Restored topic modeling, keyword extraction, and summarization

app.py

@@ -77,7 +77,19 @@ def analyze_demographics(file):
 
 def analyze_why_columns(file):
     df = pd.read_excel(file.name)
-    why_columns = [col for col in df.columns if col.startswith("Why")]
+    
+    # Map column names to new labels
+    column_label_map = {
+        "Why? (optional)": "HF NPS Why?",
+        "Why? (optional.1)": "Support Team NPS Why?",
+        "Why? (optional.2)": "Productivity Why?"
+    }
+    
+    # Rename columns in the DataFrame
+    df = df.rename(columns=column_label_map)
+
+    # Get the renamed columns that start with "Why"
+    why_columns = [col for col in df.columns if col in column_label_map.values()]
 
     results = {}
 
@@ -110,7 +122,7 @@ def analyze_why_columns(file):
 
         # Keyword Extraction
         combined_text = " ".join(column_data)
-        word_list = re.findall(r"\b\w+\b", combined_text.lower())
+        word_list = re.findall(r"\\b\\w+\\b", combined_text.lower())
         bigram_vectorizer = CountVectorizer(ngram_range=(2, 3), stop_words='english')
         bigram_counts = bigram_vectorizer.fit_transform([combined_text])
         bigram_features = bigram_vectorizer.get_feature_names_out()