Spaces:
Runtime error
Runtime error
| import gradio as gr | |
| import pandas as pd | |
| from transformers import pipeline | |
| import matplotlib.pyplot as plt | |
| import io | |
| import base64 | |
| # Configurar el clasificador de sentimientos multilingüe | |
| classifier = pipeline(task="zero-shot-classification", model="facebook/bart-large-mnli") | |
| # Función para analizar los sentimientos de una lista de textos | |
| def analyze_sentiments(texts): | |
| if not texts: | |
| return "0.0%", "0.0%", "0.0%", None # Manejar el caso donde no hay textos para analizar | |
| positive, negative, neutral = 0, 0, 0 | |
| for text in texts: | |
| results = classifier(text, candidate_labels=["positive", "negative", "neutral"], multi_label=True) | |
| mx = max(results['scores']) | |
| ind = results['scores'].index(mx) | |
| result = results['labels'][ind] | |
| if result == "positive": | |
| positive += 1 | |
| elif result == "negative": | |
| negative += 1 | |
| else: | |
| neutral += 1 | |
| total = len(texts) | |
| positive_percent = round((positive / total) * 100, 1) | |
| negative_percent = round((negative / total) * 100, 1) | |
| neutral_percent = round((neutral / total) * 100, 1) | |
| # Crear el gráfico circular | |
| labels = 'Positivo', 'Negativo', 'Neutral' | |
| sizes = [positive_percent, negative_percent, neutral_percent] | |
| colors = ['#ff9999','#66b3ff','#99ff99'] | |
| fig, ax = plt.subplots() | |
| ax.pie(sizes, labels=labels, colors=colors, autopct='%1.1f%%', startangle=90) | |
| ax.axis('equal') # Para asegurar que el pie sea circular | |
| # Guardar el gráfico en un buffer de memoria | |
| buf = io.BytesIO() | |
| plt.savefig(buf, format='png') | |
| buf.seek(0) | |
| img_base64 = base64.b64encode(buf.read()).decode('utf-8') | |
| buf.close() | |
| return f"{positive_percent}%", f"{negative_percent}%", f"{neutral_percent}%", img_base64 | |
| # Función para cargar el archivo CSV y analizar los primeros 100 comentarios | |
| def analyze_sentiment_from_csv(file): | |
| try: | |
| df = pd.read_csv(file.name) | |
| if 'content' not in df.columns: | |
| raise ValueError("El archivo CSV no contiene una columna 'content'") | |
| texts = df['content'].head(100).tolist() # Tomar solo los primeros 100 comentarios | |
| return analyze_sentiments(texts) | |
| except pd.errors.ParserError as e: | |
| return f"Error al analizar el archivo CSV: {e}", "", "", None | |
| except Exception as e: | |
| return f"Error inesperado: {e}", "", "", None | |
| # Configurar la interfaz de Gradio | |
| demo = gr.Interface( | |
| fn=analyze_sentiment_from_csv, | |
| inputs=gr.File(file_count="single", label="Sube tu archivo CSV"), # Permitir la carga del archivo CSV | |
| outputs=[ | |
| gr.Textbox(label="Porcentaje Positivo"), | |
| gr.Textbox(label="Porcentaje Negativo"), | |
| gr.Textbox(label="Porcentaje Neutro"), | |
| gr.Image(label="Gráfico de Resultados") # Añadir un output para el gráfico | |
| ], | |
| title="Analizador de Sentimientos V.2", | |
| description="Porcentaje de comentarios positivos, negativos y neutrales" | |
| ) | |
| demo.launch(share=True) | |