本地csv,txt
pandas库 pd.read_csv() pd.to_csv()
with open() as f: f.read()/f.write() ??readline() readlines()
mysql
import pymysql
from sqlalchemy import create_engine
– 读
connection=pymysql.connect(host=,port=,user=,password=,use_unicode=,charset=)
tmp=connection.cursor()
tmp.excute(sql_query_data) #sql dml命令
df=pd.Dataframe(list(tmp.fetchall()))
– 写
conn=create_engin(‘mysql+pymysql://{0}:{1}@{2}:{3}?charset=utf8’.format(
user,password,host,port,database))
pd.io.sql.to_sql(dataframe,table_name,conn,if_exists=‘replace’,index=False)
hdfs
from pyhdfs import HdfsClient
tenant_id=1
hosts=
user_name=
file_path=
client=HafsClient(host=,user_name=)
hafs_ds_dir_list=client.listdir(file_path)
??一个path一张表
……
te_file_open=client.open(te_file_path)
df=pd.read_table(te_file_open,encoding=‘utf-8’,sep=’\x01’,header=None)