1
import pandas as pd
2
import numpy as np
3

4
df = pd.DataFrame(
5
    {
6
        'name': ['tom', 'tom', 'jack', 'alice', 'bob', 'allen'],
7
        'score': [60.5, 60.5, 80, 30.6, 70, 83.5],
8
        'age': [15, 15, 15, 20, 26, 30]
9
    },
10
    index=[1, 2, 3, 4, 5, 6]
11
)

1
print(df.loc[4])    # 按标签取第4行
2
print(df.iloc[3])   # 按位置取第4行（索引从0开始）

1
name     alice
2
score     30.6
3
age         20
4
Name: 4, dtype: object
5
name     alice
6
score     30.6
7
age         20
8
Name: 4, dtype: object

1
print(df.loc[:, 'name'])   # 所有行的 name 列
2
print(df.iloc[:, 0])        # 所有行的第1列

1
1      tom
2
2      tom
3
3     jack
4
4    alice
5
5      bob
6
6    allen
7
Name: name, dtype: object
8
1      tom
9
2      tom
10
3     jack
11
4    alice
12
5      bob
13
6    allen
14
Name: name, dtype: object

1
print(df.at[3, 'score'])    # 标签访问
2
print(df.iat[2, 1])          # 位置访问（第3行第2列）
3
print(df.loc[3, 'score'])    # loc 同样可访问单个元素
4
print(df.iloc[2, 1])         # iloc 同样可访问单个元素

1
80.0
2
80.0
3
80.0
4
80.0

1
print(df['name'])
2
print(type(df['name']))   # <class 'pandas.core.series.Series'>
3
print(df.name)            # 也可通过属性方式访问

1
1      tom
2
2      tom
3
3     jack
4
4    alice
5
5      bob
6
6    allen
7
Name: name, dtype: object
8
<class 'pandas.core.series.Series'>
9
1      tom
10
2      tom
11
3     jack
12
4    alice
13
5      bob
14
6    allen
15
Name: name, dtype: object

1
print(df[['name', 'score']])
2
print(type(df[['name', 'score']]))  # <class 'pandas.core.frame.DataFrame'>

1
    name  score
2
1    tom   60.5
3
2    tom   60.5
4
3   jack   80.0
5
4  alice   30.6
6
5    bob   70.0
7
6  allen   83.5
8
<class 'pandas.core.frame.DataFrame'>

1
print(df.head(2))   # 前2行
2
print(df.tail(3))   # 后3行

1
  name  score  age
2
1  tom   60.5   15
3
2  tom   60.5   15
4
    name  score  age
5
4  alice   30.6   20
6
5    bob   70.0   26
7
6  allen   83.5   30

1
print(df[df.score > 70])                        # 单条件
2
print(df[(df.score > 70) & (df.age < 20)])       # 多条件（与）

1
    name  score  age
2
3   jack   80.0   15
3
6  allen   83.5   30
4
   name  score  age
5
3  jack   80.0   15

1
print(df.sample(3))  # 随机抽取3行

1
    name  score  age
2
6  allen   83.5   30
3
1    tom   60.5   15
4
4  alice   30.6   20