Upload 2 files

nrp.py

@@ -0,0 +1,173 @@
+import streamlit as st
+import nltk
+from nltk.corpus import stopwords
+from nltk.tokenize import word_tokenize
+from nltk.stem import PorterStemmer
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+from PyPDF2 import PdfReader
+import os
+from io import BytesIO
+import pickle
+import pdfminer
+from pdfminer.high_level import extract_text
+import re
+import PyPDF2
+import docx
+import textract
+
+nltk.download('punkt')
+nltk.download('stopwords')
+
+def preprocess_text(text):
+    words = word_tokenize(text.lower())
+
+    stop_words = set(stopwords.words('english'))
+    words = [word for word in words if word not in stop_words]
+
+    stemmer = PorterStemmer()
+    words = [stemmer.stem(word) for word in words]
+
+    return ' '.join(words)
+
+import textract
+import tempfile
+
+import fitz  # PyMuPDF
+
+def extract_text_from_pdf(pdf_content):
+    pdf_document = fitz.open(stream=pdf_content, filetype="pdf")
+    text = ""
+    for page_number in range(pdf_document.page_count):
+        page = pdf_document[page_number]
+        text += page.get_text()
+    pdf_document.close()
+    return text
+
+from docx import Document
+
+def extract_text_from_docx(docx_content):
+    doc = Document(BytesIO(docx_content))
+    text = " ".join(paragraph.text for paragraph in doc.paragraphs)
+    return text
+
+
+def extract_text_from_txt(txt_content):
+    text = textract.process(input_filename=None, input_bytes=txt_content)
+    return text
+
+
+def extract_text_from_resume(file_path):
+    file_extension = file_path.split('.')[-1].lower()
+
+    if file_extension == 'pdf':
+        return extract_text_from_pdf(file_path)
+    elif file_extension == 'docx':
+        return extract_text_from_docx(file_path)
+    elif file_extension == 'txt':
+        return extract_text_from_txt(file_path)
+    else:
+        raise ValueError(f"Unsupported file format: {file_extension}")
+
+def clean_pdf_text(text):
+    text = re.sub('http\S+\s*', ' ', text)
+    text = re.sub('RT|cc', ' ', text)
+    text = re.sub('#\S+', '', text)
+    text = re.sub('@\S+', '  ', text)
+    text = re.sub('[%s]' % re.escape("""!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~"""), ' ', text)
+    text = re.sub(r'[^\x00-\x7f]',r' ', text)
+    text = re.sub('\s+', ' ', text)
+    return text
+
+def extract_candidate_name(text):
+    pattern = r'(?:Mr\.|Ms\.|Mrs\.)?\s?([A-Z][a-z]+)\s([A-Z][a-z]+)'
+    match = re.search(pattern, text)
+    if match:
+        return match.group(0)
+    return "Candidate Name Not Found"
+
+def calculate_similarity(job_description, cvs, cv_file_names):
+    processed_job_desc = preprocess_text(job_description)
+
+    processed_cvs = [preprocess_text(cv) for cv in cvs]
+
+    all_text = [processed_job_desc] + processed_cvs
+
+    vectorizer = TfidfVectorizer()
+    tfidf_matrix = vectorizer.fit_transform(all_text)
+
+    similarity_scores = cosine_similarity(tfidf_matrix)[0][1:]
+
+    ranked_cvs = list(zip(cv_file_names, similarity_scores))
+    ranked_cvs.sort(key=lambda x: x[1], reverse=True)
+
+    return ranked_cvs
+
+def rank_and_shortlist(job_description, cv_files, threshold=0.15):
+    cv_texts = []
+    cv_file_names = []
+
+    for cv_file in cv_files:
+        file_extension = os.path.splitext(cv_file.name)[1].lower()
+
+        try:
+            if file_extension == '.pdf':
+                cv_text = extract_text_from_pdf(cv_file.read())
+            elif file_extension == '.docx':
+                cv_text = extract_text_from_docx(cv_file.read())
+            elif file_extension == '.txt':
+                cv_text = cv_file.read().decode('utf-8', errors='ignore')
+            else:
+                st.warning(f"Unsupported file format: {file_extension}. Skipping file: {cv_file.name}")
+                continue
+
+            cv_texts.append(clean_pdf_text(cv_text))
+            cv_file_names.append(cv_file.name)
+
+        except Exception as e:
+            st.warning(f"Error processing file '{cv_file.name}': {str(e)}")
+            continue
+
+    if not cv_texts:
+        st.error("No valid resumes found. Please upload resumes in supported formats (PDF, DOCX, or TXT).")
+        return [], []
+
+    similarity_scores = calculate_similarity(job_description, cv_texts, cv_file_names)
+
+    ranked_cvs = [(cv_name, score) for (cv_name, score) in similarity_scores]
+    shortlisted_cvs = [(cv_name, score) for (cv_name, score) in ranked_cvs if score >= threshold]
+
+    return ranked_cvs, shortlisted_cvs
+
+
+def main():
+    st.title("Resume Ranking App")
+
+    st.write("Upload the Job Description:")
+    job_description = st.text_area("Job Description", height=200, key='job_description')
+
+    st.write("Upload the Resumes :")
+    cv_files = st.file_uploader("Choose files", accept_multiple_files=True, key='cv_files')
+
+    if st.button("Submit"):
+        if job_description and cv_files:
+            # Rank and shortlist candidates
+            ranked_cvs, shortlisted_cvs = rank_and_shortlist(job_description, cv_files)
+
+            # Display ranking with larger text
+            st.markdown("### Ranking of Resumes:")
+            for rank, score in ranked_cvs:
+                st.markdown(f"**File Name:** {rank}, **Similarity Score:** {score:.2f}")
+
+            # Display shortlisted candidates with larger text
+            st.markdown("### Shortlisted Candidates:")
+            if not shortlisted_cvs:  # Check if the shortlisted_cvs list is empty
+                st.markdown("None")
+            else:
+                for rank, score in shortlisted_cvs:
+                    st.markdown(f"**File Name:** {rank}, **Similarity Score:** {score:.2f}")
+    else:
+        st.write("Please upload both the job description and resumes to proceed.")
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -1,5 +1,8 @@
-streamlit
+docx
+fitz
 nltk
-scikit-learn
+pdfminer.six
 PyPDF2
-pdfminer.six
+scikit-learn
+streamlit
+textract