Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,39 @@
-*.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
+*.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
+**/*.h5 filter=lfs diff=lfs merge=lfs -text
+*.preproc filter=lfs diff=lfs merge=lfs -text
+Models/tf_model/* filter=lfs diff=lfs merge=lfs -text
+Models/Naive_Bayes_model filter=lfs diff=lfs merge=lfs -text

.github/workflows/update_space.yml

@@ -0,0 +1,28 @@
+name: Run Python script
+
+on:
+  push:
+    branches:
+      - main
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v2
+
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.9'
+
+    - name: Install Gradio
+      run: python -m pip install gradio
+
+    - name: Log in to Hugging Face
+      run: python -c 'import huggingface_hub; huggingface_hub.login(token="${{ secrets.hf_token }}")'
+
+    - name: Deploy to Spaces
+      run: gradio deploy

.gradio/certificate.pem

@@ -0,0 +1,31 @@
+-----BEGIN CERTIFICATE-----
+MIIFazCCA1OgAwIBAgIRAIIQz7DSQONZRGPgu2OCiwAwDQYJKoZIhvcNAQELBQAw
+TzELMAkGA1UEBhMCVVMxKTAnBgNVBAoTIEludGVybmV0IFNlY3VyaXR5IFJlc2Vh
+cmNoIEdyb3VwMRUwEwYDVQQDEwxJU1JHIFJvb3QgWDEwHhcNMTUwNjA0MTEwNDM4
+WhcNMzUwNjA0MTEwNDM4WjBPMQswCQYDVQQGEwJVUzEpMCcGA1UEChMgSW50ZXJu
+ZXQgU2VjdXJpdHkgUmVzZWFyY2ggR3JvdXAxFTATBgNVBAMTDElTUkcgUm9vdCBY
+MTCCAiIwDQYJKoZIhvcNAQEBBQADggIPADCCAgoCggIBAK3oJHP0FDfzm54rVygc
+h77ct984kIxuPOZXoHj3dcKi/vVqbvYATyjb3miGbESTtrFj/RQSa78f0uoxmyF+
+0TM8ukj13Xnfs7j/EvEhmkvBioZxaUpmZmyPfjxwv60pIgbz5MDmgK7iS4+3mX6U
+A5/TR5d8mUgjU+g4rk8Kb4Mu0UlXjIB0ttov0DiNewNwIRt18jA8+o+u3dpjq+sW
+T8KOEUt+zwvo/7V3LvSye0rgTBIlDHCNAymg4VMk7BPZ7hm/ELNKjD+Jo2FR3qyH
+B5T0Y3HsLuJvW5iB4YlcNHlsdu87kGJ55tukmi8mxdAQ4Q7e2RCOFvu396j3x+UC
+B5iPNgiV5+I3lg02dZ77DnKxHZu8A/lJBdiB3QW0KtZB6awBdpUKD9jf1b0SHzUv
+KBds0pjBqAlkd25HN7rOrFleaJ1/ctaJxQZBKT5ZPt0m9STJEadao0xAH0ahmbWn
+OlFuhjuefXKnEgV4We0+UXgVCwOPjdAvBbI+e0ocS3MFEvzG6uBQE3xDk3SzynTn
+jh8BCNAw1FtxNrQHusEwMFxIt4I7mKZ9YIqioymCzLq9gwQbooMDQaHWBfEbwrbw
+qHyGO0aoSCqI3Haadr8faqU9GY/rOPNk3sgrDQoo//fb4hVC1CLQJ13hef4Y53CI
+rU7m2Ys6xt0nUW7/vGT1M0NPAgMBAAGjQjBAMA4GA1UdDwEB/wQEAwIBBjAPBgNV
+HRMBAf8EBTADAQH/MB0GA1UdDgQWBBR5tFnme7bl5AFzgAiIyBpY9umbbjANBgkq
+hkiG9w0BAQsFAAOCAgEAVR9YqbyyqFDQDLHYGmkgJykIrGF1XIpu+ILlaS/V9lZL
+ubhzEFnTIZd+50xx+7LSYK05qAvqFyFWhfFQDlnrzuBZ6brJFe+GnY+EgPbk6ZGQ
+3BebYhtF8GaV0nxvwuo77x/Py9auJ/GpsMiu/X1+mvoiBOv/2X/qkSsisRcOj/KK
+NFtY2PwByVS5uCbMiogziUwthDyC3+6WVwW6LLv3xLfHTjuCvjHIInNzktHCgKQ5
+ORAzI4JMPJ+GslWYHb4phowim57iaztXOoJwTdwJx4nLCgdNbOhdjsnvzqvHu7Ur
+TkXWStAmzOVyyghqpZXjFaH3pO3JLF+l+/+sKAIuvtd7u+Nxe5AW0wdeRlN8NwdC
+jNPElpzVmbUq4JUagEiuTDkHzsxHpFKVK7q4+63SM1N95R1NbdWhscdCb+ZAJzVc
+oyi3B43njTOQ5yOf+1CceWxG1bQVs5ZufpsMljq4Ui0/1lvh+wjChP4kqKOJ2qxq
+4RgqsahDYVvTH9w7jXbyLeiNdd8XM2w9U/t7y0Ff/9yi0GE44Za4rF2LN9d11TPA
+mRGunUHBcnWEvgJBQl9nJEiU0Zsnvgc/ubhPgXRR4Xq37Z0j4r7g1SgEEzwxA57d
+emyPxgcYxn/eR44/KJ4EBs+lVDR3veyJm+kXQ99b21/+jh5Xos1AnX5iItreGCc=
+-----END CERTIFICATE-----

.gradio/flagged/dataset1.csv

@@ -0,0 +1,4 @@
+text,output,timestamp
+Testing store data,📊 Sentiment: **Neutral**,2025-05-30 17:21:18.740457
+Apple reports record-breaking profits in Q4,📊 Sentiment: **Negative**,2025-05-30 17:23:05.719872
+Markets crash amid global economic fears,📊 Sentiment: **Negative**,2025-05-30 17:24:25.995378

Models/Naive_Bayes_model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2cae70244cc7ae96eb54a427d3adf1eb007be3c3dec1af65f3d3f0e40bd1316
+size 3098902

README.md

@@ -1,12 +1,41 @@
 ---
-title: Financial Sentiment Analyzer
-emoji: 🐠
-colorFrom: yellow
-colorTo: green
-sdk: gradio
-sdk_version: 5.33.1
+title: financial-sentiment-analyzer
 app_file: app.py
-pinned: false
+sdk: gradio
+sdk_version: 5.31.0
+---
+# 🧠 Financial News Sentiment Analyzer
+
+This is a modern AI-powered application that analyzes the sentiment of financial news headlines or articles using either:
+- ✅ Naive Bayes (fast & lightweight)
+- 🤖 BERT transformer model (powerful & context-aware)
+
+Built with **Gradio**, **Hugging Face Transformers**, and deployable on **Hugging Face Spaces**.
+
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+## 🚀 Features
+
+- 🔍 Text sentiment classification (positive / neutral / negative)
+- 📈 Live usage statistics (locally or via Google Sheets)
+- 🧪 Preloaded examples
+- 🌙 Responsive UI with light/dark mode support
+
+---
+
+## 🧰 Tech Stack
+
+- `Gradio`
+- `Transformers` + `TensorFlow`
+- `Joblib` for Naive Bayes model
+- `Google Sheets` for logging (via Apps Script endpoint)
+
+---
+
+## 🛠 How to Run Locally
+
+```bash
+git clone https://github.com/yourusername/financial-sentiment-analyzer.git
+cd financial-sentiment-analyzer
+pip install -r requirements.txt
+python app.py

app.py

@@ -0,0 +1,12 @@
+from interface import create_interface
+
+if __name__ == "__main__":
+    interface, model_manager = create_interface()
+
+    if not model_manager.models_available:
+        print("⚠️ No models were loaded successfully. Please check your configuration.")
+
+    interface.launch(
+        share=True,
+        show_error=True
+    )

config.py

@@ -0,0 +1,12 @@
+class Config:
+    BERT_MODEL_REPO_ID = "Yousif22/financial-sentiment-analyzerv2"
+    NAIVE_BAYES_MODEL_PATH = "Models/Naive_Bayes_model"
+    GOOGLE_SHEET_ENDPOINT = "GOOGLE_SHEET_ENDPOINT"
+    GOOGLE_SHEET_TOKEN = "GOOGLE_SHEET_TOKEN"
+    GOOGLE_SHEET_CSV_URL = "GOOGLE_SHEET_CSV_URL"
+
+    LABEL_MAP = {
+        0: "negative",
+        1: "neutral",
+        2: "positive"
+    }

css.py

@@ -0,0 +1,352 @@
+def get_custom_css():
+    """Modern blue theme with dark/light mode support"""
+    return """
+    /* Modern Blue Theme with Dark/Light Mode Support */
+    :root {
+        /* Light mode colors */
+        --primary-blue: #2563eb;
+        --primary-blue-light: #3b82f6;
+        --primary-blue-dark: #1d4ed8;
+        --secondary-blue: #60a5fa;
+        --accent-blue: #93c5fd;
+        --light-blue: #dbeafe;
+        
+        --bg-primary: linear-gradient(135deg, #2563eb 0%, #1e40af 50%, #1d4ed8 100%);
+        --bg-secondary: #ffffff;
+        --bg-card: #f8fafc;
+        --bg-hover: #f1f5f9;
+        
+        --text-primary: #1e293b;
+        --text-secondary: #475569;
+        --text-muted: #64748b;
+        --text-inverse: #ffffff;
+        
+        --border-color: #e2e8f0;
+        --border-hover: #cbd5e1;
+        --shadow-sm: 0 1px 2px 0 rgb(0 0 0 / 0.05);
+        --shadow-md: 0 4px 6px -1px rgb(0 0 0 / 0.1), 0 2px 4px -2px rgb(0 0 0 / 0.1);
+        --shadow-lg: 0 10px 15px -3px rgb(0 0 0 / 0.1), 0 4px 6px -4px rgb(0 0 0 / 0.1);
+        --shadow-xl: 0 20px 25px -5px rgb(0 0 0 / 0.1), 0 8px 10px -6px rgb(0 0 0 / 0.1);
+        
+        --success-color: #22c55e;
+        --warning-color: #f59e0b;
+        --error-color: #ef4444;
+        --info-color: #3b82f6;
+    }
+    
+    /* Dark mode */
+    @media (prefers-color-scheme: dark) {
+        :root {
+            --bg-primary: linear-gradient(135deg, #1e3a8a 0%, #1e40af 50%, #1d4ed8 100%);
+            --bg-secondary: #0f172a;
+            --bg-card: #1e293b;
+            --bg-hover: #334155;
+            
+            --text-primary: #f1f5f9;
+            --text-secondary: #cbd5e1;
+            --text-muted: #94a3b8;
+            --text-inverse: #0f172a;
+            
+            --border-color: #334155;
+            --border-hover: #475569;
+            --shadow-sm: 0 1px 2px 0 rgb(0 0 0 / 0.25);
+            --shadow-md: 0 4px 6px -1px rgb(0 0 0 / 0.3), 0 2px 4px -2px rgb(0 0 0 / 0.3);
+            --shadow-lg: 0 10px 15px -3px rgb(0 0 0 / 0.3), 0 4px 6px -4px rgb(0 0 0 / 0.3);
+            --shadow-xl: 0 20px 25px -5px rgb(0 0 0 / 0.3), 0 8px 10px -6px rgb(0 0 0 / 0.3);
+        }
+    }
+    
+    /* Manual dark mode toggle */
+    .dark-mode {
+        --bg-primary: linear-gradient(135deg, #1e3a8a 0%, #1e40af 50%, #1d4ed8 100%);
+        --bg-secondary: #0f172a;
+        --bg-card: #1e293b;
+        --bg-hover: #334155;
+        
+        --text-primary: #f1f5f9;
+        --text-secondary: #cbd5e1;
+        --text-muted: #94a3b8;
+        --text-inverse: #0f172a;
+        
+        --border-color: #334155;
+        --border-hover: #475569;
+    }
+    
+    /* Global styles */
+    .gradio-container {
+        background: var(--bg-primary);
+        font-family: 'Inter', 'Segoe UI', system-ui, sans-serif;
+        color: var(--text-primary);
+        min-height: 100vh;
+    }
+    
+    /* Header */
+    .header {
+        text-align: center;
+        background: rgba(255, 255, 255, 0.1);
+        backdrop-filter: blur(20px);
+        border-radius: 24px;
+        padding: 3rem 2rem;
+        margin: 2rem;
+        border: 1px solid rgba(255, 255, 255, 0.2);
+        box-shadow: var(--shadow-xl);
+    }
+    
+    .header h1 {
+        color: var(--text-inverse) !important;
+        font-size: 3rem;
+        font-weight: 800;
+        margin: 0;
+        text-shadow: 0 4px 8px rgba(0, 0, 0, 0.3);
+        letter-spacing: -0.025em;
+    }
+    
+    .header p {
+        color: rgba(255, 255, 255, 0.9);
+        font-size: 1.25rem;
+        margin: 1rem 0 0;
+        font-weight: 400;
+    }
+    
+    /* Input container */
+    .input-container {
+        background: var(--bg-card);
+        border-radius: 20px;
+        padding: 2rem;
+        margin: 1rem;
+        box-shadow: var(--shadow-lg);
+        border: 1px solid var(--border-color);
+        transition: all 0.3s ease;
+    }
+    
+    .input-container:hover {
+        box-shadow: var(--shadow-xl);
+        border-color: var(--border-hover);
+    }
+    
+    /* Sentiment results */
+    .sentiment-result {
+        text-align: center;
+        padding: 2rem;
+        border-radius: 20px;
+        margin: 1rem 0;
+        background: var(--bg-card);
+        border: 2px solid var(--border-color);
+        box-shadow: var(--shadow-lg);
+        transition: all 0.3s ease;
+    }
+    
+    .sentiment-result[data-sentiment="positive"] {
+        border-color: var(--success-color);
+        background: linear-gradient(135deg, rgba(34, 197, 94, 0.1), rgba(34, 197, 94, 0.05));
+    }
+    
+    .sentiment-result[data-sentiment="negative"] {
+        border-color: var(--error-color);
+        background: linear-gradient(135deg, rgba(239, 68, 68, 0.1), rgba(239, 68, 68, 0.05));
+    }
+    
+    .sentiment-result[data-sentiment="neutral"] {
+        border-color: var(--info-color);
+        background: linear-gradient(135deg, rgba(59, 130, 246, 0.1), rgba(59, 130, 246, 0.05));
+    }
+    
+    .sentiment-result.error {
+        border-color: var(--error-color);
+        background: linear-gradient(135deg, rgba(239, 68, 68, 0.1), rgba(239, 68, 68, 0.05));
+        color: var(--error-color);
+    }
+    
+    .sentiment-result.warning {
+        border-color: var(--warning-color);
+        background: linear-gradient(135deg, rgba(245, 158, 11, 0.1), rgba(245, 158, 11, 0.05));
+        color: var(--warning-color);
+    }
+    
+    .result-title {
+        margin: 0 0 1rem;
+        color: var(--text-primary);
+        font-size: 1.75rem;
+        font-weight: 700;
+    }
+    
+    .sentiment-label {
+        font-size: 2rem;
+        font-weight: 800;
+        margin: 1rem 0;
+        color: var(--text-inverse);
+        letter-spacing: 0.05em;
+    }
+    
+    .model-info, .confidence-info {
+        color: var(--text-inverse);
+        font-size: 1rem;
+        margin: 0.5rem 0;
+        font-weight: 500;
+    }
+    
+    .confidence-info {
+        font-size: 0.875rem;
+    }
+    
+    /* Statistics */
+    .stats-container {
+        background: var(--bg-card);
+        padding: 2rem;
+        border-radius: 20px;
+        color: var(--text-primary);
+        text-align: center;
+        box-shadow: var(--shadow-lg);
+        border: 1px solid var(--border-color);
+    }
+    
+    .stats-title {
+        color: var(--text-primary);
+        margin-bottom: 1.5rem;
+        font-size: 1.5rem;
+        font-weight: 700;
+    }
+    
+    .stats-total {
+        font-weight: 600;
+        margin: 1rem 0;
+        color: var(--text-primary);
+        font-size: 1.125rem;
+    }
+    
+    .stats-section {
+        margin: 1.5rem 0;
+        text-align: left;
+    }
+    
+    .stats-section p {
+        font-weight: 600;
+        color: var(--text-primary);
+        margin-bottom: 0.75rem;
+    }
+    
+    .stats-list {
+        list-style: none;
+        padding: 0;
+        margin: 0;
+    }
+    
+    .stats-item {
+        padding: 0.5rem 0;
+        color: var(--text-secondary);
+        font-weight: 500;
+        border-bottom: 1px solid var(--border-color);
+    }
+    
+    .stats-item:last-child {
+        border-bottom: none;
+    }
+    
+    .stats-item.stats-positive {
+        color: var(--success-color);
+    }
+    
+    .stats-item.stats-negative {
+        color: var(--error-color);
+    }
+    
+    .stats-item.stats-neutral {
+        color: var(--info-color);
+    }
+    
+    .no-stats, .error-stats {
+        text-align: center;
+        padding: 2rem;
+        color: var(--text-muted);
+        background: var(--bg-card);
+        border-radius: 16px;
+        border: 1px solid var(--border-color);
+    }
+    
+    /* Buttons */
+    .submit-btn {
+        background: linear-gradient(135deg, var(--primary-blue), var(--primary-blue-dark)) !important;
+        border: none !important;
+        border-radius: 16px !important;
+        padding: 1rem 2rem !important;
+        color: var(--text-inverse) !important;
+        font-weight: 600 !important;
+        font-size: 1rem !important;
+        cursor: pointer !important;
+        transition: all 0.3s ease !important;
+        box-shadow: var(--shadow-md) !important;
+    }
+    
+    .submit-btn:hover {
+        transform: translateY(-2px) !important;
+        box-shadow: var(--shadow-lg) !important;
+        background: linear-gradient(135deg, var(--primary-blue-light), var(--primary-blue)) !important;
+    }
+    
+    /* Footer */
+    .footer {
+        text-align: center;
+        background: var(--block-background-fill);
+        color: var(--text-inverse);
+        padding: 2rem;
+        border-radius: 20px;
+        margin: 2rem;
+        backdrop-filter: blur(10px);
+    }
+    
+    .footer h3 {
+        margin: 0 0 1rem;
+        font-weight: 700;
+    }
+    
+    .social-links {
+        margin: 1rem 0;
+    }
+    
+    .social-links a {
+        color: var(--secondary-blue);
+        text-decoration: none;
+        margin: 0 1rem;
+        font-weight: 600;
+        transition: color 0.3s ease;
+    }
+    
+    .social-links a:hover {
+        color: var(--accent-blue);
+        text-decoration: underline;
+    }
+    
+    /* Responsive design */
+    @media (max-width: 768px) {
+        .header {
+            margin: 1rem;
+            padding: 2rem 1rem;
+        }
+        
+        .header h1 {
+            font-size: 2rem !important;
+        }
+        
+        .header p {
+            font-size: 1rem !important;
+        }
+        
+        .input-container {
+            margin: 0.5rem;
+            padding: 1.5rem;
+        }
+        
+        .sentiment-result {
+            padding: 1.5rem;
+        }
+        
+        .stats-container {
+            padding: 1.5rem;
+        }
+    }
+    
+    /* Smooth transitions */
+    * {
+        transition: background-color 0.3s ease, border-color 0.3s ease, color 0.3s ease;
+    }
+    """

examples.py

@@ -0,0 +1,7 @@
+EXAMPLE_DATA = [
+    ["Fed raises interest rates amid inflation concerns", "Naive Bayes"],
+    ["Apple reports record-breaking quarterly profits", "BERT"],
+    ["Global markets crash as recession fears mount", "Naive Bayes"],
+    ["Tesla announces breakthrough in battery technology", "BERT"],
+    ["Banking sector shows mixed results this quarter", "Naive Bayes"]
+]

interface.py

@@ -0,0 +1,99 @@
+import gradio as gr
+from models import ModelManager
+from prediction import PredictionEngine
+from stats import StatsManager
+from css import get_custom_css
+from examples import EXAMPLE_DATA
+
+def create_interface():
+    """Create and configure the Gradio interface"""
+    # Initialize components
+    model_manager = ModelManager()
+    prediction_engine = PredictionEngine(model_manager)
+    
+    # Create interface
+    with gr.Blocks(css=get_custom_css(), title="🧠 Financial Sentiment Analyzer", theme=gr.themes.Base()) as interface:
+        # Header
+        gr.HTML("""
+            <div class="header">
+                <h1>🧠 Financial News Sentiment Analyzer</h1>
+                <p>Powered by AI • Analyze financial news sentiment with advanced ML models</p>
+            </div>
+        """)
+        
+        # Main content
+        with gr.Row():
+            # Input column
+            with gr.Column(scale=2):
+                
+                
+                text_input = gr.Textbox(
+                    lines=4,
+                    placeholder="💼 Enter financial news headline or text...\n\nExample: 'Apple stock surges after strong earnings report'",
+                    label="📝 Financial News Text",
+                    elem_classes=["input-text"]
+                )
+                
+                model_choice = gr.Radio(
+                    choices=["Naive Bayes", "BERT"],
+                    value=model_manager.default_model,
+                    label="🤖 Select AI Model",
+                    info="Choose between Naive Bayes (fast) or BERT (advanced)"
+                )
+                
+                predict_btn = gr.Button(
+                    "🔍 Analyze Sentiment",
+                    variant="primary",
+                    elem_classes=["submit-btn"]
+                )
+                
+                gr.HTML('</div>')
+                
+                # Examples
+                gr.Examples(
+                    examples=EXAMPLE_DATA,
+                    inputs=[text_input, model_choice],
+                    label="💡 Try these examples:"
+                )
+            
+            # Output column
+            with gr.Column(scale=1):
+                output = gr.HTML(
+                    value="<div style='text-align: center; padding: 3rem; color: var(--text-invers);'>👆 Enter text and click analyze to see results</div>",
+                    label="📊 Analysis Result"
+                )
+                
+                stats_display = gr.HTML(
+                    label="📈 Usage Statistics"
+                )
+                
+                refresh_stats_btn = gr.Button("🔄 Refresh Stats", variant="secondary")
+        
+        # Event handlers
+        predict_btn.click(
+            fn=prediction_engine.predict_sentiment,
+            inputs=[text_input, model_choice],
+            outputs=output
+        )
+        
+        refresh_stats_btn.click(
+            fn=StatsManager.get_stats,
+            inputs=None,
+            outputs=stats_display
+        )
+        
+        # Load initial stats
+        interface.load(StatsManager.get_stats, None, stats_display)
+        
+        # Footer
+        gr.HTML("""
+            <div class="footer">
+                <h3>👨‍💻 Developed by Yousif Al Nasser</h3>
+                <div class="social-links">
+                    <a href="https://yousif.engineer" target="_blank">🌐 Portfolio Website</a>
+                    <a href="https://linkedin.com/in/yalnasser" target="_blank">💼 LinkedIn Profile</a>
+                </div>
+            </div>
+        """)
+    
+    return interface, model_manager

models.py

@@ -0,0 +1,42 @@
+import os
+import joblib
+from transformers import AutoTokenizer, TFAutoModelForSequenceClassification
+from config import Config
+
+class ModelManager:
+    def __init__(self):
+        self.bert_model = None
+        self.bert_tokenizer = None
+        self.naive_bayes_model = None
+        self._load_models()
+
+    def _load_models(self):
+        self._load_bert_model()
+        self._load_naive_bayes_model()
+
+    def _load_bert_model(self):
+        try:
+            print(f"Loading BERT model from {Config.BERT_MODEL_REPO_ID}...")
+            self.bert_tokenizer = AutoTokenizer.from_pretrained(Config.BERT_MODEL_REPO_ID)
+            self.bert_model = TFAutoModelForSequenceClassification.from_pretrained(Config.BERT_MODEL_REPO_ID)
+            print("✅ BERT model loaded successfully!")
+        except Exception as e:
+            print(f"❌ Error loading BERT model: {e}")
+
+    def _load_naive_bayes_model(self):
+        try:
+            if os.path.exists(Config.NAIVE_BAYES_MODEL_PATH):
+                self.naive_bayes_model = joblib.load(Config.NAIVE_BAYES_MODEL_PATH)
+                print("✅ Naive Bayes model loaded successfully")
+            else:
+                print(f"⚠️ Naive Bayes model not found at {Config.NAIVE_BAYES_MODEL_PATH}")
+        except Exception as e:
+            print(f"❌ Error loading Naive Bayes model: {e}")
+
+    @property
+    def models_available(self):
+        return self.bert_model or self.naive_bayes_model
+
+    @property
+    def default_model(self):
+        return "Naive Bayes" if self.naive_bayes_model else "BERT"

prediction.py

@@ -0,0 +1,78 @@
+import tensorflow as tf
+import requests
+from config import Config
+from utils import preprocess
+from models import ModelManager
+
+class PredictionEngine:
+    def __init__(self, model_manager: ModelManager):
+        self.model_manager = model_manager
+
+    def predict_with_bert(self, text: str):
+        try:
+            inputs = self.model_manager.bert_tokenizer(
+                text, return_tensors="tf", truncation=True, padding=True
+            )
+            outputs = self.model_manager.bert_model(**inputs)
+            logits = outputs.logits.numpy()[0]
+            prediction = int(tf.math.argmax(logits).numpy())
+            confidence = float(tf.nn.softmax(logits)[prediction].numpy())
+            label = Config.LABEL_MAP.get(prediction, "neutral")
+            return prediction, label, confidence
+        except Exception as e:
+            print(f"❌ BERT prediction error: {e}")
+            return 1, "neutral", 0.5
+
+    def predict_with_naive_bayes(self, text: str):
+        try:
+            cleaned = preprocess(text, model_type="naive_bayes")
+            prediction = self.model_manager.naive_bayes_model.predict([cleaned])[0]
+            label = Config.LABEL_MAP.get(prediction, "unknown")
+            return prediction, label, 0.85  # Static confidence
+        except Exception as e:
+            print(f"❌ Naive Bayes prediction error: {e}")
+            return 1, "neutral", 0.5
+
+    def predict_sentiment(self, text: str, model_choice: str):
+        if not text.strip():
+            return self._html_message("⚠️ Please enter some text to analyze.", "warning")
+
+        if model_choice == "Naive Bayes":
+            if self.model_manager.naive_bayes_model is None:
+                return self._html_message("Naive Bayes model not available.", "error")
+            pred, label, conf = self.predict_with_naive_bayes(text)
+        elif model_choice == "BERT":
+            if self.model_manager.bert_model is None:
+                return self._html_message("BERT model not available.", "error")
+            pred, label, conf = self.predict_with_bert(text)
+        else:
+            return self._html_message("Invalid model selection.", "error")
+
+        self._log_to_sheet(text, model_choice, label, conf)
+        return self._render_result(label, model_choice, conf)
+
+    def _log_to_sheet(self, text, model, sentiment, confidence):
+        try:
+            requests.post(Config.GOOGLE_SHEET_ENDPOINT, json={
+                "token": Config.GOOGLE_SHEET_TOKEN,
+                "text": text,
+                "model_used": model,
+                "sentiment": sentiment,
+                "confidence": confidence
+            })
+        except Exception as e:
+            print(f"⚠️ Logging failed: {e}")
+
+    def _render_result(self, label, model, confidence):
+        emoji = {"positive": "📈", "negative": "📉", "neutral": "📊"}.get(label, "📊")
+        return f"""
+        <div class="sentiment-result" data-sentiment="{label}">
+            <h2 style="color: white;">{emoji} Sentiment Result</h2>
+            <p class="sentiment-label">{label.upper()}</p>
+            <p class="model-info">Model: {model}</p>
+            <p class="confidence-info">Confidence: {confidence:.2%}</p>
+        </div>
+        """
+
+    def _html_message(self, msg, level):
+        return f"<div class='sentiment-result {level}'>{msg}</div>"

requirements.txt

@@ -0,0 +1,20 @@
+# Core libraries
+pandas
+numpy
+joblib
+
+# Gradio interface
+gradio
+
+# Hugging Face Transformers
+transformers
+tensorflow  # for TFAutoModelForSequenceClassification
+
+# Requests for API logging
+requests
+
+# Optional: required by utils.py for advanced preprocessing
+regex
+
+# To run locally
+gunicorn  # if deploying on platforms like Heroku or similar

stats.py

@@ -0,0 +1,31 @@
+import os
+import pandas as pd
+
+class StatsManager:
+    @staticmethod
+    def get_stats():
+        try:
+            if os.path.exists("usage_stats.csv"):
+                df = pd.read_csv("usage_stats.csv")
+                return StatsManager._render_html(df)
+            return "<div class='no-stats'>📊 No usage data yet.</div>"
+        except Exception as e:
+            return f"<div class='error-stats'>❌ Error: {e}</div>"
+
+    @staticmethod
+    def _render_html(df: pd.DataFrame):
+        if df.empty:
+            return "<div class='no-stats'>📊 No usage data yet.</div>"
+
+        total = len(df)
+        sentiments = df['sentiment'].value_counts()
+        models = df['model_used'].value_counts()
+
+        html = f"<div class='stats-container'><h3>📈 Stats</h3><p>Total: {total}</p><ul>"
+        for s, c in sentiments.items():
+            html += f"<li>{s.title()}: {c} ({(c/total)*100:.1f}%)</li>"
+        html += "</ul><ul>"
+        for m, c in models.items():
+            html += f"<li>{m}: {c} ({(c/total)*100:.1f}%)</li>"
+        html += "</ul></div>"
+        return html

utils.py

@@ -0,0 +1,198 @@
+# utils.py
+import re
+import string
+from typing import Optional
+
+def preprocess(text: str, model_type: str = "naive_bayes") -> str:
+    """
+    Enhanced preprocessing function with model-specific optimizations
+    
+    Args:
+        text (str): Input text to preprocess
+        model_type (str): Type of model ("naive_bayes" or "bert")
+    
+    Returns:
+        str: Preprocessed text
+    """
+    if not text or not isinstance(text, str):
+        return ""
+    
+    # Basic cleaning
+    text = text.strip()
+    
+    if model_type.lower() == "bert":
+        # BERT-specific preprocessing (less aggressive)
+        # BERT can handle punctuation and case better
+        
+        # Remove excessive whitespace
+        text = re.sub(r'\s+', ' ', text)
+        
+        # Remove URLs
+        text = re.sub(r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\\(\\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', '', text)
+        
+        # Remove email addresses
+        text = re.sub(r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b', '', text)
+        
+        # Remove excessive punctuation (more than 2 consecutive)
+        text = re.sub(r'[.]{3,}', '...', text)
+        text = re.sub(r'[!]{2,}', '!', text)
+        text = re.sub(r'[?]{2,}', '?', text)
+        
+        return text.strip()
+    
+    else:
+        # Naive Bayes preprocessing (more aggressive cleaning)
+        
+        # Convert to lowercase
+        text = text.lower()
+        
+        # Remove URLs
+        text = re.sub(r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\\(\\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', '', text)
+        
+        # Remove email addresses
+        text = re.sub(r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b', '', text)
+        
+        # Remove special financial symbols but keep dollar signs and percentages
+        text = re.sub(r'[^\w\s$%.-]', ' ', text)
+        
+        # Handle numbers and percentages
+        text = re.sub(r'\b\d+\.\d+%\b', 'PERCENTAGE', text)
+        text = re.sub(r'\b\d+%\b', 'PERCENTAGE', text)
+        text = re.sub(r'\$\d+\.?\d*[KMB]?\b', 'DOLLAR_AMOUNT', text)
+        
+        # Remove extra whitespace
+        text = re.sub(r'\s+', ' ', text)
+        
+        return text.strip()
+
+def clean_financial_text(text: str) -> str:
+    """
+    Specialized cleaning for financial text
+    
+    Args:
+        text (str): Financial text to clean
+        
+    Returns:
+        str: Cleaned financial text
+    """
+    if not text:
+        return ""
+    
+    # Common financial abbreviations to preserve
+    financial_terms = {
+        'q1': 'first quarter',
+        'q2': 'second quarter', 
+        'q3': 'third quarter',
+        'q4': 'fourth quarter',
+        'yoy': 'year over year',
+        'qoq': 'quarter over quarter',
+        'ipo': 'initial public offering',
+        'ceo': 'chief executive officer',
+        'cfo': 'chief financial officer',
+        'fed': 'federal reserve',
+        'gdp': 'gross domestic product',
+        'etf': 'exchange traded fund'
+    }
+    
+    text_lower = text.lower()
+    for abbrev, full_form in financial_terms.items():
+        text_lower = text_lower.replace(abbrev, full_form)
+    
+    return text_lower
+
+def extract_financial_entities(text: str) -> dict:
+    """
+    Extract financial entities from text
+    
+    Args:
+        text (str): Input text
+        
+    Returns:
+        dict: Dictionary containing extracted entities
+    """
+    entities = {
+        'percentages': [],
+        'dollar_amounts': [],
+        'stock_symbols': [],
+        'quarters': [],
+        'years': []
+    }
+    
+    # Extract percentages
+    percentages = re.findall(r'\b\d+\.?\d*%\b', text)
+    entities['percentages'] = percentages
+    
+    # Extract dollar amounts
+    dollar_amounts = re.findall(r'\$\d+\.?\d*[KMB]?\b', text)
+    entities['dollar_amounts'] = dollar_amounts
+    
+    # Extract potential stock symbols (2-5 uppercase letters)
+    stock_symbols = re.findall(r'\b[A-Z]{2,5}\b', text)
+    entities['stock_symbols'] = stock_symbols
+    
+    # Extract quarters
+    quarters = re.findall(r'\bQ[1-4]\b|\b[1-4]Q\b', text, re.IGNORECASE)
+    entities['quarters'] = quarters
+    
+    # Extract years
+    years = re.findall(r'\b20\d{2}\b', text)
+    entities['years'] = years
+    
+    return entities
+
+def get_text_stats(text: str) -> dict:
+    """
+    Get basic statistics about the text
+    
+    Args:
+        text (str): Input text
+        
+    Returns:
+        dict: Text statistics
+    """
+    if not text:
+        return {
+            'word_count': 0,
+            'char_count': 0,
+            'sentence_count': 0,
+            'avg_word_length': 0
+        }
+    
+    words = text.split()
+    sentences = re.split(r'[.!?]+', text)
+    
+    stats = {
+        'word_count': len(words),
+        'char_count': len(text),
+        'sentence_count': len([s for s in sentences if s.strip()]),
+        'avg_word_length': sum(len(word) for word in words) / len(words) if words else 0
+    }
+    
+    return stats
+
+def validate_input(text: str, min_length: int = 5, max_length: int = 1000) -> tuple[bool, str]:
+    """
+    Validate user input
+    
+    Args:
+        text (str): Input text to validate
+        min_length (int): Minimum required length
+        max_length (int): Maximum allowed length
+        
+    Returns:
+        tuple: (is_valid, error_message)
+    """
+    if not text or not text.strip():
+        return False, "Text cannot be empty"
+    
+    if len(text.strip()) < min_length:
+        return False, f"Text must be at least {min_length} characters long"
+    
+    if len(text) > max_length:
+        return False, f"Text cannot exceed {max_length} characters"
+    
+    # Check if text contains only special characters
+    if re.match(r'^[^\w\s]+$', text.strip()):
+        return False, "Text must contain alphanumeric characters"
+    
+    return True, ""