pandas将不同文件合并
- 文件类型不同【此代码为tsv,xlsx文件】
- 内容格式一致
import os
import pandas as pd
err_lst=[]
data = pd.DataFrame()
file_chdir=os.path.join(os.getcwd(),'data',name)
for root,dirs,files in os.walk(file_chdir):
for file in files:
suffix_name=os.path.splitext(file)[1]
try:
root_file=os.path.join(root,file)
if suffix_name== '.tsv':
df=pd.read_csv(root_file, sep='\t',skiprows=7)
elif suffix_name== '.xls':
df=pd.read_excel(root_file,skiprows=5,skipfooter=21)
data=data.append(df)
print(file,'successfully')
except Exception as e:
err_lst.append(file)
print(file,'error')
continue