Upload 11 files

.gitattributes

@@ -1,35 +1 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,2 @@
+clf.pkl
+*.pkl

app.py

@@ -0,0 +1,476 @@
+import streamlit as st
+import pickle
+import re
+import docx
+import PyPDF2
+from sklearn.metrics.pairwise import cosine_similarity
+
+# 1. CONFIG
+st.set_page_config(
+    page_title="AI Resume Screening",
+    layout="wide",
+    initial_sidebar_state="collapsed"
+)
+
+# Custom CSS for styling
+st.markdown("""
+<style>
+    /* Main background */
+    .stApp {
+        background: linear-gradient(135deg, #0f0f0f 0%, #1a1a1a 100%);
+    }
+    
+    /* Main container styling */
+    .main .block-container {
+        padding-top: 2rem;
+        padding-bottom: 2rem;
+        max-width: 1200px;
+    }
+    
+    /* Header styling */
+    h1 {
+        color: #ffffff !important;
+        font-weight: 700 !important;
+        text-align: center;
+        font-size: 3rem !important;
+        margin-bottom: 0.5rem !important;
+        text-shadow: 2px 2px 8px rgba(0,0,0,0.5);
+    }
+    
+    .subtitle {
+        color: #a0a0a0;
+        text-align: center;
+        font-size: 1.1rem;
+        margin-bottom: 2rem;
+    }
+    
+    /* Remove default streamlit styling */
+    .element-container {
+        background: transparent !important;
+    }
+    
+    /* File uploader styling */
+    section[data-testid="stFileUploader"] {
+        background: rgba(30, 30, 30, 0.6);
+        border: 2px dashed #404040;
+        border-radius: 15px;
+        padding: 2rem;
+        backdrop-filter: blur(10px);
+    }
+    
+    section[data-testid="stFileUploader"]:hover {
+        border-color: #606060;
+        background: rgba(35, 35, 35, 0.7);
+    }
+    
+    section[data-testid="stFileUploader"] label {
+        color: #e0e0e0 !important;
+        font-size: 1.1rem !important;
+        font-weight: 600 !important;
+    }
+    
+    /* Metric cards */
+    div[data-testid="metric-container"] {
+        background: linear-gradient(135deg, #2a2a2a 0%, #1f1f1f 100%);
+        border: 1px solid #404040;
+        border-radius: 15px;
+        padding: 1.5rem;
+        box-shadow: 0 4px 20px rgba(0, 0, 0, 0.5);
+    }
+    
+    div[data-testid="metric-container"] label {
+        color: #b0b0b0 !important;
+        font-weight: 600 !important;
+        font-size: 0.9rem !important;
+    }
+    
+    div[data-testid="metric-container"] div[data-testid="stMetricValue"] {
+        color: #ffffff !important;
+        font-size: 2rem !important;
+        font-weight: 700 !important;
+    }
+    
+    div[data-testid="metric-container"] div[data-testid="stMetricDelta"] {
+        color: #808080 !important;
+    }
+    
+    /* Success box styling */
+    .stSuccess {
+        background: rgba(40, 40, 40, 0.8);
+        color: #e0e0e0;
+        border-left: 4px solid #606060;
+        border-radius: 10px;
+        padding: 1.5rem;
+        box-shadow: 0 4px 15px rgba(0, 0, 0, 0.3);
+    }
+    
+    .stSuccess h3 {
+        color: #ffffff !important;
+    }
+    
+    /* Warning box styling */
+    .stWarning {
+        background: rgba(50, 40, 40, 0.8);
+        color: #e0e0e0;
+        border-left: 4px solid #707070;
+        border-radius: 10px;
+        padding: 1.5rem;
+        box-shadow: 0 4px 15px rgba(0, 0, 0, 0.3);
+    }
+    
+    /* Info box styling */
+    .stInfo {
+        background: rgba(40, 40, 40, 0.8);
+        color: #e0e0e0;
+        border-left: 4px solid #606060;
+        border-radius: 10px;
+        padding: 1.5rem;
+        box-shadow: 0 4px 15px rgba(0, 0, 0, 0.3);
+    }
+    
+    /* Progress bar */
+    .stProgress > div > div > div {
+        background: linear-gradient(90deg, #505050 0%, #707070 100%);
+        border-radius: 10px;
+    }
+    
+    /* Expander */
+    .streamlit-expanderHeader {
+        background: rgba(40, 40, 40, 0.6);
+        border: 1px solid #404040;
+        border-radius: 10px;
+        color: #e0e0e0 !important;
+        font-weight: 600;
+    }
+    
+    .streamlit-expanderContent {
+        background: rgba(30, 30, 30, 0.8);
+        border: 1px solid #404040;
+        border-radius: 0 0 10px 10px;
+    }
+    
+    /* Text area */
+    textarea {
+        background: #1a1a1a !important;
+        color: #e0e0e0 !important;
+        border: 1px solid #404040 !important;
+        border-radius: 8px !important;
+    }
+    
+    /* Custom Loading Animation */
+    .loading-container {
+        display: flex;
+        flex-direction: column;
+        align-items: center;
+        justify-content: center;
+        padding: 3rem;
+        margin: 2rem 0;
+    }
+    
+    .spinner {
+        width: 60px;
+        height: 60px;
+        border: 4px solid #2a2a2a;
+        border-top: 4px solid #707070;
+        border-radius: 50%;
+        animation: spin 1s linear infinite;
+    }
+    
+    @keyframes spin {
+        0% { transform: rotate(0deg); }
+        100% { transform: rotate(360deg); }
+    }
+    
+    .loading-text {
+        color: #b0b0b0;
+        font-size: 1.1rem;
+        margin-top: 1.5rem;
+        font-weight: 600;
+        animation: pulse 1.5s ease-in-out infinite;
+    }
+    
+    @keyframes pulse {
+        0%, 100% { opacity: 0.6; }
+        50% { opacity: 1; }
+    }
+    
+    .loading-dots {
+        display: inline-block;
+        margin-left: 5px;
+    }
+    
+    .loading-dots span {
+        animation: blink 1.4s infinite;
+        animation-fill-mode: both;
+    }
+    
+    .loading-dots span:nth-child(2) {
+        animation-delay: 0.2s;
+    }
+    
+    .loading-dots span:nth-child(3) {
+        animation-delay: 0.4s;
+    }
+    
+    @keyframes blink {
+        0%, 80%, 100% { opacity: 0; }
+        40% { opacity: 1; }
+    }
+    
+    .progress-bar-container {
+        width: 300px;
+        height: 4px;
+        background: #2a2a2a;
+        border-radius: 2px;
+        margin-top: 1rem;
+        overflow: hidden;
+    }
+    
+    .progress-bar-fill {
+        height: 100%;
+        background: linear-gradient(90deg, #505050, #707070, #505050);
+        background-size: 200% 100%;
+        animation: loading 1.5s ease-in-out infinite;
+    }
+    
+    @keyframes loading {
+        0% { background-position: 200% 0; }
+        100% { background-position: -200% 0; }
+    }
+    
+    /* Spinner */
+    .stSpinner > div {
+        border-top-color: #707070 !important;
+    }
+    
+    /* Hide Streamlit branding */
+    #MainMenu {visibility: hidden;}
+    footer {visibility: hidden;}
+    
+    /* Score badge */
+    .score-badge {
+        display: inline-block;
+        padding: 0.75rem 2rem;
+        border-radius: 25px;
+        font-weight: 700;
+        font-size: 1.5rem;
+        margin: 1.5rem 0;
+        box-shadow: 0 4px 15px rgba(0, 0, 0, 0.4);
+    }
+    
+    .score-high {
+        background: linear-gradient(135deg, #3a3a3a 0%, #4a4a4a 100%);
+        color: #ffffff;
+        border: 2px solid #606060;
+    }
+    
+    .score-medium {
+        background: linear-gradient(135deg, #353535 0%, #454545 100%);
+        color: #e0e0e0;
+        border: 2px solid #555555;
+    }
+    
+    .score-low {
+        background: linear-gradient(135deg, #2f2f2f 0%, #3f3f3f 100%);
+        color: #d0d0d0;
+        border: 2px solid #505050;
+    }
+    
+    /* Section headers */
+    h3, h4 {
+        color: #e0e0e0 !important;
+    }
+    
+    /* Remove white backgrounds */
+    div[data-testid="stVerticalBlock"] > div {
+        background: transparent !important;
+    }
+    
+    div[data-testid="column"] {
+        background: transparent !important;
+    }
+</style>
+""", unsafe_allow_html=True)
+
+# 2. LOAD RESOURCES
+@st.cache_resource
+def load_resources():
+    try:
+        clf = pickle.load(open('clf.pkl', 'rb'))
+        tfidf = pickle.load(open('tfidf.pkl', 'rb'))
+        le = pickle.load(open('encoder.pkl', 'rb'))
+        ats = pickle.load(open('ats_scorer.pkl', 'rb'))
+        prototypes = pickle.load(open('prototypes.pkl', 'rb'))
+        return clf, tfidf, le, ats, prototypes
+    except FileNotFoundError:
+        return None, None, None, None, None
+
+clf, tfidf, le, ats_model, prototypes = load_resources()
+
+# 3. UTILS
+def clean_text(txt):
+    txt = re.sub(r'http\S+\s', ' ', txt)
+    txt = re.sub(r'[^\w\s]', ' ', txt)
+    return txt.lower()
+
+def extract_text(file):
+    try:
+        if file.name.endswith('.pdf'):
+            reader = PyPDF2.PdfReader(file)
+            return " ".join([page.extract_text() for page in reader.pages])
+        elif file.name.endswith('.docx'):
+            doc = docx.Document(file)
+            return " ".join([p.text for p in doc.paragraphs])
+        elif file.name.endswith('.txt'):
+            return file.read().decode('utf-8')
+    except:
+        return ""
+
+def calculate_scores(text, category):
+    if category not in prototypes:
+        return 0, 0, 0
+    
+    master_profile = prototypes[category]
+    cleaned_resume = clean_text(text)
+    
+    # Cosine Similarity
+    vecs = tfidf.transform([cleaned_resume, master_profile])
+    cosine_sim = cosine_similarity(vecs[0], vecs[1])[0][0]
+    
+    # Keyword Match
+    res_tokens = set(cleaned_resume.split())
+    mp_tokens = set(master_profile.split())
+    keyword_match = len(res_tokens.intersection(mp_tokens)) / len(mp_tokens) if mp_tokens else 0
+    
+    # AI Prediction
+    try:
+        ml_score = ats_model.predict([[cosine_sim, keyword_match]])[0]
+    except:
+        ml_score = 0
+    
+    # Fallback Logic
+    if ml_score < 10:
+        final_score = cosine_sim * 100
+    else:
+        final_score = ml_score
+    if final_score < 1:
+        final_score *= 100
+        
+    return round(final_score, 1), round(cosine_sim*100, 1), round(keyword_match*100, 1)
+
+# 4. MAIN APP
+def main():
+    # Header
+    st.markdown("<h1>🎯 AI Resume Screening</h1>", unsafe_allow_html=True)
+    st.markdown("<p class='subtitle'>Powered by Machine Learning & Natural Language Processing</p>", unsafe_allow_html=True)
+    
+    if not clf:
+        st.error("⚠️ Models missing! Run `train_model.py` then `train_ats_model.py`.")
+        st.stop()
+    
+    # Upload section
+    st.markdown("<br>", unsafe_allow_html=True)
+    col1, col2, col3 = st.columns([1, 2, 1])
+    with col2:
+        file = st.file_uploader(
+            "📤 Upload Your Resume",
+            type=['pdf', 'docx', 'txt'],
+            help="Supported formats: PDF, DOCX, TXT"
+        )
+    
+    if file:
+        # Custom loading animation
+        loading_placeholder = st.empty()
+        
+        with loading_placeholder.container():
+            st.markdown("""
+            <div class='loading-container'>
+                <div class='spinner'></div>
+                <div class='loading-text'>
+                    Analyzing your resume<span class='loading-dots'><span>.</span><span>.</span><span>.</span></span>
+                </div>
+                <div class='progress-bar-container'>
+                    <div class='progress-bar-fill'></div>
+                </div>
+            </div>
+            """, unsafe_allow_html=True)
+        
+        # Extract and process
+        text = extract_text(file)
+        
+        # Clear loading animation
+        loading_placeholder.empty()
+            
+        if len(text) > 20:
+            clean = clean_text(text)
+            vec = tfidf.transform([clean])
+            cat_id = clf.predict(vec)[0]
+            category = le.inverse_transform([cat_id])[0]
+            
+            ats_score, raw_sim, key_match = calculate_scores(text, category)
+            
+            st.markdown("<br>", unsafe_allow_html=True)
+            
+            # Category prediction
+            st.success(f"### 🎯 Predicted Role: **{category}**")
+            
+            # Score badge
+            if ats_score >= 75:
+                badge_class = "score-high"
+                emoji = "🌟"
+            elif ats_score >= 50:
+                badge_class = "score-medium"
+                emoji = "⚡"
+            else:
+                badge_class = "score-low"
+                emoji = "💡"
+            
+            st.markdown(f"<div class='score-badge {badge_class}'>{emoji} ATS Score: {ats_score}%</div>", unsafe_allow_html=True)
+            
+            # Metrics
+            st.markdown("### 📊 Detailed Analysis")
+            col1, col2, col3 = st.columns(3)
+            
+            with col1:
+                st.metric(
+                    label="🤖 AI Score",
+                    value=f"{ats_score}%",
+                    delta="Primary Score"
+                )
+            
+            with col2:
+                st.metric(
+                    label="📝 Content Match",
+                    value=f"{raw_sim}%",
+                    delta="Similarity"
+                )
+            
+            with col3:
+                st.metric(
+                    label="🔑 Keywords",
+                    value=f"{key_match}%",
+                    delta="Overlap"
+                )
+            
+            # Progress bar
+            st.markdown("#### Match Strength")
+            st.progress(min(ats_score/100, 1.0))
+            
+            # Feedback
+            if ats_score > 75: 
+                st.balloons()
+                st.info("🎉 Excellent match! Your resume aligns well with this role.")
+            elif ats_score >= 50:
+                st.info("✨ Good match! Consider adding more role-specific keywords to improve.")
+            else:
+                st.warning("💡 Low match. Try adding more relevant skills and experience keywords.")
+            
+            # Extracted text
+            with st.expander("📄 View Extracted Text"):
+                st.text_area("Resume Content", text, height=300)
+        else:
+            st.warning("⚠️ Could not extract text. File might be an image or scan. Please use a text-based document.")
+
+if __name__ == "__main__":
+    main()
+    

ats_scorer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46a86039608acdbfa77e66aa3c1f28e7f8a973a7d8afab60e29fcb1d608d50e2
+size 136514

clf.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98aef3fe524a35a33ed5c2ae0eec3a776e2723a6c9e2ce5eac13856e56c23a92
+size 931343794

encoder.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78015b3f43903a6934275ab46f36735b862d6c8876ac36028e461e879a1f05c4
+size 1104

prototypes.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3061636877e02cc7eef55acb57a6ba899c63ce14c310021816e258d89250cfd4
+size 27298599

tfidf.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d353d58aff8571ebd20b03567ab10aae98e5e71b350b17f69e06c7b3162af60
+size 185690

train_ats_model.py

@@ -0,0 +1,94 @@
+import pandas as pd
+import pickle
+import numpy as np
+from datasets import load_dataset
+from sklearn.metrics.pairwise import cosine_similarity
+from sklearn.ensemble import GradientBoostingRegressor
+from sklearn.model_selection import train_test_split
+import re
+import time
+
+def train_ats_scorer():
+    # 1. Load Dependencies
+    print("Loading TF-IDF Vectorizer (from Step 1)...")
+    try:
+        tfidf = pickle.load(open('tfidf.pkl', 'rb'))
+    except FileNotFoundError:
+        print("ERROR: 'tfidf.pkl' not found. Run 'train_model.py' first!")
+        exit()
+
+    # 2. Load ATS Dataset (0xnbk)
+    print("Loading 0xnbk/resume-ats-score-v1-en...")
+    try:
+        ds = load_dataset("0xnbk/resume-ats-score-v1-en")
+        df = pd.DataFrame(ds['train'])
+        print(f"Loaded {len(df)} rows.")
+    except Exception as e:
+        print(f"Error loading dataset: {e}")
+        exit()
+
+    # 3. Pre-Process
+    res_col = 'text'
+    score_col = 'ats_score'
+    cat_col = 'original_label'
+
+    df[score_col] = pd.to_numeric(df[score_col], errors='coerce')
+    df.dropna(subset=[score_col, res_col], inplace=True)
+
+    # 4. Generate Training Prototypes
+    print("Generating Training Prototypes...")
+    # Group resumes by label to simulate "Job Descriptions"
+    train_prototypes = df.groupby(cat_col)[res_col].apply(lambda x: ' '.join(x)).to_dict()
+
+    # Optimization: Pre-calculate vectors
+    print("Pre-calculating vectors...")
+    proto_vectors = {}
+    proto_tokens = {}
+    
+    for cat, text in train_prototypes.items():
+        proto_vectors[cat] = tfidf.transform([text])
+        proto_tokens[cat] = set(re.findall(r'\w+', text.lower()))
+
+    # 5. Feature Engineering
+    print("Calculating features...")
+    cosine_sims = []
+    keyword_matches = []
+
+    for i, row in enumerate(df.itertuples()):
+        text = str(getattr(row, res_col))
+        cat = getattr(row, cat_col)
+        
+        if cat in proto_vectors:
+            # Feature 1: Similarity
+            vec = tfidf.transform([text])
+            target_vec = proto_vectors[cat]
+            sim = cosine_similarity(vec, target_vec)[0][0]
+            
+            # Feature 2: Keyword Match
+            tokens = set(re.findall(r'\w+', text.lower()))
+            target_tokens = proto_tokens[cat]
+            match = len(tokens.intersection(target_tokens)) / len(target_tokens) if target_tokens else 0
+        else:
+            sim = 0
+            match = 0
+            
+        cosine_sims.append(sim)
+        keyword_matches.append(match)
+
+    df['cosine_sim'] = cosine_sims
+    df['keyword_match'] = keyword_matches
+
+    # 6. Train Regressor
+    print("Training ATS Regressor...")
+    X = df[['cosine_sim', 'keyword_match']]
+    y = df[score_col]
+
+    reg = GradientBoostingRegressor()
+    reg.fit(X, y)
+
+    # 7. Save
+    pickle.dump(reg, open('ats_scorer.pkl', 'wb'))
+    print("SUCCESS: 'ats_scorer.pkl' saved.")
+
+if __name__ == "__main__":
+    train_ats_scorer()

train_model.py

@@ -0,0 +1,60 @@
+import pandas as pd
+import pickle
+import re
+from datasets import load_dataset
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.multiclass import OneVsRestClassifier
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.preprocessing import LabelEncoder
+
+def train_classifier():
+    print("Loading AzharAli05/Resume-Screening-Dataset...")
+    try:
+        ds = load_dataset("AzharAli05/Resume-Screening-Dataset")
+        df = pd.DataFrame(ds['train'])
+        print(f"Loaded {len(df)} resumes.")
+    except Exception as e:
+        print(f"Error loading dataset: {e}")
+        exit()
+
+    text_col = 'Resume'
+    label_col = 'Role'
+
+    def clean_resume(txt):
+        cleanText = re.sub(r'http\S+\s', ' ', str(txt))
+        cleanText = re.sub(r'RT|cc', ' ', cleanText)
+        cleanText = re.sub(r'#\S+\s', ' ', cleanText)
+        cleanText = re.sub(r'@\S+', '  ', cleanText)
+        cleanText = re.sub(r'[!"#$%&\'()*+,-./:;<=>?@[\]^_`{|}~]', ' ', cleanText)
+        cleanText = re.sub(r'[^\x00-\x7f]', ' ', cleanText)
+        cleanText = re.sub(r'\s+', ' ', cleanText)
+        return cleanText
+
+    print("Cleaning data...")
+    df['cleaned_resume'] = df[text_col].apply(clean_resume)
+
+    print("Generating Master Profiles (Prototypes)...")
+
+    prototypes = df.groupby(label_col)['cleaned_resume'].apply(lambda x: ' '.join(x)).to_dict()
+    pickle.dump(prototypes, open('prototypes.pkl', 'wb'))
+
+    le = LabelEncoder()
+    df['Category_ID'] = le.fit_transform(df[label_col])
+
+    print("Vectorizing...")
+    tfidf = TfidfVectorizer(stop_words='english', max_features=5000)
+    tfidf.fit(df['cleaned_resume'])
+    requiredText = tfidf.transform(df['cleaned_resume'])
+
+    print("Training Classifier...")
+    clf = OneVsRestClassifier(KNeighborsClassifier())
+    clf.fit(requiredText, df['Category_ID'])
+
+    print("Saving models...")
+    pickle.dump(clf, open('clf.pkl', 'wb'))
+    pickle.dump(tfidf, open('tfidf.pkl', 'wb')) 
+    pickle.dump(le, open('encoder.pkl', 'wb'))
+    print("SUCCESS: Classification models + Prototypes saved.")
+
+if __name__ == "__main__":
+    train_classifier()