writing idiomatic python 读书笔记(4)

这篇是三个
字典、集合、元组

字典

(1)使用dict代替switch...case

python中没有switch啊。。。用dict好处多多，面向对象嘛，函数也只是变量一样，使用可以一样来用。

def apply_operation(left_operand, right_operand, operator):

if operator == '+':

return left_operand + right_operand

elif operator == '-':

return left_operand - right_operand

elif operator == '*':

return left_operand * right_operand

elif operator == '/':

return left_operand / right_operand

要是写出这样的函数，会被说的，代码冗余度高，性能没有

def apply_operation(left_operand, right_operand, operator):

import operator as op

operator_mapper = {'+': op.add, '-': op.sub,

'*': op.mul, '/': op.truediv}

return operator_mapper[operator](left_operand, right_operand)

函数也只是当做一个value值来用

(2)dict 也是可以用来提供默认参数的。

python中有很多地方可以提供默认参数，dict容易被忘了，使代码清晰可读，必不可少啊

不知道的人：

log_severity = None

if 'severity' in configuration:

log_severity = configuration['severity']

else:

log_severity = 'Info'

习惯了就提高代码质量：

log_severity = configuration.get('severity', 'Info')

(3)字典推导

list推导很多人都使用，字典推导却很少人使用。

理解推导语法后可以用来创建一个字典

user_email = {}

for user in users_list:

if user.email:

user_email[user.name] = user.email

使用字典推导式

user_email = {user.name: user.email

for user in users_list if user.email}

和list的差不多还是很好理解的，多多使用效率提高

sets(集合)

(1)使用集合的数学操作

交并补 脑补高中知识

def get_both_popular_and_active_users():

# Assume the following two functions each return a

# list of user names

most_popular_users = get_list_of_most_popular_users()

most_active_users = get_list_of_most_active_users()

popular_and_active_users = []

for user in most_active_users:

if user in most_popular_users:

popular_and_active_users.append(user)

set() 将list->set

def get_both_popular_and_active_users():

# Assume the following two functions each return a

# list of user names

return(set(

get_list_of_most_active_users()) & set(get_list_of_most_popular_users()))

(2)使用set推导式生成sets

其他语法中没有的推导式经常被忽视。

users_first_names = set()

for user in users:

users_first_names.add(user.first_name)

推导式：

users_first_names = {user.first_name for user in users}

(3)set可以用来去重

unique_surnames = []

for surname in employee_surnames:

if surname not in unique_surnames:

unique_surnames.append(surname)

unique_surnames = set(employee_surnames)

都是一些提高代码效率的小技巧。

元组

(1)使用命名元组namedtuple

# Assume the 'employees' table has the following columns:

# first_name, last_name, department, manager, salary, hire_date

def print_employee_information(db_connection):

db_cursor = db_connection.cursor()

results = db_cursor.execute('select * from employees').fetchall()

for row in results:

# It's basically impossible to follow what's getting printed

print(row[1] + ', ' + row[0] + ' was hired '

'on ' + row[5] + ' (for $' + row[4] + ' per annum)'

' into the ' + row[2] + ' department and reports to ' + row[3])

from collections import namedtuple

EmployeeRow = namedtuple('EmployeeRow', ['first_name',

'last_name', 'department', 'manager', 'salary', 'hire_date'])

EMPLOYEE_INFO_STRING = '{last}, {first} was hired on {date} \

${salary} per annum) into the {department} department and reports to \

ager}'

def print_employee_information(db_connection):

db_cursor = db_connection.cursor()

results = db_cursor.execute('select * from employees').fetchall()

for row in results:

employee = EmployeeRow._make(row)

# It's now almost impossible to print a field in the wrong place

print(EMPLOYEE_INFO_STRING.format(

last=employee.last_name,

first=employee.first_name,

date=employee.hire_date,

salary=employee.salary,

department=employee.department,

manager=employee.manager))

(2)使用_做占位符，里面的数据会被忽视掉

(name, age, temp, temp2) = get_user_info(user)

if age > 21:

output = '{name} can drink!'.format(name=name)

# "Wait, where are temp and temp2 being used?"

_用来代替变量，优化啊

(name, age, _, _) = get_user_info(user)

if age > 21:

output = '{name} can drink!'.format(name=name)

# "Clearly, only name and age are interesting"

(3)使用元组解析数据

list_from_comma_separated_value_file = ['dog', 'Fido', 10]

animal = list_from_comma_separated_value_file[0]

name = list_from_comma_separated_value_file[1]

age = list_from_comma_separated_value_file[2]

output = ('{name} the {animal} is {age} years old'.format(

animal=animal, name=name, age=age))

很常用吧：

list_from_comma_separated_value_file = ['dog', 'Fido', 10]

(animal, name, age) = list_from_comma_separated_value_file

output = ('{name} the {animal} is {age} years old'.format(

animal=animal, name=name, age=age))

(4)使用元组来返回函数的多个值

from collections import Counter

STATS_FORMAT = """Statistics:

Mean: {mean}

Median: {median}

Mode: {mode}"""

def calculate_mean(value_list):

return float(sum(value_list) / len(value_list))

def calculate_median(value_list):

return value_list[int(len(value_list) / 2)]

def calculate_mode(value_list):

return Counter(value_list).most_common(1)[0][0]

values = [10, 20, 20, 30]

mean = calculate_mean(values)

median = calculate_median(values)

mode = calculate_mode(values)

print(STATS_FORMAT.format(mean=mean, median=median,

mode=mode))

这个来优化一些函数挺好用。

from collections import Counter

STATS_FORMAT = """Statistics:

Mean: {mean}

Median: {median}

Mode: {mode}"""

def calculate_staistics(value_list):

mean = float(sum(value_list) / len(value_list))

median = value_list[int(len(value_list) / 2)]

mode = Counter(value_list).most_common(1)[0][0]

return (mean, median, mode)

(mean, median, mode) = calculate_staistics([10, 20, 20, 30])

print(STATS_FORMAT.format(mean=mean, median=median, mode=mode))

同学们应该都能想到这个