Bairly/statistics_model2025
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

modify

Browse Source
This commit is contained in:
Bairly 2025-03-29 15:41:31 +08:00
parent c94cfe4ab0
commit 3a996704a1
2 changed files with 157 additions and 51 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

65
弹幕情感评分-字典法.py
View File

@ -1,6 +1,7 @@
import pandas as pd
import numpy as np
from snownlp import SnowNLP
import matplotlib.pyplot as plt
import os
def load_data(file_path):
try:
@ -10,21 +11,53 @@ def load_data(file_path):
print(f"数据加载失败: {str(e)}")
return []
# 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)
def analyze_sentiment(danmu_texts):
emotions = {'positive': 0, 'negative': 0, 'neutral': 0}
sentiment_scores = []
emotions = {'positive': 0,
'negative': 0,
'neutral': 0}
for item in danmu_texts:
s = SnowNLP(item)
score = s.sentiments
sentiment_scores.append(score)
if score > 0.6:
emotions['positive'] += 1
elif score < 0.4:
emotions['negative'] += 1
else:
emotions['neutral'] += 1
for item in danmu_texts:
s = SnowNLP(item)
if s.sentiments > 0.6:
emotions['positive'] += 1
elif s.sentiments < 0.4:
emotions['negative'] += 1
else:
emotions['neutral'] += 1
avg_score = np.mean(sentiment_scores)
return emotions, avg_score
def process_partition(partition_path):
info_file = os.path.join(partition_path, 'info.csv')
if not os.path.exists(info_file):
print(f"未找到info文件: {info_file}")
return
info_df = pd.read_csv(info_file,encoding='utf-8')
scores = []
for bv in info_df['BV号']:
danmu_file = os.path.join(partition_path, bv, f"{bv}_273_danmaku.csv")
if not os.path.exists(danmu_file):
scores.append(None)
continue
danmu_texts = load_data(danmu_file)
if not danmu_texts:
scores.append(None)
continue
_, avg_score = analyze_sentiment(danmu_texts)
scores.append(avg_score)
info_df['情感评分'] = scores
info_df.to_csv(info_file, index=False)
# 使用示例 - 处理GMV分区
partition_path = "hot_data/GMV"
process_partition(partition_path)

143
弹幕情感评分.py
View File

@ -1,43 +1,116 @@
import pandas as pd
import torch
from modelscope import AutoModelForSequenceClassification, AutoTokenizer
from transformers import AutoTokenizer, AutoModelForSequenceClassification
from pathlib import Path
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"""
# 使用模型配置
model_name = "damo/nlp_structbert_sentiment-classification_chinese-base"
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()
class SentimentAnalyzer:
def __init__(self, model_path: str = "uer/roberta-base-finetuned-dianping-chinese"):
"""
初始化情感分析模型
:param model_path: 本地模型路径或HuggingFace模型名称
"""
self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
try:
# 优先尝试加载本地模型
local_path = Path(model_path)
if local_path.exists():
self.tokenizer = AutoTokenizer.from_pretrained(local_path)
self.model = AutoModelForSequenceClassification.from_pretrained(local_path)
else:
# 从HuggingFace加载（使用国内镜像）
self.tokenizer = AutoTokenizer.from_pretrained(model_path,
mirror="https://hf-mirror.com")
self.model = AutoModelForSequenceClassification.from_pretrained(model_path,
mirror="https://hf-mirror.com")
self.model = self.model.to(self.device)
self.model.eval()
print(f"成功加载模型: {model_path}")
except Exception as e:
raise RuntimeError(f"模型加载失败: {str(e)}")
def analyze(self, texts: list, batch_size: int = 32) -> list:
"""
批量情感分析
:param texts: 待分析文本列表
:param batch_size: 批处理大小
:return: 情感概率列表（0-1之间）
"""
if not texts:
return []
# 自动调整批大小防止内存溢出
mem = torch.cuda.mem_get_info()[0] if torch.cuda.is_available() else 2e9
safe_batch_size = min(batch_size, max(1, int(mem // 1e7)))
all_probs = []
for i in range(0, len(texts), safe_batch_size):
batch = texts[i:i + safe_batch_size]
try:
inputs = self.tokenizer(
batch,
padding=True,
truncation=True,
max_length=128,
return_tensors="pt"
).to(self.device)
with torch.no_grad():
outputs = self.model(**inputs)
probs = torch.softmax(outputs.logits, dim=1)[:, 1]
all_probs.extend(probs.cpu().numpy().tolist())
except RuntimeError as e:
if "CUDA out of memory" in str(e):
safe_batch_size = max(1, safe_batch_size // 2)
print(f"检测到显存不足，调整批大小为: {safe_batch_size}")
continue
raise
return all_probs
# ----------------- 使用示例 -----------------
if __name__ == "__main__":
# 示例文件路径
file_path = "hot_data/GMV/BV1ajXMYUE6S/BV1ajXMYUE6S_273_danmaku.csv"
# 初始化分析器（自动选择本地/在线模型）
analyzer = SentimentAnalyzer("./local_models/sentiment") # 优先尝试本地模型
# 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")
# 测试数据
test_texts = [
"这个视频真的太棒了！",
"完全看不懂在讲什么",
"浪费时间，不建议观看",
"画面精美，内容有深度"
]
# 获取情感概率
scores = analyzer.analyze(test_texts)
# 输出结果
for text, score in zip(test_texts, scores):
print(f"「{text}」=> 积极概率: {score:.4f}")
# 从CSV文件读取弹幕
def load_danmu(file_path: str) -> list:
try:
df = pd.read_csv(file_path)
return df['弹幕内容'].dropna().astype(str).tolist()
except Exception as e:
print(f"文件读取失败: {str(e)}")
return []
# 实际使用
# 文件路径
file_path = "hot_data/GMV/BV1ajXMYUE6S/BV1ajXMYUE6S_273_danmaku.csv"
danmu_list = load_danmu(file_path)
if danmu_list:
danmu_scores = analyzer.analyze(danmu_list)
avg_score = sum(danmu_scores) / len(danmu_scores)
print(f"\n弹幕平均情感评分：{avg_score:.4f}")