Create app.py

app.py

@@ -0,0 +1,95 @@
+from transformers import pipeline
+import gradio as gr
+import docx
+import pandas as pd
+
+# Cargar el modelo NER
+model_name = "johnyyhk/bert-finetuned-ner-chinese-people-daily"
+get_completion = pipeline("ner", model=model_name)
+
+# Función para fusionar tokens
+def merge_tokens(tokens):
+    merged_tokens = []
+    for token in tokens:
+        if merged_tokens and token['entity'].startswith('I-') and merged_tokens[-1]['entity'].endswith(token['entity'][2:]):
+            # Si el token continúa la entidad del anterior, fusiónalos
+            last_token = merged_tokens[-1]
+            last_token['word'] += token['word'].replace('##', '')
+            last_token['end'] = token['end']
+            last_token['score'] = (last_token['score'] + token['score']) / 2
+        else:
+            # De lo contrario, agrega el token a la lista
+            merged_tokens.append(token)
+    return merged_tokens
+
+# Extraer nombres de personas de la respuesta del modelo
+def extract_person_names(tokens):
+    names = []
+    current_name = ""
+    for token in tokens:
+        if token['entity'] == 'B-PER':
+            if current_name:
+                names.append(current_name)
+            current_name = token['word']
+        elif token['entity'] == 'I-PER' and current_name:
+            current_name += token['word']
+        else:
+            if current_name:
+                names.append(current_name)
+                current_name = ""
+    if current_name:
+        names.append(current_name)
+    return list(set(names))  # Eliminar duplicados
+
+# Procesar el archivo DOCX
+def process_docx(file_path):
+    doc = docx.Document(file_path)
+    paragraphs = []
+    for p in doc.paragraphs:
+        text = p.text.strip()
+        if text:
+            # Dividir por saltos de línea internos si existen
+            sub_paragraphs = text.split("\n")
+            paragraphs.extend([sub_p.strip() for sub_p in sub_paragraphs if sub_p.strip()])
+    return paragraphs
+
+# Crear bloques de párrafos
+def create_paragraph_blocks(paragraphs, block_size=4):
+    return ["\n".join(paragraphs[i:i + block_size]) for i in range(0, len(paragraphs), block_size)]
+
+# Función principal de procesamiento
+def process_ner(file):
+    paragraphs = process_docx(file.name)
+    paragraph_blocks = create_paragraph_blocks(paragraphs)
+
+    all_names = []
+    for block in paragraph_blocks:
+        tokens = get_completion(block)
+        merged_tokens = merge_tokens(tokens)
+        names = extract_person_names(merged_tokens)
+        all_names.extend(names)
+
+    all_names = list(set(all_names))  # Eliminar duplicados
+
+    # Guardar en un archivo Excel
+    df = pd.DataFrame({'Person Names': all_names})
+    output_path = "ner_output.xlsx"
+    df.to_excel(output_path, index=False)
+
+    return output_path
+
+# Gradio interfaz
+def ner_interface(file):
+    output_path = process_ner(file)
+    return f"NER completado. Archivo guardado en: {output_path}", output_path
+
+demo = gr.Interface(
+    fn=ner_interface,
+    inputs=gr.File(label="Sube un archivo DOCX"),
+    outputs=[gr.Textbox(label="Resultado"), gr.File(label="Descargar archivo")],
+    title="NER de Nombres de Personas",
+    description="Extrae nombres de personas desde un archivo DOCX usando NER y guarda los resultados en un archivo Excel.",
+    allow_flagging="never"
+)
+
+demo.launch(inline=False)