我试图实现以下目标。我想创建一个python类,将数据库中的所有表转换为pandas数据帧。
我就是这样做的,这不是很通用......
class sql2df():
def __init__(self, db, password='123',host='127.0.0.1',user='root'):
self.db = db
mysql_cn= MySQLdb.connect(host=host,
port=3306,user=user, passwd=password,
db=self.db)
self.table1 = psql.frame_query('select * from table1', mysql_cn)
self.table2 = psql.frame_query('select * from table2', mysql_cn)
self.table3 = psql.frame_query('select * from table3', mysql_cn)
现在我可以像这样访问所有表:
my_db = sql2df('mydb')
my_db.table1
我想要类似的东西:
class sql2df():
def __init__(self, db, password='123',host='127.0.0.1',user='root'):
self.db = db
mysql_cn= MySQLdb.connect(host=host,
port=3306,user=user, passwd=password,
db=self.db)
tables = (""" SELECT TABLE_NAME FROM information_schema.TABLES WHERE TABLE_SCHEMA = '%s' """ % self.db)
<some kind of iteration that gives back all the tables in df as class attributes>
建议最受欢迎......
答案 0 :(得分:5)
我会使用SQLAlchemy:
engine = sqlalchemy.create_engine("mysql+mysqldb://root:123@127.0.0.1/%s" % db)
注意syntax是dialect + driver:// username:password @ host:port / database。
def db_to_frames_dict(engine):
meta = sqlalchemy.MetaData()
meta.reflect(bind=engine)
tables = meta.sorted_tables
return {t: pd.read_sql('SELECT * FROM %s' % t.name,
engine.raw_connection())
for t in tables}
# Note: frame_query is depreciated in favor of read_sql
这会返回一个字典,但您也可以将这些作为类属性(例如,通过更新类字典和__getitem__
)
class SQLAsDataFrames:
def __init__(self, engine):
self.__dict__ = db_to_frames_dict(engine) # allows .table_name access
def __getitem__(self, key): # allows [table_name] access
return self.__dict__[key]
在pandas 0.14中,sql代码已经被重写为引擎,IIRC有所有表的帮助器和读取所有表(使用read_sql(table_name)
)。
答案 1 :(得分:1)
这是我现在拥有的: 进口
import sqlalchemy
from sqlalchemy import create_engine
from sqlalchemy import Table, Column,Date, Integer, String, MetaData, ForeignKey
from sqlalchemy.ext.declarative import declarative_base
from sqlalchemy.orm import relationship, backref
import pandas as pd
engine = sqlalchemy.create_engine("mysql+mysqldb://root:password@127.0.0.1/%s" % 'surveytest')
def db_to_frames_dict(engine):
meta = sqlalchemy.MetaData()
meta.reflect(bind=engine)
tables = meta.sorted_tables
return {t: pd.read_sql('SELECT * FROM %s' % t.name, engine.connect())
for t in tables}
# Note: frame_query is depreciated in favor of read_sql
尚未开始摆弄这部分!下面:
class SQLAsDataFrames:
def __init__(self, engine):
self.__dict__ = db_to_frames_dict(engine) # allows .table_name access
def __getitem__(self, key): # allows [table_name] access
return self.__dict__[key]
错误:看起来至少它试图得到表名......
frames=db_to_frames_dict(engine)
frames
Error on sql SELECT * FROM tbl_original_survey_master
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-4-6b0006e1ce47> in <module>()
----> 1 frames=db_to_frames_dict(engine)
>>>> more tracebck
---> 53 con.rollback()
54 except Exception: # pragma: no cover
55 pass
AttributeError: 'Connection' object has no attribute 'rollback'
感谢您坚持这一点!
答案 2 :(得分:0)
感谢所有帮助,这就是我最终使用的内容:
import sqlalchemy
from sqlalchemy import create_engine
from sqlalchemy import Table, Column,Date, Integer, String, MetaData, ForeignKey
from sqlalchemy.ext.declarative import declarative_base
from sqlalchemy.orm import relationship, backref
import pandas as pd
engine = sqlalchemy.create_engine("mysql+mysqldb://root:123@127.0.0.1/%s" % 'mydb')
def db_to_frames_dict(engine):
meta = sqlalchemy.MetaData()
meta.reflect(engine)
tables = meta.tables.keys()
cnx = engine.raw_connection()
return {t: pd.read_sql('SELECT * FROM %s' % t, cnx )
for t in tables}
class SQLAsDataFrames:
def __init__(self, engine):
self.__dict__ = db_to_frames_dict(engine) # allows .table_name access
def __getitem__(self, key): # allows [table_name] access
return self.__dict__[key]