Python可视化数据分析09、Pandas_MySQL读写

pip3 install sqlalchemy

pip3 install pymysql

import pandas as pd
from sqlalchemy import create_engine  # 引入create_engine方法

df = pd.DataFrame({"id": [1, 2, 3], "name": ["雷静", "小凤", "春梦"], "age": ["21", "22", "20"]})
conn = create_engine('mysql+pymysql://root:12345678@localhost:3306/mytest?charset=utf8')
# 将df对象保存到数据库名为mytest的库，名称为user的数据库表中
pd.io.sql.to_sql(df, 'user', conn, schema='mytest', if_exists='append')
# # 执行“select * from words;”SQL语句读取数据库中的数据
df1 = pd.read_sql('select * from user;', con=conn)
print(df1)

import pandas as pd
from sqlalchemy import create_engine  # 引入create_engine方法
from sqlalchemy.orm import sessionmaker

conn = create_engine('mysql+pymysql://root:12345678@localhost:3306/mytest?charset=utf8')
# 修改-删除
DB_Session = sessionmaker(bind=conn)
session = DB_Session()
# session.execute("insert into user values(3,0,'小龙女',22)")
# session.execute("update user set name='晓凤' where id=2")
session.execute("delete from user where id=4")
session.commit()
# # 执行“select * from words;”SQL语句读取数据库中的数据
df = pd.read_sql('select * from user;', con=conn)
print(df)

import pandas as pd
from sqlalchemy import create_engine  # 引入create_engine方法

conn = create_engine('mysql+pymysql://root:12345678@localhost:3306/mytest?charset=utf8')
# # 执行“select * from words;”SQL语句读取数据库中的数据
df = pd.read_sql('select * from user;', con=conn)
print(df)
#  基础信息
print(df.info)
# 查看列名
print(df.columns)
# 查看各列数据类型
print(df.dtypes)
# 查看下标
print(df.index)
#  数据浏览前2条
print(df.head(2))
#  查看name到age列
print(df.loc[:, "name":"age"])
#  基本统计
print("最大年龄：", df.age.max())
print("平均年龄：", df.age.mean())
# 查询
print(df[df.name == "春梦"])
# 排序·True正序False倒序
print(df.sort_values(by=["age"], ascending=False))
# 在第二列【下标是1】添加列
df.insert(1, "sex", "女")
print(df)
# 在最后添加列
df["introduce"] = "巾帼"
print(df)
# 删除某行
df = df.drop(1)
print(df)
# 替换
value = pd.Series([1, "女", "雷静静", 20, "大眼姑娘"], index=["id", "sex", "name", "age", "introduce"])
df.loc[0] = value
value = pd.Series([4, "女", "小龙女", 18, "冰山美人"], index=["id", "sex", "name", "age", "introduce"])
df.loc[3] = value
print(df)
# 条数
print(len(df))