test.py

# import os

# # ---------------- SAFE CACHE ----------------
# os.environ["HF_HOME"] = "/tmp/hf"
# os.environ["TRANSFORMERS_CACHE"] = "/tmp/hf"
# os.environ["TORCH_HOME"] = "/tmp/torch"

# # ---------------- IMPORTS ----------------
# import streamlit as st
# import pdfplumber
# import re
# import pandas as pd
# import spacy
# import json

# from keybert import KeyBERT
# from sentence_transformers import SentenceTransformer, util
# from streamlit_lottie import st_lottie

# # =========================================================
# # PAGE CONFIG
# # =========================================================
# st.set_page_config(
#     page_title="AI Resume ATS Matcher",
#     page_icon="📄",
#     layout="wide"
# )

# # =========================================================
# # CUSTOM CSS (LIGHT MODERN UI)
# # =========================================================
# st.markdown("""
# <style>

# /* Main Background */
# .stApp {
#     background-color: #f8fafc;
# }

# /* Header */
# .main-title {
#     font-size: 42px;
#     font-weight: 800;
#     color: #111827;
#     text-align: center;
#     margin-bottom: 5px;
# }

# .sub-title {
#     font-size: 18px;
#     color: #6b7280;
#     text-align: center;
#     margin-bottom: 30px;
# }

# /* Upload Box */
# .upload-box {
#     background: white;
#     padding: 25px;
#     border-radius: 18px;
#     border: 1px solid #e5e7eb;
#     box-shadow: 0px 2px 10px rgba(0,0,0,0.04);
#     margin-bottom: 20px;
# }

# /* Candidate Card */
# .candidate-card {
#     background: white;
#     padding: 20px;
#     border-radius: 18px;
#     border: 1px solid #e5e7eb;
#     margin-bottom: 20px;
#     box-shadow: 0px 2px 10px rgba(0,0,0,0.05);
# }

# /* Skill Tags */
# .skill-tag {
#     display: inline-block;
#     background: #eff6ff;
#     color: #2563eb;
#     padding: 6px 12px;
#     border-radius: 30px;
#     margin: 4px;
#     font-size: 13px;
#     font-weight: 500;
# }

# /* Buttons */
# .stButton > button {
#     width: 100%;
#     height: 55px;
#     border-radius: 14px;
#     background-color: #2563eb;
#     color: white;
#     font-size: 18px;
#     font-weight: 700;
#     border: none;
# }

# .stButton > button:hover {
#     background-color: #1d4ed8;
#     color: white;
# }

# /* Dataframe */
# [data-testid="stDataFrame"] {
#     border-radius: 15px;
#     overflow: hidden;
# }

# /* Hide Streamlit Footer */
# footer {
#     visibility: hidden;
# }

# </style>
# """, unsafe_allow_html=True)

# # =========================================================
# # LOAD MODELS
# # =========================================================
# @st.cache_resource
# def load_models():

#     model = SentenceTransformer("all-MiniLM-L6-v2")

#     nlp = spacy.load("en_core_web_sm")

#     kw_model = KeyBERT(model=model)

#     return model, nlp, kw_model


# model, nlp, kw_model = load_models()

# # =========================================================
# # LOAD ANIMATION
# # =========================================================
# def load_lottiefile(filepath):

#     try:
#         with open(filepath, "r") as f:
#             return json.load(f)

#     except:
#         return None


# lottie_animation = load_lottiefile("Animation.json")

# # =========================================================
# # HEADER
# # =========================================================
# if lottie_animation:
#     st_lottie(lottie_animation, height=180)

# st.markdown(
#     '<div class="main-title">🤖 AI Resume ATS </div>',
#     unsafe_allow_html=True
# )

# st.markdown(
#     '<div class="sub-title">Upload multiple resumes and instantly rank the best candidates</div>',
#     unsafe_allow_html=True
# )

# # =========================================================
# # HELPERS
# # =========================================================
# def extract_text_from_pdf(pdf_file):

#     text = ""

#     with pdfplumber.open(pdf_file) as pdf:

#         for page in pdf.pages:

#             page_text = page.extract_text()

#             if page_text:
#                 text += page_text + "\n"

#     return text.strip()


# def clean_text(text):

#     return re.sub(r"\s+", " ", text).strip()


# def extract_skills_auto(text, top_n=15):

#     text = text[:3000]

#     keywords = kw_model.extract_keywords(
#         text,
#         keyphrase_ngram_range=(1, 3),
#         stop_words='english',
#         top_n=top_n
#     )

#     return [kw[0] for kw in keywords]


# def calculate_similarity(text1, text2):

#     emb1 = model.encode(text1, convert_to_tensor=True)

#     emb2 = model.encode(text2, convert_to_tensor=True)

#     score = util.pytorch_cos_sim(
#         emb1,
#         emb2
#     ).item()

#     return round(score * 100, 2)

# # =========================================================
# # INPUT SECTION
# # =========================================================
# #st.markdown('<div class="upload-box">', unsafe_allow_html=True)

# st.markdown("### 📄 Upload Resumes")

# resume_files = st.file_uploader(
#     "Upload Multiple PDF Resumes",
#     type=["pdf"],
#     accept_multiple_files=True
# )

# st.markdown("### 📝 Paste Job Description")

# job_description = st.text_area(
#     "Enter Job Description",
#     height=220,
#     placeholder="Paste the job description here..."
# )

# st.markdown('</div>', unsafe_allow_html=True)

# # =========================================================
# # MATCH BUTTON
# # =========================================================
# if st.button("🚀 Match Resumes"):

#     if resume_files and job_description:

#         with st.spinner("Analyzing resumes..."):

#             jd_skills = extract_skills_auto(job_description)

#             results = []

#             progress_bar = st.progress(0)

#             total_files = len(resume_files)

#             # =========================================================
#             # PROCESS RESUMES
#             # =========================================================
#             for idx, resume_file in enumerate(resume_files):

#                 try:

#                     resume_text = clean_text(
#                         extract_text_from_pdf(resume_file)
#                     )

#                     resume_skills = extract_skills_auto(
#                         resume_text
#                     )

#                     score = calculate_similarity(
#                         " ".join(resume_skills),
#                         " ".join(jd_skills)
#                     )

#                     results.append({
#                         "Resume": resume_file.name,
#                         "ATS Score": score,
#                         "Skills": resume_skills[:8]
#                     })

#                 except Exception as e:

#                     results.append({
#                         "Resume": resume_file.name,
#                         "ATS Score": 0,
#                         "Skills": [f"Error: {str(e)}"]
#                     })

#                 progress_bar.progress((idx + 1) / total_files)

#             # =========================================================
#             # SORT RESULTS
#             # =========================================================
#             results = sorted(
#                 results,
#                 key=lambda x: x["ATS Score"],
#                 reverse=True
#             )

#             # =========================================================
#             # TOP STATS
#             # =========================================================
#             st.markdown("## 📊 ATS Analytics")

#             col1, col2, col3 = st.columns(3)

#             with col1:
#                 st.metric(
#                     "Total Resumes",
#                     len(results)
#                 )

#             with col2:
#                 st.metric(
#                     "Top ATS Score",
#                     f"{results[0]['ATS Score']}%"
#                 )

#             with col3:
#                 avg_score = round(
#                     sum(r["ATS Score"] for r in results) / len(results),
#                     2
#                 )

#                 st.metric(
#                     "Average Score",
#                     f"{avg_score}%"
#                 )

#             st.divider()

#             # =========================================================
#             # TABLE
#             # =========================================================
#             st.markdown("## 🏆 Candidate Rankings")

#             table_data = []

#             for idx, item in enumerate(results, start=1):

#                 table_data.append({
#                     "Rank": idx,
#                     "Resume": item["Resume"],
#                     "ATS Score": f"{item['ATS Score']}%"
#                 })

#             df = pd.DataFrame(table_data)

#             st.dataframe(
#                 df,
#                 use_container_width=True
#             )

#             # =========================================================
#             # TOP CANDIDATES
#             # =========================================================
#             st.markdown("## ⭐ Best Candidates")

#             top_candidates = results[:5]

#             for idx, candidate in enumerate(top_candidates, start=1):

#                 score = candidate["ATS Score"]

#                 # Status
#                 if score >= 85:
#                     status = "Excellent Match ✅"

#                 elif score >= 65:
#                     status = "Good Match 👍"

#                 else:
#                     status = "Average Match ⚠️"

#                 # CARD
#                 st.markdown(
#                     '<div class="candidate-card">',
#                     unsafe_allow_html=True
#                 )

#                 col1, col2 = st.columns([1, 5])

#                 # LEFT
#                 with col1:

#                     st.metric(
#                         label=f"🏅 Rank #{idx}",
#                         value=f"{score}%"
#                     )

#                 # RIGHT
#                 with col2:

#                     st.markdown(
#                         f"### 📄 {candidate['Resume']}"
#                     )

#                     st.progress(score / 100)

#                     st.markdown(
#                         f"**Status:** {status}"
#                     )

#                     st.markdown("#### 🛠 Matching Skills")

#                     skill_html = ""

#                     for skill in candidate["Skills"]:

#                         skill_html += f"""
#                         <span class="skill-tag">
#                         {skill}
#                         </span>
#                         """

#                     st.markdown(
#                         skill_html,
#                         unsafe_allow_html=True
#                     )

#                 st.markdown(
#                     '</div>',
#                     unsafe_allow_html=True
#                 )

#             # =========================================================
#             # DOWNLOAD CSV
#             # =========================================================
#             csv = pd.DataFrame(results).to_csv(index=False).encode("utf-8")

#             st.download_button(
#                 label="📥 Download ATS Report CSV",
#                 data=csv,
#                 file_name="ats_report.csv",
#                 mime="text/csv"
#             )

#     else:

#         st.warning(
#             "⚠️ Please upload resumes and enter a job description."
#         )

# # =========================================================
# # FOOTER
# # =========================================================
# st.markdown("""
# <br><br>
# <hr>
# <p style='text-align:center; color:gray;'>
# Developed by <b>Ashvinkumar Bari</b> • AI Resume Screening Platform
# </p>
# """, unsafe_allow_html=True)