Datawhale Task03 索引 打卡

import numpy as np
import pandas as pd

3.1 索引器

3.1.1 表的列索引

df = pd.read_csv('joyful-pandas-master/data/learn_pandas.csv',usecols = ['School','Grade','Name','Gender','Weight','Transfer']) 
#usecoles表示读取列的集合

df['Name'].head() #通过[]来实现

0      Gaopeng Yang
1    Changqiang You
2           Mei Sun
3      Xiaojuan Sun
4       Gaojuan You
Name: Name, dtype: object

df[['Name','Gender']].head()  #通过[列名组成的列表来实现]

	Name	Gender
0	Gaopeng Yang	Female
1	Changqiang You	Male
2	Mei Sun	Male
3	Xiaojuan Sun	Female
4	Gaojuan You	Male

df.Name.head()

0      Gaopeng Yang
1    Changqiang You
2           Mei Sun
3      Xiaojuan Sun
4       Gaojuan You
Name: Name, dtype: object

3.1.2 序列的行索引

#以字符串为索引的Series
s = pd.Series([1,2,3,4,5,6],index = ['a','b','a','a','a','c'])
s

a    1
b    2
a    3
a    4
a    5
c    6
dtype: int64

s['c':'b':-2]  #？？？

c    6
a    4
b    2
dtype: int64

s['c':'b':-3]

c    6
a    3
dtype: int64

s['c':'b':-1]

c    6
a    5
a    4
a    3
b    2
dtype: int64

s['b']

2

s[['c','b']]

c    6
b    2
dtype: int64

s['c':'b':-2] #-2是步长

c    6
a    4
b    2
dtype: int64

s['c':'b':-3]

c    6
a    3
dtype: int64

s['c':'b':-3]

c    6
a    3
dtype: int64

s['c':'b':-1]

c    6
a    5
a    4
a    3
b    2
dtype: int64

#以整数为索引的Series
s = pd.Series(['a','b','c','d','e','f'],index = [1,3,1,2,5,4])
s

1    a
3    b
1    c
2    d
5    e
4    f
dtype: object

s[1]

1    a
1    c
dtype: object

s[[2,3]]

2    d
3    b
dtype: object

s[1:-1:2]  #从第2个元素到到最后一个元素，而且最后一个元素取不到，步长为2，所以取
        #索引是从0开始的!脑子瓦特了吧 
        #3 1 2 5 步长为2  所以取b d

3    b
2    d
dtype: object

3.1.3 loc索引器

df_demo = df.set_index('Name')

df_demo.head()

	School	Grade	Gender	Weight	Transfer
Name
Gaopeng Yang	Shanghai Jiao Tong University	Freshman	Female	46.0	N
Changqiang You	Peking University	Freshman	Male	70.0	N
Mei Sun	Shanghai Jiao Tong University	Senior	Male	89.0	N
Xiaojuan Sun	Fudan University	Sophomore	Female	41.0	N
Gaojuan You	Fudan University	Sophomore	Male	74.0	N

#*为单个元素
df_demo.loc['Qiang Sun']  #重复为dataframe

	School	Grade	Gender	Weight	Transfer
Name
Qiang Sun	Tsinghua University	Junior	Female	53.0	N
Qiang Sun	Tsinghua University	Sophomore	Female	40.0	N
Qiang Sun	Shanghai Jiao Tong University	Junior	Female	NaN	N

df_demo.loc['Quan Zhao']  #不重复为series

School      Shanghai Jiao Tong University
Grade                              Junior
Gender                             Female
Weight                                 53
Transfer                                N
Name: Quan Zhao, dtype: object

#同时选择行和列
df_demo.loc['Qiang Sun','School'] #返回Series

Name
Qiang Sun              Tsinghua University
Qiang Sun              Tsinghua University
Qiang Sun    Shanghai Jiao Tong University
Name: School, dtype: object

df_demo.loc['Quan Zhao','School']  #返回单个元素

'Shanghai Jiao Tong University'

# *为元素列表
df_demo.loc[['Quan Zhao','Qiang Sun'],['School','Gender']] #取出所有元素值对应的行和列

	School	Gender
Name
Quan Zhao	Shanghai Jiao Tong University	Female
Qiang Sun	Tsinghua University	Female
Qiang Sun	Tsinghua University	Female
Qiang Sun	Shanghai Jiao Tong University	Female

#*为切片
df_demo.loc['Gaojuan You':'Gaoqiang Qian','School':'Gender']

	School	Grade	Gender
Name
Gaojuan You	Fudan University	Sophomore	Male
Xiaoli Qian	Tsinghua University	Freshman	Female
Qiang Chu	Shanghai Jiao Tong University	Freshman	Female
Gaoqiang Qian	Tsinghua University	Junior	Female

df_loc_slice_demo = df_demo.copy()
df_loc_slice_demo.index = range(df_demo.shape[0],0,-1)  #倒序反着来
df_loc_slice_demo

	School	Grade	Gender	Weight	Transfer
200	Shanghai Jiao Tong University	Freshman	Female	46.0	N
199	Peking University	Freshman	Male	70.0	N
198	Shanghai Jiao Tong University	Senior	Male	89.0	N
197	Fudan University	Sophomore	Female	41.0	N
196	Fudan University	Sophomore	Male	74.0	N
...	...	...	...	...	...
5	Fudan University	Junior	Female	46.0	N
4	Tsinghua University	Senior	Female	50.0	N
3	Shanghai Jiao Tong University	Senior	Female	45.0	N
2	Shanghai Jiao Tong University	Senior	Male	71.0	N
1	Tsinghua University	Sophomore	Male	51.0	N

200 rows × 5 columns

df_demo.shape[0]

200

df_loc_slice_demo.loc[5:3]

	School	Grade	Gender	Weight	Transfer
5	Fudan University	Junior	Female	46.0	N
4	Tsinghua University	Senior	Female	50.0	N
3	Shanghai Jiao Tong University	Senior	Female	45.0	N

df_loc_slice_demo.loc[3:5]

	School	Grade	Gender	Weight	Transfer

#*为布尔值列表
df_demo.loc[df_demo.Weight>70].head()

	School	Grade	Gender	Weight	Transfer
Name
Mei Sun	Shanghai Jiao Tong University	Senior	Male	89.0	N
Gaojuan You	Fudan University	Sophomore	Male	74.0	N
Xiaopeng Zhou	Shanghai Jiao Tong University	Freshman	Male	74.0	N
Xiaofeng Sun	Tsinghua University	Senior	Male	71.0	N
Qiang Zheng	Shanghai Jiao Tong University	Senior	Male	87.0	N

df_demo.loc[df_demo.Grade.isin(['Freshman','Senior'])].head()

	School	Grade	Gender	Weight	Transfer
Name
Gaopeng Yang	Shanghai Jiao Tong University	Freshman	Female	46.0	N
Changqiang You	Peking University	Freshman	Male	70.0	N
Mei Sun	Shanghai Jiao Tong University	Senior	Male	89.0	N
Xiaoli Qian	Tsinghua University	Freshman	Female	51.0	N
Qiang Chu	Shanghai Jiao Tong University	Freshman	Female	52.0	N

#复合条件
condition_1_1 = df_demo.School == 'Fudan University'
condition_1_2 = df_demo.Grade == 'Senior'
condition_1_3 = df_demo.Weight > 70
condition_1 = condition_1_1 & condition_1_2 &condition_1_3

condition_2_1 = df_demo.School == 'Peking University'
condition_2_2 = df_demo.Grade == 'Senior'
condition_2_3 = df_demo.Weight > 80
condition_2 = condition_2_1 & (~condition_2_2) & condition_2_3  #~是取反
df_demo.loc[condition_1 | condition_2]

	School	Grade	Gender	Weight	Transfer
Name
Qiang Han	Peking University	Freshman	Male	87.0	N
Chengpeng Zhou	Fudan University	Senior	Male	81.0	N
Changpeng Zhao	Peking University	Freshman	Male	83.0	N
Chengpeng Qian	Fudan University	Senior	Male	73.0	Y

#*为函数
def condition(x):
    condition_1_1 = x.School == 'Fudan University'
    condition_1_2 = x.Grade == 'Senior'
    condition_1_3 = x.Weight > 70
    condition_1 = condition_1_1 & condition_1_2 &condition_1_3
    condition_2_1 = x.School == 'Peking University'
    condition_2_2 = x.Grade == 'Senior'
    condition_2_3 = x.Weight > 80
    condition_2 = condition_2_1 & (~condition_2_2) & condition_2_3  #~是取反
    result = condition_1 | condition_2
    return result

df_demo.loc[condition]  

	School	Grade	Gender	Weight	Transfer
Name
Qiang Han	Peking University	Freshman	Male	87.0	N
Chengpeng Zhou	Fudan University	Senior	Male	81.0	N
Changpeng Zhao	Peking University	Freshman	Male	83.0	N
Chengpeng Qian	Fudan University	Senior	Male	73.0	Y

#lambda表达式
df_demo.loc[lambda x: 'Quan Zhao',lambda x:'Gender']

'Female'

df_demo.loc[lambda x: slice('Gaojuan You','Gaoqiang Qian')]

	School	Grade	Gender	Weight	Transfer
Name
Gaojuan You	Fudan University	Sophomore	Male	74.0	N
Xiaoli Qian	Tsinghua University	Freshman	Female	51.0	N
Qiang Chu	Shanghai Jiao Tong University	Freshman	Female	52.0	N
Gaoqiang Qian	Tsinghua University	Junior	Female	50.0	N

不要使用链式赋值

df_chain = pd.DataFrame([[0,0],[1,0],[-1,0]],columns = list('AB'))
df_chain

	A	B
0	0	0
1	1	0
2	-1	0

3.1.4 iloc索引器

iloc 的使用与loc类似，是针对位置进行筛选

df_demo.iloc[1,1]  #索引从0开始 

'Freshman'

df_demo.iloc[[0,1],[0,1]] #01行 01列 前两行 前两列

	School	Grade
Name
Gaopeng Yang	Shanghai Jiao Tong University	Freshman
Changqiang You	Peking University	Freshman

df_demo.iloc[1:4,2:4]  #2-4行 3-4列

	Gender	Weight
Name
Changqiang You	Male	70.0
Mei Sun	Male	89.0
Xiaojuan Sun	Female	41.0

df_demo

	School	Grade	Gender	Weight	Transfer
Name
Gaopeng Yang	Shanghai Jiao Tong University	Freshman	Female	46.0	N
Changqiang You	Peking University	Freshman	Male	70.0	N
Mei Sun	Shanghai Jiao Tong University	Senior	Male	89.0	N
Xiaojuan Sun	Fudan University	Sophomore	Female	41.0	N
Gaojuan You	Fudan University	Sophomore	Male	74.0	N
...	...	...	...	...	...
Xiaojuan Sun	Fudan University	Junior	Female	46.0	N
Li Zhao	Tsinghua University	Senior	Female	50.0	N
Chengqiang Chu	Shanghai Jiao Tong University	Senior	Female	45.0	N
Chengmei Shen	Shanghai Jiao Tong University	Senior	Male	71.0	N
Chunpeng Lv	Tsinghua University	Sophomore	Male	51.0	N

200 rows × 5 columns

df_demo.iloc[lambda x:slice(1,4)] #234行

	School	Grade	Gender	Weight	Transfer
Name
Changqiang You	Peking University	Freshman	Male	70.0	N
Mei Sun	Shanghai Jiao Tong University	Senior	Male	89.0	N
Xiaojuan Sun	Fudan University	Sophomore	Female	41.0	N

#布尔列表
df_demo.iloc[(df_demo.Weight>80).values].head()

	School	Grade	Gender	Weight	Transfer
Name
Mei Sun	Shanghai Jiao Tong University	Senior	Male	89.0	N
Qiang Zheng	Shanghai Jiao Tong University	Senior	Male	87.0	N
Qiang Han	Peking University	Freshman	Male	87.0	N
Chengpeng Zhou	Fudan University	Senior	Male	81.0	N
Feng Han	Shanghai Jiao Tong University	Sophomore	Male	82.0	N

#Series同样也可以通过iloc返回相应位置的值或子序列
df_demo.School.iloc[1]

'Peking University'

df_demo.School.iloc[1:5:2]

Name
Changqiang You    Peking University
Xiaojuan Sun       Fudan University
Name: School, dtype: object

3.1.5 query方法

#简化前面的loc索引器 布尔列表 复合条件
df.query('((School == "Fudan University")&'
         '(Grade == "Senior")&'
         '(Weight > 70))|'
         '((School == "Peking University")&'
         '(Grade != "Senior")&'
         '(Weight > 80))'
)

	School	Grade	Name	Gender	Weight	Transfer
38	Peking University	Freshman	Qiang Han	Male	87.0	N
66	Fudan University	Senior	Chengpeng Zhou	Male	81.0	N
99	Peking University	Freshman	Changpeng Zhao	Male	83.0	N
131	Fudan University	Senior	Chengpeng Qian	Male	73.0	Y

df.query('Weight > Weight.mean()').head()

	School	Grade	Name	Gender	Weight	Transfer
1	Peking University	Freshman	Changqiang You	Male	70.0	N
2	Shanghai Jiao Tong University	Senior	Mei Sun	Male	89.0	N
4	Fudan University	Sophomore	Gaojuan You	Male	74.0	N
10	Shanghai Jiao Tong University	Freshman	Xiaopeng Zhou	Male	74.0	N
14	Tsinghua University	Senior	Xiaomei Zhou	Female	57.0	N

df.query('(Grade not in ["Freshman","Sophomore"]) and ' 
        '(Gender == "Male")').head()

	School	Grade	Name	Gender	Weight	Transfer
2	Shanghai Jiao Tong University	Senior	Mei Sun	Male	89.0	N
16	Tsinghua University	Junior	Xiaoqiang Qin	Male	68.0	N
17	Tsinghua University	Junior	Peng Wang	Male	65.0	N
18	Tsinghua University	Senior	Xiaofeng Sun	Male	71.0	N
21	Shanghai Jiao Tong University	Senior	Xiaopeng Shen	Male	62.0	NaN

df.query('Grade == ["Junior","Senior"]').head()

	School	Grade	Name	Gender	Weight	Transfer
2	Shanghai Jiao Tong University	Senior	Mei Sun	Male	89.0	N
7	Tsinghua University	Junior	Gaoqiang Qian	Female	50.0	N
9	Peking University	Junior	Juan Xu	Female	NaN	N
11	Tsinghua University	Junior	Xiaoquan Lv	Female	43.0	N
12	Shanghai Jiao Tong University	Senior	Peng You	Female	48.0	NaN

#引用外部变量
low,high =70,80
df.query('Weight.between(@low,@high)').head()  #?

---------------------------------------------------------------------------

TypeError                                 Traceback (most recent call last)

<ipython-input-82-f7e7d81043c7> in <module>
      1 #引用外部变量
      2 low,high =70,80
----> 3 df.query('Weight.between(@low,@high)').head()


D:\anaconda\lib\site-packages\pandas\core\frame.py in query(self, expr, inplace, **kwargs)
   3343         kwargs["level"] = kwargs.pop("level", 0) + 1
   3344         kwargs["target"] = None
-> 3345         res = self.eval(expr, **kwargs)
   3346 
   3347         try:


D:\anaconda\lib\site-packages\pandas\core\frame.py in eval(self, expr, inplace, **kwargs)
   3473         kwargs["resolvers"] = kwargs.get("resolvers", ()) + tuple(resolvers)
   3474 
-> 3475         return _eval(expr, inplace=inplace, **kwargs)
   3476 
   3477     def select_dtypes(self, include=None, exclude=None) -> "DataFrame":


D:\anaconda\lib\site-packages\pandas\core\computation\eval.py in eval(expr, parser, engine, truediv, local_dict, global_dict, resolvers, level, target, inplace)
    344         eng = _engines[engine]
    345         eng_inst = eng(parsed_expr)
--> 346         ret = eng_inst.evaluate()
    347 
    348         if parsed_expr.assigner is None:


D:\anaconda\lib\site-packages\pandas\core\computation\engines.py in evaluate(self)
     71 
     72         # make sure no names in resolvers and locals/globals clash
---> 73         res = self._evaluate()
     74         return reconstruct_object(
     75             self.result_type, res, self.aligned_axes, self.expr.terms.return_type


D:\anaconda\lib\site-packages\pandas\core\computation\engines.py in _evaluate(self)
    111         env = self.expr.env
    112         scope = env.full_scope
--> 113         _check_ne_builtin_clash(self.expr)
    114         return ne.evaluate(s, local_dict=scope)
    115 


D:\anaconda\lib\site-packages\pandas\core\computation\engines.py in _check_ne_builtin_clash(expr)
     27         Terms can contain
     28     """
---> 29     names = expr.names
     30     overlap = names & _ne_builtins
     31 


D:\anaconda\lib\site-packages\pandas\core\computation\expr.py in names(self)
    812         """
    813         if is_term(self.terms):
--> 814             return frozenset([self.terms.name])
    815         return frozenset(term.name for term in com.flatten(self.terms))
    816 


D:\anaconda\lib\site-packages\pandas\core\generic.py in __hash__(self)
   1667     def __hash__(self):
   1668         raise TypeError(
-> 1669             f"{repr(type(self).__name__)} objects are mutable, "
   1670             f"thus they cannot be hashed"
   1671         )


TypeError: 'Series' objects are mutable, thus they cannot be hashed

3.1.6 随机抽样

df_sample = pd.DataFrame({'id':list('abcde'),
                          'value':[1,2,3,4,90]
    
})
df_sample

	id	value
0	a	1
1	b	2
2	c	3
3	d	4
4	e	90

df_sample.sample(3,replace = True,weights = df_sample.value)  #以value值的相对大小为抽样概率进行有放回的抽样，比如说e = 90,值很大，被抽到的概率就很高。

	id	value
4	e	90
4	e	90
4	e	90

weights = df_sample.value