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)
df_loc_slice_demo
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

#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

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
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