svm支持向量机-吴恩达机器学习基于python

最新推荐文章于 2024-05-29 21:17:05 发布

吃菜拌胡椒

最新推荐文章于 2024-05-29 21:17:05 发布

阅读量1k

点赞数 1

分类专栏： # 吴恩达机器学习文章标签：机器学习吴恩达 python

本文链接：https://blog.csdn.net/qq_42221092/article/details/88903945

版权

吴恩达机器学习专栏收录该内容

4 篇文章 0 订阅

订阅专栏

1 线性svm

所需要的包

import numpy as np
import pandas as pd
import sklearn.svm
import seaborn as sns
import scipy.io as sio #读取matlab的mat数据
import matplotlib.pyplot as plt

1.1 导入数据

mat = sio.loadmat(r'D:\python_try\5. AndrewNg_ML\data\svm\ex6data1.mat')
data = pd.DataFrame(mat.get('X'), columns=['X1', 'X2'])
data['y'] = mat.get('y')

positive：1；negative：0
方便画图

positive = data[data['y'].isin([1])]
negative = data[data['y'].isin([0])]

1.2 visualize data

fig, ax = plt.subplots(figsize=(6,4))
ax.scatter(positive['X1'], positive['X2'], s=50, marker='x', label='Positive')
ax.scatter(negative['X1'], negative['X2'], s=50, marker='o', label='Negative')
ax.legend()
ax.set_title('Raw data')
ax.set_xlabel('X1')
ax.set_ylabel('X2')
plt.show()

1.3 svm算法

使用已有的包sklearn.svm来训练和预测
sklearn.svm中线性svm参考网址

1.3.1训练

C=1

# 调用sklearn.svm线性svm函数
svc1 = sklearn.svm.LinearSVC(C=1, loss='hinge')
svc1

在这里插入图片描述

# 训练
svc1.fit(data[['X1', 'X2']], data['y'])
# Returns the mean accuracy on the given test data and labels.返回测试结果和标签的平均误差
svc1.score(data[['X1', 'X2']], data['y'])

0.9803921568627451
C=100

svc100 = sklearn.svm.LinearSVC(C=100, loss='hinge', max_iter=1000)
svc100.fit(data[['X1', 'X2']], data['y'])
svc100.score(data[['X1', 'X2']], data['y'])

C=1我们得到训练数集的完美分类，但是通过增加C的值，我们创建了一个不再适合数据的决策边界，我们可以通过查看每个预测的置信水平来看出这一点，这是该点与超平面距离的函数

1.3.2预测

decision_function：测试样本的置信度得分
predict：预测标签

## C = 1
data['SVM1 Confidence'] = svc1.decision_function(data[['X1', 'X2']])
data['SVM1 Predict'] = svc1.predict(data[['X1', 'X2']])

## C = 100
data['SVM100 Confidence'] = svc100.decision_function(data[['X1', 'X2']])
data['SVM100 Predict'] = svc100.predict(data[['X1', 'X2']])

coef_：变量的权重（方向向量W）
intercept_：截距项b

# 变量的权重（方向向量W）
Weight1 = svc1.coef_
Weight100 = svc100.coef_
# 截距项b
b1 = svc1.intercept_
b100 = svc100.intercept_

Weight1: [[0.59213514 0.81626829]]
Weight100: [[1.23422417 3.08565111]]
b1: [-4.11515251]
b100: [-12.30774519]
$W x + b = 0$
根据公式编写边界函数

## 边界函数
def boundary(Weight, b):
    y = -Weight[0][0]/Weight[0][1]*x - b/Weight[0][1]
    return y

画图

x = np.linspace(data['X1'].min(), data['X1'].max())
fig = plt.figure(figsize=(12,4))
ax1 = fig.add_subplot(1,2,1)
ax2 = fig.add_subplot(1,2,2)
ax1.scatter(data['X1'], data['X2'], s=50, c=data['SVM1 Predict'], cmap='seismic', label='Predict')
# y1 = -Weight1[0][0]/Weight1[0][1]*x - b1/Weight1[0][1]
y1 = boundary(Weight1, b1)
ax1.plot(x, y1, 'r' , label='Boundary')
ax1.set_title('SVM (C=1) Decision Predict')
ax2.scatter(data['X1'], data['X2'], s=50, c=data['SVM100 Predict'], cmap='seismic', label='Predict')
# y100 = -Weight100[0][0]/Weight100[0][1]*x - b100/Weight100[0][1]
y100 = boundary(Weight100, b100)
ax2.plot(x, y100, 'r' , label='Boundary')
ax2.set_title('SVM (C=100) Decision Predict')
ax1.legend()
ax2.legend()
plt.show()

在这里插入图片描述

2 高斯核函数

所需要的包

import matplotlib.pyplot as plt
import numpy as np
import scipy.io as sio # 读取mat数据
import pandas as pd
import seaborn as sns # 画图
from sklearn import svm

2.1 高斯核函数

def gaussian_kernel(x1, x2, sigma):
    return np.exp(-np.power(x1-x2, 2).sum()/(2*sigma**2))

x1 = np.array([1, 2, 1])
x2 = np.array([0, 4, -1])
sigma = 2
gaussian_kernel(x1, x2, sigma)

0.32465246735834974

2.2 导入数据

mat = sio.loadmat(r'D:\python_try\5. AndrewNg_ML\data\svm\ex6data2.mat')
data = pd.DataFrame(mat.get('X'), columns=['X1', 'X2'])
data['y'] = mat.get('y')

2.3 visualize data

画图包seaborn例子参考网址

scatterplot画散点图的不存在了

sns.set(style='white')
sns.lmplot(x="X1", y="X2", hue="y", data=data, markers=["x", "o"], fit_reg=False, scatter_kws={'s':10})

在这里插入图片描述

2.4 try build-in Gaussian Kernel of sklearn

尝试创建一个高斯内核模型

2.4.1 训练

svm.SVC参考网址

# 查看参数设置
svm.SVC()

在这里插入图片描述

高斯核函数： $exp(-\frac{||x-l||^2}{2\sigma^2})$
其中， $gamma=\frac{1}{2\sigma^2}$
C = 1

svc1 = svm.SVC(C=1, kernel='rbf', gamma=10, probability=True)
svc1.fit(data[['X1', 'X2']], data['y'])
svc1.score(data[['X1', 'X2']], data['y'])

0.9698725376593279

C = 100

svc100 = svm.SVC(C=100, kernel='rbf', gamma=10, probability=True)
svc100.fit(data[['X1', 'X2']], data['y'])
svc100.score(data[['X1', 'X2']], data['y'])

0.9895712630359212

C较大时，可能会导致过拟合，高方差
C较小时，可能会导致欠拟合，高偏差
$\sigma$ 较大时,可能会导致欠拟合，高偏差
$\sigma$ 较小时,可能会导致过拟合，高方差

2.4.2 预测

predict1 = svc1.predict(data[['X1', 'X2']])
predict100 = svc100.predict(data[['X1', 'X2']])

画图

fig = plt.figure(figsize=(8,4))
ax1 = fig.add_subplot(1,2,1)
ax2 = fig.add_subplot(1,2,2)
ax1.scatter(data['X1'], data['X2'], s=10, c=predict1, cmap='seismic', label='Predict')
ax1.set_title('C=1')
ax2.scatter(data['X1'], data['X2'], s=10, c=predict100, cmap='seismic', label='Predict')
ax2.set_title('C=100')
plt.show()

2.4.3 画出边界（利用等高线）

#  画等高线需要先生成网格
x1 = np.linspace(data['X1'].min(), data['X1'].max(), 100)
x2 = np.linspace(data['X2'].min(), data['X2'].max(), 100)
X1, X2 = np.meshgrid(x1, x2)
grid_points=np.c_[X1.ravel(), X2.ravel()] # np.c_:合并

# C=1，预测
grid_predict1 = svc1.predict(grid_points).reshape(X1.shape) 
# C=100，预测
grid_predict100 = svc100.predict(grid_points).reshape(X1.shape)

fig = plt.figure(figsize=(8,4))
ax1 = fig.add_subplot(1,2,1)
ax2 = fig.add_subplot(1,2,2)
ax1.scatter(data['X1'], data['X2'], s=10, c=data['y'], cmap='seismic')
ax1.contour(X1, X2, grid_predict1, colors='black', linewidths=0.5)
ax1.set_title('C=1')
ax2.scatter(data['X1'], data['X2'], s=10, c=data['y'], cmap='seismic')
ax2.contour(X1, X2, grid_predict100, colors='black', linewidths=0.5)
ax2.set_title('C=100')
plt.show()

在这里插入图片描述

3 寻找最优参数 $C$ & $\sigma$

import scipy.io as sio #导入mat数据
import pandas as pd
import matplotlib.pyplot as plt # 画图
import sklearn.svm as svm # 训练svm
import numpy as np

3.1 导入数据

** 训练数据**

mat = sio.loadmat(r'D:\python_try\5. AndrewNg_ML\data\svm\ex6data3.mat')
TrainData = pd.DataFrame(mat.get('X'), columns=['X1', 'X2'])
TrainData['y'] = mat.get('y')

交叉验证数据

cvData = pd.DataFrame(mat.get('Xval'), columns=['X1', 'X2'])
cvData['y'] = mat.get('yval')

3.2 visualize data

TrainPositive = TrainData[TrainData['y'].isin([1])]
TrainNegative = TrainData[TrainData['y'].isin([0])]
# 画图
fig, ax = plt.subplots(figsize=(8,6))
ax.scatter(TrainPositive['X1'], TrainPositive['X2'], marker='x', c='blue', label='Positive')
ax.scatter(TrainNegative['X1'], TrainNegative['X2'],  marker='o', c='red', label='Negative')
ax.legend()
plt.show()

在这里插入图片描述

3.3 manual grid search for $C$ and $\sigma$

3.3.1定义参数

参数集合

$C$ : {0:01; 0:03; 0:1; 0:3; 1; 3; 10; 30}
$\sigma$ : {0:01; 0:03; 0:1; 0:3; 1; 3; 10; 30}

# 定义gamma和sigma转换函数
def gamma(sigma):
    return 1/(2*sigma**2)

C和gamma集合

candidate = [0.01, 0.03, 0.1, 0.3, 1, 3, 10, 30]
combination = [(C, gamma(sigma))for C in candidate for sigma in candidate]

3.3.2 利用交叉验证集寻找最优参数

svm.svc参考网址

# 查看参数
svm.SVC()

在这里插入图片描述

Score = []
for C, Gamma in combination:
    svc = svm.SVC(C=C, gamma=Gamma)
    svc.fit(TrainData[['X1', 'X2']], TrainData['y'])
    Score.append(svc.score(cvData[['X1', 'X2']], cvData['y']))
# 找最优参数
bestScore = Score[np.argmax(Score)]
bestParameter = combination[np.argmax(Score)]

print("bestScore: ", bestScore)
print("bestParameter: ", bestParameter)

bestScore: 0.965
bestParameter: (1, 49.99999999999999)

因为np.argmax只能返回一个索引，所以参数和吴恩达老师所给的不一样

4 spam filter 垃圾邮件分类器

import scipy.io as sio # load mat
import pandas as pd
from sklearn import svm # svm
from sklearn import metrics # 准确率
from os import listdir # 文件夹中的文件名
import re #regular expression for e-mail processing
import nltk, nltk.stem.porter # 这个英文算法似乎更符合作业里面所用的代码，与上面效果差不多
import numpy as np
from sklearn.linear_model import LogisticRegression # logistic

4.1 训练集训练

TrainMat = sio.loadmat(r'D:\python_try\5. AndrewNg_ML\data\svm\spamTrain.mat')
X_train, y_train = TrainMat.get('X'), TrainMat.get('y').ravel()
svc = svm.SVC()
svc.fit(X_train, y_train)

在这里插入图片描述

4.2 测试

4.2.1 测试集测试

# 导入测试集
TestMat = sio.loadmat(r'D:\python_try\5. AndrewNg_ML\data\svm\spamTest.mat')
X_test, y_test = TestMat.get('Xtest'), TestMat.get('ytest').ravel()
# 预测
predict1 = svc.predict(X_test)
# 准确率
print(metrics.classification_report(y_test, predict1))

在这里插入图片描述

4.2.2 文本测试

先查看一个垃圾邮件例子
在这里插入图片描述

4.2.2.1 文本预处理

Lower-casing: 把整封邮件转化为小写。
Stripping HTML: 移除所有HTML标签，只保留内容。
Normalizing URLs: 将所有的URL替换为字符串 “httpaddr”。
Normalizing Email Addresses: 所有的地址替换为 “emailaddr”。
Normalizing Dollars: 所有dollar符号($)替换为“dollar”。
Normalizing Numbers: 所有数字替换为“number”。
Word Stemming(词干提取): 将所有单词还原为词源。例如，“discount”, “discounts”, “discounted” and “discounting”都替换为“discount”。
Removal of non-words: 移除所有非文字类型，所有的空格(tabs, newlines, spaces)调整为一个空格。

做除了7. 和 8. 的邮件处理

def processEmail(email):
    email = email.lower() # 1. Lower-casing
    email = re.sub('<[^<>]+>' , ' ', email) # 2. Stripping HTML
    email = re.sub('(http:|https:)//[^\s]*', 'httpaddr', email) # 3. Normalizing URLS
    email = re.sub('[^\s]+@[^\s]+', 'emailaddr', email) # Normalizing Email Addresses
    email = re.sub('[$]+', 'dollar',email) # Normalizing dollars
    email = re.sub('\d+', 'number', email) #Normalizing Numbers
    return email

做剩下两个的处理，并返回单词列表

def email2Tokenlist(email):
    tokenList = []
    stemmer = nltk.stem.porter.PorterStemmer()
    email = processEmail(email)
    
    tokens = re.split('[ \@\$\/\#\.\-\:\&\*\+\=\[\]\?\!\(\)\{\}\,\'\"\>\_\<\;\%]', email)
    for token in tokens:
        token = re.sub('[^a-zA-Z0-9]', '', token)
        # 提取词根
        stemmed = stemmer.stem(token)
        if not len(token): continue
        tokenList.append(stemmed)
    return tokenList

词汇表索引

def email2vocabIndex(email, vocab):
    token = email2Tokenlist(email)
    index = [i for i in range(len(vocab)) if vocab[i] in token]
    return index

将email转化成变量形式，词向量

def email2FeatureVector(email):
    df = pd.read_table(r'D:\python_try\5. AndrewNg_ML\data\svm\vocab.txt', names=['words'])
    vocab = df.as_matrix() # retuen array
    vector = np.zeros(len(vocab)) # 向量
    vocabIndex = email2vocabIndex(email, vocab)
    for i in vocabIndex:
        vector[i] = 1
    return vector

预测

for name in emailList:
    emailName = r'D:\python_try\5. AndrewNg_ML\data\svm\email\%s'  %name
    #print(emailName)
    with open(emailName, 'r') as f:
        email = f.read()
        vector = pd.DataFrame(email2FeatureVector(email)).T
        predict2 = svc.predict(vector)
        print("the email %s is predicted as " % name, predict2)

the email emailSample1.txt is predicted as [0]
the email emailSample2.txt is predicted as [0]
the email spamSample1.txt is predicted as [1]
the email spamSample2.txt is predicted as [0]
“spamSample2.txt” 预测错了

4.3 与逻辑回归作比较

4.3.1 测试集预测

logit = LogisticRegression()
logit.fit(X_train, y_train) # 模型训练
pred = logit.predict(X_test) # 预测
print(metrics.classification_report(y_test, pred)) # 验证

在这里插入图片描述

4.3.2 邮件文本预测

for name in emailList:
    emailName = r'D:\python_try\5. AndrewNg_ML\data\svm\email\%s'  %name
    print(emailName)
    with open(emailName, 'r') as f:
        email = f.read()
        #print(email)
        vector = pd.DataFrame(email2FeatureVector(email)).T
        print(np.average(vector))
        #print(set(vector))
        predict2 = logit.predict(vector)
        print("the email %s is predicted as " % name, predict2)

the email emailSample1.txt is predicted as [0]
the email emailSample2.txt is predicted as [0]
the email spamSample1.txt is predicted as [1]
the email spamSample2.txt is predicted as [1]

综上两种比较，logistic回归的效果更好

吃菜拌胡椒

关注

1
点赞
踩
11

收藏

觉得还不错? 一键收藏
0
评论
svm支持向量机-吴恩达机器学习基于python

导入包import numpy as npimport pandas as pdimport sklearn.svmimport seaborn as snsimport scipy.io as sio #读取matlab的mat数据import matplotlib.pyplot as plt 1 线性svm1.1 导入数据mat = sio.loadmat(r'D:\pyt...
复制链接

扫一扫