Pandas基本操作：Series和DataFrame（Python）

直接上代码

Series

import pandas

# print(pandas.Series([232, 455, 2, 3456, 2]))

t = pandas.Series([15,2,3,4,5],index=list("abcde"))


# print(t["c"])

# print(t[1:4])

# print(t[[1,4]])

# print(t[t>2])

print(t.values)

DataFrame

import numpy
import pandas
numpy.random.seed(9)
t = pandas.DataFrame(numpy.random.random(40).reshape(10,4),
                     index=list("abcdefghij"),columns=list("ABCD"))

# print(t)  #同理，t也可以是字典，或者字典构成的列表

# print(t.index)

# print(t.columns)

# print(t.values)

# print(t["D"].mean())

# print(t.shape)

# print(t.dtypes)

# print(t.ndim)

# print(t.info())

# print(t.describe())

# print(t.sort_values(by = "e", ascending= False))

# print(t[:7])   #取前7行

# print(t["B"])   #取列
# print(type(t["B"]))

# print(t.loc["h", :])  #用loc的各种切片。这里注意loc后面是[]
# print(t.loc[["h","a"], ["B","D"]])
# print(t.loc[["h","a"], "A":"C"])
# print(t.iloc[1:8,[3,1]])  #用iloc切片，直接用数字索引

# t = t.iloc[1:4,[3,2,1]]   #测试下赋值
# print(t)
# t[t>0.5]=numpy.NaN
# print(t)

# print(t[(t["D"]>0.2)&(t["D"]<0.8)])  #带条件切片，与条件
# print(t[(t["A"]>0.8)|(t["D"]>0.8)])    #带条件切片，或条件

# t = t[t>0.5]
# t2 = pandas.notnull(t)   #False为NaN
# # print(t)
# # print(t2)
# # print(t.dropna(how="all"))   #删除NaN
# print(t.fillna(8888))  #填充NaN