Pandas-数据结构-DataFrame（七）：添加元素、修改元素、删除元素

一时失言乱红尘 2023-09-29 10:09 1阅读 0赞

## 一、添加元素 ##

新增列/行并赋值

import numpy as np
    import pandas as pd
    
    df = pd.DataFrame(np.random.rand(16).reshape(4, 4) * 100,
                      columns=['a', 'b', 'c', 'd'])
    print("df = \n", df)
    print("-" * 100)
    
    # 新增列/行并赋值
    df['e'] = 10
    df.loc[4] = 20
    print("df = \n", df)

打印结果：

df = 
                a          b          c          d
    0  39.621173  36.363400  21.042923  36.160210
    1  39.775787  32.010771  86.375488  15.035171
    2  49.328983  58.402799  12.979410  59.408702
    3  21.167906  91.684124  22.953356  98.618665
    ----------------------------------------------------------------------------------------------------
    df = 
                a          b          c          d   e
    0  39.621173  36.363400  21.042923  36.160210  10
    1  39.775787  32.010771  86.375488  15.035171  10
    2  49.328983  58.402799  12.979410  59.408702  10
    3  21.167906  91.684124  22.953356  98.618665  10
    4  20.000000  20.000000  20.000000  20.000000  20

## 二、修改元素 ##

import numpy as np
    import pandas as pd
    
    df = pd.DataFrame(np.random.rand(16).reshape(4, 4) * 100,
                      columns=['a', 'b', 'c', 'd'])
    print("df = \n", df)
    print("-" * 100)
    
    # 索引后直接修改值
    df[['a', 'c']] = 100
    print("df = \n", df)

打印结果：

df = 
                a          b          c          d
    0  39.621173  36.363400  21.042923  36.160210
    1  39.775787  32.010771  86.375488  15.035171
    2  49.328983  58.402799  12.979410  59.408702
    3  21.167906  91.684124  22.953356  98.618665
    ----------------------------------------------------------------------------------------------------
    df = 
          a          b    c          d   e
    0  100  36.363400  100  36.160210  10
    1  100  32.010771  100  15.035171  10
    2  100  58.402799  100  59.408702  10
    3  100  91.684124  100  98.618665  10
    4  100  20.000000  100  20.000000  20

## 三、删除：del / drop() ##

删除：del / drop()

*  del：为原地删除
 *  df.drop(\[1, 2\]：返回新对象，其中的索引为名词索引而非位置下标索引

import numpy as np
    import pandas as pd
    
    # 删除  del / drop()
    
    df = pd.DataFrame(np.random.rand(16).reshape(4, 4) * 100,
                      index=[2, 1, 3, 0],
                      columns=['a', 'b', 'c', 'd'])
    print("df = \n", df)
    print("-" * 50)
    
    # del语句 - 删除列
    del df['a']
    print("删除第a列后：df = \n", df)
    print("-" * 100)
    
    # drop()删除行，inplace=False → 删除后生成新的数据，不改变原数据
    df2 = df.drop(0)
    df3 = df.drop([1, 2])
    print("df = \n", df)
    print("-" * 50)
    print("删除第0行后：df2 = \n", df2)
    print("-" * 50)
    print("删除第1、2行后：df3 = \n", df3)
    print("-" * 100)
    
    # drop()删除列，需要加上axis = 1，inplace=False → 删除后生成新的数据，不改变原数据
    df4 = df.drop(['d'], axis=1)
    print("df = \n", df)
    print("-" * 50)
    print("df4 = \n", df4)

打印结果：

df = 
                a          b          c          d
    2  97.538939  28.115040  25.287657  82.030868
    1  58.227305  40.422558  58.629622  19.732153
    3  39.179936  57.157078  33.694614  68.138918
    0  57.069357  35.340227  91.023129  69.587282
    --------------------------------------------------
    删除第a列后：df = 
                b          c          d
    2  28.115040  25.287657  82.030868
    1  40.422558  58.629622  19.732153
    3  57.157078  33.694614  68.138918
    0  35.340227  91.023129  69.587282
    ----------------------------------------------------------------------------------------------------
    df = 
                b          c          d
    2  28.115040  25.287657  82.030868
    1  40.422558  58.629622  19.732153
    3  57.157078  33.694614  68.138918
    0  35.340227  91.023129  69.587282
    --------------------------------------------------
    删除第0行后：df2 = 
                b          c          d
    2  28.115040  25.287657  82.030868
    1  40.422558  58.629622  19.732153
    3  57.157078  33.694614  68.138918
    --------------------------------------------------
    删除第1、2行后：df3 = 
                b          c          d
    3  57.157078  33.694614  68.138918
    0  35.340227  91.023129  69.587282
    ----------------------------------------------------------------------------------------------------
    df = 
                b          c          d
    2  28.115040  25.287657  82.030868
    1  40.422558  58.629622  19.732153
    3  57.157078  33.694614  68.138918
    0  35.340227  91.023129  69.587282
    --------------------------------------------------
    df4 = 
                b          c
    2  28.115040  25.287657
    1  40.422558  58.629622
    3  57.157078  33.694614
    0  35.340227  91.023129
    
    Process finished with exit code 0