Upload 2 files

app.py

@@ -0,0 +1,73 @@
+import streamlit as st
+from PyPDF2 import PdfReader
+from sklearn.feature_extraction.text import TfidfVectorizer
+import spacy
+
+# Load spaCy model
+nlp = spacy.load('en_core_web_sm')
+
+# Function to extract text from PDF resumes
+def extract_text_from_pdf(file):
+    text = ""
+    pdf_reader = PdfReader(file)
+    for page in pdf_reader.pages:
+        text += page.extract_text()
+    return text
+
+# Function to preprocess text using spaCy
+def preprocess_text(text):
+    doc = nlp(text)
+    tokens = [token.lemma_ for token in doc if not token.is_stop and token.is_alpha]
+    return " ".join(tokens)
+
+# Main function to create the Streamlit app
+def main():
+    st.title("Resume Ranker and Prescreening Software")
+    st.write("Upload resumes (in PDF format) and enter job descriptions or keywords to filter and rank them.")
+
+    # Upload resumes
+    uploaded_files = st.file_uploader("Upload Resumes (PDF files)", accept_multiple_files=True)
+    
+    # Input field for job description or keywords
+    job_description = st.text_area("Enter Job Description or Keywords")
+
+    if st.button("Rank Resumes"):
+        if not uploaded_files:
+            st.warning("Please upload one or more resumes.")
+            return
+        
+        if not job_description:
+            st.warning("Please enter a job description or keywords.")
+            return
+        
+        # Preprocess the job description
+        job_description_processed = preprocess_text(job_description)
+        
+        # Vectorize job description and resumes
+        vectorizer = TfidfVectorizer()
+        job_vec = vectorizer.fit_transform([job_description_processed])
+        resume_texts = []
+        resume_vecs = []
+        for file in uploaded_files:
+            # Parse and preprocess resumes
+            text = extract_text_from_pdf(file)
+            text_processed = preprocess_text(text)
+            resume_texts.append(text_processed)
+            resume_vecs.append(vectorizer.transform([text_processed]))
+
+        # Calculate similarity scores
+        similarities = []
+        for i, resume_vec in enumerate(resume_vecs):
+            similarity = (resume_vec * job_vec.T).A[0][0]
+            similarities.append((uploaded_files[i].name, similarity))
+
+        # Sort resumes by similarity
+        similarities.sort(key=lambda x: x[1], reverse=True)
+
+        # Display sorted resumes with matching percentage
+        st.header("Ranked Resumes")
+        for resume, similarity in similarities:
+            st.write(f"Resume: {resume}, Match Percentage: {similarity * 100:.2f}%")
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,69 @@
+altair==5.3.0
+annotated-types==0.7.0
+attrs==23.2.0
+blinker==1.8.2
+blis==0.7.11
+cachetools==5.3.3
+catalogue==2.0.10
+certifi==2024.2.2
+charset-normalizer==3.3.2
+click==8.1.7
+cloudpathlib==0.16.0
+confection==0.1.4
+cymem==2.0.8
+en-core-web-sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.7.1/en_core_web_sm-3.7.1-py3-none-any.whl
+gitdb==4.0.11
+GitPython==3.1.43
+idna==3.7
+Jinja2==3.1.4
+joblib==1.4.2
+jsonschema==4.22.0
+jsonschema-specifications==2023.12.1
+langcodes==3.4.0
+language_data==1.2.0
+marisa-trie==1.1.1
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+mdurl==0.1.2
+murmurhash==1.0.10
+numpy==1.26.4
+packaging==24.0
+pandas==2.2.2
+pillow==10.3.0
+preshed==3.0.9
+protobuf==4.25.3
+pyarrow==16.1.0
+pydantic==2.7.1
+pydantic_core==2.18.2
+pydeck==0.9.1
+Pygments==2.18.0
+PyPDF2==3.0.1
+python-dateutil==2.9.0.post0
+pytz==2024.1
+referencing==0.35.1
+requests==2.32.2
+rich==13.7.1
+rpds-py==0.18.1
+scikit-learn==1.5.0
+scipy==1.13.1
+six==1.16.0
+smart-open==6.4.0
+smmap==5.0.1
+spacy==3.7.4
+spacy-legacy==3.0.12
+spacy-loggers==1.0.5
+srsly==2.4.8
+streamlit==1.35.0
+tenacity==8.3.0
+thinc==8.2.3
+threadpoolctl==3.5.0
+toml==0.10.2
+toolz==0.12.1
+tornado==6.4
+tqdm==4.66.4
+typer==0.9.4
+typing_extensions==4.12.0
+tzdata==2024.1
+urllib3==2.2.1
+wasabi==1.1.2
+weasel==0.3.4