Create app.py

app.py

@@ -0,0 +1,199 @@
+import os
+import torch
+import pandas as pd
+import gradio as gr
+from collections import defaultdict
+from transformers import AutoTokenizer, AutoModelForTokenClassification
+
+# =========================================================================
+# 1. Sabitler ve Model Yükleme
+# =========================================================================
+
+# Hugging Face Hub'daki Lemmatization modelinizin ID'si
+HF_MODEL_ID = "LiProject/BERT-Turkish-Lemmatization-V2" 
+
+# GPU/CPU kontrolü
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+
+try:
+    # Model ve Tokenizer'ı HF Hub'dan yükle
+    tok = AutoTokenizer.from_pretrained(HF_MODEL_ID, use_fast=True)
+    mdl = AutoModelForTokenClassification.from_pretrained(HF_MODEL_ID).to(DEVICE).eval()
+    print(f"Model yükleme başarılı: {HF_MODEL_ID} ({DEVICE} üzerinde)")
+
+except Exception as e:
+    print(f"Model veya Tokenizer yüklenirken kritik hata oluştu: {e}")
+    exit(1)
+
+# =========================================================================
+# 2. Etiket (Lemma) Okuma Fonksiyonları
+# =========================================================================
+
+def build_id2label_from_config(cfg):
+    # Modelin config dosyasından id2label'ı güvenilir bir şekilde okur
+    n = getattr(cfg, "num_labels", None)
+    if n is None:
+        if isinstance(getattr(cfg, "id2label", None), dict): n = len(cfg.id2label)
+        elif isinstance(getattr(cfg, "label2id", None), dict): n = len(cfg.label2id)
+        else: raise ValueError("num_labels/id2label/label2id yok.")
+    
+    labels = [f"LABEL_{i}" for i in range(n)]
+    id2label = getattr(cfg, "id2label", None)
+    
+    if id2label:
+        if isinstance(id2label, dict):
+            for k,v in id2label.items():
+                try: i = int(k)
+                except:
+                    try: i = int(float(k))
+                    except: continue
+                if 0 <= i < n: labels[i] = str(v)
+        elif isinstance(id2label, (list,tuple)) and len(id2label)==n:
+            labels = [str(x) for x in id2label]
+            
+    l2i = getattr(cfg, "label2id", None)
+    if isinstance(l2i, dict):
+        for lbl, idx_ in l2i.items():
+            try: i = int(idx_)
+            except:
+                try: i = int(float(idx_))
+                except: continue
+            if 0 <= i < n and labels[i].startswith("LABEL_"):
+                labels[i] = str(lbl)
+                
+    for i,v in enumerate(labels):
+        if v.startswith("LABEL_"): labels[i] = str(i)
+        
+    return labels
+
+ID2LABEL = build_id2label_from_config(mdl.config)
+
+# =========================================================================
+# 3. Inference ve Çıktı Formatı
+# =========================================================================
+
+@torch.inference_mode()
+def lemmatize_rows(multiline_text: str):
+    """Metni işler ve kelime bazlı kökleri içeren DataFrame döndürür."""
+    rows = []
+    sentences = [s.strip() for s in multiline_text.splitlines() if s.strip()]
+    
+    if not sentences:
+        return pd.DataFrame(rows)
+
+    for sent in sentences:
+        enc = tok(sent, return_tensors="pt", truncation=True, add_special_tokens=True).to(DEVICE)
+        logits = mdl(**enc).logits[0] 
+
+        fast = tok(sent, return_offsets_mapping=True, add_special_tokens=True)
+        word_ids = fast.word_ids()
+        offsets  = fast["offset_mapping"]
+
+        idxs_by_word = defaultdict(list)
+        for i, wid in enumerate(word_ids):
+            if wid is not None:
+                idxs_by_word[wid].append(i)
+
+        for wid in sorted(idxs_by_word.keys()):
+            sub_idxs = idxs_by_word[wid]
+
+            start = offsets[sub_idxs[0]][0]
+            end   = offsets[sub_idxs[-1]][1]
+            surface = sent[start:end] if (start is not None and end is not None) else ""
+
+            mean_logits = logits[sub_idxs].mean(dim=0)
+            pid = int(mean_logits.argmax().item())
+            
+            # Modelin tahmin ettiği kök (lemma)
+            lemma = ID2LABEL[pid] if pid < len(ID2LABEL) else str(pid)
+
+            rows.append({"Full_Sentence": sent, "Word": surface, "Lemma": lemma})
+
+    return pd.DataFrame(rows)
+
+def add_sentence_separators(df: pd.DataFrame, char: str = "-", repeat: int = 10) -> pd.DataFrame:
+    """Görünürlük için cümleler arasına ayraç satırları ekler."""
+    rows, prev = [], None
+    for _, r in df.iterrows():
+        if prev is not None and r["Full_Sentence"] != prev:
+            sep = char * repeat
+            rows.append({"Full_Sentence": sep, "Word": sep, "Lemma": sep})
+        rows.append(r.to_dict())
+        prev = r["Full_Sentence"]
+    return pd.DataFrame(rows)
+
+def run_and_save(text):
+    """Ana çalıştırma fonksiyonu, tabloyu ve indirilebilir CSV'yi hazırlar."""
+    df = lemmatize_rows(text)
+    df_view = add_sentence_separators(df, char="-", repeat=10)
+
+    out_path = "lemma_output.csv" 
+    df.to_csv(out_path, index=False) 
+
+    return df_view, out_path
+
+examples = [
+    "kedilerimizden biri çok hızlıca koştu",
+    "gözlükçüler dükkanlarını erkenden açtılar.",
+    "Bana hikayenin sonunu anlattılar."
+]
+
+# =========================================================================
+# 4. Gradio Arayüzü
+# =========================================================================
+
+theme = gr.themes.Soft(primary_hue="slate", neutral_hue="slate")
+custom_css = """
+/* Sayfa ve temel renkler */
+.gradio-container { background: #000000 !important; color: #FFE8DB !important; font-family: Inter, ui-sans-serif, system-ui, -apple-system, Segoe UI, Roboto, "Helvetica Neue", Arial, sans-serif; }
+.prose h1, .prose h2, .prose h3, .prose p, label { color: #FFE8DB !important; }
+.gr-box, .gr-panel, .border, .container { background: #0b0b0b !important; border: 1.5px solid #739EC9 !important; border-radius: 14px !important; }
+textarea, input, .gr-textbox, .gr-file, .gr-form input, .gr-form textarea { background: #0f1a26 !important; color: #FFE8DB !important; border: 2px solid #5682B1 !important; border-radius: 12px !important; }
+button { transition: background 0.15s ease, filter 0.15s ease, box-shadow 0.15s ease; }
+button.primary, .btn-primary { background: #FFE8DB !important; color: #000000 !important; }
+button.primary:hover, .btn-primary:hover { filter: brightness(0.92); }
+button.secondary, .btn-secondary { background: rgba(86,130,177,0.15) !important; color: #FFE8DB !important; }
+button.secondary:hover, .btn-secondary:hover { background: rgba(86,130,177,0.38) !important; border-color: #5682B1 !important; }
+table { border-collapse: separate !important; border-spacing: 0 !important; }
+th { background: #5682B1 !important; color: #FFE8DB !important; }
+td { background: #0f1a26 !important; color: #FFE8DB !important; }
+tbody tr:nth-child(2n) td { background: #122434 !important; }
+#results_table { max-height: 360px !important; overflow: auto !important; }
+#results_table table { table-layout: fixed !important; width: 100% !important; }
+#results_table th, #results_table td { white-space: normal !important; word-break: break-word !important; }
+#input_text textarea { min-height: 150px !important; }
+"""
+
+with gr.Blocks(title="TR Lemmatizer", theme=theme, css=custom_css, fill_height=True) as demo:
+    gr.Markdown("# 🇹🇷 Türkçe Lemmatization (Kök Bulma)")
+    gr.Markdown(f"Model: `{HF_MODEL_ID.split('/')[-1]}`. Metni satır satır girin. Çıktı: **Full_Sentence, Word, Lemma**.")
+
+    with gr.Row():
+        with gr.Column(scale=3):
+            inp = gr.Textbox(
+                lines=6,
+                placeholder="Örn:\nKedilerimizden biri hızlıca koştu.\nGözlükçüler dükkanlarını açtılar.",
+                show_label=False,
+                elem_id="input_text"
+            )
+        with gr.Column(scale=1):
+            btn = gr.Button("Kökleri Bul ve CSV indir", variant="primary", elem_id="run_btn")
+            clr = gr.Button("Temizle", variant="secondary", elem_id="clear_btn")
+
+    out_tbl = gr.Dataframe(
+        headers=["Full_Sentence","Word","Lemma"],
+        label="Önizleme",
+        interactive=False,
+        elem_id="results_table"
+    )
+
+    out_file = gr.File(label="Çıktı CSV (lemma_output.csv)")
+
+    gr.Examples(examples=[[e] for e in examples], inputs=inp)
+
+    btn.click(run_and_save, inputs=inp, outputs=[out_tbl, out_file])
+    inp.submit(run_and_save, inputs=inp, outputs=[out_tbl, out_file])
+    clr.click(lambda: ("", None, None), outputs=[inp, out_tbl, out_file])
+
+if __name__ == "__main__":
+    demo.launch(debug=True)