52circle
利用xlrd读取excel
筛选0值超过99%的列,并删除

import xlrd

workbook=xlrd.open_workbook(r"123.xlsx")
table = workbook.sheet_by_name(\'Sheet1\')
nrows=table.nrows
ncols=table.ncols
del_col=[]
for j in range(ncols) :
sum = 0
for ai in table.col_values(j):
if ai == 0.0 :
sum+=1
if float(sum)/nrows>=0.99:
del_col.append(j)
print del_col

利用pandas读取excel
筛选0值超过99%的列,并删除


import pandas
as pd
df1=pd.read_csv(r"123.csv")
df=pd.DataFrame(df1)
nrows=df.shape[0]
ncols=df.columns.size
del_col=[]
for j in range(ncols) :
sum = 0
for ai in df.iloc[:,j]:
if ai == 0.0 :
sum+=1
if float(sum)/nrows>=0.99:
del_col.append(j)
print del_col



分类:

技术点:

相关文章: