ahmedshahriar

# data - pandas dataframe
def missing_value_describe(data):
    # check missing values in the data
    total = data.isna().sum().sort_values(ascending=False)
    missing_value_pct_stats = (data.isnull().sum() / len(data)*100)
    missing_value_col_count = sum(missing_value_pct_stats > 0)

    # missing_value_stats = missing_value_pct_stats.sort_values(ascending=False)[:missing_value_col_count]
    missing_data = pd.concat([total, missing_value_pct_stats], axis=1, keys=['Total', 'Percent'])

ahmedshahriar

import pandas as pd

# using pandas datetime converter
df = pd.DataFrame(pd.Series(['2021-02-04T09:15:00+05:30', '2021-02-04T09:15:00+05:30', '2021-02-04T09:15:00+05:30']))
pd.to_datetime(df[0]).dt.date
pd.to_datetime(df[0]).dt.time

# using dateutil library
from dateutil.parser import parse
df[0].map(lambda x: parse(x).date())

ahmedshahriar

# Install qrcode https://pypi.org/project/qrcode/
# pip install qrcode[pil]

import qrcode
qr = qrcode.QRCode(
    version=1,
    error_correction=qrcode.constants.ERROR_CORRECT_L,
    box_size=10,
    border=4,
)

ahmedshahriar

# input
import os
for dirname, _, filenames in os.walk('/files/input'):
    for filename in filenames:
        print(os.path.join(dirname, filename))

ahmedshahriar

"""
requests with session gives faster results

the below code demonstrates a comparison in speed between requests with session vs requests not with session
"""
import requests
import datetime
from bs4 import BeautifulSoup

def scrape_no_session(x):

ahmedshahriar

"""
Suppose you have a django model in models.py:

class Animal(models.Model):
    animal_name = models.CharField(u'name', max_length=255)

to create an alphabetfilter in django admin panel you need to create a class which inherits
admin.SimpleListFilter in admin.py

here is the code snippet below for admin.py file

ahmedshahriar

ahmedshahriar

import pandas as pd
import base64

def download_dataset(dataset):
    csv = dataset.to_csv(index=False)
    b64 = base64.b64encode(csv.encode()).decode()  # strings to bytes conversions
    href_link = f'<a href="data:file/csv;base64,{b64}" download="player_stats.csv">Download CSV File</a>'
    return href_link

 

ahmedshahriar

# sample Url https://www.basketball-reference.com/leagues/NBA_2021_per_game.html

import pandas as pd

def parse_data(year: str):
    url = "https://www.basketball-reference.com/leagues/NBA_" + year + "_per_game.html"
    parsed_df = pd.read_html(url, header=0)[0]
    parsed_df = parsed_df.drop(parsed_df[parsed_df['Age'] == 'Age'].index) # to remove duplicate headers
    parsed_df = parsed_df.fillna(0) 
    parsed_df = parsed_df.drop(['Rk'], axis=1) # to index(Rk column) 

ahmedshahriar

'''
A simple regex approach to find specific portion (in this case post id) from a http link 
'''

import re

link = "https://www.facebook.com/marketplace/item/391273608941747/?ref=search&referral_code=undefined"
print(re.findall("marketplace/item/(\S*)/", str(link))[0])

# output