Update app.py

app.py

@@ -25,71 +25,116 @@ from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
 import tempfile
 
-import streamlit as st
-import pandas as pd
-from PyPDF2 import PdfReader
-from gliner import GLiNER
-from sklearn.feature_extraction.text import TfidfVectorizer
-from sklearn.metrics.pairwise import cosine_similarity
+txt1 = st.text_area("Job description", key = "text 1")
+job_description_series1 = pd.Series(txt1, name="Text")
+st.dataframe(job_description_series1)
+
+uploaded_files = st.file_uploader(
+    "Choose a PDF file(s) for candidate profiles",  type="pdf", key = "candidate 1"
+)
+
+
+all_resumes_text = []  # Store the text content of each PDF
+
+if uploaded_files:
+    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()
+                model = GLiNER.from_pretrained("urchade/gliner_base")
+                labels = ["person", "country", "organization", "time", "role"]
+                entities = model.predict_entities(text_data, labels)
 
-def process_documents(job_description_key, file_uploader_key, title):
-    txt = st.text_area(f"Job description for {title}", key=job_description_key)
-    job_description_series = pd.Series([txt], name="Text")
-    st.dataframe(job_description_series)
-
-    uploaded_files = st.file_uploader(
-        f"Choose PDF file(s) for candidate profiles for {title}", type="pdf", key=file_uploader_key, 
-    )
-
-    all_extracted_data = []
-    if uploaded_files:
-        model = GLiNER.from_pretrained("urchade/gliner_base")
-        labels = ["person", "country", "organization", "time", "role"]
-        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()
+            entity_dict = {}
+            for label in labels:
+                entity_dict[label] = [entity["text"] for entity in entities if entity["label"] == label]
 
-                entities = model.predict_entities(text_data, labels)
-                entity_dict = {}
-                for label in labels:
-                    entity_dict[label] = [entity["text"] for entity in entities if entity["label"] == label]
-                data = {"Text": text_data, **entity_dict}
-                all_extracted_data.append(data)
-            except Exception as e:
-                st.error(f"Error processing file {uploaded_file.name}: {e}")
-
-        if all_extracted_data:
-            df_entities = pd.DataFrame(all_extracted_data)
-            st.subheader(f"Extracted Entities ({title}):")
-            st.dataframe(df_entities)
-
-            all_documents = [job_description_series.iloc[0]] + df_entities['Text'].tolist()
-            vectorizer = TfidfVectorizer()
-            tfidf_matrix = vectorizer.fit_transform(all_documents)
-            tfidf_df = pd.DataFrame(tfidf_matrix.toarray(), columns=vectorizer.get_feature_names_out())
-            st.subheader(f"TF-IDF Values ({title}):")
-            st.dataframe(tfidf_df)
-
-            cosine_sim_matrix = cosine_similarity(tfidf_matrix)
-            cosine_sim_df = pd.DataFrame(cosine_sim_matrix)
-            st.subheader(f"Cosine Similarity Matrix ({title}):")
-            st.dataframe(cosine_sim_df)
-
-            st.subheader(f"Cosine Similarity Scores (Job Description for {title} 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}")
-
-st.header("Analysis Set 1")
-process_documents("text 1", "candidate 1", "Set 1")
+            data = {"Text": text_data, **entity_dict}
+            
+
+
+            all_resumes_text.append(text_data)
+        except Exception as e:
+            st.error(f"Error processing file {uploaded_file.name}: {e}")
+
+    if all_resumes_text:
+        all_documents = [job_description_series.iloc[0]] + all_resumes_text
+
+        vectorizer = TfidfVectorizer()
+        tfidf_matrix = vectorizer.fit_transform(all_documents)
+
+        tfidf_df = pd.DataFrame(tfidf_matrix.toarray(), columns=vectorizer.get_feature_names_out())
+        st.subheader("TF-IDF Values:")
+        st.dataframe(tfidf_df)
+
+        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)
 
+        # 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}")
+
+
+       
 st.divider()
 
-st.header("Analysis Set 2")
-process_documents("text 2", "candidate 2", "Set 2")
+txt2 = st.text_area("Job description", key = "text 2")
+job_description_series2 = pd.Series(txt2, name="Text")
+st.dataframe(job_description_series2)
+
+uploaded_files = st.file_uploader(
+    "Choose a PDF file(s) for candidate profiles",  type="pdf", key = "candidate 2"
+)
+
+
+all_resumes_text = []  # Store the text content of each PDF
+
+if uploaded_files:
+    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()
+                model = GLiNER.from_pretrained("urchade/gliner_base")
+               labels = ["person", "country", "organization", "time", "role"]
+               entities = model.predict_entities(text_data, labels)
+
+            entity_dict = {}
+            for label in labels:
+                entity_dict[label] = [entity["text"] for entity in entities if entity["label"] == label]
+
+            data = {"Text": text_data, **entity_dict}
+            
+
+
+            all_resumes_text.append(text_data)
+        except Exception as e:
+            st.error(f"Error processing file {uploaded_file.name}: {e}")
+
+    if all_resumes_text:
+        all_documents = [job_description_series.iloc[0]] + all_resumes_text
+
+        vectorizer = TfidfVectorizer()
+        tfidf_matrix = vectorizer.fit_transform(all_documents)
+
+        tfidf_df = pd.DataFrame(tfidf_matrix.toarray(), columns=vectorizer.get_feature_names_out())
+        st.subheader("TF-IDF Values:")
+        st.dataframe(tfidf_df)
 
+        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)
 
+        # 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}")
 
-    
+