Pandas数据分析100例

Posted 2022-02-04 Harris-H

Pandas数据分析100例

1.列表转Series

import pandas as pd

if __name__ == '__main__':
    courses = ['语文', '数学', '英语', '计算机']
    result = pd.Series(courses)
    print(result)
"""
0     语文
1     数学
2     英语
3    计算机
dtype: object
"""

2.Dict转Series

import pandas as pd
grades = '语文': 80, '数学':90, '英语': 100
result = pd.Series(grades)
print(result)
"""
语文     80
数学     90
英语    100
dtype: int64
"""

3.Series转LIst

import pandas as pd
if __name__ == '__main__':
    grades = '语文': 80, '数学': 90, '英语': 100
    result = pd.Series(grades)
    # print(result)
    print(result.tolist())
"""
[80, 90, 100]
"""

4.Series转DataFrame

import pandas as pd

if __name__ == '__main__':
    grades = '语文': 80, '数学': 90, '英语': 100
    tmp = pd.Series(grades)
    result = pd.DataFrame(tmp, columns=['grade'])
    print(result)
"""
    grade
语文     80
数学     90
英语    100
"""

5.Numpy创建Series

import pandas as pd, numpy as np

if __name__ == '__main__':
    s = pd.Series(np.arange(10, 100, 10), index=np.arange(101, 110), dtype='float')
    print(s)

101    10.0
102    20.0
103    30.0
104    40.0
105    50.0
106    60.0
107    70.0
108    80.0
109    90.0
dtype: float64

6.转换Series的数据类型

import pandas as pd

if __name__ == '__main__':
    s = pd.Series(
        data=["001", "002", "003", "004"],
        index=list("abcd")
    )
    print(s)
    print(s.astype(int)) # 类型
    print(s.map(int))   # 函数

a    001
b    002
c    003
d    004
dtype: object
a    1
b    2
c    3
d    4
dtype: int32
a    1
b    2
c    3
d    4
dtype: int64

7.添加新数据

import pandas as pd

if __name__ == '__main__':
    s = pd.Series(
        data='语文': 99, '数学': 100
    )
    s = s.append(pd.Series(
        data='英语': 150
    ))
    print(s)

语文     99
数学    100
英语    150
dtype: int64

8.reset index 转换为df

import pandas as pd

if __name__ == '__main__':
    s = pd.Series(
        data='语文': 99, '数学': 100
    )
    s = s.reset_index()
    s.columns = ['project', 'grade']
    print(s)

  project  grade
0      语文     99
1      数学    100

9.Dict创建df

import pandas as pd

if __name__ == '__main__':
    df = pd.DataFrame(
        data=
            '姓名': ['herio', 'xiaoo', 'gsda'],
            '性别': ['男', '女', '男'],
            '年龄': [18, 20, 19]
        
    )
    print(df)

      姓名 性别  年龄
0  herio  男  18
1  xiaoo  女  20
2   gsda  男  19

10.df设置索引列

import pandas as pd

if __name__ == '__main__':
    df = pd.DataFrame(
        data=
            '姓名': ['herio', 'xiaoo', 'gsda'],
            '性别': ['男', '女', '男'],
            '年龄': [18, 20, 19]
        
    )
    df.set_index('姓名', inplace=True)
    print(df)

      性别  年龄
姓名          
herio  男  18
xiaoo  女  20
gsda   男  19

11.生成日期

import pandas as pd

if __name__ == '__main__':
    res = pd.date_range(start='2022-01-01',end='2022-01-31')
    res_1 = pd.date_range(start='2022-01-01',periods=31)
    print(res,res_1,sep='\\n')

取每年的所有周一(freq)

import pandas as pd

if __name__ == '__main__':
    res = pd.date_range(start='2022-01-01',end='2022-12-31',freq='W-MON')
    print(res)

生成某一天的二十四个小时的日期

import pandas as pd

if __name__ == '__main__':
    res = pd.date_range(start='2022-01-01', periods=24, freq='H')
    res_1 = pd.date_range(start='2022-01-01', end='2022-01-02', closed='left',freq='H')
    print(res)
    print(res_1)

日期生成DataFrame

import pandas as pd

if __name__ == '__main__':
    data = pd.date_range(start='2022-02-01',periods=31)
    res = pd.DataFrame(data=data,columns=['day'])
    res['day_of_year'] = res['day'].dt.day_of_year
    print(res)

          day  day_of_year
0  2022-02-01           32
1  2022-02-02           33
2  2022-02-03           34
.....
29 2022-03-02           61
30 2022-03-03           62

生成随机数据列df

import pandas as pd
import numpy as np
if __name__ == '__main__':
    year = pd.date_range(start='2022-01-01',periods=1000)
    data = 
        'normal': np.random.normal(loc=0,scale=1,size=1000),
        'uniform': np.random.uniform(low=0,high=1,size=1000),
        'binomial': np.random.binomial(n=1,p=0.2)
    
    df = pd.DataFrame(data=data,index=year)
    print(df)

             normal   uniform  binomial
2022-01-01 -1.212357  0.561198         0
2022-01-02  1.455127  0.671026         0
2022-01-03  1.458189  0.922212         0
2022-01-04 -0.164604  0.948922         0
2022-01-05 -0.292973  0.602961         0
...              ...       ...       ...
2024-09-22 -0.350369  0.788879         0
2024-09-23 -0.716147  0.671242         0
2024-09-24 -0.345326  0.282493         0
2024-09-25  0.000214  0.735941         0
2024-09-26  0.072581  0.719543         0

打印前10行和后5行

    print(df.head(10))
    print()
    print(df.tail(5))

描述基本信息

    print(df.info())
    print(df.describe())

DatetimeIndex: 1000 entries, 2022-01-01 to 2024-09-26
Freq: D
Data columns (total 3 columns):
 #   Column    Non-Null Count  Dtype  
---  ------    --------------  -----  
 0   normal    1000 non-null   float64
 1   uniform   1000 non-null   float64
 2   binomial  1000 non-null   int64  
dtypes: float64(2), int64(1)
memory usage: 31.2 KB
None
            normal      uniform  binomial
count  1000.000000  1000.000000    1000.0
mean     -0.038351     0.513840       0.0
std       1.000126     0.289779       0.0
min      -3.250206     0.000009       0.0
25%      -0.732684     0.263531       0.0
50%      -0.091297     0.521737       0.0
75%       0.612340     0.773006       0.0
max       3.682969     0.997907       0.0

统计数据列的值出现的次数

print(df['binomial'].value_counts())

前50行数据存到csv文件中

df.head(50).to_csv("数据前50行.csv")

csv读取为DataFrame

import pandas as pd
import numpy as np
if __name__ == '__main__':
    df = pd.read_csv("数据前50行.csv",index_col=0)
    print(df.info())
    print(df.head(10))