python数据清洗

数据清洗 过滤 筛选 删除 某行

#方法 str
df = pd.DataFrame([  
            ['green', 'M', 10.1, 'label1'],   
            ['red', 'L', 13.5, 'label2'],   
            ['蓝色', 'XL', 15.3, 'label2']])
df.columns=['color','size','length', 'label']
#删除含有特定字符的行
df1=df[~ df['color'].str.contains('蓝色|red')]
print(df1)
#保留含有特定字符的行
df2=df[df['color'].str.contains('蓝色|red')]
print(df2)

#isin
#isin([278,382]
df3=df[df['color'].isin(['red','蓝色'])]
print(df3)

df4=df[~df['color'].isin(['red','蓝色'])]
#print(df4)
print('-----')
df5=df[(df['color'].str.contains('蓝色|red')) & (df['length']>14)]
#or:df5=df[(df['color'].str.contains('蓝色|red')) & (df.length>14)]
print(df5)

#删除重复的行
df = pd.DataFrame([  
            ['M', 10.1],   
            ['L', 13.5],   
            ['XL', 15.3],
            ['XL', 15.3]])
df.columns=['size','length']
a=df.duplicated()
print(a)
df1=df.drop_duplicates()
print(df1)

FastStoneEditor1 - Copy.jpg