一文掌握sklearn中的支持向量机

sklearn.svm.SVC(
                C=1.0,
                kernel='rbf',
                degree=3,
                gamma='auto_deprecated',
                coef0=0.0,
                shrinking=True,
                probability=False,
                tol=0.001,
                cache_size=200,
                class_weight=None,
                verbose=False,
                max_iter=-1,
                decision_function_shape='ovr',
                random_state=None,
                )

from sklearn.datasets import load_breast_cancer
from sklearn.svm import SVC
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
import numpy as np
from time import time
import datetime
data = load_breast_cancer()
X = data.data
y = data.target
Xtrain, Xtest, Ytrain, Ytest = train_test_split(X,y,test_size=0.3,random_state=420)
#调线性核函数
score = []
C_range = np.linspace(0.01,30,50)
for i in C_range:
    clf = SVC(kernel="linear",C=i,cache_size=5000).fit(Xtrain,Ytrain)
    score.append(clf.score(Xtest,Ytest))
print(max(score), C_range[score.index(max(score))])
plt.figure(figsize=(10,6))
plt.plot(C_range,score)
plt.show()

from sklearn.datasets import load_breast_cancer
from sklearn.svm import SVC
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
import numpy as np
from time import time
import datetime
data = load_breast_cancer()
X = data.data
y = data.target
Xtrain, Xtest, Ytrain, Ytest = train_test_split(X,y,test_size=0.3,random_state=420)
Kernel = ["linear","poly","rbf","sigmoid"]
for kernel in Kernel:
    time0 = time()
    clf= SVC(kernel = kernel
             , gamma="auto"
             , degree = 1
             , cache_size=5000
             ).fit(Xtrain,Ytrain)
    print("The accuracy under kernel %s is %f" % (kernel,clf.score(Xtest,Ytest)))
    print(datetime.datetime.fromtimestamp(time()-time0).strftime("%M:%S:%f"))

import pandas as pd
data = pd.DataFrame(X)
data.describe([0.01,0.05,0.1,0.25,0.5,0.75,0.9,0.99]).T

from sklearn.preprocessing import StandardScaler
X = StandardScaler().fit_transform(X)
Xtrain, Xtest, Ytrain, Ytest = train_test_split(X,y,test_size=0.3,random_state=420)
Kernel = ["linear","poly","rbf","sigmoid"]
for kernel in Kernel:
    time0 = time()
    clf= SVC(kernel = kernel
             , gamma="auto"
             , degree = 1
             , cache_size=5000
             ).fit(Xtrain,Ytrain)
    print("The accuracy under kernel %s is %f" % (kernel,clf.score(Xtest,Ytest)))
    print(datetime.datetime.fromtimestamp(time()-time0).strftime("%M:%S:%f"))

score = []
gamma_range = np.logspace(-10, 1, 50) #返回在对数刻度上均匀间隔的数字
for i in gamma_range:
    clf = SVC(kernel="rbf",gamma = i,cache_size=5000).fit(Xtrain,Ytrain)
    score.append(clf.score(Xtest,Ytest))
print(max(score), gamma_range[score.index(max(score))])
plt.figure(figsize=(10,6))
plt.plot(gamma_range,score)
plt.show()

from sklearn.model_selection import StratifiedShuffleSplit
from sklearn.model_selection import GridSearchCV
time0 = time()
gamma_range = np.logspace(-10,1,20)
coef0_range = np.linspace(0,5,10)
param_grid = dict(gamma = gamma_range,coef0 = coef0_range)

cv = StratifiedShuffleSplit(n_splits=5, test_size=0.3, random_state=420)
grid = GridSearchCV(SVC(kernel = "poly",degree=1,cache_size=5000),
param_grid=param_grid, cv=cv)
grid.fit(X, y)
print("The best parameters are %s with a score of %0.5f" % (grid.best_params_,grid.best_score_))
print(datetime.datetime.fromtimestamp(time()-time0).strftime("%M:%S:%f"))

>>> The best parameters are {'coef0': 0.0, 'gamma': 0.18329807108324375} with a score of 0.96959
>>> 00:08:358310

import numpy as np
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
from sklearn import svm
from sklearn.datasets import make_circles, make_moons, make_blobs,make_classification

n_samples = 100

datasets = [
    make_moons(n_samples=n_samples, noise=0.2, random_state=0),
    make_circles(n_samples=n_samples, noise=0.2, factor=0.5, random_state=1),
    make_blobs(n_samples=n_samples, centers=2, random_state=5),
    make_classification(n_samples=n_samples,n_features = 2,n_informative=2,n_redundant=0, random_state=5)
]

Kernel = ["linear","poly","sigmoid","rbf"]

#四个数据集分别是什么样子呢？
# for X,Y in datasets:
#     plt.figure(figsize=(5,4))
#     plt.scatter(X[:,0],X[:,1],c=Y,s=50,cmap="rainbow")

nrows=len(datasets)
ncols=len(Kernel) + 1

fig, axes = plt.subplots(nrows, ncols,figsize=(25,16))

#第一层循环：在不同的数据集中循环
for ds_cnt, (X,Y) in enumerate(datasets):
    
    #在图像中的第一列，放置原数据的分布
    ax = axes[ds_cnt, 0]
    if ds_cnt == 0:
        ax.set_title("Input data",fontsize=25)
    ax.scatter(X[:, 0], X[:, 1], c=Y, zorder=10, cmap=plt.cm.Paired,edgecolors='k')
    ax.set_xticks(())
    ax.set_yticks(())
    
    #第二层循环：在不同的核函数中循环
    #从图像的第二列开始，一个个填充分类结果
    for est_idx, kernel in enumerate(Kernel):
        
        #定义子图位置
        ax = axes[ds_cnt, est_idx + 1]
        
        #建模
        clf = svm.SVC(kernel=kernel, gamma=2).fit(X, Y)
        score = clf.score(X, Y)
        
        #绘制图像本身分布的散点图
        ax.scatter(X[:, 0], X[:, 1], c=Y
                   ,zorder=10
                   ,cmap=plt.cm.Paired,edgecolors='k')
        #绘制支持向量
        ax.scatter(clf.support_vectors_[:, 0], clf.support_vectors_[:, 1], s=100,
                    facecolors='none', zorder=10, edgecolors='white')
        
        #绘制决策边界
        x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5
        y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5
        
        #np.mgrid，合并了我们之前使用的np.linspace和np.meshgrid的用法
        #一次性使用最大值和最小值来生成网格
        #表示为[起始值：结束值：步长]
        #如果步长是复数，则其整数部分就是起始值和结束值之间创建的点的数量，并且结束值被包含在内
        XX, YY = np.mgrid[x_min:x_max:200j, y_min:y_max:200j]
        #np.c_，类似于np.vstack的功能
        Z = clf.decision_function(np.c_[XX.ravel(), YY.ravel()]).reshape(XX.shape)
        #填充等高线不同区域的颜色
        ax.pcolormesh(XX, YY, Z > 0, cmap=plt.cm.Paired,shading='auto')
        #绘制等高线
        ax.contour(XX, YY, Z, colors=['k', 'k', 'k'], linestyles=['--', '-', '--'],
                    levels=[-1, 0, 1])
        
        #设定坐标轴为不显示
        ax.set_xticks(())
        ax.set_yticks(())
        
        #将标题放在第一行的顶上
        if ds_cnt == 0:
            ax.set_title(kernel,fontsize=25)
            
        #为每张图添加分类的分数   
        ax.text(0.95, 0.06, ('%.2f' % score).lstrip('0')
                , size=15
                , bbox=dict(boxstyle='round', alpha=0.8, facecolor='white')
                  #为分数添加一个白色的格子作为底色
                , transform=ax.transAxes #确定文字所对应的坐标轴，就是ax子图的坐标轴本身
                , horizontalalignment='right' #位于坐标轴的什么方向
               )

plt.tight_layout()
plt.show()

import numpy as np
import matplotlib.pyplot as plt
from sklearn import svm
from sklearn.datasets import make_blobs
plt.rcParams['axes.unicode_minus']=False

class_1 = 500 #类别1有500个样本
class_2 = 50 #类别2只有50个
centers = [[0.0, 0.0], [2.0, 2.0]] #设定两个类别的中心
clusters_std = [1.5, 0.5] #设定两个类别的方差，通常来说，样本量比较大的类别会更加松散
X, y = make_blobs(n_samples=[class_1, class_2],
                  centers=centers,
                  cluster_std=clusters_std,
                  random_state=0, shuffle=False)

#其中红色点是少数类，紫色点是多数类
#不设定class_weight
clf = svm.SVC(kernel='linear', C=1.0)
clf.fit(X, y)
#设定class_weight
wclf = svm.SVC(kernel='linear', class_weight={1: 10})
wclf.fit(X, y)
#给两个模型分别打分看看，这个分数是accuracy准确度



#首先要有数据分布
plt.figure(figsize=(10,6))
plt.scatter(X[:, 0], X[:, 1], c=y, cmap="rainbow",s=10)
ax = plt.gca() #获取当前的子图，如果不存在，则创建新的子图
#绘制决策边界的第一步：要有网格

xlim = ax.get_xlim()
ylim = ax.get_ylim()
xx = np.linspace(xlim[0], xlim[1], 30)
yy = np.linspace(ylim[0], ylim[1], 30)
YY, XX = np.meshgrid(yy, xx)
xy = np.vstack([XX.ravel(), YY.ravel()]).T
#第二步：找出我们的样本点到决策边界的距离
Z_clf = clf.decision_function(xy).reshape(XX.shape)
a = ax.contour(XX, YY, Z_clf, colors='black', levels=[0], alpha=0.5, linestyles=['-'])
Z_wclf = wclf.decision_function(xy).reshape(XX.shape)
b = ax.contour(XX, YY, Z_wclf, colors='orange', levels=[0], alpha=0.5, linestyles=['-'])
#第三步：画图例
plt.legend([a.collections[0], b.collections[0]], ["non weighted", "weighted"],loc="upper right",fontsize=14) 
plt.text(0.95, 0.06, ('non weighted:%.2f \n weighted:%.2f ' % (clf.score(X,y), wclf.score(X,y)))
        , size=15
        , bbox=dict(boxstyle='round', alpha=0.8, facecolor='white')
          #为分数添加一个白色的格子作为底色
        , transform=ax.transAxes #确定文字所对应的坐标轴，就是ax子图的坐标轴本身
        , horizontalalignment='right' #位于坐标轴的什么方向
       )

plt.show()