Update app.py

app.py

@@ -18,54 +18,47 @@ import pandas as pd
 from PyPDF2 import PdfReader
 from gliner import GLiNER
 
-txt = st.text_area("Job description")
-data1 = pd.Series(txt, name = "Text")
-st.dataframe(data1)
-
 
+txt = st.text_area("Job description")
+job_description_series = pd.Series([txt], name="Text")
+st.dataframe(job_description_series)
 
 uploaded_files = st.file_uploader(
-    "Choose a PDF file(s) and job description as pdf", accept_multiple_files=True, type="pdf"
+    "Choose a PDF file(s) for candidate profiles", accept_multiple_files=True, type="pdf"
 )
 
+all_resumes_text = []  # Store the text content of each PDF
+
 if uploaded_files:
-    all_data = []  # Store dictionaries of text and entities for each PDF
     for uploaded_file in uploaded_files:
         try:
             pdf_reader = PdfReader(uploaded_file)
             text_data = ""
             for page in pdf_reader.pages:
                 text_data += page.extract_text()
+            all_resumes_text.append(text_data)
+        except Exception as e:
+            st.error(f"Error processing file {uploaded_file.name}: {e}")
 
-            model = GLiNER.from_pretrained("urchade/gliner_base")
-            labels = ["person", "country", "organization", "time", "role"]
-            entities = model.predict_entities(text_data, labels)
+    if all_resumes_text:
+        all_documents = [job_description_series.iloc[0]] + all_resumes_text
 
-            entity_dict = {}
-            for label in labels:
-                entity_dict[label] = [entity["text"] for entity in entities if entity["label"] == label]
+        vectorizer = TfidfVectorizer()
+        tfidf_matrix = vectorizer.fit_transform(all_documents)
 
-            data = {"Text": text_data, **entity_dict}
-            all_data.append(data)
+        tfidf_df = pd.DataFrame(tfidf_matrix.toarray(), columns=vectorizer.get_feature_names_out())
+        st.subheader("TF-IDF Values:")
+        st.dataframe(tfidf_df)
 
-        except Exception as e:
-            st.error(f"Error processing file {uploaded_file.name}: {e}")
+        cosine_sim_matrix = cosine_similarity(tfidf_matrix)
+        cosine_sim_df = pd.DataFrame(cosine_sim_matrix)
+        st.subheader("Cosine Similarity Matrix:")
+        st.dataframe(cosine_sim_df)
 
-    if all_data:
-        df = pd.DataFrame(all_data)
-        frames = [data1, df]
-        result = pd.concat(frames)
-        st.dataframe(result)
-
-        y = result[['Text']]
-        st.dataframe(y)
-
-        vec = TfidfVectorizer()
-        tf_idf = vec.fit_transform(y)
-        x = pd.DataFrame(tf_idf.toarray(), columns=vec.get_feature_names_out())
-        st.dataframe(x)
-        cosine_sim = cosine_similarity(tf_idf, tf_idf)
-        st.dataframe(cosine_sim)
+        # Display similarity scores between the job description and each resume
+        st.subheader("Cosine Similarity Scores (Job Description vs. Resumes):")
+        for i, similarity_score in enumerate(cosine_sim_matrix[0][1:]):
+            st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}")