Update app.py

app.py

@@ -1,3 +1,11 @@
+import csv
+import sys
+
+# Increase CSV field size limit
+csv.field_size_limit(sys.maxsize)
+
+
+
 import gradio as gr
 import pandas as pd
 
@@ -229,11 +237,11 @@ import numpy as np
 
 
 def extract_problem_domains(df, 
-                            text_column='Problem_Description', 
+                            text_column='Processed_ProblemDescription_forDomainExtraction', 
                             cluster_range=(10, 50), 
                             top_words=17,
-                            # method='sentence_transformers'
-                            method='tfidf_kmeans'
+                            method='sentence_transformers'
+                            # method='tfidf_kmeans'
                            ):
 
 
@@ -261,7 +269,7 @@ def extract_problem_domains(df,
         
     elif method == 'tfidf_kmeans':
         # TF-IDF Vectorization and K-Means approach
-        vectorizer = TfidfVectorizer(stop_words='english', max_features=5000)
+        vectorizer = TfidfVectorizer(stop_words='english', max_features=3000)
         X = vectorizer.fit_transform(df[text_column])
         
         # Perform K-Means clustering with Silhouette Analysis