A Minimal Example of Machine Learning (with scikit-learn)

Минимальный пример кода машинного обучения (с помощью scikit-learn)

import numpy as np
import pandas as pd
from sklearn.ensemble import RandomForestClassifier

data = [{'humidity': 80, 'wind': 20, 'temp': 15, 'clouds': 90, 'raining?': 'yes'},
{'humidity': 40, 'wind': 5, 'temp': 25, 'clouds': 15, 'raining?': 'no'},
{'humidity': 20, 'wind': 30, 'temp': 35, 'clouds': 50, 'raining?': 'no'},
{'humidity': 90, 'wind': 3, 'temp': 18, 'clouds': 100, 'raining?': 'yes'},
{'humidity': 70, 'wind': 13, 'temp': 22, 'clouds': 75, 'raining?': 'no'},
{'humidity': 85, 'wind': 10, 'temp': 17, 'clouds': 90, 'raining?': 'yes'},
{'humidity': 90, 'wind': 20, 'temp': 20, 'clouds': 80, 'raining?': 'yes'},
{'humidity': 60, 'wind': 5, 'temp': 23, 'clouds': 30, 'raining?': 'no'},
{'humidity': 95, 'wind': 25, 'temp': 13, 'clouds': 100, 'raining?': 'yes'},
{'humidity': 70, 'wind': 2, 'temp': 30, 'clouds': 100, 'raining?': 'no'},
]

df = pd.DataFrame(data, columns=['humidity', 'wind', 'temp', 'clouds', 'raining?'])
print(df)

X, y = df.to_numpy()[:8, :4], df.to_numpy()[:8, 4]

model = RandomForestClassifier()
model.fit(X, y)

model.predict([[95, 25, 13, 100],[70, 2, 30, 100]]).reshape(1, -1)

@pythonl

📶 Extract Saved WiFi Passwords in Python

Извлечение сохраненных паролей WiFi в Python (Linux OS)

import subprocess
import os
import re
from collections import namedtuple
import configparser

def get_linux_saved_wifi_passwords(verbose=1):


network_connections_path = "/etc/NetworkManager/system-connections/"
fields = ["ssid", "auth-alg", "key-mgmt", "psk"]
Profile = namedtuple("Profile", [f.replace("-", "_") for f in fields])
profiles = []
for file in os.listdir(network_connections_path):
data = { k.replace("-", "_"): None for k in fields }
config = configparser.ConfigParser()
config.read(os.path.join(network_connections_path, file))
for _, section in config.items():
for k, v in section.items():
if k in fields:
data[k.replace("-", "_")] = v
profile = Profile(**data)
if verbose >= 1:
print_linux_profile(profile)
profiles.append(profile)
return profiles


def print_linux_profiles(verbose):
"""Prints all extracted SSIDs along with Key (PSK) on Linux"""
print("SSID AUTH KEY-MGMT PSK")
print("-"*50)
get_linux_saved_wifi_passwords(verbose)

@pythonl

🔥 10 Tips And Tricks To Write Better Python Code

10 советов и приемов для написания лучшего кода на Python

1) Iterate c enumerate() вместо range(len())

data = [1, 2, -3, -4]
# плохо:
for i in range(len(data)):
if data[i] < 0:
data[i] = 0

# хорошо:
data = [1, 2, -3, -4]
for idx, num in enumerate(data):
if num < 0:
data[idx] = 0


2) list comprehension вместо for-loops

#плохо:

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

# хорошо:

squares = [i*i for i in range(10)]

3) sorted() method

data = (3, 5, 1, 10, 9)
sorted_data = sorted(data, reverse=True) # [10, 9, 5, 3, 1]

data = [{"name": "Max", "age": 6},
{"name": "Lisa", "age": 20},
{"name": "Ben", "age": 9}
]
sorted_data = sorted(data, key=lambda x: x["age"])

4) Хранение данных в Sets

my_list = [1,2,3,4,5,6,7,7,7]
my_set = set(my_list) # removes duplicates

primes = {2,3,5,7,11,13,17,19}

5) Экономьте память с помощью генераторов

# list comprehension
my_list = [i for i in range(10000)]
print(sum(my_list)) # 49995000

# generator comprehension
my_gen = (i for i in range(10000))
print(sum(my_gen)) # 49995000

import sys

my_list = [i for i in range(10000)]
print(sys.getsizeof(my_list), 'bytes') # 87616 bytes

my_gen = (i for i in range(10000))
print(sys.getsizeof(my_gen), 'bytes') # 128 bytes

6) Определение значений по умолчанию в словарях с помощью .get() и .setdefault()

my_dict = {'item': 'football', 'price': 10.00}
count = my_dict['count'] # KeyError!

# лучше:
count = my_dict.get('count', 0) # optional default value

count = my_dict.setdefault('count', 0)
print(count) # 0
print(my_dict) # {'item': 'football', 'price': 10.00, 'count': 0}

7) Подсчет хэшируемых объектов с помощью collections.Counter

from collections import Counter

my_list = [10, 10, 10, 5, 5, 2, 9, 9, 9, 9, 9, 9]
counter = Counter(my_list)

print(counter) # Counter({9: 6, 10: 3, 5: 2, 2: 1})
print(counter[10]) # 3

from collections import Counter

my_list = [10, 10, 10, 5, 5, 2, 9, 9, 9, 9, 9, 9]
counter = Counter(my_list)

most_common = counter.most_common(2)
print(most_common) # [(9, 6), (10, 3)]
print(most_common[0]) # (9, 6)
print(most_common[0][0]) # 9

8 ) Форматирование строк с помощью f-Strings

name = "Alex"
my_string = f"Hello {name}"
print(my_string) # Hello Alex

i = 10
print(f"{i} squared is {i*i}") # 10 squared is 100

9) Конкатенация строк с помощью .join()

list_of_strings = ["Hello", "my", "friend"]

#плохо:
my_string = ""
for i in list_of_strings:
my_string += i + " "

#хорошо
list_of_strings = ["Hello", "my", "friend"]
my_string = " ".join(list_of_strings)

10) Слияние словарей с синтаксисом двойной звездочки **.
d1 = {'name': 'Alex', 'age': 25}
d2 = {'name': 'Alex', 'city': 'New York'}
merged_dict = {**d1, **d2}

@pythonl

🔭 Daily Useful Scripts

Daily.py is a repository that provides a collection of ready-to-use Python scripts for automating common daily tasks.

Daily.py - это репозиторий, который предоставляет коллекцию готовых к запуску скриптов Python для автоматизации обычных повседневных задач.

git clone https://github.com/Chamepp/Daily.py.git

▪ Github

@pythonl

Machine learning — обучающий для тех, кто хочет погрузится в волшебный мир Нейронауки!

Нейронные сети, машинное обучение, Data Science, изучаем базу, объясняем код, изучаем лучшие проекты, выкладываем бесплатные курсы и книги из области Машинного обучения.

Начать учиться

🖥 Create a Mock SQL DB in Python from CSV for unit testing

Создание макета SQL-базы данных в Python из CSV для модульного тестирования.

pip install pandas
pip install sqlglot
pip install sqlalchemy
from sqlalchemy import create_engine, text
import sqlglot
import pandas as pd


def execute_sql_query(sql):
query_as_sqlite = sqlglot.transpile(sql, read="postgres", write="sqlite")[0]
mocked_db = create_engine('sqlite://')
pd.read_csv('data.csv').to_sql('table_name', con=mocked_db)
with mocked_db.connect() as connection:
result = connection.execute(text(query_as_sqlite))
return result

@pythonl

🐍 10 Useful python scripts

10 интересных скриптов Python.

• Создавайте веб-бота
# pip install selenium
import time
from selenium import webdriver
from selenium.webdriver.common.keys
import Keysbot = webdriver.Chrome("chromedriver.exe")
bot.get('http://www.google.com')
search = bot.find_element_by_name('q')
search.send_keys("@codedev101")
search.send_keys(Keys.RETURN)
time.sleep(5)
bot.quit()

• Улучшение изображений на Python
# pip install pillow
from PIL import Image,ImageFilter
from PIL import ImageEnhance
im = Image.open('img.jpg')
# Choose your filter
# add Hastag at start if you don't want to any filter below
en = ImageEnhance.Color(im)
en = ImageEnhance.Contrast(im)
en = ImageEnhance.Brightness(im)
en = ImageEnhance.Sharpness(im)# result
en.enhance(1.5).show("enhanced")

• Парсинг текстов песен
# pip install lyricsgenius
import lyricsgenius
api_key = "xxxxxxxxxxxxxxxxxxxxx"
genius = lyricsgenius.Genius(api_key)
artist = genius.search_artist("Pop Smoke",
max_songs=5,sort="title")
song = artist.song("100k On a Coupe")
print(song.lyrics)

• Получение данных Exif для фотографий
# Get Exif of Photo
# Method 1
# pip install pillow
import PIL.Image
import PIL.ExifTags
img = PIL.Image.open("Img.jpg")
exif_data =
{
PIL.ExifTags.TAGS[i]: j
for i, j in img._getexif().items()
if i in PIL.ExifTags.TAGS
}
print(exif_data)
# Method 2
# pip install ExifRead
import exifread
filename = open(path_name, 'rb')
tags = exifread.process_file(filename)
print(tags)

• Поиск в Google
# pip install google
from googlesearch import search
query = "Medium.com"
for url in search(query):
print(url)

• Преобразование: шестнадцатеричная система в RGB
# Conversion: Hex to RGB
def Hex_to_Rgb(hex):
h = hex.lstrip('#')
return tuple(int(h[i:i+2], 16) for i in (0, 2, 4))
print(Hex_to_Rgb('#c96d9d')) # (201, 109, 157)
print(Hex_to_Rgb('#fa0515')) # (250, 5, 21)

• Конвертация фотографий в формат Cartonize
# pip install opencv-python
import cv2
img = cv2.imread('img.jpg')
grayimg = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
grayimg = cv2.medianBlur(grayimg, 5)
edges = cv2.Laplacian(grayimg , cv2.CV_8U, ksize=5)
r,mask =cv2.threshold(edges,100,255,cv2.THRESH_BINARY_INV)
img2 = cv2.bitwise_and(img, img, mask=mask)
img2 = cv2.medianBlur(img2, 5)
cv2.imwrite("cartooned.jpg", mask)

• Тестирование скорости соединения с помощью Python.
# pip install pyspeedtest
# pip install speedtest
# pip install speedtest-cli
#method 1
import speedtest
speedTest = speedtest.Speedtest()
print(speedTest.get_best_server())
#Check download speed
print(speedTest.download())
#Check upload speed
print(speedTest.upload())
# Method 2
import pyspeedtest
st = pyspeedtest.SpeedTest()
st.ping()
st.download()
st.upload()

• Проверка состояния сайта
# pip install requests
#method 1
import urllib.request
from urllib.request import Request, urlopenreq = Request('https://medium.com/@pythonians', headers={'User-Agent': 'Mozilla/5.0'})
webpage = urlopen(req).getcode()
print(webpage) # 200
# method 2
import requests
r = requests.get("https://medium.com/@pythonians")
print(r.status_code) # 200

• Извлечение текста OCR из изображений
# pip install pytesseract
import pytesseract
from PIL import Image
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'
t=Image.open("img.png")
text = pytesseract.image_to_string(t, config='')
print(text)

@pythonl

🕸 Python Web Scraping

Этот исчерпывающий список содержит библиотеки python, связанные с веб-парсингом и обработкой данных.

Web Scraping: Frameworks
scrapy - web-scraping framework (twisted based).
•pyspider - A powerful spider system.
•autoscraper - A smart, automatic and lightweight web scraper
•grab - web-scraping framework (pycurl/multicurl based)
•ruia - Async Python 3.6+ web scraping micro-framework based on asyncio
•cola - A distributed crawling framework.
•frontera - A scalable frontier for web crawlers
•dude - A simple framework for writing web scrapers using decorators.
•ioweb - Web scraping framework based on gevent and lxml

Web Scraping : Tools
•portia - Visual scraping for Scrapy.
•restkit - HTTP resource kit for Python. It allows you to easily access to HTTP resource and build objects around it.
•requests-html - Pythonic HTML Parsing for Humans.
•ScrapydWeb - A full-featured web UI for Scrapyd cluster management, which supports Scrapy Log Analysis & Visualization, Auto Packaging, Timer Tasks, Email Notice and so on.
•Starbelly - Starbelly is a user-friendly and highly configurable web crawler front end.
•Gerapy - Distributed Crawler Management Framework Based on Scrapy, Scrapyd, Django and Vue.js

Web Scraping : Bypass Protection
•cloudscraper - A Python module to bypass Cloudflare's anti-bot page.

▪ GIthub

@pythonl