pandas dataframe统计填充空值方式

目录

• 1.判断dataframe是否有空值
• 2.统计空值个数
• 3.按列填充空值
• 4.按分组平均值填充
• 总结

def t2():
    df = pd.DataFrame({
        'name': ['lili', 'lucy','pegga','alin',np.nan],
        'age': [18, 16, np.nan, 23, np.nan],
        'salary': [np.nan, 300, np.nan, 1000, 800]
    })
    df_contains_nan = df.isnull()
    print(df_contains_nan)

    df_contains_nan_2 = df.isna()
    print(df_contains_nan_2)

def t3():
    df = pd.DataFrame({
        'name': ['lili', 'lucy','pegga','alin',np.nan],
        'age': [18, 16, np.nan, 23, np.nan],
        'salary': [np.nan, 300, np.nan, 1000, 800]
    })
    contains_nan = df.isnull().values.any()
    print(contains_nan)

    def any(self, axis=None, out=None, keepdims=False): # real signature unknown; restored from __doc__
        """
        a.any(axis=None, out=None, keepdims=False)
        
            Returns True if any of the elements of `a` evaluate to True.
        
            Refer to `numpy.any` for full documentation.
        
            See Also
            --------
            numpy.any : equivalent function
        """
        pass

def t4():
    df = pd.DataFrame({
        'name': ['lili', 'lucy','pegga','alin',np.nan],
        'age': [18, 16, np.nan, 23, np.nan],
        'salary': [np.nan, 300, np.nan, 1000, 800]
    })

    # 每一列有多少个nan
    nan_column = df.isnull().values.astype(int).sum(axis=0)
    # 各列的nan个数
    nan_column_name = df.isnull().sum()
    print(nan_column)
    print('*'*10)
    print(nan_column_name)
    print('*'*10)
    # nan的总个数
    nan_all = df.isnull().sum().sum()
    print(nan_all)

def t5():
    df = pd.DataFrame({
        'name': ['lili', 'lucy','pegga','alin',np.nan],
        'age': [18, 16, np.nan, 23, np.nan],
        'salary': [np.nan, 300, np.nan, 1000, 800]
    })
    print(df)

    df.name = df.name.fillna('unknown')
    df.age = df.age.fillna(df.age.mean())
    df.salary = df.salary.fillna(df.salary.max())

    print(df)

def t52():
    df = pd.DataFrame({
        'name': ['lili', 'lucy','pegga','alin',np.nan],
        'age': [18, 16, np.nan, 23, np.nan],
        'salary': [np.nan, 300, np.nan, 1000, 800]
    })
    print(df)

    df.name.fillna('unknown', inplace=True)
    df.age.fillna(df.age.mean(), inplace=True)
    df.salary.fillna(df.salary.max(), inplace=True)
    print(df)

def t6():
    df = pd.DataFrame({
        'level': ['A','A','A','A','B','B','B','B','C','C','C'],
        'score': [2,1,3,np.nan,4,6,5,np.nan,7,9,np.nan],
    })

    fun = lambda x: x.fillna(df.groupby('level').score.mean()[x.level])
    df = df.apply(lambda x: fun(x), axis=1)
    # 以下一行代码也可以实现相同功能
    #df = df.apply(lambda x: x.fillna(df.groupby('level').score.mean()[x.level]), axis=1)
    print(df)