数据挖掘工具pandas（四）DataFrame的属性

一，DataFrame的基本属性：

shape、dtypes、ndim、index、columns、values、T

import pandas as pd
import numpy as np
# from sqlalchemy import create_engine
# engine = create_engine('mysql+pymysql://root:root@localhost:3306/yoyo')
# sql = """select * from role_info;"""
# df = pd.read_sql(sql,engine)
day_data = np.random.normal(0,1,(500,507))
stock_list = ["股票"+ str(i) for i in range(day_data.shape[0])]
date = ["第"+ str(i)+"天" for i in range(day_data.shape[1])]

df = pd.DataFrame(day_data,index=stock_list,columns=date)

# 1,pandas-dataframe的type
# print(type(df))

# 2,shape dataframe的形状（行数、列数）
# print(df.shape)

# 3,dtypes 每一列的数据类型
# print(df.dtypes)

# 4,ndim 数据维度
# print(df.ndim)

# 5,index 行索引
# print(df.index,df.index[0])

# 6,columns 列索引
# print(df.columns,df.columns[0])

# 7,values 对象值，二维ndarray数组
# print(df.values)

# 8, T , transpose() 两种转置
# print(df.T)
print(df.transpose())

二，DataFrame的整体情况：

head()，tail()，info()，describe()
import pandas as pd
import numpy as np
# from sqlalchemy import create_engine
# engine = create_engine('mysql+pymysql://root:root@localhost:3306/yoyo')
# sql = """select * from role_info;"""
# df = pd.read_sql(sql,engine)
day_data = np.random.normal(0,1,(500,507))
stock_list = ["股票"+ str(i) for i in range(day_data.shape[0])]
date = ["第"+ str(i)+"天" for i in range(day_data.shape[1])]
df = pd.DataFrame(day_data,index=stock_list,columns=date)

# 1,head(nums) 显示头部几行，默认5行
# print(df.head(3))

# 2,tail(nums) 显示末尾几行，默认5行
# print(df.tail(3))

# 3,info() 相关信息概览：行数，列数，列索引，列非空值个数、列类型、内存占用
# print(df.info())

# 4,describe() 快速综合统计带有数值的结果。计数、均值、标准差、最大值、四分位数、最小值
print(df.describe())