Python常用小技巧总结

import pandas as pd

d = {"sex": ["male", "female", "male", "female"],
     "color": ["red", "green", "blue", "yellow"],
     "age": [12, 56, 21, 31]}
df = pd.DataFrame(d)
df

pd.DataFrame() # 自己创建数据框，用于练习

pd.read_csv(filename) # 从CSV⽂件导⼊数据

pd.read_table(filename) # 从限定分隔符的⽂本⽂件导⼊数据

pd.read_excel(filename) # 从Excel⽂件导⼊数据

pd.read_sql(query,connection_object) # 从SQL表/库导⼊数据

pd.read_json(json_string) # 从JSON格式的字符串导⼊数据

pd.read_html(url) # 解析URL、字符串或者HTML⽂件，抽取其中的tables表格

df.to_csv(filename) #导出数据到CSV⽂件

df.to_excel(filename) #导出数据到Excel⽂件

df.to_sql(table_name,connection_object) #导出数据到SQL表

df.to_json(filename) #以Json格式导出数据到⽂本⽂件

writer=pd.ExcelWriter('test.xlsx',index=False) 
df1.to_excel(writer,sheet_name='单位')和writer.save()，将多个数据帧写⼊同⼀个⼯作簿的多个sheet(⼯作表)

df.head(n) # 查看DataFrame对象的前n⾏

df.tail(n) # 查看DataFrame对象的最后n⾏

df.shape() # 查看⾏数和列数

df.info() # 查看索引、数据类型和内存信息

df.columns() # 查看字段（⾸⾏）名称

df.describe() # 查看数值型列的汇总统计

s.value_counts(dropna=False) # 查看Series对象的唯⼀值和计数

df.apply(pd.Series.value_counts) # 查看DataFrame对象中每⼀列的唯⼀值和计数

df.isnull().any() # 查看是否有缺失值

df[df[column_name].duplicated()] # 查看column_name字段数据重复的数据信息

df[df[column_name].duplicated()].count() # 查看column_name字段数据重复的个数

df[col] # 根据列名，并以Series的形式返回列

df[[col1,col2]] # 以DataFrame形式返回多列

s.iloc[0] # 按位置选取数据

s.loc['index_one'] # 按索引选取数据

df.iloc[0,:] # 返回第⼀⾏

df.iloc[0,0] # 返回第⼀列的第⼀个元素

df.loc[0,:] # 返回第⼀⾏（索引为默认的数字时，⽤法同df.iloc），但需要注意的是loc是按索引,iloc参数只接受数字参数

df.ix[[:5],["col1","col2"]] # 返回字段为col1和col2的前5条数据，可以理解为loc和
iloc的结合体。

df.at[5,"col1"] # 选择索引名称为5，字段名称为col1的数据

df.iat[5,0] # 选择索引排序为5，字段排序为0的数据

df.columns= ['a','b','c'] # 重命名列名（需要将所有列名列出，否则会报错）

pd.isnull() # 检查DataFrame对象中的空值，并返回⼀个Boolean数组

pd.notnull() # 检查DataFrame对象中的⾮空值，并返回⼀个Boolean数组

df.dropna() # 删除所有包含空值的⾏

df.dropna(axis=1) # 删除所有包含空值的列

df.dropna(axis=1,thresh=n) # 删除所有⼩于n个⾮空值的⾏

df.fillna(value=x) # ⽤x替换DataFrame对象中所有的空值，⽀持

df[column_name].fillna(x)

s.astype(float) # 将Series中的数据类型更改为float类型

s.replace(1,'one') # ⽤‘one’代替所有等于1的值

s.replace([1,3],['one','three']) # ⽤'one'代替1，⽤'three'代替3

df.rename(columns=lambdax:x+1) # 批量更改列名

df.rename(columns={'old_name':'new_ name'}) # 选择性更改列名

df.set_index('column_one') # 将某个字段设为索引，可接受列表参数，即设置多个索引

df.reset_index("col1") # 将索引设置为col1字段，并将索引新设置为0,1,2...

df.rename(index=lambdax:x+1) # 批量重命名索引

df.sort_index().loc[:5] # 对前5条数据进⾏索引排序

df.sort_values(col1) # 按照列col1排序数据，默认升序排列

df.sort_values(col2,ascending=False) # 按照列col1降序排列数据

df.sort_values([col1,col2],ascending=[True,False]) # 先按列col1升序排列，后按col2降序排列数据

df.groupby(col) # 返回⼀个按列col进⾏分组的Groupby对象

df.groupby([col1,col2]) # 返回⼀个按多列进⾏分组的Groupby对象

df.groupby(col1)[col2].agg(mean) # 返回按列col1进⾏分组后，列col2的均值,agg可以接受列表参数，agg([len,np.mean])

df.pivot_table(index=col1,values=[col2,col3],aggfunc={col2:max,col3:[ma,min]}) # 创建⼀个按列col1进⾏分组，计算col2的最⼤值和col3的最⼤值、最⼩值的数据透视表

df.groupby(col1).agg(np.mean) # 返回按列col1分组的所有列的均值,⽀持

df.groupby(col1).col2.agg(['min','max'])

data.apply(np.mean) # 对DataFrame中的每⼀列应⽤函数np.mean

data.apply(np.max,axis=1) # 对DataFrame中的每⼀⾏应⽤函数np.max

df.groupby(col1).col2.transform("sum") # 通常与groupby连⽤，避免索引更改

df1.append(df2) # 将df2中的⾏添加到df1的尾部

df.concat([df1,df2],axis=1,join='inner') # 将df2中的列添加到df1的尾部,值为空的对应⾏与对应列都不要

df1.join(df2.set_index(col1),on=col1,how='inner') # 对df1的列和df2的列执⾏SQL形式的join，默认按照索引来进⾏合并，如果df1和df2有共同字段时，会报错，可通过设置lsuffix,rsuffix来进⾏解决，如果需要按照共同列进⾏合并，就要⽤到set_index(col1)

pd.merge(df1,df2,on='col1',how='outer') # 对df1和df2合并，按照col1，⽅式为outer

pd.merge(df1,df2,left_index=True,right_index=True,how='outer') #与 df1.join(df2, how='outer')效果相同

d = {"male": 1, "female": 0}
df["gender"] = df["sex"].map(d)
df

d = {"customer": ["A", "B", "C", "D"],
     "sales": [1000, "950.5RMB", "$400", "$1250.75"]}
df = pd.DataFrame(d)
df

df["sales"] = df["sales"].replace("[$,RMB]", "", regex=True).astype("float")

df

df["sales"].apply(type)

0    <class 'float'>
1    <class 'float'>
2    <class 'float'>
3    <class 'float'>
Name: sales, dtype: object

d = {"district_code": [12345, 56789, 101112, 131415],
     "apple": [5.2, 2.4, 4.2, 3.6],
     "banana": [3.5, 1.9, 4.0, 2.3],
     "orange": [8.0, 7.5, 6.4, 3.9]
     }
df = pd.DataFrame(d)
df

df = df.melt(id_vars="district_code",
             var_name="fruit_name",
             value_name="price")
df

d = {"name": ['Jone', 'Alica', 'Emily', 'Robert', 'Tomas',
              'Zhang', 'Liu', 'Wang', 'Jack', 'Wsx', 'Guo'],
     "categories": ["A", "C", "A", "D", "A",
                    "B", "B", "C", "A", "E", "F"]}
df = pd.DataFrame(d)
df

frequencies = df["categories"].value_counts(normalize=True)
frequencies

A    0.363636
B    0.181818
C    0.181818
E    0.090909
D    0.090909
F    0.090909
Name: categories, dtype: float64

threshold = 0.1
small_categories = frequencies[frequencies < threshold].index
small_categories

Index(['E', 'D', 'F'], dtype='object')

df["categories"] = df["categories"].replace(small_categories, "Others")

df

# -*- coding:utf-8 -*-
# @Address:https://beishan.blog.csdn.net/
# @Author:北山啦
import pandas as pd
import os
os.chdir(r"E:\北山啦\五省PM2.5")
path = "./archive/"
dfs,index = [],0
for i in os.listdir(path):
    dfs.append(pd.read_csv(os.path.join(path,i)))
    print(f"正在合并{index+1}工作表")
    index += 1
df = pd.concat(dfs)
df.to_csv("./archive/数据汇总.csv",index=False)

s = pd.Series([1,2,3])

s

0    1
1    2
2    3
dtype: int64

s = s.to_frame(name="列名")

s

s.squeeze()

0    1
1    2
2    3
Name: 列名, dtype: int64

from collections import Counter
trd = dict(Counter(train_label_names))
tsd = dict(Counter(test_label_names))
(pd.DataFrame([[key, trd[key], tsd[key]] for key in trd], 
             columns=['Target Label', 'Train Count', 'Test Count'])
.sort_values(by=['Train Count', 'Test Count'],
             ascending=False))

squares = []
for x in range(10):
    squares.append(x**2)
squares

[0, 1, 4, 9, 16, 25, 36, 49, 64, 81]

squares = list(map(lambda x: x**2, range(10)))
squares

[0, 1, 4, 9, 16, 25, 36, 49, 64, 81]

squares = [x**2 for x in range(10)]
squares

[0, 1, 4, 9, 16, 25, 36, 49, 64, 81]

[(x, y) for x in [1,2,3] for y in [3,1,4] if x != y]

[(1, 3), (1, 4), (2, 3), (2, 1), (2, 4), (3, 1), (3, 4)]

from math import pi
[str(round(pi, i)) for i in range(1, 6)]

['3.1', '3.14', '3.142', '3.1416', '3.14159']

matrix = [
    [1, 2, 3, 4],
    [5, 6, 7, 8],
    [9, 10, 11, 12],
]

[[row[i] for row in matrix] for i in range(4)]

[[1, 5, 9], [2, 6, 10], [3, 7, 11], [4, 8, 12]]

a = 1
b = 2
a, b = b, a
print("a = ",a)
print("b = ",b)

a =  2
b =  1

import sys
mylist = range(1,10000)
print(sys.getsizeof(mylist))

48

d1 ={"a":1,"b":2}
d2 = {"b":2,"c":4}
m = {**d1,**d2}
print(m)

{'a': 1, 'b': 2, 'c': 4}

string = "the author is beishanla"
s = string.split(" ")
s

['the', 'author', 'is', 'beishanla']

l = ["the","author","is","beishanla"]
l = " ".join(l)
l

'the author is beishanla'

pip install Pillow

from PIL import Image
im = Image.open("E:/Python/00网络爬虫/Project/词云图跳舞视频/aip-python-sdk-4.15.1/pictures/img_88.jpg")
im.show()

print(im.format,im.size,im.mode)

JPEG (1920, 1080) RGB

import itertools
list1 = [1,3,4,5]
list2 = []
for i in range(1,len(list1)+1):
    iter1 = itertools.combinations(list1,i)
    list2.append(list(iter1))
print(list2)

[[(1,), (3,), (4,), (5,)], [(1, 3), (1, 4), (1, 5), (3, 4), (3, 5), (4, 5)], [(1, 3, 4), (1, 3, 5), (1, 4, 5), (3, 4, 5)], [(1, 3, 4, 5)]]

import itertools
list1 = [1,2,3,4]
list2 = list(itertools.combinations(list1,2))
list2

[(1, 2), (1, 3), (1, 4), (2, 3), (2, 4), (3, 4)]

from functools import reduce

def add(x, y) :            # 两数相加
    return x + y
sum1 = reduce(add, [1,2,3,4,5])   # 计算列表和：1+2+3+4+5
sum2 = reduce(lambda x, y: x+y, [1,2,3,4,5])  # 使用 lambda 匿名函数
print(sum1)
print(sum2)

15
15

D = {"姓名":"北山啦",
    "博客地址":"https://beishan.blog.csdn.net/"}
print(D.get("姓名"))
print(D.get("Sex","NA"))

北山啦
NA

import zipfile
import os

src_path=r"D:\浏览器\chrome\chromedriver_win32.zip"
target_path="D:\浏览器\chrome\数据"
if(not os.path.isdir(target_path)):
    z = zipfile.ZipFile(src_path, 'r')
    z.extractall(path=target_path)
    z.close()

from itertools import combinations
from functools import reduce
import openpyxl
from openpyxl import Workbook

def getActors(filename):
    actors = dict()
    # 打开xlsx文件，并获取第一个worksheet
    wb = openpyxl.load_workbook(filename)
    ws = wb.worksheets[0]
    # 遍历Excel文件中的所有行
    for index, row in enumerate(ws.rows):
        # 绕过第一行的表头
        if index == 0:
            continue
        # 获取电影名称和演员列表
        filmName, actor = row[0].value, row[2].value.split('，')
        # 遍历该电影的所有演员，统计参演电影
        for a in actor:
            actors[a] = actors.get(a, set())
            actors[a].add(filmName)
    print(actors)
    return actors

data = getActors('电影导演演员.xlsx')

def relations(num):
    # 参数num表示要查找关系最好的num个人    
    # 包含全部电影名称的集合
    allFilms = reduce(lambda x,y: x|y, data.values(), set())
    # 关系最好的num个演员及其参演电影名称
    combiData = combinations(data.items(), num)
    trueLove = max(combiData,
                   key=lambda item: len(reduce(lambda x,y:x&y,
                                           [i[1] for i in item],
                                           allFilms)))
    return ('关系最好的{0}个演员是{1}，'
            'Ta们共同主演的电影数量是{2}'.format(num,
                              tuple((item[0] for item in trueLove)),
                              len(reduce(lambda x,y:x&y,
                                     [item[1] for item in trueLove],
                                     allFilms))))

print(relations(2))
print(relations(3))
print(relations(4))