Update WordCloud

pages/10 WordCloud.py

@@ -5,7 +5,7 @@ from wordcloud import WordCloud
 from tools import sourceformat as sf
 import nltk
 from nltk.corpus import stopwords
-from gensim.parsing.preprocessing import remove_stopwords
+from nltk.tokenize import word_tokenize
 nltk.download('stopwords')
 
 
@@ -177,14 +177,23 @@ if uploaded_file is not None:
                     texts = conv_txt(uploaded_file)
                     colcho = c1.selectbox("Choose Column", list(texts))
                     fulltext = " ".join(list(texts[colcho]))
-                    fulltext = remove_stopwords(fulltext)
+                    tokenized = word_tokenize(fulltext)
+
+                    filtered = [word for word in tokenized if word.lower() not in stopwords.words('english')]
+
+                    fulltext = ' '.join(filtered)
                     
 
                 except:
                     fulltext = read_txt(uploaded_file)
-                
-                if st.button("Submit"):
                     
+                    tokenized = word_tokenize(fulltext)
+
+                    filtered = [word for word in tokenized if word.lower() not in stopwords.words('english')]
+
+                    fulltext = ' '.join(filtered)
+
+                if st.button("Submit"):
                     
                     wordcloud = WordCloud(max_font_size = max_font,
                     max_words = max_words,
@@ -205,7 +214,11 @@ if uploaded_file is not None:
 
                 fullcolumn = " ".join(list(texts[colcho]))
                 
-                fullcolumn = remove_stopwords(fullcolumn)
+                tokenized = word_tokenize(fullcolumn)
+
+                filtered = [word for word in tokenized if word.lower() not in stopwords.words('english')]
+
+                fullcolumn = ' '.join(filtered)
 
                 if st.button("Submit"):