Create app.py

app.py

@@ -0,0 +1,149 @@
+import streamlit as st
+from transformers import BertForQuestionAnswering, BertTokenizer
+import torch
+from io import BytesIO
+import PyPDF2
+import pandas as pd
+import spacy
+from spacy.matcher import Matcher
+
+# Load Spacy Model
+nlp = spacy.load("en_core_web_sm")
+
+# Extract Text from PDF
+def extract_text_from_pdf(uploaded_file):
+    pdf_reader = PyPDF2.PdfReader(BytesIO(uploaded_file.read()))
+    resume_text = ''
+    for page in pdf_reader.pages:
+        resume_text += page.extract_text()
+    return resume_text
+
+# Load BERT Model for QA
+model = BertForQuestionAnswering.from_pretrained("bert-large-uncased-whole-word-masking-finetuned-squad")
+tokenizer = BertTokenizer.from_pretrained("bert-large-uncased-whole-word-masking-finetuned-squad")
+
+# Generate Answer from QA Model
+def answer_question(question, context, model, tokenizer):
+    inputs = tokenizer.encode_plus(
+        question,
+        context,
+        add_special_tokens=True,
+        return_tensors="pt",
+        truncation="only_second",
+        max_length=512,
+    )
+    outputs = model(**inputs, return_dict=True)
+    answer_start_scores = outputs.start_logits
+    answer_end_scores = outputs.end_logits
+    answer_start = torch.argmax(answer_start_scores)
+    answer_end = torch.argmax(answer_end_scores) + 1
+    input_ids = inputs["input_ids"].tolist()[0]
+    answer = tokenizer.convert_tokens_to_string(
+        tokenizer.convert_ids_to_tokens(input_ids[answer_start:answer_end])
+    )
+    return answer
+
+# Extract Keywords for Resume Improvement
+def extract_keywords_for_sections(text):
+    doc = nlp(text)
+    skills_keywords = set()
+    project_keywords = set()
+
+    # Define patterns for skills and project ideas
+    skill_patterns = [[{"POS": "NOUN", "OP": "+"}], [{"POS": "PROPN", "OP": "+"}]]
+    project_patterns = [[{"POS": "VERB"}, {"POS": "NOUN", "OP": "+"}], [{"POS": "VERB"}, {"POS": "PROPN", "OP": "+"}]]
+
+    matcher = Matcher(nlp.vocab)
+    matcher.add("SKILLS", skill_patterns)
+    matcher.add("PROJECTS", project_patterns)
+
+    for match_id, start, end in matcher(doc):
+        span = doc[start:end]
+        if nlp.vocab.strings[match_id] == "SKILLS":
+            skills_keywords.add(span.text)
+        elif nlp.vocab.strings[match_id] == "PROJECTS":
+            project_keywords.add(span.text)
+
+    return skills_keywords, project_keywords
+
+# Suggest Resume Improvements
+def suggest_resume_improvements(resume_text, job_description):
+    skills_keywords, project_keywords = extract_keywords_for_sections(job_description)
+    missing_skills = [kw for kw in skills_keywords if kw.lower() not in resume_text.lower()]
+    potential_projects = [f"Consider a project involving '{keyword}'." for keyword in project_keywords]
+
+    skill_suggestions = [f"Consider highlighting your experience or skills related to '{keyword}'." for keyword in missing_skills[:5]]
+    project_suggestions = potential_projects[:5]
+
+    return skill_suggestions, project_suggestions
+
+# Analyze Matches between Resume and Job Description
+def analyze_matches(resume_text, job_description):
+    resume_keywords = set(extract_keywords_for_sections(resume_text)[0])
+    job_desc_keywords = set(extract_keywords_for_sections(job_description)[0])
+
+    matches = resume_keywords & job_desc_keywords
+    if matches:
+        commentary = f"Your resume matches the following keywords from the job description: {', '.join(matches)}"
+    else:
+        commentary = "There are no direct keyword matches between your resume and the job description."
+    
+    return commentary
+
+# Initialize session state to store the log of QA pairs and satisfaction responses
+if 'qa_log' not in st.session_state:
+    st.session_state.qa_log = []
+
+# Streamlit App Interface
+st.title('Resume Enhancement and Analysis App')
+
+# Resume PDF upload
+uploaded_file = st.file_uploader("Upload your resume (PDF format):", type='pdf')
+resume_text = ''
+if uploaded_file is not None:
+    resume_text = extract_text_from_pdf(uploaded_file)
+    st.write("Resume Text:")
+    st.write(resume_text)
+
+    # Question-Answer Functionality
+    user_question = st.text_input("Ask a question based on your resume:")
+    if user_question:
+        answer = answer_question(user_question, resume_text, model, tokenizer)
+        st.write("Answer:")
+        st.write(answer)
+
+        # Log the interaction
+        st.session_state.qa_log.append({
+            'Question': user_question,
+            'Answer': answer,
+            'Satisfaction': 'Pending'
+        })
+
+# Job Description Input for Resume Improvement
+job_description = st.text_area("Input the job description here for resume improvement suggestions:")
+if job_description:
+    skill_suggestions, project_suggestions = suggest_resume_improvements(resume_text, job_description)
+    
+    st.write('Technical Skill Improvement Suggestions:')
+    for suggestion in skill_suggestions:
+        st.write(suggestion)
+
+    st.write('Notable Project Ideas:')
+    for suggestion in project_suggestions:
+        st.write(suggestion)
+
+    # Analyze Matches and Provide Commentary
+    match_commentary = analyze_matches(resume_text, job_description)
+    st.write("Match Commentary:")
+    st.write(match_commentary)
+
+# User Feedback and Interaction Log
+if st.session_state.qa_log:
+    st.write("Interaction Log:")
+    for i, interaction in enumerate(st.session_state.qa_log):
+        if interaction['Satisfaction'] == 'Pending':
+            satisfaction = st.radio(f'Are you satisfied with the answer to: "{interaction["Question"]}"?', ('Yes', 'No'), key=f'satisfaction_{i}')
+            st.session_state.qa_log[i]['Satisfaction'] = satisfaction
+    
+    log_df = pd.DataFrame(st.session_state.qa_log)
+    st.dataframe(log_df)