Update app.py

app.py

@@ -1,6 +1,7 @@
 import streamlit as st
 from PyPDF2 import PdfReader
 import pandas as pd
+from sklearn.feature_extraction.text import TfidfVectorizer
 
 uploaded_files = st.file_uploader(
     "Choose a CSV file", accept_multiple_files=True
@@ -13,6 +14,21 @@ for uploaded_file in uploaded_files:
         text_data+= page.extract_text()
 
     
-    data = pd.Series(text_data)
+    data = pd.Series(text_data, index = ["Resume"]
     
-    st.dataframe(data) # view the text data
+    st.dataframe(data) # view the text data
+
+    st.subheader("Paste the job description")
+
+    txt = st.text_area("Job description")
+    st.write(txt)
+
+    vec = TfidfVectorizer()
+    tf_idf = vec.fit_transform(data['Resume'])
+    st.write(pd.DataFrame(tf_idf.toarray(), columns=vec.get_feature_names_out()))
+    from sklearn.metrics.pairwise import cosine_similarity
+    cosine_sim = cosine_similarity(tf_idf, tf_idf)
+    st.write(cosine_sim)
+
+
+