统计词频python实现gensim_gensim自然语言处理

参考代码

ChineseClean_demo1.py：

# -*- coding:utf-8 -*-

import xlrd

import xlwt

'''

python3.4

'''

# file 表示源文件名字，修改此处即可

file="./data/answer_detail_5_15307860968687.xls"

dirs="./result"

def read_excel(rows_numb,cols_numb):

f = xlwt.Workbook() #创建工作簿

'''

创建第一个sheet:

sheet1

'''

sheet1 = f.add_sheet(u'sheet1_1',cell_overwrite_ok=True) #创建sheet

sheet2 = f.add_sheet(u'sheet1_2',cell_overwrite_ok=True) #创建sheet

row0 = [u'UserNo',u'Name',u'Question',u'Answer',u'Layer',u'Mark',u'Score',u'AbilityID']

# 打开文件

workbook = xlrd.open_workbook(file)

sheet0 = workbook.sheet_by_index(0) # sheet索引从0开始

cols = sheet0.col_values(cols_numb)

rows_list_1=[]

rows_list_2=[]

for i in range(1,len(cols)):

if cols[i] == '0':

rows_list_1.append(i)

else:

rows_list_2.append(i)

for i in range(0,len(row0)):

sheet1.write(0,i,row0[i])

sheet2.write(0,i,row0[i])

'''

sheet1_1保存0分数据

'''

for j in range(0,len(rows_list_1)):

rows = sheet0.row_values(rows_list_1[j]) # 获取行内容

for i in range(0,len(rows)):

sheet1.write(j+1,i,rows[i])

'''

sheet1_2保存非0分数据

'''

for j in range(0,len(rows_list_2)):

rows = sheet0.row_values(rows_list_2[j]) # 获取行内容

for i in range(0,len(rows)):

sheet2.write(j+1,i,rows[i])

f.save('./data/demo1.xls') #保存文件

if __name__ == '__main__':

# 读取文件的行和列

rows_numb=0

cols_numb=6

read_excel(rows_numb,cols_numb)

ChineseClean_demo2.py：

# -*- coding:utf-8 -*-

import xlrd

import xlwt

'''

python3.4

'''

# file 表示源文件名字，修改此处即可

file="./data/demo1.xls"

def read_excel(rows_numb,cols_numb):

f = xlwt.Workbook() #创建工作簿

'''

创建第sheet:

'''

sheet1 = f.add_sheet(u'sheet2_1',cell_overwrite_ok=True) #创建sheet

sheet2 = f.add_sheet(u'sheet2_2',cell_overwrite_ok=True) #创建sheet

sheet3 = f.add_sheet(u'sheet2_3',cell_overwrite_ok=True) #创建sheet

sheet4 = f.add_sheet(u'sheet2_4',cell_overwrite_ok=True) #创建sheet

row0 = [u'UserNo',u'Name',u'Question',u'Answer',u'Layer',u'Mark',u'Score',u'AbilityID']

for i in range(0,len(row0)):

sheet1.write(0,i,row0[i])

sheet2.write(0,i,row0[i])

sheet3.write(0,i,row0[i])

sheet4.write(0,i,row0[i])

# 打开文件

workbook = xlrd.open_workbook(file)

sheet0 = workbook.sheet_by_index(0) # sheet索引从0开始

cols = sheet0.col_values(cols_numb) # 获取列内容

rows_list_1=[]

rows_list_2=[]

rows_list_3=[]

rows_list_4=[]

for i in range(1,len(cols)):

if float(cols[i]) < 12.0:

rows_list_1.append(i)

if float(cols[i]) >= 12.0 and float(cols[i]) < 16.0:

rows_list_2.append(i)

if float(cols[i]) >= 16.0 and float(cols[i]) < 18.0:

rows_list_3.append(i)

if float(cols[i]) >= 18.0:

print(i)

print(type(cols[i]))

exit()

rows_list_4.append(i)

'''

sheet2_1保存差，小于12分

'''

for j in range(0,len(rows_list_1)):

rows = sheet0.row_values(rows_list_1[j]) # 获取行内容

for i in range(0,len(rows)):

sheet1.write(j+1,i,rows[i])

'''

sheet2_2保存中，大于等于12，且小于16分

'''

for j in range(0,len(rows_list_2)):

rows = sheet0.row_values(rows_list_2[j]) # 获取行内容

for i in range(0,len(rows)):

sheet2.write(j+1,i,rows[i])

'''

sheet2_3保存良，大于等于16，且小于18分

'''

for j in range(0,len(rows_list_3)):

rows = sheet0.row_values(rows_list_3[j]) # 获取行内容

for i in range(0,len(rows)):

sheet3.write(j+1,i,rows[i])

'''

sheet2_4保存优，大于等于18分

'''

for j in range(0,len(rows_list_4)):

rows = sheet0.row_values(rows_list_4[j]) # 获取行内容

for i in range(0,len(rows)):

sheet4.write(j+1,i,rows[i])

f.save('./data/demo2.xls')

if __name__ == '__main__':

# 读取文件的行和列

rows_numb=0

cols_numb=6

read_excel(rows_numb,cols_numb)

ChineseClean_demo3.py:

# -*- coding:utf-8 -*-

import xlrd

import xlwt

'''

python3.4

'''

file="./data/answer_detail_5_15307860968687.xls"

def read_excel(rows_numb,cols_numb):

f = xlwt.Workbook() #创建工作簿

'''

创建第一个sheet:

sheet1

'''

sheet1 = f.add_sheet(u'sheet1',cell_overwrite_ok=True) #创建sheet

sheet2 = f.add_sheet(u'sheet2',cell_overwrite_ok=True) #创建sheet

sheet3 = f.add_sheet(u'she