new_data: 0 1 2
0 3.542485 1.977398 -1.0
1 3.018896 2.556416 -1.0
2 7.551510 -1.580030 1.0
3 2.114999 -0.004466 -1.0
4 8.127113 1.274372 1.0
列与标号不对应
import matplotlib.pyplot as plt
import numpy as np
from sklearn import svm,datasets
import pandas as pd
import openpyxl
import numpy as np
import matplotlib.pyplot as plt
import os
from numpy import *
from time import sleep
from os import listdir
import math
import matplotlib.pyplot as plt
import time
from sklearn.datasets import load_iris #导入数据集iris
iris = load_iris() #载入数据集
#print (iris.data)
import matplotlib.pyplot as plt
import numpy as np
from sklearn import svm,datasets
import pandas as pd
def loadDataSet(filename):
dataMat=[]
labelMat=[]
fr=open(filename)
for line in fr.readlines():
lineArr=line.strip().split('\t')
dataMat.append([float(lineArr[0]),float(lineArr[1])])
labelMat.append(float(lineArr[2]))
return dataMat,labelMat
trainDataSet,trainLabel=loadDataSet("testSet.txt")#导入数据
tem_X =mat( np.array(trainDataSet))[:, :2] #取前两列
#print('tem_X:',tem_X)
tem_Y = trainLabel
#print('tem_Y:',tem_Y)
data = np.column_stack([tem_X,tem_Y])
print('data:',data)
new_data = pd.DataFrame(np.column_stack([tem_X,tem_Y]))
#过滤掉其中一种类型的花
#new_data = new_data[new_data[2] != 1.0]
print('new_data:',new_data)
#生成X和Y
X = new_data[[0,1]].values
Y = new_data[[2]].values
Y=Y.ravel()
clf = svm.SVC(kernel='linear')
clf.fit(X, Y)
KeyError: "None of [Index([(0, 1)], dtype='object')] are in the [columns]"
tem_X = iris.data[:, :2] #取前两列
print('tem_X:',tem_X)
tem_Y = iris.target
print('tem_Y:',tem_Y)
new_data = pd.DataFrame(np.column_stack([tem_X,tem_Y]))
取得的数据有重合，删掉即可