Update src/streamlit_app.py

src/streamlit_app.py

@@ -2,11 +2,12 @@ import streamlit as st
 import pandas as pd
 from sklearn.metrics.pairwise import cosine_similarity
 import joblib
-
-st.title("Arxiv Expert Finder")
-
 from pathlib import Path
 import urllib.request
+import re
+from nltk.stem import PorterStemmer
+
+st.title("Arxiv Expert Finder")
 
 # URLs
 BASE_URL = "https://huggingface.co/datasets/jadenhochh/TF_IDF/resolve/main"
@@ -34,7 +35,15 @@ except Exception as e:
     print(f"Fehler: {e}")
 
 st.sidebar.header("Query")
-user_query = st.text_input("Suchtext eingeben", "")
+
+if user_query:
+    # Remove numbers and special characters, convert to lowercase
+    user_query = re.sub(r'[^a-zA-Z\s]', ' ', user_query).lower()
+    # Stem words
+    stemmer = PorterStemmer()
+    user_query = " ".join([stemmer.stem(word) for word in user_query.split()])
+
+
 num_experts = st.sidebar.number_input("Anzahl Experten", min_value=1, max_value=10, value=5, step=1)
 
 if user_query: