Update app.py

app.py

@@ -4,10 +4,9 @@ import torch
 import re
 from typing import Dict
 import textstat
-from fastapi import FastAPI
 
 # =======================
-# إعداد النموذج والمكتبات
+# إعداد النموذج
 # =======================
 MODEL_PATH = "GhadaAlothman/arabert_readability_3class"
 tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
@@ -19,15 +18,14 @@ AR_LETTERS = r"[\u0600-\u06FF]"
 SENT_SEP = re.compile(r"[\.!\?؟؛…]+")
 WORD_RE = re.compile(fr"{AR_LETTERS}+")
 
-
 # =======================
-# دوال المعالجة المساعدة
+# دوال المساعدة
 # =======================
 def strip_diacritics(s: str):
     return DIACRITICS.sub("", s)
 
 def normalize_arabic(s: str):
-    return re.sub("[\u0622\u0623\u0625]", "ا", strip_diacritics(s)).replace("ى", "ي").replace("ة", "ه")
+    return re.sub("[\u0622\u0623\u0625]", "ا", strip_diacritics(s)).replace("ى","ي").replace("ة","ه")
 
 def split_sentences(text: str):
     return [p.strip() for p in SENT_SEP.split(text) if p.strip()]
@@ -37,68 +35,32 @@ def tokenize_words(text: str):
 
 def difficult_word(w: str, min_len: int = 6):
     return len(w) >= min_len
-    
+
 def compute_metrics(ar_text: str) -> Dict[str, float]:
     text_norm = normalize_arabic(ar_text)
     sents = split_sentences(text_norm)
     words = tokenize_words(text_norm)
-    n_sents, n_words = max(len(sents), 1), max(len(words), 1)
+    n_sents, n_words = max(len(sents),1), max(len(words),1)
     diff_count = sum(1 for w in words if difficult_word(w))
     try:
         osman = float(textstat.osman(ar_text))
     except Exception:
         osman = 0.0
-
-    # 🔹 حساب عدد الأحرف (بدون مسافات)
     n_chars = sum(len(w) for w in words)
-
-    # 🔹 حساب مؤشر ARI للعربية
     ari_ar_score = round((4.71 * (n_chars / n_words)) + (0.5 * (n_words / n_sents)) - 21.43, 3)
-
     return {
         "Word count": n_words,
         "Sentence count": n_sents,
         "Character count": n_chars,
-        "OSMAN_Score": round(osman, 3),
+        "OSMAN_Score": round(osman,3),
         "ARI_ArScore": ari_ar_score,
         "Difficult_Words_Count": diff_count,
-        "Average_Sentence_Length_in_Words": round(n_words / n_sents, 3)
+        "Average_Sentence_Length_in_Words": round(n_words/n_sents,3)
     }
 
-
 # =======================
-# دالة التنبؤ بالنص
+# دالة التنبؤ
 # =======================
 def analyze_text(text):
     inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=128)
-    with torch.no_grad():
-        outputs = model(**inputs)
-        probs = torch.nn.functional.softmax(outputs.logits, dim=-1)
-        label_id = torch.argmax(probs, dim=1).item()
-    label_map = {0: "سهل", 1: "متوسط", 2: "صعب"}
-    label = label_map[label_id]
-    stats = compute_metrics(text)
-    return {"Predicted_Label": label, **stats}
-
-
-# =======================
-# واجهة Gradio + FastAPI
-# =======================
-app = FastAPI()
-
-demo = gr.Interface(
-    fn=analyze_text,
-    inputs=gr.Textbox(label="أدخل النص العربي هنا", lines=6),
-    outputs=gr.JSON(label="نتائج التحليل"),
-    title="Arabic Readability Analyzer",
-    description="أداة ذكية لتقييم مقروئية النصوص العربية باستخدام نموذج AraBERT.",
-)
-
-# واجهة المستخدم في المسار الرئيسي "/"
-app = gr.mount_gradio_app(app, demo, path="/")
-
-# ✅ واجهة REST API بسيطة في /predict
-@app.post("/predict")
-async def predict(request: dict):
-    text = request.get("text", "")
-    return analyze_text(text)
+    w