对python .txt文件读取及数据处理方法总结

TypeError: ufunc 'subtract' did not contain a loop with signature matching types dtype('<U3') dtype('<U3') dtype('<U3')

from numpy import *
import random
#读取数据函数,返回list类型的训练数据集和测试数据集
def loadData(fileName): 
 trainingData=[]
 testData=[]
 with open(fileName) as txtData:
 lines=txtData.readlines()
 for line in lines:
  lineData=line.strip().split(',') #去除空白和逗号“,”
  if random.random()<0.7:  #数据集分割比例
  trainingData.append(lineData) #训练数据集
  else:
  testData.append(lineData) #测试数据集
 return trainingData,testData
#输入数据为list类型,分割数据集，分割为特征和标签两部分，返回数据为np.narray类型
def splitData(dataSet): 
 character=[]
 label=[]
 for i in range(len(dataSet)):
 character.append([float(tk) for tk in dataSet[i][:-1]])
 label.append(dataSet[i][-1])
 return array(character),array(label)

#__author__=='qustl_000'
#-*- coding: utf-8 -*-
import numpy as np
import Function
fileName="1.txt"
trainingData,testData=Function.loadData(fileName)
trainingCharacter,trainingLabel=Function.splitData(trainingData)
testCharacter,testLabel=Function.splitData(testData)
diff1=np.tile(testCharacter[0],(len(trainingCharacter),1))-trainingCharacter
print('测试数据集的一条数据，扩充到与训练数据集同维：')
print(np.tile(testCharacter[0],(len(trainingCharacter),1)))
print('训练数据集：')
print(trainingCharacter)
print('作差后的结果：')
print(diff1)

测试数据集的一条数据，扩充到与训练数据集同维：
[[ 1.5 60. ]
 [ 1.5 60. ]
 [ 1.5 60. ]
 [ 1.5 60. ]
 [ 1.5 60. ]
 [ 1.5 60. ]
 [ 1.5 60. ]
 [ 1.5 60. ]
 [ 1.5 60. ]
 [ 1.5 60. ]
 [ 1.5 60. ]
 [ 1.5 60. ]
 [ 1.5 60. ]]
训练数据集：
[[ 1.5 40. ]
 [ 1.5 50. ]
 [ 1.6 40. ]
 [ 1.6 50. ]
 [ 1.6 60. ]
 [ 1.6 70. ]
 [ 1.7 60. ]
 [ 1.7 70. ]
 [ 1.7 80. ]
 [ 1.8 60. ]
 [ 1.8 80. ]
 [ 1.8 90. ]
 [ 1.9 90. ]]
作差后的结果：
[[ 0. 20. ]
 [ 0. 10. ]
 [ -0.1 20. ]
 [ -0.1 10. ]
 [ -0.1 0. ]
 [ -0.1 -10. ]
 [ -0.2 0. ]
 [ -0.2 -10. ]
 [ -0.2 -20. ]
 [ -0.3 0. ]
 [ -0.3 -20. ]
 [ -0.3 -30. ]
 [ -0.4 -30. ]]

1.5,40,thin
1.5,50,fat
1.5,60,fat
1.6,40,thin
1.6,50,thin
1.6,60,fat
1.6,70,fat
1.7,50,thin
1.7,60,thin
1.7,70,fat
1.7,80,fat
1.8,60,thin
1.8,70,thin
1.8,80,fat
1.8,90,fat
1.9,80,thin
1.9,90,fat

lineString = re.sub("[\n\.\!\/_\-$%^*(+\"\')]+|[+—()?【】“”！:,;.？、~@#￥%…&*（）0123456789]+", " ", lines)

 for allDir in pathDirPos:
 child = os.path.join('%s' % allDir)

'''获取数据，并去除数据中的多余符号,返回list类型的数据集'''
def loadData(pathDirPos,pathDirNeg):
 posAllData = [] # 积极评论
 negAllData = [] # 消极评论
 # 积极评论
 for allDir in pathDirPos:
 lineDataPos = []
 child = os.path.join('%s' % allDir)
 filename = r"review_polarity/txt_sentoken/pos/" + child
 with open(filename) as childFile:
  for lines in childFile:
  lineString = re.sub("[\n\.\!\/_\-$%^*(+\"\')]+|[+—()?【】“”！:,;.？、~@#￥%…&*（）0123456789]+", " ", lines)
  line = lineString.split(' ') #用空白分割每个文件中的数据集（此时还包含许多空白字符）
  for strc in line:
   if strc != "" and len(strc) > 1: #删除空白字符，并筛选出长度大于1的单词
   lineDataPos.append(strc)
  posAllData.append(lineDataPos)
 # 消极评论
 for allDir in pathDirNeg:
 lineDataNeg = []
 child = os.path.join('%s' % allDir)
 filename = r"review_polarity/txt_sentoken/neg/" + child
 with open(filename) as childFile:
  for lines in childFile:
  lineString = re.sub("[\n\.\!\/_\-$%^*(+\"\')]+|[+—()?【】“”！:,;.？、~@#￥%…&*（）0123456789]+", " ", lines)
  line = lineString.split(' ') #用空白分割每个文件中的数据集（此时还包含许多空白字符）
  for strc in line:
   if strc != "" and len(strc) > 1: #删除空白字符，并筛选出长度大于1的单词
   lineDataNeg.append(strc)
  negAllData.append(lineDataNeg)
 return posAllData,negAllData
'''划分数据集，将数据集划分为训练数据和测试数据,参数splitPara为分割比例'''
def splitDataSet(pathDirPos,pathDirNeg,splitPara):
 trainingData=[]
 testData=[]
 traingLabel=[]
 testLabel=[]
 posData,negData=loadData(pathDirPos,pathDirNeg)
 pos_len=len(posData)
 neg_len=len(negData)
 #操作积极评论数据
 for i in range(pos_len):
 if(random.random()<splitPara):
  trainingData.append(posData[i])
  traingLabel.append(1)
 else:
  testData.append(posData[i])
  testLabel.append(1)
 for j in range(neg_len):
 if(random.random()<splitPara):
  trainingData.append(negData[j])
  traingLabel.append(0)
 else:
  testData.append(negData[j])
  testLabel.append(0)
 return trainingData,traingLabel,testData,testLabel