支持向量机模型训练与调参

数据要求

输入的数据为csv格式，可输出混淆矩阵，可将训练好的模型给保存

训练代码

import sklearn.utils
from sklearn.svm import SVC
import pandas as pd
from sklearn.utils.multiclass import unique_labels
from sklearn.metrics import confusion_matrix
import matplotlib.pyplot as plt
import numpy as np
import joblib

def plot_confusion_matrix(y_true, y_pred, classes,
                          normalize=False,
                          title=None,
                          cmap=plt.cm.Blues):
    """
    This function prints and plots the confusion matrix.
    Normalization can be applied by setting `normalize=True`.
    """
    if not title:
        if normalize:
            title = 'Normalized confusion matrix'
        else:
            title = 'Confusion matrix, without normalization'

    # Compute confusion matrix
    cm = confusion_matrix(y_true, y_pred)
    # Only use the labels that appear in the data
    classes = classes[unique_labels(y_true, y_pred)]
    if normalize:
        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
        #print("Normalized confusion matrix")
    else:
        pass
        #print('Confusion matrix, without normalization')

    #print(cm)

    fig, ax = plt.subplots()
    im = ax.imshow(cm, interpolation='nearest', cmap=cmap)
    ax.figure.colorbar(im, ax=ax)
    # We want to show all ticks...
    ax.set(xticks=np.arange(cm.shape[1]),
           yticks=np.arange(cm.shape[0]),
           # ... and label them with the respective list entries
           xticklabels=classes, yticklabels=classes,
           title=title,
           ylabel='True label',
           xlabel='Predicted label')

    ax.set_ylim(len(classes)-0.5, -0.5)

    # Rotate the tick labels and set their alignment.
    plt.setp(ax.get_xticklabels(), rotation=45, ha="right",
             rotation_mode="anchor")

    # Loop over data dimensions and create text annotations.
    fmt = '.2f' if normalize else 'd'
    thresh = cm.max() / 2.
    for i in range(cm.shape[0]):
        for j in range(cm.shape[1]):
            ax.text(j, i, format(cm[i, j], fmt),
                    ha="center", va="center",
                    color="white" if cm[i, j] > thresh else "black")
    fig.tight_layout()
    plt.show()
    return ax


x_1=pd.read_csv('D:/桌面文件夹/重采样后/800维信号数据(csv)/train/train_data.csv')
x_train=x_1.iloc[:,0:23]
x_train_data = x_train.values

y_1 = pd.read_csv('D:/桌面文件夹/重采样后/800维信号数据(csv)/train/train_label.csv')
y_train = y_1.iloc[:,0:1]
y_train_data = y_train.values

x_2 = pd.read_csv('D:/桌面文件夹/重采样后/800维信号数据(csv)/test/test_data.csv')
x_test = x_2.iloc[:,0:23]
x_test_data = x_test.values


y_2 = pd.read_csv('D:/桌面文件夹/重采样后/800维信号数据(csv)/test/test_label.csv')
y_test = y_2.iloc[:,0:1]
y_test_data = y_test.values

y_train = np.ravel(y_train)
y_test = np.ravel(y_test)

x_train_data,y_train = sklearn.utils.shuffle(x_train_data,y_train,random_state=1)
x_test_data,y_test = sklearn.utils.shuffle(x_test_data,y_test,random_state=1)

clf1 = SVC(kernel='linear',probability=True)#不采用核函数
clf2 = SVC(kernel='rbf',C=0.1, gamma=0.1,probability=True)#采用高斯核函数

svm_1 = clf1.fit(x_train_data, y_train)
#scaler_filename = 'D:\AI\课题模拟\svm模型可输出概率/down_speed_svm.save'
#joblib.dump(svm_1, scaler_filename)
svm_2 = clf2.fit(x_train_data, y_train)
#joblib.dump(svm_2, scaler_filename)

clf1_output = clf1.score(x_test_data, y_test)
clf2_output = clf2.score(x_test_data, y_test)

clf2_predict = clf2.predict(x_test_data)
clf1_predict = clf1.predict(x_test_data)
print(clf1_predict)
class_names= np.array(['0','1','2','3','4','5','6','7','8','9'])
plot_confusion_matrix(y_test, clf1_predict, classes=class_names, normalize=False)
plot_confusion_matrix(y_test, clf2_predict, classes=class_names, normalize=False)


print('线性SVM的精度为{}：'.format(clf1_output))
print('高斯核函数SVM的精度为{}：'.format(clf2_output))

支持向量机调参

import sklearn.utils
from sklearn.svm import SVC
import pandas as pd
import numpy as np


x_1=pd.read_csv("D:\桌面文件夹\重采样后/after_train/train_data.csv")
x_train=x_1.iloc[:,0:23]
x_train_data = x_train.values

y_1 = pd.read_csv('D:\桌面文件夹\重采样后/after_train/train_label.csv')
y_train = y_1.iloc[:,0:1]
y_train_data = y_train.values

x_2 = pd.read_csv('D:\桌面文件夹\重采样后/after_test/test_data.csv')
x_test = x_2.iloc[:,0:23]
x_test_data = x_test.values


y_2 = pd.read_csv('D:\桌面文件夹\重采样后/after_test/test_label.csv')
y_test = y_2.iloc[:,0:1]
y_test_data = y_test.values

y_train = np.ravel(y_train)
y_test = np.ravel(y_test)

x_train_data,y_train = sklearn.utils.shuffle(x_train_data,y_train,random_state=1)
x_test_data,y_test = sklearn.utils.shuffle(x_test_data,y_test,random_state=1)

c = [i for  i in np.arange(0.1,2,0.01)]
g = [i for i in np.arange(0.1,2,0.01)]
result = {}
score_list = []

x=1
for i in c:
    for j in g:
        clf2 = SVC(kernel='rbf', C=i, gamma=j)
        clf2.fit(x_train_data, y_train)
        clf2_output = clf2.score(x_test_data, y_test)
        key_value={clf2_output:[i,j]}
        result.update(key_value)
        score_list.append(clf2_output)
        print("第{}次，准确率为{}".format(x,clf2_output))
        x+=1

max_key = max(score_list)
print('最高得分{}'.format(max_key))
print('参数值{}'.format(result[max_key]))
print('计算次数{}'.format(len(c)*len(g)))