Spaces:
Sleeping
Sleeping
| # ============================================================ | |
| # Hugging Face Spaces / Gradio | |
| # Hassaniya Sentiment Analysis – MARBERT | |
| # Multilingual UI: Français / العربية / English | |
| # ============================================================ | |
| import re | |
| import html | |
| import torch | |
| import gradio as gr | |
| from transformers import AutoTokenizer, AutoModelForSequenceClassification | |
| # ============================================================ | |
| # 1) MODEL CONFIGURATION | |
| # ============================================================ | |
| # Les fichiers du modèle sont directement dans main/ | |
| MODEL_PATH = "." | |
| ID2LABEL = { | |
| 0: "Negative", | |
| 1: "Neutral", | |
| 2: "Positive", | |
| } | |
| LABELS = { | |
| "fr": { | |
| "Negative": "Négatif", | |
| "Neutral": "Neutre", | |
| "Positive": "Positif", | |
| }, | |
| "ar": { | |
| "Negative": "سلبي", | |
| "Neutral": "محايد", | |
| "Positive": "إيجابي", | |
| }, | |
| "en": { | |
| "Negative": "Negative", | |
| "Neutral": "Neutral", | |
| "Positive": "Positive", | |
| }, | |
| } | |
| UI_TEXT = { | |
| "fr": { | |
| "empty": "Veuillez saisir un texte.", | |
| "confidence": "Confiance", | |
| "prediction": "Prédiction finale", | |
| "normalized": "Texte normalisé", | |
| }, | |
| "ar": { | |
| "empty": "يرجى إدخال نص.", | |
| "confidence": "نسبة الثقة", | |
| "prediction": "التصنيف النهائي", | |
| "normalized": "النص بعد التنظيف", | |
| }, | |
| "en": { | |
| "empty": "Please enter a text.", | |
| "confidence": "Confidence", | |
| "prediction": "Final prediction", | |
| "normalized": "Normalized text", | |
| }, | |
| } | |
| COLORS = { | |
| "Positive": "#2563eb", | |
| "Neutral": "#f59e0b", | |
| "Negative": "#dc2626", | |
| } | |
| # ============================================================ | |
| # 2) HASSANIYA CLEANING | |
| # ============================================================ | |
| ARABIC_REPLACEMENTS = { | |
| "أ": "ا", | |
| "إ": "ا", | |
| "آ": "ا", | |
| "ى": "ي", | |
| "ؤ": "و", | |
| "ئ": "ي", | |
| "ة": "ه", | |
| "گ": "ك", | |
| "ڨ": "ق", | |
| "چ": "ج", | |
| } | |
| DIACRITICS = re.compile(r"[ًٌٍَُِّْـ]") | |
| def clean_hassaniya(text: str) -> str: | |
| text = str(text) | |
| text = re.sub(r"http\S+|www\S+", " ", text) | |
| text = re.sub(r"@\w+|#\w+", " ", text) | |
| text = re.sub(r"[a-zA-Z0-9]", " ", text) | |
| text = re.sub(DIACRITICS, "", text) | |
| for old, new in ARABIC_REPLACEMENTS.items(): | |
| text = text.replace(old, new) | |
| text = re.sub(r"(.)\1{2,}", r"\1", text) | |
| text = re.sub(r"[^\u0600-\u06FF\s]", " ", text) | |
| text = re.sub(r"\s+", " ", text).strip() | |
| return text | |
| # ============================================================ | |
| # 3) LOAD MODEL | |
| # ============================================================ | |
| device = torch.device( | |
| "cuda" if torch.cuda.is_available() else "cpu" | |
| ) | |
| print(f"Loading model from: {MODEL_PATH}") | |
| print(f"Using device: {device}") | |
| tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH) | |
| model = AutoModelForSequenceClassification.from_pretrained( | |
| MODEL_PATH | |
| ) | |
| model.to(device) | |
| model.eval() | |
| print("✅ Model loaded successfully") | |
| # ============================================================ | |
| # 4) PREDICTION | |
| # ============================================================ | |
| def predict_sentiment(text, language): | |
| lang = language if language in UI_TEXT else "fr" | |
| if not text or not str(text).strip(): | |
| return f""" | |
| <div class="result-card"> | |
| <h3 class="empty-message"> | |
| {UI_TEXT[lang]["empty"]} | |
| </h3> | |
| </div> | |
| """ | |
| cleaned_text = clean_hassaniya(text) | |
| if not cleaned_text: | |
| return f""" | |
| <div class="result-card"> | |
| <h3 class="empty-message"> | |
| {UI_TEXT[lang]["empty"]} | |
| </h3> | |
| </div> | |
| """ | |
| inputs = tokenizer( | |
| cleaned_text, | |
| return_tensors="pt", | |
| truncation=True, | |
| padding=True, | |
| max_length=96, | |
| ) | |
| inputs = { | |
| key: value.to(device) | |
| for key, value in inputs.items() | |
| } | |
| with torch.inference_mode(): | |
| outputs = model(**inputs) | |
| probs = torch.softmax( | |
| outputs.logits, | |
| dim=-1 | |
| )[0].detach().cpu() | |
| scores = { | |
| ID2LABEL[i]: float(probs[i]) | |
| for i in range(len(ID2LABEL)) | |
| } | |
| best_label = max(scores, key=scores.get) | |
| best_score = scores[best_label] * 100 | |
| best_color = COLORS[best_label] | |
| bars_html = "" | |
| for label in ["Positive", "Neutral", "Negative"]: | |
| percent = scores[label] * 100 | |
| color = COLORS[label] | |
| display_label = LABELS[lang][label] | |
| bars_html += f""" | |
| <div class="bar-row"> | |
| <div | |
| class="bar-label" | |
| style="color:{color} !important;" | |
| > | |
| {display_label} | |
| </div> | |
| <div class="bar-track"> | |
| <div | |
| class="bar-fill" | |
| style=" | |
| width:{percent:.2f}%; | |
| background:{color}; | |
| " | |
| ></div> | |
| </div> | |
| <div class="bar-value"> | |
| {percent:.2f}% | |
| </div> | |
| </div> | |
| """ | |
| safe_cleaned_text = html.escape(cleaned_text) | |
| return f""" | |
| <div class="result-card"> | |
| <div | |
| class="final-prediction" | |
| style="border-color:{best_color};" | |
| > | |
| <div class="prediction-title"> | |
| {UI_TEXT[lang]["prediction"]} | |
| </div> | |
| <div | |
| class="prediction-label" | |
| style="color:{best_color} !important;" | |
| > | |
| {LABELS[lang][best_label]} | |
| </div> | |
| <div class="confidence"> | |
| {UI_TEXT[lang]["confidence"]}: {best_score:.2f}% | |
| </div> | |
| </div> | |
| <div class="bars-container"> | |
| {bars_html} | |
| </div> | |
| <div class="normalized-box"> | |
| <strong> | |
| {UI_TEXT[lang]["normalized"]}: | |
| </strong> | |
| <div> | |
| {safe_cleaned_text} | |
| </div> | |
| </div> | |
| </div> | |
| """ | |
| def clear_fields(): | |
| return "", """ | |
| <div class="result-card"> | |
| <h3 class="result-placeholder"> | |
| Result will appear here | |
| </h3> | |
| </div> | |
| """ | |
| # ============================================================ | |
| # 5) CSS | |
| # ============================================================ | |
| custom_css = """ | |
| .gradio-container { | |
| background: | |
| linear-gradient( | |
| 135deg, | |
| #006233 0%, | |
| #ffffff 47%, | |
| #d01c1f 100% | |
| ) !important; | |
| font-family: "Segoe UI", Arial, sans-serif !important; | |
| min-height: 100vh !important; | |
| color: #111827 !important; | |
| overflow-x: hidden !important; | |
| } | |
| #main-card { | |
| width: calc(100% - 40px); | |
| max-width: 1180px; | |
| margin: 28px auto; | |
| padding: 30px; | |
| box-sizing: border-box; | |
| border-radius: 26px; | |
| background: rgba(255,255,255,0.97); | |
| border: 3px solid #ffc400; | |
| box-shadow: 0 18px 45px rgba(0,0,0,0.18); | |
| } | |
| #header-box { | |
| text-align: center; | |
| padding: 30px; | |
| border-radius: 22px; | |
| background: linear-gradient(135deg, #006233, #008f4c); | |
| margin-bottom: 24px; | |
| border-bottom: 7px solid #ffc400; | |
| } | |
| #header-box h1 { | |
| margin: 0; | |
| font-size: 34px; | |
| font-weight: 800; | |
| color: #ffffff !important; | |
| } | |
| #header-box p { | |
| margin-top: 10px; | |
| margin-bottom: 0; | |
| font-size: 16px; | |
| color: #fff7cc !important; | |
| } | |
| #language-selector, | |
| #language-selector label { | |
| color: #111827 !important; | |
| } | |
| #input-box textarea { | |
| direction: rtl !important; | |
| text-align: right !important; | |
| font-size: 18px !important; | |
| line-height: 1.8 !important; | |
| color: #111827 !important; | |
| -webkit-text-fill-color: #111827 !important; | |
| background: #ffffff !important; | |
| border: 2px solid #006233 !important; | |
| border-radius: 14px !important; | |
| } | |
| #input-box textarea::placeholder { | |
| color: #6b7280 !important; | |
| -webkit-text-fill-color: #6b7280 !important; | |
| opacity: 1 !important; | |
| } | |
| button.primary { | |
| background: linear-gradient(135deg, #006233, #008f4c) !important; | |
| color: #ffffff !important; | |
| border-radius: 14px !important; | |
| border: none !important; | |
| font-weight: 800 !important; | |
| } | |
| #clear-button { | |
| color: #111827 !important; | |
| background: #ffffff !important; | |
| border: 1px solid #d1d5db !important; | |
| border-radius: 14px !important; | |
| font-weight: 700 !important; | |
| } | |
| .result-card { | |
| width: 100%; | |
| box-sizing: border-box; | |
| background: #ffffff !important; | |
| color: #111827 !important; | |
| border-radius: 20px; | |
| padding: 24px; | |
| border: 2px solid #ffc400; | |
| box-shadow: 0 12px 30px rgba(0,0,0,0.12); | |
| min-height: 290px; | |
| } | |
| .final-prediction { | |
| text-align: center; | |
| padding: 20px; | |
| border: 3px solid; | |
| border-radius: 18px; | |
| margin-bottom: 24px; | |
| background: #f9fafb !important; | |
| } | |
| .prediction-title { | |
| font-size: 15px; | |
| color: #374151 !important; | |
| font-weight: 700; | |
| margin-bottom: 8px; | |
| } | |
| .prediction-label { | |
| font-size: 34px; | |
| font-weight: 900; | |
| margin-bottom: 8px; | |
| } | |
| .confidence { | |
| font-size: 16px; | |
| color: #111827 !important; | |
| font-weight: 700; | |
| } | |
| .bars-container { | |
| display: flex; | |
| flex-direction: column; | |
| gap: 16px; | |
| } | |
| .bar-row { | |
| display: grid; | |
| grid-template-columns: 110px minmax(120px, 1fr) 80px; | |
| gap: 12px; | |
| align-items: center; | |
| } | |
| .bar-label { | |
| font-weight: 800; | |
| font-size: 15px; | |
| } | |
| .bar-track { | |
| width: 100%; | |
| height: 24px; | |
| background: #e5e7eb !important; | |
| border-radius: 999px; | |
| overflow: hidden; | |
| } | |
| .bar-fill { | |
| height: 100%; | |
| border-radius: 999px; | |
| } | |
| .bar-value { | |
| font-weight: 800; | |
| color: #111827 !important; | |
| font-size: 14px; | |
| text-align: right; | |
| } | |
| .normalized-box { | |
| margin-top: 22px; | |
| padding: 14px 16px; | |
| border-radius: 14px; | |
| background: #f3f4f6 !important; | |
| color: #374151 !important; | |
| font-size: 13px; | |
| } | |
| .normalized-box strong { | |
| color: #374151 !important; | |
| } | |
| .normalized-box div { | |
| margin-top: 6px; | |
| direction: rtl; | |
| text-align: right; | |
| font-size: 15px; | |
| color: #111827 !important; | |
| } | |
| .empty-message, | |
| .result-placeholder { | |
| text-align: center; | |
| color: #006233 !important; | |
| padding-top: 70px; | |
| } | |
| /* Examples */ | |
| .gradio-container table, | |
| .gradio-container table td, | |
| .gradio-container table th { | |
| color: #111827 !important; | |
| background: #ffffff !important; | |
| } | |
| .gradio-container table * { | |
| color: #111827 !important; | |
| -webkit-text-fill-color: #111827 !important; | |
| } | |
| footer { | |
| display: none !important; | |
| } | |
| /* ============================================================ | |
| MOBILE | |
| ============================================================ */ | |
| @media (max-width: 768px) { | |
| .gradio-container { | |
| padding: 0 !important; | |
| } | |
| #main-card { | |
| width: calc(100% - 12px) !important; | |
| margin: 6px auto !important; | |
| padding: 10px !important; | |
| border-radius: 14px !important; | |
| } | |
| #header-box { | |
| padding: 17px 10px !important; | |
| border-radius: 13px !important; | |
| margin-bottom: 12px !important; | |
| } | |
| #header-box h1 { | |
| font-size: 21px !important; | |
| } | |
| #header-box p { | |
| font-size: 12px !important; | |
| } | |
| #main-row { | |
| flex-direction: column !important; | |
| flex-wrap: nowrap !important; | |
| gap: 12px !important; | |
| } | |
| #main-row > div { | |
| width: 100% !important; | |
| max-width: 100% !important; | |
| min-width: 0 !important; | |
| flex: 1 1 100% !important; | |
| } | |
| #input-box textarea { | |
| min-height: 145px !important; | |
| font-size: 16px !important; | |
| } | |
| #action-row { | |
| gap: 8px !important; | |
| flex-wrap: wrap !important; | |
| } | |
| #action-row button { | |
| min-height: 46px !important; | |
| flex: 1 1 145px !important; | |
| } | |
| .result-card { | |
| min-height: auto !important; | |
| padding: 14px !important; | |
| } | |
| .prediction-label { | |
| font-size: 26px !important; | |
| } | |
| .bar-row { | |
| grid-template-columns: 68px minmax(0,1fr) 54px !important; | |
| gap: 6px !important; | |
| } | |
| .bar-label { | |
| font-size: 12px !important; | |
| } | |
| .bar-value { | |
| font-size: 11px !important; | |
| } | |
| .bar-track { | |
| height: 17px !important; | |
| } | |
| .normalized-box { | |
| font-size: 12px !important; | |
| } | |
| } | |
| """ | |
| # ============================================================ | |
| # 6) GRADIO INTERFACE | |
| # ============================================================ | |
| with gr.Blocks( | |
| title="Hassaniya Sentiment Analysis" | |
| ) as demo: | |
| with gr.Column(elem_id="main-card"): | |
| gr.HTML(""" | |
| <div id="header-box"> | |
| <h1> | |
| Hassaniya Sentiment Analysis | |
| </h1> | |
| <p> | |
| تحليل المشاعر للنصوص الحسانية باستخدام MARBERT | |
| </p> | |
| <p> | |
| Analyse des sentiments · Sentiment Analysis | |
| </p> | |
| </div> | |
| """) | |
| language = gr.Radio( | |
| choices=[ | |
| ("Français", "fr"), | |
| ("العربية", "ar"), | |
| ("English", "en"), | |
| ], | |
| value="fr", | |
| label="Language / Langue / اللغة", | |
| elem_id="language-selector", | |
| ) | |
| with gr.Row( | |
| equal_height=True, | |
| elem_id="main-row", | |
| ): | |
| # INPUT | |
| with gr.Column( | |
| scale=6, | |
| min_width=300, | |
| ): | |
| text_input = gr.Textbox( | |
| lines=10, | |
| placeholder="اكتب نصا بالحسانية هنا...", | |
| label=( | |
| "Texte Hassaniya / " | |
| "النص الحساني / " | |
| "Hassaniya Text" | |
| ), | |
| value="أنا ماشي عجلان يحنين حد", | |
| elem_id="input-box", | |
| ) | |
| with gr.Row(elem_id="action-row"): | |
| analyze_btn = gr.Button( | |
| "🔍 Analyser / تحليل / Analyze", | |
| variant="primary", | |
| ) | |
| clear_btn = gr.Button( | |
| "🗑️ Clear / Effacer / مسح", | |
| elem_id="clear-button", | |
| ) | |
| # OUTPUT | |
| with gr.Column( | |
| scale=5, | |
| min_width=300, | |
| ): | |
| output = gr.HTML( | |
| value=""" | |
| <div class="result-card"> | |
| <h3 class="result-placeholder"> | |
| Result will appear here | |
| </h3> | |
| </div> | |
| """ | |
| ) | |
| # Examples | |
| gr.Examples( | |
| examples=[ | |
| ["ذ شغل زينة حته"], | |
| ["أنا ماشي عجلان يحنين حد"], | |
| ["الموقع عادي كاع ماه اكبر من كدو"], | |
| ["اشغل ما عجبتني"], | |
| ["شكرا بارك الله فيكم"], | |
| ], | |
| inputs=[text_input], | |
| label="Examples / Exemples / أمثلة", | |
| ) | |
| # Analyze | |
| analyze_btn.click( | |
| fn=predict_sentiment, | |
| inputs=[ | |
| text_input, | |
| language, | |
| ], | |
| outputs=output, | |
| ) | |
| # Press Enter | |
| text_input.submit( | |
| fn=predict_sentiment, | |
| inputs=[ | |
| text_input, | |
| language, | |
| ], | |
| outputs=output, | |
| ) | |
| # Clear | |
| clear_btn.click( | |
| fn=clear_fields, | |
| inputs=None, | |
| outputs=[ | |
| text_input, | |
| output, | |
| ], | |
| ) | |
| # ============================================================ | |
| # 7) START HUGGING FACE SPACE | |
| # ============================================================ | |
| if __name__ == "__main__": | |
| demo.launch( | |
| css=custom_css | |
| ) |