使用pandas对cvs文件进行解析并导入到数据中心
# -*- coding: utf-8 -*-
import pandas as pd
from sqlalchemy import create_engine
import os
def eachFile(filepath):
pathDir = os.listdir(filepath)
#根据文件夹目录,循环所有的文件
for allDir in pathDir:
child = os.path.join('%s/%s' % (filepath, allDir))
print(child)
cvstosql(child)
def cvstosql(path):
csv_data = pd.read_csv(path,encoding='ANSI') # 读取训练数据
print(csv_batch_data) # (5, 9)
db_info = {'user': 'root',
'password': 'root',
'host': 'localhost',
'port': 3306,
'database': 'test'
}
engine = create_engine(
'mysql+pymysql://%(user)s:%(password)s@%(host)s:%(port)d/%(database)s?charset=utf8' % db_info, encoding='utf-8')
pd.io.sql.to_sql(csv_data, 'example', con=engine, index=False, if_exists='append')
print('{}完成'.format(path))
if __name__ == '__main__':
eachFile('C:/Users/Administrator/Downloads/9month/RPT_202109_126723')