Multiple files added

Models.py

@@ -39,23 +39,29 @@ def get_HF_embeddings(sentences):
 def get_doc2vec_embeddings(JD, text_resume):
     nltk.download("punkt")
     data = [JD]
-
+    resume_embeddings = []
+
     tagged_data = [TaggedDocument(words=word_tokenize(_d.lower()), tags=[str(i)]) for i, _d in enumerate(data)]
     #print (tagged_data)
 
     model = gensim.models.doc2vec.Doc2Vec(vector_size=512, min_count=3, epochs=80)
     model.build_vocab(tagged_data)
     model.train(tagged_data, total_examples=model.corpus_count, epochs=80)
     JD_embeddings = np.transpose(model.docvecs['0'].reshape(-1,1))
-    text_resume = word_tokenize(text_resume.lower())
-    resume_embeddings = model.infer_vector(text_resume)
-    resume_embeddings = np.transpose(resume_embeddings.reshape(-1,1))
+
+    for i in text_resume:
+        text = word_tokenize(i.lower())
+        embeddings = model.infer_vector(text)
+        resume_embeddings.append(np.transpose(embeddings.reshape(-1,1)))
     return (JD_embeddings, resume_embeddings)
 
 
 def cosine(embeddings1, embeddings2):
   # get the match percentage
-  matchPercentage = cosine_similarity(np.array(embeddings1), np.array(embeddings2))
-  matchPercentage = np.round(matchPercentage, 4)*100 # round to two decimal
-  print("Your resume matches about" + str(matchPercentage[0])+ "% of the job description.")
-  return str(matchPercentage[0][0])
+  score_list = []
+  for i in embeddings1:
+      matchPercentage = cosine_similarity(np.array(i), np.array(embeddings2))
+      matchPercentage = np.round(matchPercentage, 4)*100 # round to two decimal
+      print("Your resume matches about" + str(matchPercentage[0])+ "% of the job description.")
+      score_list.append(str(matchPercentage[0][0]))
+  return score_list

Resume_scanner.py

@@ -12,26 +12,31 @@ def extract_data(feed):
     return data # build more code to return a dataframe
 
 
-def compare(uploaded_file, JD, flag = 'HuggingFace-BERT'):
+def compare(uploaded_files, JD, flag = 'HuggingFace-BERT'):
 
     if flag == 'HuggingFace-BERT':
         JD_embeddings = None
-        resume_embeddings = None
+        resume_embeddings = []
 
-        if uploaded_file is not None:
-            df = extract_data(uploaded_file)
-            resume_embeddings = get_HF_embeddings(df)
         if JD is not None:
             JD_embeddings = get_HF_embeddings(JD)
+        if uploaded_files is not None:
+            for i in uploaded_files:
+                df = extract_data(i)
+                resume_embeddings.append(get_HF_embeddings(df))
         if JD_embeddings is not None and resume_embeddings is not None:
             cos = cosine(resume_embeddings, JD_embeddings)
             #st.write("Score is: ", cos)
 
     else:
-        if uploaded_file is not None:
-            df = extract_data(uploaded_file)
+        df = []
+        if uploaded_files is not None:
+            for i in uploaded_files:
+                data = extract_data(i)
+                df.append(data)
 
         JD_embeddings, resume_embeddings = get_doc2vec_embeddings(JD, df)
-        cos = cosine(resume_embeddings, JD_embeddings)
+        if JD_embeddings is not None and resume_embeddings is not None:
+            cos = cosine(resume_embeddings, JD_embeddings)
         #st.write("Cosine similarity is: ", cos)
     return cos

application.py

@@ -19,17 +19,26 @@
 
 with tab1:
     st.title("Applicant Tracking System")
-    uploaded_file = st.file_uploader('**Choose your resume.pdf file:** ', type="pdf")
-    st.write(uploaded_file)
+    uploaded_files = st.file_uploader('**Choose your resume.pdf file:** ', type="pdf", accept_multiple_files = True)
+    #st.write(uploaded_files)
     st.write("")
     JD = st.text_area("**Enter the job description:**")
     comp_pressed = st.button("Compare!")
     if comp_pressed:
-        score = compare(uploaded_file, JD, flag)
+        #st.write(uploaded_files[0].name)
+        score = compare(uploaded_files, JD, flag)
 
 with tab2:
     st.header("Results")
+    my_dict = {}
     if comp_pressed:
-        st.write("Cosine similarity is: ", score)
+        for i in range(len(score)):
+            my_dict[uploaded_files[i].name] = score[i]
+        print(my_dict)
+        sorted_dict = dict(sorted(my_dict.items()))
+        print(sorted_dict)
+        for i in sorted_dict.items():
+            with st.expander(str(i[0])):
+                st.write("Score is: ", i[1])
     else:
         st.write("#### Throw in some Resumes to see the score :)")