pandas 链接数据库
直接执行sql
from pandas.io import sql
sql.execute(‘SELECT * FROM table_name’, engine)
sql.execute(‘INSERT INTO table_name VALUES(?, ?, ?)’, engine,
params=[(‘id’, 1, 12.2, True)])
创建链接
from sqlalchemy import create_engine
engine = create_engine('postgresql://scott:tiger@localhost:5432/mydatabase')
engine = create_engine('mysql+mysqldb://scott:tiger@localhost/foo')
engine = create_engine('oracle://scott:[email protected]:1521/sidname')
engine = create_engine('mssql+pyodbc://mydsn')
# sqlite:///
# where is relative:
engine = create_engine('sqlite:///foo.db')
# or absolute, starting with a slash:
engine = create_engine('sqlite:////absolute/path/to/foo.db')
创建引擎
from sqlalchemy import create_engine
engine = create_engine('sqlite:///:memory:')
with engine.connect() as conn:
data = pd.read_sql_table('data', conn)
chunksize设置每次写入的数量，有些数据库会设置限制。
data.to_sql(‘data_chunked’, conn, chunksize=1000)
指定相应的数据类型
from sqlalchemy.types import String
data.to_sql(‘data_dtype’, engine, dtype={‘Col_1’: String})
指定索引列
pd.read_sql_table(‘data’, engine, index_col=‘id’)
指定时间类型
pd.read_sql_table(‘data’, engine, parse_dates=[‘Date’])
读取sql语句选择的数据
pd.read_sql_query(‘SELECT * FROM data’, engine)
列子：
通过sqlalchemy转换指定的数据库格式
from sqlalchemy import create_engine
from sqlalchemy import Date
import pandas as pd
a=[{"time":"2018-09-19","age":17,"salary":199.2,"name":"wang"}]
df=pd.DataFrame(a)
engine = create_engine(
"postgresql://user:psword@localhost:5432/postgres",
pool_size=20, max_overflow=0,
)
with engine.connect() as conn:
df.to_sql("test", conn, if_exists='replace', index=False,dtype={'time': Date})
参考文献：
http://pandas.pydata.org/pandas-docs/stable/io.html#io-sql
http://docs.sqlalchemy.org/en/latest/core/type_basics.html