Create app.py

app.py

@@ -0,0 +1,63 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+import re
+from typing import Dict
+import textstat
+
+# ---------- تحميل الموديل ----------
+MODEL_PATH = "GhadaAlothman/arabert_readability_3class"  # بعد شوي نشرح كيف ترفعين مودلك له
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
+model = AutoModelForSequenceClassification.from_pretrained(MODEL_PATH)
+model.eval()
+
+# ---------- كود التحليل الإحصائي ----------
+DIACRITICS = re.compile(r"[\u0610-\u061A\u064B-\u065F\u0670\u06D6-\u06ED]")
+AR_LETTERS = r"[\u0600-\u06FF]"
+SENT_SEP = re.compile(r"[\.!\?؟؛…]+")
+WORD_RE = re.compile(fr"{AR_LETTERS}+")
+
+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")
+def split_sentences(text: str): return [p.strip() for p in SENT_SEP.split(text) if p.strip()]
+def tokenize_words(text: str): return WORD_RE.findall(text)
+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)
+    diff_count = sum(1 for w in words if difficult_word(w))
+    try: osman = float(textstat.osman(ar_text))
+    except Exception: osman = 0.0
+    return {
+        "Word count": n_words,
+        "Sentence count": n_sents,
+        "OSMAN_Score": round(osman,3),
+        "Difficult_Words_Count": diff_count,
+        "Average_Sentence_Length_in_Words": round(n_words/n_sents,3)
+    }
+
+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 f"🔹 التصنيف: {label}\n\n" + "\n".join([f"{k}: {v}" for k,v in stats.items()])
+
+demo = gr.Interface(
+    fn=analyze_text,
+    inputs=gr.Textbox(label="أدخل النص العربي هنا", lines=6, placeholder="ألصق النشرة أو النص العربي هنا..."),
+    outputs=gr.Textbox(label="نتائج التحليل", lines=10),
+    title="Arabic Readability Analyzer",
+    description="أداة ذكية لتقييم مقروئية النصوص العربية وحساب مؤشراتها الإحصائية باستخدام نموذج AraBERT"
+)
+
+demo.launch()