pandas初级

以下代码基于数据结构DataFrame！！！
读取数据的函数：read_excel()和read_csv()
“”“pandas读excel里面的数据”“”

data1 = pd.read_excel(‘data1.xlsx’, skiprows=‘Sheet1’, header=0, index_col=0, usecols=[2])

data1 = pd.read_excel(‘data1.xlsx’, skiprows=‘Sheet1’, usecols=[1,2,3])

data1 = pd.read_excel(“data1.xlsx”)

print(data1)

“”“pandas read csv”“”

data2 = pd.read_csv(“data2.csv”, encoding=“gbk”, nrows=3)

print(data2)

“”" pandas find data “”"

data2 = pd.read_csv(“data2.csv”, encoding=“gbk”)

View the data in the first n rows,n=6

print(data2.head(6))

find the number of row,cow.返回一个元组

print(data2.shape)

查看数据属性

print(data2.info())

查看某一列的属性

print(data2[‘age’].info())

转换数据类型

data2[‘age’] = data2[‘age’].astype(“float64”)

print(data2[‘age’].dtype) #查看数据类型

“”“分隔”“”

data1 = pd.read_excel(“data1.xlsx”, index_col=0) #选择行标签

print(data1)

“”“选择数据”“”

选择单行数据loc、iloc

print(data1.loc[“d1”])

print(data1.iloc[1])

选择多行数据

print(data1.loc[[‘d1’,‘d3’]])

print(data1.iloc[[1,5]])

print(data1.iloc[1:4]) #切片

根据条件选择行

a = data1[‘性别’] == ‘男’

print(data1[a])

选择单列数据

print(data1[‘姓名’]) #通过列标签

选择多列数据

print(data1[[‘姓名’, ‘年龄’]])

print(data1.iloc[:, [0,1, 2]])

print(data1.iloc[:, 0:3])

“”“同时选中行列”“”

print(data1.loc[[‘d1’,‘d3’],[‘姓名’,‘性别’]])

print(data1.iloc[[2,4],[0,2]])

“”“修改行标签和列标签”“”
data1 = pd.read_excel(“data1.xlsx”)

print(data1)

设置列标签

print(data1.set_index(‘编号’))

print(data1.rename(columns={‘编号’:‘订单编号’,‘姓名’:‘name’,‘年龄’:‘age’,‘性别’:‘sex’},index={0:‘A’,1:‘B’,2:‘C’,3:‘D’}))

data1.columns = [‘编号’,‘name’,‘age’,‘sex’]

data1.index = [‘A’,‘B’,‘C’,‘D’,‘E’,‘F’,‘G’,‘H’]

print(data1)

以上代码基于下面的表格