Update app.py

app.py

@@ -117,11 +117,25 @@ plt.imshow(wordcloud)
 plt.axis('off')
 plt.show()
 fig.savefig("word1.png", dpi=900)
-
 from sklearn.feature_extraction.text import CountVectorizer
 import re
-cv=CountVectorizer(max_df=0.8,stop_words=stop_words, max_features=10000, ngram_range=(1,3))
-X=cv.fit_transform(corpus)
+
+# Assuming you have the 'corpus' defined
+# and 'stop_words' defined as in your previous code
+
+# Create a CountVectorizer with predefined English stop words
+cv = CountVectorizer(max_df=0.8, stop_words='english', max_features=10000, ngram_range=(1, 3))
+X = cv.fit_transform(corpus)
+
+# Alternatively, use your custom stop words
+custom_stop_words = ['same', 'hers', 'they', 'with', 'if', 'y', 'iv', 'new', ...]  # Add your custom stop words
+cv = CountVectorizer(max_df=0.8, stop_words=custom_stop_words, max_features=10000, ngram_range=(1, 3))
+X = cv.fit_transform(corpus)
+
+#from sklearn.feature_extraction.text import CountVectorizer
+#import re
+#cv=CountVectorizer(max_df=0.8,stop_words=stop_words, max_features=10000, ngram_range=(1,3))
+#X=cv.fit_transform(corpus)
 
 from sklearn.feature_extraction.text import CountVectorizer