This file contains 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 spacy | |
import pandas as pd | |
import os | |
DATA_DIR="path to data" | |
"""Create a list of common words to remove""" | |
stop_words=["i", "me", "my", "myself", "we", "our", "ours", "ourselves", "you", "your", "yours", "yourself", | |
"yourselves", "he", "him", "his", "himself", "she", "her", "hers", "herself", "it", "its", "itself", | |
"they", "them", "their", "theirs", "themselves", "what", "which", "who", "whom", "this", "that", "these", | |
"those", "am", "is", "are", "was", "were", "be", "been", "being", "have", "has", "had", "having", "do", |