Upload 3 files

app.py

@@ -0,0 +1,134 @@
+import streamlit as st
+import joblib
+from textblob import TextBlob
+import mammoth
+import pdfplumber
+import io
+import re
+import os
+
+# --- 1. MODEL FUNCTION ---
+def ekkok(text):
+    try:
+        words = TextBlob(str(text)).words
+        return [word.lemmatize() for word in words]
+    except:
+        return str(text).split()
+
+# --- PAGE CONFIG ---
+st.set_page_config(page_title="AI Resume Analyzer", layout="centered", page_icon="🎯")
+
+# --- SECTOR KEYWORDS ---
+SECTOR_KEYWORDS = {
+    "Hospitality & Management": ["hospitality", "restaurant", "hotel", "waiter", "bartender", "bar manager", "chef", "tourism"],
+    "Marketing / Advertising": ["marketing", "advertising", "social media", "branding", "seo", "store manager", "salesman"],
+    "Information Technology": ["software", "developer", "java", "python", "javascript", "cloud", "data science"],
+    "Finance & Accounting": ["finance", "accounting", "audit", "banking", "tax", "budget"],
+    "Human Resources": ["recruitment", "hr", "payroll", "onboarding", "talent acquisition"]
+}
+
+# --- FILE EXTRACTOR ---
+def extract_text(uploaded_file):
+    try:
+        if uploaded_file.name.lower().endswith('.docx'):
+            return mammoth.extract_raw_text(io.BytesIO(uploaded_file.getvalue())).value
+        elif uploaded_file.name.lower().endswith('.pdf'):
+            full_text = ""
+            with pdfplumber.open(io.BytesIO(uploaded_file.getvalue())) as pdf:
+                for page in pdf.pages:
+                    page_text = page.extract_text()
+                    if page_text: full_text += page_text + "\n"
+            return full_text if full_text.strip() else "ERR_SCAN"
+    except: return None
+
+# --- LOAD ASSETS ---
+@st.cache_resource
+def load_assets():
+    m_p, v_p = "best_model.pkl", "tfidf_vectorizer.pkl"
+    if os.path.exists(m_p) and os.path.exists(v_p):
+        try: return joblib.load(m_p), joblib.load(v_p)
+        except: return None, None
+    return None, None
+
+model, vectorizer = load_assets()
+
+# --- BILINGUAL TITLE (İNGİLİZCE & TÜRKÇE BAŞLIK) ---
+st.markdown("""
+    <div style="text-align: center;">
+        <h1 style="color: #1E3A8A; margin-bottom: 0;">🎯 AI Resume Classifier / Akıllı CV Sınıflandırıcı</h1>
+        <p style="color: #666; font-size: 1.1rem; margin-top: 5px;">Automated Department Prediction System / Otomatik Bölüm Tahmin Sistemi</p>
+    </div>
+""", unsafe_allow_html=True)
+
+st.divider()
+
+# --- INPUT SECTION ---
+
+# 1. Metin Girişi
+manual_input = st.text_area("✍️ Paste CV Text / CV Metnini Yapıştırın:", height=150, key="m_input")
+
+# 2. Dosya Yükleme
+uploaded_file = st.file_uploader("📂 Upload CV (PDF/DOCX) / Dosya Yükleyin:", type=['pdf', 'docx'], key="f_input")
+
+# --- VALIDATION ---
+final_cv_text = ""
+
+if manual_input.strip() and uploaded_file:
+    st.error("⚠️ Please use ONLY ONE method! Delete text OR remove file. / Lütfen SADECE BİR yöntem kullanın! Metni silin VEYA dosyayı kaldırın.")
+elif manual_input.strip():
+    final_cv_text = manual_input
+elif uploaded_file:
+    with st.spinner('Reading...'):
+        res = extract_text(uploaded_file)
+        if res == "ERR_SCAN":
+            st.error("❌ This PDF is an image. Please paste text instead. / Bu PDF resimden oluşuyor, lütfen metni kopyalayıp kutuya yapıştırın.")
+        elif res:
+            final_cv_text = res
+            st.success(f"✅ {uploaded_file.name} ready!")
+
+st.divider()
+
+# --- ANALYSIS BUTTON ---
+if st.button("🚀 START ANALYSIS / ANALİZİ BAŞLAT", use_container_width=True):
+    if not final_cv_text or len(final_cv_text.strip()) < 10:
+        st.warning("⚠️ Please provide CV content! / Lütfen CV içeriği sağlayın!")
+    else:
+        with st.spinner('Processing...'):
+            # Email Identity
+            email_id = "NOT FOUND"
+            match = re.search(r'([a-zA-Z0-9_.+-]+)@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+', final_cv_text)
+            if match: email_id = match.group(1).upper()
+
+            # Prediction
+            low_txt = final_cv_text.lower()
+            scores = {s: sum(1 for k in kw if k in low_txt) for s, kw in SECTOR_KEYWORDS.items()}
+            prediction = max(scores, key=scores.get)
+            
+            if scores[prediction] == 0 and model:
+                try: prediction = model.predict(vectorizer.transform([final_cv_text]))[0]
+                except: prediction = "Unclassified"
+
+            st.balloons()
+            st.success("### Results / Sonuçlar")
+            c1, c2 = st.columns(2)
+            c1.metric("Email Identity / E-posta", email_id)
+            c2.metric("Department / Bölüm", prediction)
+
+# --- FOOTER ---
+st.markdown("<br><br><br><hr>", unsafe_allow_html=True)
+footer_html = """
+<div style="display: flex; justify-content: space-between; align-items: center; font-family: sans-serif;">
+    <div style="text-align: left;">
+        <h4 style="margin:0; color: #1E3A8A;">Developed by Data Science Dept.</h4>
+        <p style="margin:0; font-size: 0.8rem; color: #666;">Advanced HR Analytics Solutions</p>
+    </div>
+    <div style="text-align: right;">
+        <h4 style="margin:0; color: #1E3A8A;">Veri Bilimi Departmanı</h4>
+        <p style="margin:0; font-size: 0.8rem; color: #666;">Gelişmiş İK Analitik Çözümleri</p>
+    </div>
+</div>
+<div style="text-align: center; margin-top: 15px; border-top: 1px solid #eee; padding-top: 10px;">
+    <span style="color: #444; font-size: 0.9rem;">Developer / Geliştirici: <b>EsmaTuğba MERGEN</b> | <b>v37.0</b></span>
+</div>
+"""
+st.markdown(footer_html, unsafe_allow_html=True)

best_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be4a35e6e614b78d533da996920d32572a3d41e62fecb76154d80b0ef3a13f1f
+size 1001583

tfidf_vectorizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9682403882e7d81b7dfb2a10b7a6376015771d2f2f028e42df36c9ee446ebe7
+size 191865