statistics_model2025/弹幕情感评分.py

import pandas as pd
import torch
from transformers import AutoModelForSequenceClassification, AutoTokenizer  # 修改为从transformers导入


def load_data(file_path):
    """优化后的数据加载函数"""
    try:
        df = pd.read_csv(file_path, usecols=['弹幕内容'], engine='python')
        return df['弹幕内容'].dropna().astype(str).tolist()
    except Exception as e:
        print(f"数据加载失败: {str(e)}")
        return []


def analyze_sentiment(texts):
    """改进的情感分析函数"""
    # 使用新的模型配置
    model_name = "IDEA-CCNL/Erlangshen-Roberta-330M-Sentiment"
    try:
        tokenizer = AutoTokenizer.from_pretrained(model_name)
        model = AutoModelForSequenceClassification.from_pretrained(model_name)

        # 批量处理提升效率
        inputs = tokenizer(texts, padding=True, truncation=True, max_length=128, return_tensors="pt")
        with torch.no_grad():
            outputs = model(**inputs)

        # 调整概率计算方式
        probs = torch.softmax(outputs.logits, dim=1)
        return probs[:, 1].mean().item()  # 假设正例在位置1

    except Exception as e:
        print(f"模型加载失败: {str(e)}")
        return 0.5  # 返回中性评分作为默认值


if __name__ == "__main__":
    # 示例文件路径
    file_path = "hot_data/GMV/BV1ajXMYUE6S/BV1ajXMYUE6S_273_danmaku.csv"

    # 执行分析
    danmu_texts = load_data(file_path)
    if danmu_texts:
        final_score = analyze_sentiment(danmu_texts)
        print(f"B站弹幕情感评分：{final_score:.4f}")
    else:
        print("未找到有效弹幕数据")