Update app.py

app.py

@@ -2,9 +2,10 @@
 import PyPDF2
 from transformers import pipeline
 import gradio as gr
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
 
-# Step 1: Load the pre-trained model
-# You can choose a suitable model for extracting relevant entities like skills, job titles, etc.
+# Step 1: Load the pre-trained model for Named Entity Recognition (NER)
 model = pipeline('ner', model='dbmdz/bert-large-cased-finetuned-conll03-english')
 
 # Step 2: Extract text from uploaded PDF resume
@@ -16,29 +17,59 @@ def extract_text_from_pdf(pdf_file):
             text += reader.getPage(page).extract_text()
     return text
 
-# Step 3: Resume analysis function
+# Step 3: Extract relevant information (skills, job titles, etc.) from text using the model
 def analyze_resume(resume_text):
     model_output = model(resume_text)
     
-    # Extract relevant information (e.g., skills, job titles)
+    # Extract skills and job titles
     skills = [item['word'] for item in model_output if item['entity'] == 'SKILL']
     job_title = [item['word'] for item in model_output if item['entity'] == 'JOB_TITLE']
     
     # Returning extracted data
     return {'skills': skills, 'job_title': job_title}
 
-# Step 4: Gradio interface function to process the resume
-def process_resume(file):
-    # Extract text from the uploaded resume
-    text = extract_text_from_pdf(file.name)
+# Step 4: Calculate similarity between the job description and the resume
+def calculate_similarity(job_desc, resume_text):
+    # Create a Tfidf Vectorizer to convert text into vectors
+    vectorizer = TfidfVectorizer(stop_words='english')
     
-    # Analyze the resume
-    result = analyze_resume(text)
+    # Combine the job description and resume text into a single list
+    documents = [job_desc, resume_text]
     
+    # Convert the texts into TF-IDF vectors
+    tfidf_matrix = vectorizer.fit_transform(documents)
+    
+    # Compute cosine similarity between job description and resume
+    similarity = cosine_similarity(tfidf_matrix[0:1], tfidf_matrix[1:2])
+    return similarity[0][0]
+
+# Step 5: Check if the resume matches the job description and return "Good Fit" or "Not Fit"
+def match_job_description(job_desc, resume_file):
+    # Extract text from resume
+    resume_text = extract_text_from_pdf(resume_file.name)
+    
+    # Calculate the similarity between job description and resume
+    similarity_score = calculate_similarity(job_desc, resume_text)
+    
+    # If the similarity score is greater than a threshold (e.g., 0.7), it's a good fit
+    if similarity_score >= 0.7:
+        return "Good Fit"
+    else:
+        return "Not Fit"
+
+# Step 6: Gradio Interface function
+def process_resume(job_desc, resume_file):
+    # Match the job description with the uploaded resume
+    result = match_job_description(job_desc, resume_file)
     return result
 
-# Step 5: Create Gradio Interface
-interface = gr.Interface(fn=process_resume, inputs="file", outputs="json")
+# Step 7: Create Gradio Interface
+interface = gr.Interface(
+    fn=process_resume, 
+    inputs=["text", "file"],  # Job Description (text) and Resume (file) as inputs
+    outputs="text",  # Output will be a simple text response (Good Fit / Not Fit)
+    live=True
+)
 
-# Step 6: Launch the app
+# Step 8: Launch the app
 interface.launch()