Update app.py

app.py

@@ -25,116 +25,100 @@ from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
 import tempfile
 
-txt1 = st.text_area("Job description", key = "text 1")
+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"
+uploaded_files1 = 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:
+all_resumes_text1 = []  # Store the text content of each PDF
+if uploaded_files1:
+    for uploaded_file in uploaded_files1:
         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)
+            if uploaded_file is not None:  # Check if a file was uploaded
+                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_text1.append(text_data)
+            else:
+                st.warning("No file uploaded for the first set of candidates.")
         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())
+            if hasattr(uploaded_file, 'name'):
+                st.error(f"Error processing file {uploaded_file.name}: {e}")
+            else:
+                st.error(f"Error processing a file: {e}")
+
+    if all_resumes_text1:
+        all_documents1 = [job_description_series1.iloc[0]] + all_resumes_text1
+        vectorizer1 = TfidfVectorizer()
+        tfidf_matrix1 = vectorizer1.fit_transform(all_documents1)
+        tfidf_df1 = pd.DataFrame(tfidf_matrix1.toarray(), columns=vectorizer1.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.dataframe(tfidf_df1)
+        cosine_sim_matrix1 = cosine_similarity(tfidf_matrix1)
+        cosine_sim_df1 = pd.DataFrame(cosine_sim_matrix1)
         st.subheader("Cosine Similarity Matrix:")
-        st.dataframe(cosine_sim_df)
-
+        st.dataframe(cosine_sim_df1)
         # 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:]):
+        for i, similarity_score in enumerate(cosine_sim_matrix1[0][1:]):
             st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}")
 
-
-       
 st.divider()
 
-txt2 = st.text_area("Job description", key = "text 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"
+uploaded_files2 = 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:
+all_resumes_text2 = []  # Store the text content of each PDF
+if uploaded_files2:
+    for uploaded_file in uploaded_files2:
         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)
+            if uploaded_file is not None:  # Check if a file was uploaded
+                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_text2.append(text_data)
+            else:
+                st.warning("No file uploaded for the second set of candidates.")
         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())
+            if hasattr(uploaded_file, 'name'):
+                st.error(f"Error processing file {uploaded_file.name}: {e}")
+            else:
+                st.error(f"Error processing a file: {e}")
+
+    if all_resumes_text2:
+        all_documents2 = [job_description_series2.iloc[0]] + all_resumes_text2
+        vectorizer2 = TfidfVectorizer()
+        tfidf_matrix2 = vectorizer2.fit_transform(all_documents2)
+        tfidf_df2 = pd.DataFrame(tfidf_matrix2.toarray(), columns=vectorizer2.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.dataframe(tfidf_df2)
+        cosine_sim_matrix2 = cosine_similarity(tfidf_matrix2)
+        cosine_sim_df2 = pd.DataFrame(cosine_sim_matrix2)
         st.subheader("Cosine Similarity Matrix:")
-        st.dataframe(cosine_sim_df)
-
+        st.dataframe(cosine_sim_df2)
         # 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}")
-
-    
+        for i, similarity_score in enumerate(cosine_sim_matrix2[0][1:]):
+            st.write(f"Similarity with Candidate Profile {i + 1}: {similarity_score:.4f}")