pandas入门：pandas的数据结构介绍

Series

from pandas import Series,DataFrame
import pandas as pd
import numpy as np

# Series是一种类似于一维数组的对象，由一组数据(各种Numpy数据类型)以及一组与之相关的数据标签（即索引）组成
obj = Series([4,7,-5,3])
print(obj)
'''
0    4
1    7
2   -5
3    3
dtype: int64
'''
# 索引在左边，值在右边，可通过Series的values和index属性获取其数组表示形式和索引对象
print(obj.values) # [ 4  7 -5  3]
print(obj.index) # RangeIndex(start=0, stop=4, step=1)

# 创建一个带有可以对各个数据点进行标记的索引
obj2 = Series([4,7,-5,1],index=['d','b','a','c'])
print(obj2)
'''
d    4
b    7
a   -5
c    1
dtype: int64
'''
print(obj2.index) # Index(['d', 'b', 'a', 'c'], dtype='object')

# 与普通NumPy数据相比，可以通过索引的方式选取Series中单个或一组值
print(obj2['a']) # -5
obj2['d'] = 6
print(obj2[['c','a','d']])
'''
c    1
a   -5
d    6
dtype: int64
'''
print(obj2[obj2>0])
'''
d    6
b    7
c    1
dtype: int64
'''
print(obj2*2)
'''
d    12
b    14
a   -10
c     2
dtype: int64
'''
print(np.exp(obj2))
'''
d     403.428793
b    1096.633158
a       0.006738
c       2.718282
dtype: float64
'''
print('b'in obj2) # True
print('e'in obj2) # False

# 通过字典创建Series
sdata = {'Ohio':35000,'Texas':71000,'Oregon':16000,'Utah':5000}
obj3 = Series(sdata)
print(obj3)
'''
Ohio      35000
Oregon    16000
Texas     71000
Utah       5000
dtype: int64
'''
states = ['California','Ohio','Oregon','Texas']
obj4 = Series(sdata,index=states)
print(obj4)
'''
California        NaN
Ohio          35000.0
Oregon        16000.0
Texas         71000.0
dtype: float64
'''
# sdata中跟states索引相匹配的3个值会找出来放到对应位置上，由于California所对应的sdata找不到，其结果就是NaN（not a number，表示缺失或NA值）
# Pandas的isnull和notnull函数可用于检测缺失值
print(pd.isnull(obj4))
'''
California     True
Ohio          False
Oregon        False
Texas         False
dtype: bool
'''
print(pd.notnull(obj4))
'''
California    False
Ohio           True
Oregon         True
Texas          True
dtype: bool
'''
print(obj4.isnull())
'''
California     True
Ohio          False
Oregon        False
Texas         False
dtype: bool
'''
# Series的一个重要功能是：在算术运算中会自动对齐不同索引数据
print(obj3+obj4)
'''
California         NaN
Ohio           70000.0
Oregon         32000.0
Texas         142000.0
Utah               NaN
dtype: float64
'''
# Series对象本身及其索引都有一个name属性
obj4.name = 'population'
obj4.index.name = 'state'
print(obj4)
'''
state
California        NaN
Ohio          35000.0
Oregon        16000.0
Texas         71000.0
Name: population, dtype: float64
'''
# Series的索引可以通过赋值的方式就地修改
obj.index = ['Bob','Steve','Jeff','Ryan']
print(obj)
'''
Bob      4
Steve    7
Jeff    -5
Ryan     3
dtype: int64
'''

DataFrame

from pandas import Series,DataFrame
import pandas as pd
import numpy as np

# DataFrame既有行索引也有列索引，可以看做由Series组成的字典
data = {'state':['Ohio','Ohio','Ohio','Nevada','Nevada'],
        'year':[2000,2001,2002,2001,2002],
        'pop':[1.5,1.7,3.6,2.4,2.9]}
frame = DataFrame(data)
print(frame)
'''
   pop   state  year
0  1.5    Ohio  2000
1  1.7    Ohio  2001
2  3.6    Ohio  2002
3  2.4  Nevada  2001
4  2.9  Nevada  2002
'''

# 如果指定了列序列，则dataframe的列就会按照指定顺序进行排列
frame1 = DataFrame(data,columns=['year','state','pop'])
print(frame1)
'''
   year   state  pop
0  2000    Ohio  1.5
1  2001    Ohio  1.7
2  2002    Ohio  3.6
3  2001  Nevada  2.4
4  2002  Nevada  2.9
'''
# 如果传入列在数据中找不到，就会产生NA值
frame2 = DataFrame(data,columns=['year','state','pop','debt'],
                  index=['one','two','three','four','five'])
print(frame2)
'''
       year   state  pop debt
one    2000    Ohio  1.5  NaN
two    2001    Ohio  1.7  NaN
three  2002    Ohio  3.6  NaN
four   2001  Nevada  2.4  NaN
five   2002  Nevada  2.9  NaN
'''
print(frame2.columns) # Index(['year', 'state', 'pop', 'debt'], dtype='object')
# 通过类似字典标记的方式或者属性的方式，可将dataframe的列获取为一个series
print(frame2['state'])
'''
one        Ohio
two        Ohio
three      Ohio
four     Nevada
five     Nevada
Name: state, dtype: object
'''
print(frame2.year)
'''
one      2000
two      2001
three    2002
four     2001
five     2002
Name: year, dtype: int64
'''
# 通过索引字段ix获取
print(frame2.ix['three'])
'''
year     2002
state    Ohio
pop       3.6
debt      NaN
Name: three, dtype: object
'''
# 列可以通过赋值的方式进行修改，例如给debt列赋上一个标量的值或一组值
frame2['debt'] = 16.5
print(frame2)
'''
       year   state  pop  debt
one    2000    Ohio  1.5  16.5
two    2001    Ohio  1.7  16.5
three  2002    Ohio  3.6  16.5
four   2001  Nevada  2.4  16.5
five   2002  Nevada  2.9  16.5
'''
frame2['debt'] = np.arange(5.)
print(frame2)
'''
       year   state  pop  debt
one    2000    Ohio  1.5   0.0
two    2001    Ohio  1.7   1.0
three  2002    Ohio  3.6   2.0
four   2001  Nevada  2.4   3.0
five   2002  Nevada  2.9   4.0
'''
# 将列表或数组赋值给某列时，其长度必须跟dataframe的长度相匹配，如果赋值的是一个series，就是精确匹配dataframe的索引，所有空位都将被填上缺失值
val = Series([-1.2,-1.5,-1.7],index = ['two','four','five'])
frame2['debt'] = val
print(frame2)
'''
       year   state  pop  debt
one    2000    Ohio  1.5   NaN
two    2001    Ohio  1.7  -1.2
three  2002    Ohio  3.6   NaN
four   2001  Nevada  2.4  -1.5
five   2002  Nevada  2.9  -1.7
'''
# 为不存在的列赋值会创建出一个新列，关键字del用于删除列
frame2['eastern'] = frame2.state =='Ohio'
print(frame2)
'''
       year   state  pop  debt  eastern
one    2000    Ohio  1.5   NaN     True
two    2001    Ohio  1.7  -1.2     True
three  2002    Ohio  3.6   NaN     True
four   2001  Nevada  2.4  -1.5    False
five   2002  Nevada  2.9  -1.7    False
'''
del frame2['eastern']
print(frame2)
'''
       year   state  pop  debt
one    2000    Ohio  1.5   NaN
two    2001    Ohio  1.7  -1.2
three  2002    Ohio  3.6   NaN
four   2001  Nevada  2.4  -1.5
five   2002  Nevada  2.9  -1.7
'''

# 嵌套字典
pop = {"Nevada":{2001:2.4,2002:2.9},
       'Ohio':{2000:1.5,2001:1.7,2002:3.6}}
frame3 = DataFrame(pop)
print(frame3)
# 字典外层的键作为列，内层键座位行索引
'''
      Nevada  Ohio
2000     NaN   1.5
2001     2.4   1.7
2002     2.9   3.6
'''
# 进行转置
print(frame3.T)
'''
        2000  2001  2002
Nevada   NaN   2.4   2.9
Ohio     1.5   1.7   3.6
'''
# 显示指定索引
print(DataFrame(pop,index=[2001,2002,2003]))
'''
      Nevada  Ohio
2001     2.4   1.7
2002     2.9   3.6
2003     NaN   NaN
'''

# print(frame3['Ohio'][:-1])
# print(frame3['Nevada'][:2])
pdata = {"Nevada":frame3['Nevada'][:2],
       'Ohio':frame3['Ohio'][:-1]}
print(DataFrame(pdata))
'''
      Nevada  Ohio
2000     NaN   1.5
2001     2.4   1.7
'''

# 如果设置了dataframe的index和columns的name属性，则这些信息也会被显示出来
frame3.index.name = 'year'
frame3.columns.name = 'state'
print(frame3)
'''
state  Nevada  Ohio
year               
2000      NaN   1.5
2001      2.4   1.7
2002      2.9   3.6
'''
#与series一样，values属性也会以二维ndarray的形式返回
print(frame3.values)
'''
[[nan 1.5]
 [2.4 1.7]
 [2.9 3.6]]
'''

索引对象

from pandas import Series,DataFrame
import pandas as pd
import numpy as np

obj = Series(range(3),index=['a','b','c'])
index = obj.index
print(index) # Index(['a', 'b', 'c'], dtype='object')
print(index[1:]) # Index(['b', 'c'], dtype='object')
# index是不可修改的
index = pd.Index(np.arange(3))
obj2 = Series([1.5,-2.5,0],index=index)
print(obj2.index is index) # True

pop = {"Nevada":{2001:2.4,2002:2.9},
       'Ohio':{2000:1.5,2001:1.7,2002:3.6}}
frame3 = DataFrame(pop)
print('Ohio' in frame3.columns) # True
print(2003 in frame3.index) # False

Index的方法和属性

from pandas import Series
obj1 = Series([1,6,5,9],index=['a','b','c','d'])
obj2 = Series([2,10,6],index=['a','a','b'])
obj3 = Series([2,10,10])

# append 连接另一个index对象，产生一个新的index
obj_append = obj1.append(obj2)
print(obj_append)
'''
a     1
b     6
c     5
d     9
a     2
a    10
b     6
dtype: int64
'''

# diff 计算差集，得到一个index
obj_diff = obj1.diff()
print(obj_diff)
# 后一个value-前一个value
'''
a    NaN
b    5.0
c   -1.0
d    4.0
dtype: float64
'''

# intersection 计算交集
obj_intersection =obj1.index.intersection(obj2.index)
print(obj_intersection) # Index(['a', 'a', 'b'], dtype='object')

# union 计算并集
obj_union = obj1.index.union(obj2.index)
print(obj_union) # Index(['a', 'a', 'b', 'c', 'd'], dtype='object')

# isin 计算一个指示各值是否都包含在参数几个中的布尔型数据
obj_isin = obj1.index.isin(obj2.index)
print(obj_isin) # [ True  True False False]

# delete 删除索引处的元素，并得到新的index
obj_delete =obj1.index.delete(2)
print(obj_delete) # Index(['a', 'b', 'd'], dtype='object')

# drop 删除传入的值，并得到新的index
obj_drop = obj1.drop(['a']) # 删除第a行
print(obj_drop)
'''
b    6
c    5
d    9
dtype: int64
'''

# is_monotonic 当各元素均大于等于前一个元素时，返回True
print(obj3.is_monotonic) # True
print(obj2.is_monotonic) # False

# is_unique 当index没有重复值时，返回True
print(obj3.is_unique) # False
print(obj2.is_unique) # True

# unique 计算index中唯一值的数组
print(obj3.unique()) # [ 2 10]