Upload 3 files

README.md

@@ -1,13 +1,93 @@
----
-title: Advance ATS System
-emoji: 🏢
-colorFrom: purple
-colorTo: purple
-sdk: gradio
-sdk_version: 6.4.0
-app_file: app.py
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# ATS Resume Scorer
+
+An AI-powered tool to analyze resume-job description compatibility using ATS (Applicant Tracking System) scoring and skill matching.
+
+## 🚀 Features
+
+- **PDF Resume Upload**: Extract text from PDF resumes using pdfplumber
+- **Job Description Input**: Paste job descriptions for comparison
+- **ATS Match Scoring**: Calculate similarity score using TF-IDF vectorization and cosine similarity
+- **Skill Matching**: Identify matched and missing skills from a predefined list
+- **Interactive UI**: Clean Streamlit interface with progress bars and color-coded tags
+- **Error Handling**: Graceful handling of invalid PDFs, empty inputs, and extraction failures
+
+## 🛠️ Tech Stack
+
+- **Frontend/UI**: Streamlit
+- **PDF Processing**: pdfplumber
+- **NLP Processing**: NLTK (tokenization, stopwords, lemmatization)
+- **Machine Learning**: scikit-learn (TF-IDF, Cosine Similarity)
+- **Python**: Core language
+
+## 📁 Project Structure
+
+```
+ATS-Resume-Scorer/
+├── app.py                 # Main Streamlit application
+├── utils/
+│   ├── text_extraction.py # PDF text extraction utilities
+│   ├── preprocessing.py   # Text preprocessing (lowercase, punctuation, stopwords, lemmatization)
+│   ├── scoring.py         # ATS score calculation using TF-IDF and cosine similarity
+│   └── skill_matcher.py   # Skill matching against predefined list
+├── data/
+│   └── skills.txt         # Predefined list of skills for matching
+├── requirements.txt       # Python dependencies
+└── README.md             # Project documentation
+```
+
+## 🏃‍♂️ How to Run Locally
+
+1. **Clone or download the project**:
+   ```bash
+   cd /path/to/your/workspace
+   # Place the ATS-Resume-Scorer folder here
+   ```
+
+2. **Install dependencies**:
+   ```bash
+   cd ATS-Resume-Scorer
+   pip install -r requirements.txt
+   ```
+
+3. **Run the application**:
+   ```bash
+   streamlit run app.py
+   ```
+
+4. **Open your browser** and go to `http://localhost:8501`
+
+## ☁️ Deploy on Streamlit Cloud
+
+1. **Fork or upload to GitHub**: Ensure all files are in a GitHub repository.
+
+2. **Go to Streamlit Cloud**: Visit [share.streamlit.io](https://share.streamlit.io)
+
+3. **Connect your GitHub repo**: Select the repository containing this project.
+
+4. **Deploy**: Choose `app.py` as the main file and click deploy.
+
+5. **Access your app**: Once deployed, you'll get a public URL to access the application.
+
+## 📝 Usage
+
+1. Upload a PDF resume using the file uploader.
+2. Paste the job description text in the text area.
+3. Click "Analyze" to get:
+   - ATS match score (0-100%)
+   - Visual progress bar
+   - Matched skills (green tags)
+   - Missing skills (red tags)
+
+## 🔧 Customization
+
+- **Skills List**: Edit `data/skills.txt` to add or modify the predefined skills for matching.
+- **Preprocessing**: Modify `utils/preprocessing.py` to adjust text cleaning steps.
+- **Scoring Algorithm**: Enhance `utils/scoring.py` for more advanced similarity measures.
+
+## 🤝 Contributing
+
+Feel free to fork this project and submit pull requests for improvements!
+
+## 📄 License
+
+This project is open-source and available under the MIT License.

app.py

@@ -0,0 +1,110 @@
+import streamlit as st
+import tempfile, os
+import pandas as pd
+
+os.chdir(os.path.dirname(__file__))
+
+from utils.text_extraction import extract_text_from_pdf
+from utils.preprocessing import preprocess_text
+from utils.experience_extractor import extract_experience_years
+from utils.skill_matcher import load_skills, skill_percentage
+from utils.bert_matcher import bert_similarity
+from utils.scoring import final_ats_score
+
+# ---------------- PAGE CONFIG ----------------
+st.set_page_config(
+    page_title="Smart ATS Shortlisting System",
+    layout="wide"
+)
+
+st.title("🤖 Smart BERT-Based ATS Resume Shortlister")
+
+# ---------------- FILE UPLOADERS ----------------
+jd_file = st.file_uploader(
+    "Upload Job Description (PDF)",
+    type=["pdf"],
+    accept_multiple_files=False
+)
+
+resumes = st.file_uploader(
+    "Upload Resumes (Multiple PDFs)",
+    type=["pdf"],
+    accept_multiple_files=True
+)
+
+SHORTLIST_THRESHOLD = 60
+
+# ---------------- MAIN LOGIC ----------------
+if st.button("Analyze Resumes"):
+
+    if not jd_file or not resumes:
+        st.error("Please upload Job Description and at least one Resume")
+        st.stop()
+
+    # -------- JD PROCESSING --------
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as f:
+        f.write(jd_file.read())
+        jd_path = f.name
+
+    jd_text = extract_text_from_pdf(jd_path)
+    jd_clean = preprocess_text(jd_text)
+    os.unlink(jd_path)
+
+    skills = load_skills("data/skills.txt")
+    results = []
+
+    # -------- PROCESS EACH RESUME --------
+    for resume_file in resumes:
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as rf:
+            rf.write(resume_file.read())
+            resume_path = rf.name
+
+        resume_text = extract_text_from_pdf(resume_path)
+        os.unlink(resume_path)
+
+        if not resume_text.strip():
+            continue
+
+        resume_clean = preprocess_text(resume_text)
+
+        # -------- SCORES --------
+        bert_score = bert_similarity(jd_clean, resume_clean)
+        skill_pct, matched_skills = skill_percentage(resume_text, skills)
+        experience = extract_experience_years(resume_text)
+
+        final_score = final_ats_score(
+            bert_score,
+            skill_pct,
+            experience
+        )
+
+        status = "✅ Selected" if final_score >= SHORTLIST_THRESHOLD else "❌ Rejected"
+
+        results.append({
+            "Resume Name": resume_file.name,
+            "ATS %": final_score,
+            "BERT Match %": bert_score,
+            "Skill Match %": skill_pct,
+            "Experience (Years)": experience,
+            "Status": status,
+            "Matched Skills": ", ".join(matched_skills) if matched_skills else "None"
+        })
+
+    # -------- FINAL OUTPUT --------
+    if not results:
+        st.warning("No resumes could be processed")
+        st.stop()
+
+    df = pd.DataFrame(results).sort_values("ATS %", ascending=False)
+
+    st.subheader("📊 Resume Shortlisting Result")
+    st.dataframe(df, use_container_width=True)
+
+    st.success(f"✅ Shortlist Threshold: {SHORTLIST_THRESHOLD}%")
+
+    st.download_button(
+        "⬇️ Download Result CSV",
+        df.to_csv(index=False),
+        "ATS_Shortlisting_Result.csv",
+        "text/csv"
+    )

requirements.txt

@@ -0,0 +1,7 @@
+streamlit
+pdfplumber
+nltk
+scikit-learn
+sentence-transformers
+pandas
+torch