sklearn学习笔记之svm

支持向量机:

# -*- coding: utf-8 -*-
import sklearn
from sklearn.svm import SVC
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn import datasets
import pandas as pd
import numpy


def getData_1():

    iris = datasets.load_iris()
    X = iris.data   #样本特征矩阵，150*4矩阵，每行一个样本，每个样本维度是4
    y = iris.target #样本类别矩阵，150维行向量，每个元素代表一个样本的类别


    df1=pd.DataFrame(X, columns =['SepalLengthCm','SepalWidthCm','PetalLengthCm','PetalWidthCm'])
    df1['target']=y

    return df1

df=getData_1()


X_train, X_test, y_train, y_test = train_test_split(df.iloc[:,0:3],df['target'], test_size=0.3, random_state=42)
print X_train, X_test, y_train, y_test


model = SVC(C=1.0, kernel='rbf', gamma='auto')
"""参数
---
    C：误差项的惩罚参数C
    gamma: 核相关系数。浮点数，If gamma is ‘auto’ then 1/n_features will be used instead.
"""


model.fit(X_train,y_train)
predict=model.predict(X_test)
print predict
print y_test.values

print 'SVC分类:{:.3f}'.format(model.score(X_test, y_test))

结果：

[1 0 2 1 1 0 1 2 1 1 2 0 0 0 0 1 2 1 1 2 0 2 0 2 2 2 2 2 0 0 0 0 1 0 0 2 1
 0 0 0 2 1 1 0 0]
[1 0 2 1 1 0 1 2 1 1 2 0 0 0 0 1 2 1 1 2 0 2 0 2 2 2 2 2 0 0 0 0 1 0 0 2 1
 0 0 0 2 1 1 0 0]

SVC分类:1.000

准确度惊人的100%......,比线性回归和朴素贝叶斯分类高很多。。。