056]
 [ 3.24340533  2.14809174  0.89650978 -0.25114765]
 [ 0.82696908  3.23547716  2.20967506 -0.25046731]
 [ 0.77046828  2.18930222  3.26499186 -0.24959236]
 [ 1.11964505  3.23028535  2.06731009 -0.25098136]
 [ 0.78502606  2.23589281  3.23544913 -0.25020768]]

predict:
 [2 2 0 0 2 0 1 2 1 2 2 2 0 1 1 2 1 1 1 0 0 0 1 0 1 2 1 0 0 1 0 2 1 2 2 2 2
 2 1 0 1 0 1 2 0 2 0 0 2 2 1 0 0 1 0 2 0 2 2 0 1 0 1 0 1 1 3 0 2 0 1 1 0 1
 1 1 0 2 0 0 1 1 2 2 1 2 2 1 2 0]

 高斯核——γ高斯分布的精度，γ越大，高斯分布精度越大

import numpy as np
from sklearn import svm
from sklearn.model_selection import GridSearchCV    # 0.17 grid_search
import matplotlib.pyplot as plt

if __name__ == "__main__":
    N = 50
    np.random.seed(0)
    x = np.sort(np.random.uniform(0, 6, N), axis=0)
    y = 2*np.sin(x) + 0.1*np.random.randn(N)
    x = x.reshape(-1, 1)
    print('x =\n', x)
    print('y =\n', y)

    model = svm.SVR(kernel='rbf')
    c_can = np.logspace(-2, 2, 10)
    gamma_can = np.logspace(-2, 2, 10)
    svr = GridSearchCV(model, param_grid={'C': c_can, 'gamma': gamma_can}, cv=5)
    svr.fit(x, y)
    print('验证参数：\n', svr.best_params_)

x =
 [[0.1127388]
 [0.12131038]
 [0.36135283]
 [0.42621635]
 [0.5227758 ]
 [0.70964656]
 [0.77355779]
 [0.86011972]
 [1.26229537]
 [1.58733367]
 [1.89257011]
 [2.1570474 ]
 [2.18226463]]

y =
 [ 0.05437325  0.43710367  0.65611482  0.78304981  0.87329469  1.38088042
  1.23598022  1.49456731  1.81603293  2.03841677  1.84627139  1.54797796
  1.63479377  1.53337832  1.22278185  1.15897721  0.92928812  0.95065638
  0.72022281  0.69233817 -0.06030957 -0.23617129 -0.23697659 -0.34160192
 -0.69007014 -0.48527812 -1.00538468 -1.00756566 -0.98948253 -1.05661601
 -1.17133143 -1.46283398 -1.47415531 -1.61280243 -1.7131299  -1.78692494
 -1.85631003 -1.98989791 -2.11462751 -1.90906396 -1.95199287 -2.14681169
 -1.77143442 -1.55815674 -1.48840245 -1.35114367 -1.27027958 -1.04875251
 -1.00128962 -0.67767925]
验证参数：
 {'C': 35.93813663804626, 'gamma': 0.5994842503189409}