【Python】数据分析之Pandas数据选取

import pandas as pd

1. 直接索引

df = pd.DataFrame({
   'AdmissionDate': ['2021-01-25','2021-01-22','2021-01-20',

                        '2021-01-18','2021-01-17','2021-01-17','2021-01-21'],

                     'StudentID': [7,1,3,2,6,3,4],

                     'Name': ['Jack','Shyam','Mohan','Janne','Lucky','Abhinav','Danny'],

                     'Stream':['CSE','ECE','Civil','Mechanical','CSE','IT','EEE']

                   })
df.set_index("Name",inplace=True)

# 选取某一列或者某几列
print(df["AdmissionDate"])
print(df[["AdmissionDate","StudentID"]])  # 选取多列时，多个列要放到一个list中

Name
Jack       2021-01-25
Shyam      2021-01-22
Mohan      2021-01-20
Janne      2021-01-18
Lucky      2021-01-17
Abhinav    2021-01-17
Danny      2021-01-21
Name: AdmissionDate, dtype: object
        AdmissionDate  StudentID
Name                            
Jack       2021-01-25          7
Shyam      2021-01-22          1
Mohan      2021-01-20          3
Janne      2021-01-18          2
Lucky      2021-01-17          6
Abhinav    2021-01-17          3
Danny      2021-01-21          4

# 按行编号选取连续的行
df[1:3]  # df[start:end], [start,end)闭开区间

	AdmissionDate	StudentID	Stream
Name
Shyam	2021-01-22	1	ECE
Mohan	2021-01-20	3	Civil

# 按行时间索引选取连续的行
df["AdmissionDate"] = pd.to_datetime(df["AdmissionDate"])
df.set_index("AdmissionDate",inplace=True)

# df["2021-01-01":"2021-01-20"]  # 将被弃用
df.sort_index().loc["2021-01-01":"2021-01-20",:]  # 推荐写法

	StudentID	Stream
AdmissionDate
2021-01-17	6	CSE
2021-01-17	3	IT
2021-01-18	2	Mechanical
2021-01-20	3	Civil

2. 布尔索引

df = pd.DataFrame({
   'AdmissionDate': ['2021-01-25','2021-01-22','2021-01-20',

                        '2021-01-18','2021-01-17','2021-01-17','2021-01-21'],

                     'StudentID': [7,1,3,2,6,3,4],

                     'Name': ['Jack','Shyam','Mohan','Janne','Lucky','Abhinav','Danny'],

                     'Stream':['CSE'<