remove stopwords for word cloud

handler.py

@@ -2,6 +2,7 @@ from typing import Dict, List, Any
 from scipy.special import softmax
 import numpy as np
 import weakref
+import nltk
 
 from utils import clean_str, clean_str_nopunct
 import torch
@@ -135,10 +136,12 @@ class Transcript:
         teacher_dict = {}
         student_dict = {}
         uptake_teacher_dict = {}
+        stopwords = nltk.corpus.stopwords.word('english')
+        print("stopwords: ", stopwords)
         for utt in self.utterances:
-
             words = (utt.get_clean_text(remove_punct=True)).split(' ')
             for word in words:
+                if word in stopwords: continue
                 if utt.role == 'teacher':
                     if word not in teacher_dict:
                         teacher_dict[word] = 0

requirements.txt

@@ -3,4 +3,5 @@ num2words==0.5.10
 numpy==1.22.4
 scipy==1.7.3
 torch==1.10.2
-transformers==4.29.1
+transformers==4.29.1
+nltk==3.8.1