【机器学习】支持向量机SVM

参考博客：《学习SVM，这篇文章就够了！（附详细代码）》

https://www.jiqizhixin.com/articles/2018-10-17-20

公众号文章：【白话机器学习】算法理论+实战之支持向量机（SVM）

https://mp.weixin.qq.com/s?__biz=MzIwODI2NDkxNQ==&mid=2247487899&idx=5&sn=9ebc893c29831f0b800554e6f613c03d&chksm=97049a27a0731331115fee11d4f27d45d5e34e2da0785eece300514b4ee5af248631c67dfe55&scene=21#wechat_redirect

B站：机器学习-白板推导系列(六)-支持向量机SVM（Support Vector Machine）

https://www.bilibili.com/video/av28186618?from=search&seid=3278332437610810809

理论以后补充

数据集下载地址：

链接：https://pan.baidu.com/s/1SE1K3mw7Xam_zi-1i9Axug 
提取码：xa82 
数据集来自美国威斯康星州的乳腺癌诊断数据集，也可在该数据集可在UCI数据库：http://mlr.cs.umass.edu/ml/machine-learning-databases/breast-cancer-wisconsin/中找到

以下是【白话机器学习】算法理论+实战之支持向量机（SVM）中的代码复现：

from sklearn import svm
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

from sklearn.svm import SVC, LinearSVC
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import accuracy_score

# 加载数据集
data = pd.read_csv("data/wdbc.data.csv")
# 数据探索
# 因为数据集中列比较多，我们需要把dataframe中的列全部显示出来
pd.set_option('display.max_columns', None)
#print('data.columns', data.columns)
#print('data.head(5)', data.head(5))
#print('data.describe()', data.describe())
'''
data.columns Index(['id', 'diagnosis', 'radius_mean', 'texture_mean', 'perimeter_mean',
       'area_mean', 'smoothness_mean', 'compactness_mean', 'concavity_mean',
       'concave points_mean', 'symmetry_mean', 'fractal_dimension_mean',
       'radius_se', 'texture_se', 'perimeter_se', 'area_se', 'smoothness_se',
       'compactness_se', 'concavity_se', 'concave points_se', 'symmetry_se',
       'fractal_dimension_se', 'radius_worst', 'texture_worst',
       'perimeter_worst', 'area_worst', 'smoothness_worst',
       'compactness_worst', 'concavity_worst', 'concave points_worst',
       'symmetry_worst', 'fractal_dimension_worst'],
      dtype='object')
'
data.head(5)          
         id diagnosis  radius_mean  texture_mean  perimeter_mean  area_mean   ......
0    842302         M        17.99         10.38          122.80     1001.0
1    842517         M        20.57         17.77          132.90     1326.0
2  84300903         M        19.69         21.25          130.00     1203.0
3  84348301         M        11.42         20.38           77.58      386.1
4  84358402         M        20.29         14.34          135.10     1297.0

data.describe()                  
                 id  radius_mean  texture_mean  perimeter_mean    area_mean   ......
count  5.690000e+02   569.000000    569.000000      569.000000   569.000000
mean   3.037183e+07    14.127292     19.289649       91.969033   654.889104
std    1.250206e+08     3.524049      4.301036       24.298981   351.914129
min    8.670000e+03     6.981000      9.710000       43.790000   143.500000
25%    8.692180e+05    11.700000     16.170000       75.170000   420.300000
50%    9.060240e+05    13.370000     18.840000       86.240000   551.100000
75%    8.813129e+06    15.780000     21.800000      104.100000   782.700000
max    9.113205e+08    28.110000     39.280000      188.500000  2501.000000

'''
# 将特征字段分成3组
features_mean = list(data.columns[2:12])
features_se = list(data.columns[12:22])
features_worst = list(data.columns[22:32])
# 数据清洗
# ID列没有用，删除该列
data.drop("id",axis=1,inplace=True)
# 将B良性替换为0，M恶性替换为1
data['diagnosis'] = data['diagnosis'].map({'M':1,'B':0})

# 将肿瘤诊断结果可视化
sns.countplot(data['diagnosis'],label='Count')
plt.savefig('./result/diagnosis.jpg')
plt.show()

# 用热力图呈现features_mean字段之间的相关性
corr = data[features_mean].corr()
plt.figure(figsize=(14,14))
# annot=True显示每个方格的数据
sns.heatmap(corr, annot=True)
plt.savefig('./result/heatmap.jpg')
plt.show()

# 特征选择
features_remain = ['radius_mean','texture_mean','smoothness_mean','compactness_mean','symmetry_mean','fractal_dimension_mean']
# 抽取30%的数据作为测试集，其余作为训练集
train,test = train_test_split(data,test_size = 0.3)#in this our main data is splitted into train and test
# 抽取特征选择的数值作为训练和测试数据
train_X = train[features_remain]
train_y = train['diagnosis']
test_X = test[features_remain]
test_y = test['diagnosis']
# 采用Z-Score规范化数据，保证每个特征维度的数据均值为0，方差为1
ss = StandardScaler()
train_X = ss.fit_transform(train_X)
test_X = ss.transform(test_X)

# 创建SVM分类器
model = svm.SVC()
# 用训练集做训练
model.fit(train_X,train_y)
# 用测试集做预测
prediction = model.predict(test_X)
print('准确率：', accuracy_score(prediction,test_y)) #准确率： 0.9415204678362573