python函数总结记录（2022）

1.extend()函数

The extend() method adds all the elements of an iterable (list, tuple, string etc.) to the end of the list.

# create a list
prime_numbers = [2, 3, 5]

# create another list
numbers = [1, 4]
# create another string
name = "zsq"
# create another tuple
age = (22,24)
# add all elements of prime_numbers to numbers
numbers.extend(prime_numbers)

numbers.extend(name)

numbers.extend(age)
print('List after extend():', numbers)

# List after extend(): [1, 4, 2, 3, 5, 'z', 's', 'q', 22, 24]

2.*list

prime_numbers = [2, 3, 5]

print(*prime_numbers)

2 3 5

3.getattr() 函数

作用：返回一个对象属性值。

getattr 语法：

getattr(object, name[, default])

[, default]意思是方框中内容可有可无
如果有name属性，则放回属性值，否则给name属性值赋值defalut。

参数：
object – 对象。
name – 字符串，对象属性。
default – 默认返回值，如果不提供该参数，在没有对应属性时，将触发 AttributeError。

例子：

class Student:
  marks = 88
  name = 'Sheeran'

person = Student()

name = getattr(person, 'name')
print(name)

marks = getattr(person, 'marks', 5)
print(marks)

age = getattr(person, 'age', 15)
print(age)

output:

Sheeran
88
15

4.pandas.DataFrame.agg

import pandas as pd
import numpy as np
df = pd.DataFrame([[1, 2, 3],
                   [4, 5, 6],
                   [7, 8, 9],
                   [np.nan, np.nan, np.nan]],
                  columns=['A', 'B', 'C'])
print(df)
print("**************")

print(df.agg(['sum', 'min']))
print("**************")
print(df.agg({'A' : ['sum', 'min'], 'B' : ['min', 'max']}))
print("**************")

https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.agg.html

5.pandas.DataFrame.merge

# Online Python compiler (interpreter) to run Python online.
# Write Python 3 code in this online editor and run it.
# how代表合并的方式，on代表索引的列，默认为None
import pandas as pd
df1 = pd.DataFrame({'a': ['foo', 'bar'], 'b': [1, 2]})
print(df1)
# print("\n")
print("************")
df2 = pd.DataFrame({'a': ['foo', 'baz'], 'c': [3, 4]})
print(df2)
print("************")
print(df1.merge(df2, how='inner', on='a'))
print("************")
print(df1.merge(df2, how='left', on='a'))
print("************")
print(df1.merge(df2, how='right', on='a'))
print("************")
print(df1.merge(df2, how='left'))
print("************")
print(df1.merge(df2, how='right'))

https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.merge.html

6.pandas.DataFrame.duplicated

判断重复

DataFrame.duplicated(subset=None, keep='first')

import pandas as pd 
df = pd.DataFrame({
    'brand': ['Yum Yum', 'Yum Yum', 'Indomie', 'Indomie', 'Indomie'],
    'style': ['cup', 'cup', 'cup', 'pack', 'pack'],
    'rating': [4, 4, 3.5, 15, 5]
})
print(df.duplicated())
print("**************")
print(df.duplicated(keep='last'))
print("**************")
print(df.duplicated(keep=False))
print("**************")
print(df.duplicated(subset=['brand']))

6.pandas中的dropna函数

import numpy as np
import pandas as pd
dataset = pd.DataFrame(np.arange(12).reshape(4,3),index=[0,1,2,3],columns=['a','b','c'])
dataset.iloc[1,1] = np.nan
dataset.iloc[2,[1,2]] = np.nan
print(dataset)

dataset.dropna()

dataset.dropna(axis=0)

dataset.dropna(axis=1)

dataset.dropna(axis=1,how='all')

dataset.dropna(axis=1,thresh=3)
# 列中非nan的数目大于3则保留

dataset.dropna(subset=['b'])
# 删除b列中有空值的行

dataset

dataset.dropna(subset=['b'],inplace=True)
dataset

统计哪些列有缺失值

cols_with_missing = [col for col in X_train.columns
                     if X_train[col].isnull().any()]

# df.isnull().any()则会判断哪些”列”存在缺失值