Create app.py

app.py

@@ -0,0 +1,144 @@
+# Import necessary libraries
+import streamlit as st
+import nltk
+from nltk.tokenize import word_tokenize
+import PyPDF2
+import pandas as pd
+import re
+import matplotlib.pyplot as plt
+import seaborn as sns
+import spacy
+from transformers import AutoTokenizer, AutoModel
+import torch
+from sklearn.metrics.pairwise import cosine_similarity
+
+# Download necessary NLTK data
+nltk.download('punkt')
+
+# Define regular expressions for pattern matching
+float_regex = re.compile(r'^\d{1,2}(\.\d{1,2})?$')
+email_pattern = r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b'
+float_digit_regex = re.compile(r'^\d{10}$')
+email_with_phone_regex = re.compile(r'(\d{10}).|.(\d{10})')
+
+# Load Phi-4 model and tokenizer
+@st.cache_resource
+def load_model():
+    model_name = "microsoft/Phi-4-multimodal-instruct"  # Hypothetical model name
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModel.from_pretrained(model_name)
+    return tokenizer, model
+
+tokenizer, model = load_model()
+
+# Function to extract text from PDF
+def extract_text_from_pdf(pdf_file):
+    pdf_reader = PyPDF2.PdfReader(pdf_file)
+    text = ""
+    for page_num in range(len(pdf_reader.pages)):
+        text += pdf_reader.pages[page_num].extract_text()
+    return text
+
+# Function to generate embeddings using Phi-4
+def get_embeddings(text):
+    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=512)
+    with torch.no_grad():
+        outputs = model(**inputs)
+    embeddings = outputs.last_hidden_state.mean(dim=1).squeeze()
+    return embeddings.numpy()
+
+# Function to calculate similarity between texts
+def calculate_similarity(text1, text2):
+    emb1 = get_embeddings(text1)
+    emb2 = get_embeddings(text2)
+    return cosine_similarity([emb1], [emb2])[0][0]
+
+# Function to tokenize text using SpaCy
+def tokenize_text(text, nlp_model):
+    doc = nlp_model(text, disable=["tagger", "parser"])
+    tokens = [(token.text.lower(), token.label_) for token in doc.ents]
+    return tokens
+
+# Function to extract CGPA
+def extract_cgpa(resume_text):
+    cgpa_pattern = r'\b(?:CGPA|GPA|C\.G\.PA|Cumulative GPA)\s*:?[\s-]([0-9]+(?:\.[0-9]+)?)\b|\b([0-9]+(?:\.[0-9]+)?)\s(?:CGPA|GPA)\b'
+    match = re.search(cgpa_pattern, resume_text, re.IGNORECASE)
+    return float(match.group(1 or 2)) if match else None
+
+# Streamlit Frontend
+st.markdown("# Resume Matching Tool 📃📃")
+st.markdown("An application to match resumes with a job description using Phi-4")
+
+# File Upload
+resumes_files = st.sidebar.file_uploader("Upload Resumes PDF", type=["pdf"], accept_multiple_files=True)
+job_descriptions_file = st.sidebar.file_uploader("Upload Job Description PDF", type=["pdf"])
+
+if resumes_files and job_descriptions_file:
+    # Load SpaCy model
+    nlp = spacy.load("en_Resume_Matching_Keywords")
+    
+    # Process documents
+    job_description_text = extract_text_from_pdf(job_descriptions_file)
+    resumes_texts = {file.name: extract_text_from_pdf(file) for file in resumes_files}
+    
+    # Generate embeddings
+    job_embedding = get_embeddings(job_description_text)
+    resume_embeddings = {name: get_embeddings(text) for name, text in resumes_texts.items()}
+    
+    # Calculate similarities
+    results = []
+    for name, emb in resume_embeddings.items():
+        similarity = cosine_similarity([emb], [job_embedding])[0][0] * 100
+        results.append({
+            "Resume": name,
+            "Similarity Score": f"{similarity:.2f}%",
+            "Details": "View Details"
+        })
+    
+    # Show results
+    st.dataframe(pd.DataFrame(results))
+    
+    # Detailed analysis
+    st.subheader("Detailed Analysis")
+    selected_resume = st.selectbox("Select Resume", list(resumes_texts.keys()))
+    
+    if selected_resume:
+        resume_text = resumes_texts[selected_resume]
+        
+        # Entity extraction
+        doc = nlp(resume_text)
+        entities = [(ent.text, ent.label_) for ent in doc.ents]
+        
+        # Display entities
+        st.write("### Extracted Entities")
+        entity_df = pd.DataFrame(entities, columns=["Text", "Label"])
+        st.dataframe(entity_df)
+        
+        # Skills matching
+        st.write("### Skills Matching")
+        skills = [ent.text for ent in doc.ents if ent.label_ == "SKILLS"]
+        job_skills = [ent.text for ent in nlp(job_description_text).ents if ent.label_ == "SKILLS"]
+        matched_skills = list(set(skills) & set(job_skills))
+        st.write(f"**Matched Skills ({len(matched_skills)}):** {', '.join(matched_skills)}")
+
+        # Visualization
+        st.write("### Similarity Heatmap")
+        skills_keywords = st.text_input("Enter skills for heatmap (comma-separated):").split(',')
+        
+        if skills_keywords:
+            heatmap_data = []
+            for skill in skills_keywords:
+                skill_emb = get_embeddings(skill.strip())
+                row = []
+                for name, emb in resume_embeddings.items():
+                    row.append(cosine_similarity([emb], [skill_emb])[0][0])
+                heatmap_data.append(row)
+            
+            plt.figure(figsize=(12, 8))
+            sns.heatmap(pd.DataFrame(heatmap_data, 
+                        columns=list(resumes_texts.keys()), 
+                        index=skills_keywords),
+                        annot=True, cmap="YlGnBu")
+            st.pyplot(plt)
+else:
+    st.warning("Please upload both resumes and job description to proceed.")