机器学习之支持向量机算法实例

此实例是利用svm算法预测乳腺癌肿瘤是良性还是恶性，数据格式如下图所示：第一列表示编号，2到10列表示数据属性，第11列表示肿瘤标签2表示良性4表示恶性。

代码如下

from sklearn import svm

# x = [[2, 0], [1, 1], [2, 3]]     # 特征向量
# y = [0, 0, 1]                    # 标签
# clf = svm.SVC(kernel = 'linear')
# clf.fit(x, y)
#
# print(clf)
# print(clf.support_vectors_)      # 打印支持向量点的坐标
# print(clf.support_)              # 打印支持向量点的位置
# print(clf.n_support_)            # 打印支持向量点的个数
# print(clf.predict([5,5]))        # 预测


import pandas
from sklearn.cross_validation import train_test_split
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
import numpy as np

# ---------------------------------由于数据中很多实例存在问号以下是去问号过程-------------------------------------
breast_cancer_wisconsin = np.genfromtxt("breast_cancer_wisconsin.txt", delimiter=",",dtype="str",skip_header=1)
X = breast_cancer_wisconsin[:,1:-1]
list1 = breast_cancer_wisconsin.tolist()

a = []
for i in range(X.shape[0]):
    if '?' not in list1[i]:
        a.append(list1[i][0])

breast_cancer_wisconsin1 = pandas.read_csv("breast_cancer_wisconsin.txt",dtype="str")
breast_cancer_wisconsin_a = breast_cancer_wisconsin1.set_index('a')
b = breast_cancer_wisconsin_a.loc[a]
# b.to_csv(file_path, encoding='utf-8', index=False)
b.to_csv(r'D:\BaiduNetdiskDownload\代码与素材\代码与素材(1)\04NN\test1.csv', encoding='utf-8')
# ---------------------------------------------数据预处理结束---------------------------------------------------------

test1 = np.genfromtxt("test1.csv", delimiter=",",dtype="int",skip_header=1)
X = test1[:,1:-1]
y = test1[:,-1]
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.25)
clf = svm.SVC(kernel = 'linear')
clf.fit(X_train, y_train)

y_pred = clf.predict(X_test)
print(classification_report(y_test, y_pred))
print(confusion_matrix(y_test, y_pred))
print(clf.support_vectors_)                  # 打印支持向量点的坐标
print(clf.n_support_)                        # 打印支持向量点的个数
print(clf.support_)                          # 打印支持向量点的位置
print(clf.predict([1,2,4,8,3,7,3,6,4]))        # 预测

预测结果如下图：