pandas series

series是一维数组

series创建

#方式1，通过list创建
t = pd.Series([1,2,3,'a','b','c'])
print(t) 
>>>
0    1
1    2
2    3
3    a
4    b
5    c
dtype: object

print(type(t))
>>>
<class 'pandas.core.series.Series'>

#默认索引从0开始，指定索引，索引列表长度要和数据长度一致，否则会抛异常
t = pd.Series([1,2,3,'a','b','c'],index=['a','b','c','d','e','f'])
print(t)
>>>
a    1
b    2
c    3
d    a
e    b
f    c
dtype: object

#方式2，通过字典创建，字典的key会变成Series的索引
tmp_dict = {"name":'xiaobai','age':12,'sex':'male'}
t = pd.Series(tmp_dict)
print(t)
>>>
name    xiaobai
age          12
sex        male
dtype: object

修改Series类型

t1 = pd.Series([1,2,3])
print(t1.dtype)
>>>int64
t2 = t1.astype(float)
print(t2)
>>>
0    1.0
1    2.0
2    3.0
dtype: float64

Series切片和索引

tmp_dict = {"name":'xiaobai','age':12,'sex':'male'}
t = pd.Series(tmp_dict)
print(t)
>>>
name    xiaobai
age          12
sex        male
dtype: object

#根据索引获取值
print(t["age"])
>>>12

#根据位置取值
print(t[1])
>>>12

#位置切片，取0~2的值
print(t[0:2])
>>>
name    xiaobai
age          12
dtype: object

#取位置0和2的值
print(t[[0,2]])
>>>
name    xiaobai
sex        male
dtype: object

#根据索引取值
print(t[["name","sex"]])
>>>
name    xiaobai
sex        male
dtype: object

#取某个不存在的索引，NaN
print(t[["name","height"]])
>>>
name      xiaobai
height        NaN
dtype: object

#值过滤
print(t[t=="xiaobai"])
>>>
name    xiaobai
dtype: object

Series索引和值操作

tmp_dict = {"name":'xiaobai','age':12,'sex':'male'}
t = pd.Series(tmp_dict)
>>>
name    xiaobai
age          12
sex        male
dtype: object

#索引操作
t_index = t.index
print(t_index)
>>>Index(['name', 'age', 'sex'], dtype='object')

print(type(t_index))
>>><class 'pandas.core.indexes.base.Index'>

for item in t_index:
    print(item)
>>>
name
age
sex

print(list(t_index))
>>>['name', 'age', 'sex']

#值操作
t_values = t.values
print(t_values)
>>>['xiaobai' 12 'male']

print(type(t_values))
>>><class 'numpy.ndarray'>

for item in t_values:
    print(item)
>>>
xiaobai
12
male

print(list(t_values))
>>>['xiaobai', 12, 'male']