Pandas-数据结构-DataFrame（九）：排序【按值排序：sort_values】【按索引排序：sort_index】

Myth丶恋晨 2023-09-29 09:27 18阅读 0赞

## 五、排序 ##

### 1、按值排序 ###

import numpy as np
    import pandas as pd
    
    # 排序1 - 按值排序 .sort_values
    # 同样适用于Series
    
    df1 = pd.DataFrame(np.random.rand(16).reshape(4, 4) * 100,
                       columns=['a', 'b', 'c', 'd'])
    
    print("df1 = \n", df1)
    print("-" * 100)
    # 单列排序【ascending参数：设置升序降序，默认升序】
    
    # 升序
    df3 = df1.sort_values(['a'], ascending=True)
    print("df1升序后返回新对象：df3 = df1.sort_values(['a'], ascending=True) = \n", df3)
    print('-' * 50)
    # 降序
    df4 = df1.sort_values(['a'], ascending=False)
    print("df1降序后返回新对象：df4 = df1.sort_values(['a'], ascending=False) = \n", df4)
    print('-' * 100)
    
    # 多列排序，按列顺序排序
    df2 = pd.DataFrame({
        'a': [1, 1, 1, 1, 2, 2, 2, 2],
                        'b': list(range(8)),
                        'c': list(range(8, 0, -1))})
    print("df2 = \n", df2)
    print('-' * 50)
    df5 = df2.sort_values(['a', 'c'])
    print("df2按照第a、c列升序后返回新对象：df5 = df2.sort_values(['a', 'c']) = \n", df5)

打印结果：

df1 = 
                a          b          c          d
    0  96.648434  36.714275  63.817178  28.597929
    1  68.880331  49.645003  75.562495  68.234420
    2  50.189398  81.142625  66.546337  34.114630
    3   6.967286  13.062011  33.094863  50.918002
    ----------------------------------------------------------------------------------------------------
    df1升序后返回新对象：df3 = df1.sort_values(['a'], ascending=True) = 
                a          b          c          d
    3   6.967286  13.062011  33.094863  50.918002
    2  50.189398  81.142625  66.546337  34.114630
    1  68.880331  49.645003  75.562495  68.234420
    0  96.648434  36.714275  63.817178  28.597929
    --------------------------------------------------
    df1降序后返回新对象：df4 = df1.sort_values(['a'], ascending=False) = 
                a          b          c          d
    0  96.648434  36.714275  63.817178  28.597929
    1  68.880331  49.645003  75.562495  68.234420
    2  50.189398  81.142625  66.546337  34.114630
    3   6.967286  13.062011  33.094863  50.918002
    ----------------------------------------------------------------------------------------------------
    df2 = 
        a  b  c
    0  1  0  8
    1  1  1  7
    2  1  2  6
    3  1  3  5
    4  2  4  4
    5  2  5  3
    6  2  6  2
    7  2  7  1
    --------------------------------------------------
    df2按照第a、c列升序后返回新对象：df5 = df2.sort_values(['a', 'c']) = 
        a  b  c
    3  1  3  5
    2  1  2  6
    1  1  1  7
    0  1  0  8
    7  2  7  1
    6  2  6  2
    5  2  5  3
    4  2  4  4
    
    Process finished with exit code 0

### 2、按索引排序 ###

import numpy as np
    import pandas as pd
    
    # 排序2 - 索引排序 .sort_index
    
    df1 = pd.DataFrame(np.random.rand(16).reshape(4, 4) * 100,
                       index=[5, 4, 3, 2],
                       columns=['a', 'b', 'c', 'd'])
    df2 = pd.DataFrame(np.random.rand(16).reshape(4, 4) * 100,
                       index=['h', 's', 'x', 'g'],
                       columns=['a', 'b', 'c', 'd'])
    
    # 按照index排序
    # 默认 ascending=True, inplace=False
    print("df1 = \n", df1)
    print('-' * 50)
    df3 = df1.sort_index()
    print("df1按索引排序后返回新对象：df3 = df1.sort_index() = \n", df3)
    
    print('-' * 100)
    
    print("df2 = \n", df2)
    print('-' * 50)
    df4 = df2.sort_index()
    print("df2按索引排序后返回新对象：df4 = df2.sort_index() = \n", df4)

打印结果：

df1 = 
                a          b          c          d
    5  20.335837  69.538529  48.694662  59.057213
    4  48.784583  67.559001  52.914242   5.298351
    3  99.725511  73.362798  51.517547  64.382411
    2  95.567502  41.242870  81.558410  36.106115
    --------------------------------------------------
    df1按索引排序后返回新对象：df3 = df1.sort_index() = 
                a          b          c          d
    2  95.567502  41.242870  81.558410  36.106115
    3  99.725511  73.362798  51.517547  64.382411
    4  48.784583  67.559001  52.914242   5.298351
    5  20.335837  69.538529  48.694662  59.057213
    ----------------------------------------------------------------------------------------------------
    df2 = 
                a          b          c          d
    h  63.789178  29.338815   2.731508  48.179283
    s  88.688644  22.287952  15.571920  48.406608
    x  22.671023  29.225815  29.029033  14.588667
    g  60.886301  96.096387  64.636511  37.613622
    --------------------------------------------------
    df2按索引排序后返回新对象：df4 = df2.sort_index() = 
                a          b          c          d
    g  60.886301  96.096387  64.636511  37.613622
    h  63.789178  29.338815   2.731508  48.179283
    s  88.688644  22.287952  15.571920  48.406608
    x  22.671023  29.225815  29.029033  14.588667
    
    Process finished with exit code 0