vlad-ds

vlad-ds

-- data for 1 day: 479 MB scanned
SELECT *
FROM `bigquery-public-data.google_trends.international_top_terms` 
WHERE refresh_date = DATE_SUB(CURRENT_DATE, INTERVAL 1 DAY);

-- data for 2 days: 955 MB scanned
SELECT *
FROM `bigquery-public-data.google_trends.international_top_terms` 
WHERE refresh_date > DATE_SUB(CURRENT_DATE, INTERVAL 3 DAY);

vlad-ds

SELECT term, 
       rank, 
       AVG(score) AS avg_score
FROM `bigquery-public-data.google_trends.international_top_terms` 
WHERE refresh_date = DATE_SUB(CURRENT_DATE, INTERVAL 1 DAY)
AND country_name = "United Kingdom"
GROUP BY term, rank
ORDER BY rank ASC;

vlad-ds

def fizzbuzz(n):
    return [('' + 'Fizz' * (not x % 3) + 'Buzz' * (not x % 5)) or x for x in range(1, n+1)]

vlad-ds

Hello Le Wagon 👋

vlad-ds

Hello Le Wagon 👋

vlad-ds

from pandas import DataFrame

def main():
    path = 'input/mail.mbox'
    mails = get_mails(path)
    unsub_links = add_unsubscribe(mails)
    df = DataFrame(unsub_links).T
    df = df.sort_values(by='count', ascending=False)
    df.to_csv('output.csv')

vlad-ds

import re

def add_unsubscribe(mails: List, unsub_links: dict = {}) -> dict:
    for mail in mails:
        #getting sender
        sender_line = mail.split('\n')[0]               #first line of the mail
        sender_words = sender_line.split(' ')[1:]       #removes the 'From: ' part
        sender = ' '.join(sender_words)                 #recreates the name string
        if 'Q?' in sender:
            sender = re.findall('.Q.?(.*?)\?', sender)[0]  #removing some char coding

vlad-ds

from typing import List

def get_mails(path: str, limit: int = None) -> List[str]:
    '''Extract emails from an .mbox file.'''
    mails = []
    c = -1
    mail = str()
    with open(path, 'r', encoding = 'UTF-8') as file:
        for line in file:               #read every line
            if c == limit: break

vlad-ds

print(token)
>> T2_wi8XsUpJrbD0BHQH4vX0BrSuYV0D88sVrQ_wMgApU...