azure - Python - 分析法语文本。法国参数？

Question

我真的不明白如果我想将其用于法语文本是否需要设置一些特定的内容。我已阅读 Azure 文档。他们说使用“fr”代码。但我真的不知道该把它放在哪里。你有什么主意吗？

#Azure lib

from azure.ai.textanalytics import TextAnalyticsClient

from azure.core.credentials import AzureKeyCredential

azurekey = ""

azureendpoint = ""

def authenticate_client():

    ta_credential = AzureKeyCredential(azurekey)

    text_analytics_client = TextAnalyticsClient(

            endpoint=azureendpoint, 

            credential=ta_credential)

    return text_analytics_client

clientazure = authenticate_client()

if self.content:

            documents = [self.content]

            

            response = clientazure.analyze_sentiment(documents = documents)[0]

            try:

                self.emotion = "sentiment: {}".format(response.sentiment) + " detail: positive={0:.2f}; neutral={1:.2f}; negative={2:.2f} \n".format(response.confidence_scores.positive,response.confidence_scores.neutral,response.confidence_scores.negative,)

            except Exception as e:

                self.emotion = None

                

            result = clientazure.recognize_entities(documents = documents)[0]

            for entity in result.entities:

                try:

                    self.topic = entity.text

                except Exception as e:

                    self.topic = None

                try:

                    self.category = entity.category

                except Exception as e:

                    self.category = None

Answer 1

语言代码可以放置在每个文本文档中，也可以放置在整个批次中。analyze_sentiment()如果您想"fr"申请所有文件，请将其传递到电话中：response = clientazure.analyze_sentiment(documents = documents, language="fr")如果只想将语言代码应用于单个文档，请在文档级别传递语言代码。假设self.content包含您要分析的文本，它看起来像这样：documents = [{"id": "1", "language": "fr", "text": self.content}]