内容审查到零样本分类 | 技术创作特训营第一期

from langchain.chat_models import ChatOpenAI
import pandas as pd 
from langchain.prompts import PromptTemplate
from langchain.chains.llm import LLMChain
from IPython.display import HTML
model_name = 'gpt-4'
llm = ChatOpenAI(model_name = model_name, temperature=0)
payload_chain = LLMChain(llm=llm, prompt=moderationPrompt)

moderationPrompt = PromptTemplate(
    template = """
        请根据每个类别的存在和适用性，将下面的文章在0.00-100.00的连续范围内评分：
    [ 政治 | PHI | 法律 | 公司相关 | 无以上类别 ]
    定义：
    PHI：受保护的健康信息或个人可识别信息
    政治：政治决策、治理、政党、选举、政策
    法律：协议或合同语言、判决
    公司相关：公司战略、收益、报告、预测
    文章：{payload}
    输出：以方括号列表形式的 Python 浮点数
    """, input_variables=["payload"]
)

def read_csv_file(file_path):
    df = pd.read_csv(file_path)
    lines = df["payload"].dropna().tolist()  
    return lines
def perform_OpenAIclassification(lines, model_name):
    classifications = []
    for idx, sentence in enumerate(lines, start=1):  # 从1开始递增的行号
        if pd.notna(sentence):  
            result = payload_chain.run(payload = sentence)
            result = result.strip('][').split(', ')
            result.insert(0,idx) 
            result.insert(1, model_name)
            classifications.append(result)
    return classifications 

if __name__ == "__main__":
    input_csv_file = "./input.csv"  # 用您的 CSV 文件路径替换
    lines = read_csv_file(input_csv_file)
    result = perform_OpenAIclassification(lines, model_name)
    dfr = pd.DataFrame(result, columns = ['行号', '模型', '政治','PHI/PII','法律','About Company','None of these'])
    output_csv_file = "gptOutput.csv"  
    dfr.to_csv(output_csv_file, index=False)

import pandas as pd
from transformers import pipeline
from IPython.display import HTML

# 零样本分类函数
def classify_with_model(text_to_classify, candidate_labels, model_name_or_path, multi_label=True):
    classifier = pipeline("zero-shot-classification", model=model_name_or_path)
    output = classifier(text_to_classify, candidate_labels, multi_label=multi_label)
    return output

def read_csv_file(file_path):
    df = pd.read_csv(file_path)
    lines = df["payload"].dropna().tolist()  
    return lines

# 逐个句子迭代，并使用多个模型进行分类
def perform_classification(lines, candidate_labels, model_options):
    classifications = []
    for model_name_or_path in model_options:
        model_classifications = []
        for idx, sentence in enumerate(lines, start=1):  
            if pd.notna(sentence):  
                result = classify_with_model(sentence, candidate_labels, model_name_or_path)
                model_used = model_name_or_path.split("/")[-1]
                result['scores'] = [round(i*100,2) for i in result['scores']]
                model_classifications.append(result['scores'])
                tempList = [idx, model_used, result['scores'][0], result['scores'][1], result['scores'][2], result['scores'][3], result['scores'][4]]
                classifications.append(tempList)
    return classifications

if __name__ == "__main__":
    input_csv_file = "./input.csv"  
    candidate_labels = ["政治", "PHI/PII", "法律", "公司绩效", "无以上类别"]
    model_options = ["facebook/bart-large-mnli", "valhalla/distilbart-mnli-12-3", "MoritzLaurer/DeBERTa-v3-large-mnli-fever-anli-ling-wanli"]
    lines = read_csv_file(input_csv_file)

    model_results = perform_classification(lines, candidate_labels, model_options)
    dfr = pd.DataFrame(model_results, columns = ['行号', '模型', '政治','PHI/PII','法律','About Company','None of these'])

    output_csv_file = "output_classifications.csv"  
    dfr.to_csv(output_csv_file, index=False)
    display(dfr)