构建SVM模型

#coding = utf-8
import numpy as np
import pandas as pd
from sklearn.svm import SVC
from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import GridSearchCV, train_test_split

#加载数据集
def load_data(filename):
    data = pd.read_csv(filename)
    x = data.iloc[:, 2:]    #数据特征
    y = data.iloc[:, 1]     #标签：0或1
    scaler = StandardScaler()
    x_std = scaler.fit_transform(x)  # 标准化
    # 将数据划分为训练集和测试集，test_size=.3表示30%的测试集
    x_train, x_test, y_train, y_test = train_test_split(x_std, y, test_size=.3)
    return x_train, x_test, y_train, y_test


def svm_c(x_train, x_test, y_train, y_test):
    # rbf核函数，设置数据权重
    svc = SVC(kernel='rbf', class_weight='balanced',)
    c_range = np.logspace(-5, 15, 11, base=2)   #构造等比数列：2的-5次方到2的15次方中均匀产生11个数
    gamma_range = np.logspace(-9, 3, 13, base=2)
    # 网格搜索交叉验证的参数范围，cv=3,3折交叉
    param_grid = [{'kernel': ['rbf'], 'C': c_range, 'gamma': gamma_range}]
    grid = GridSearchCV(svc, param_grid, cv=3, n_jobs=-1)
    # #降维
    # x_train = PCA(n_components=200).fit_transform(x_train)
    # x_test = PCA(n_components=200).fit_transform(x_test)
    # 训练模型
    clf = grid.fit(x_train, y_train)
    # 计算测试集精度
    score = grid.score(x_test, y_test)
    print('精度为%s' % score)

if __name__ == '__main__':
    svm_c(*load_data(r'F:\t\test\2000_data.csv'))