Egle Gradeckaite EgleGrade
backupbrain
/ guess_url_from_company_name.py
Created
November 14, 2018 18:08
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import re | |
| import requests | |
| import nltk | |
| from lxml import html | |
| from nltk.corpus import stopwords | |
| stop_words = set(stopwords.words("english")) | |
| # A Company Name | |
| company_name = "The Boring Company" | |
| search_terms = ["flamethrower"] # The Boring Company sells flamethrowers |
backupbrain
/ job_title_analysis.py
Last active
February 10, 2024 07:07
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import re | |
| import nltk | |
| from nltk.corpus import stopwords | |
| import pandas as pd | |
| stop_words = set(stopwords.words("english")) | |
| def get_first_title(title): | |
| # keep "co-founder, co-ceo, etc" | |
| title = re.sub(r"[Cc]o[\-\ ]","", title) |