SVM 参数调整过程实例

雨点打透心脏的1/2处 2023-07-16 10:55 9阅读 0赞

小彩笔的学习笔记

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
     
    X.shape
    np.unique(y)
     
    plt.scatter(X[:,0],X[:,1],c=y)
    plt.show()
     
    Xtrain, Xtest, Ytrain, Ytest = train_test_split(X,y,test_size=0.3,random_state=420)

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70]

Kernel = ["linear","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(time()-time0)

![在这里插入图片描述][20200318145320634.png]

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(time()-time0)

![在这里插入图片描述][20200318145413113.png]

#### 查看数据 ####

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#描述性统计
    #从mean列和std列可以看出严重的量纲不统一
    #从1%的数据和最小值相对比，90%的数据和最大值相对比，查看是否是正态分布或偏态分布，如果差的太多就是偏态分布，谁大方向就偏向谁
    #可以发现数据大的特征存在偏态问题
    #这个时候就需要对数据进行标准化

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 1]

from sklearn.preprocessing import StandardScaler
    X = StandardScaler().fit_transform(X)#将数据转化为0,1正态分布
    data = pd.DataFrame(X)
    data.describe([0.01,0.05,0.1,0.25,0.5,0.75,0.9,0.99]).T#均值很接近，方差为1了

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 2]

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(time()-time0)

发现准确率有了很大的提高  
![在这里插入图片描述][20200318145644490.png]  
尝试调参使准确率更高

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.plot(gamma_range,score)
    plt.show()

和之前的0.9707相比更高了  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 3]  
尝试改变两个参数

from sklearn.model_selection import StratifiedShuffleSplit#用于支持带交叉验证的网格搜索
    from sklearn.model_selection import GridSearchCV#带交叉验证的网格搜索
     
    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)#将数据分为5份，5份数据中测试集占30%
    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(time()-time0)

![在这里插入图片描述][20200318145936904.png]

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70]: /images/20230528/86ed9982604d4eec8d1a594883b26613.png
[20200318145320634.png]: /images/20230528/3fecdc8b6e7540a49cf28b6a7205b012.png
[20200318145413113.png]: /images/20230528/98430561f5d24557bcd1309c61d5c71a.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 1]: /images/20230528/9620e70d44db4189b4d06cda28b3acc1.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 2]: /images/20230528/a00cac3f6f3947309511d8cd822a01aa.png
[20200318145644490.png]: /images/20230528/c5cd0a3e122147e993c8af9496265096.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 3]: /images/20230528/9830be22d23443ca994d2a14c021b2ae.png
[20200318145936904.png]: /images/20230528/3da7290685944eafa0a13dc6ef60b383.png