Esta página foi traduzida pela API Cloud Translation.
Switch to English

Como classificar conteúdo

A classificação de conteúdo analisa um documento e retorna uma lista de categorias de conteúdo que se aplicam ao texto encontrado no documento. Para classificar o conteúdo de um documento, chame o método classifyText.

Uma lista completa das categorias de conteúdo retornadas pelo método classifyText é encontrada aqui.

Nesta seção, veja como classificar o conteúdo em um documento. Para cada documento, é preciso enviar uma solicitação separada.

Como classificar conteúdo

Aqui está um exemplo de como classificar o conteúdo fornecido como uma string:

Protocolo

Para classificar o conteúdo de um documento, faça uma solicitação POST ao método REST documents:classifyText e forneça o corpo da solicitação apropriada, como mostrado no exemplo a seguir.

No exemplo, o comando gcloud auth application-default print-access-token é usado para gerar um token de acesso para uma conta de serviço configurada para o projeto usando o SDK do Cloud do Google Cloud Platform. Para ver instruções sobre como instalar o SDK do Cloud, configurar um projeto com uma conta de serviço, consulte o Guia de início rápido.

curl -X POST \
     -H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
     -H "Content-Type: application/json; charset=utf-8" \
     --data "{
  'document':{
    'type':'PLAIN_TEXT',
    'content':'Google, headquartered in Mountain View, unveiled the new Android
    phone at the Consumer Electronic Show.  Sundar Pichai said in his keynote
    that users love their new Android phones.'
  }
}" "https://language.googleapis.com/v1/documents:classifyText"

Go


func classifyText(ctx context.Context, client *language.Client, text string) (*languagepb.ClassifyTextResponse, error) {
	return client.ClassifyText(ctx, &languagepb.ClassifyTextRequest{
		Document: &languagepb.Document{
			Source: &languagepb.Document_Content{
				Content: text,
			},
			Type: languagepb.Document_PLAIN_TEXT,
		},
	})
}

Java

// Instantiate the Language client com.google.cloud.language.v1.LanguageServiceClient
try (LanguageServiceClient language = LanguageServiceClient.create()) {
  // set content to the text string
  Document doc = Document.newBuilder().setContent(text).setType(Type.PLAIN_TEXT).build();
  ClassifyTextRequest request = ClassifyTextRequest.newBuilder().setDocument(doc).build();
  // detect categories in the given text
  ClassifyTextResponse response = language.classifyText(request);

  for (ClassificationCategory category : response.getCategoriesList()) {
    System.out.printf(
        "Category name : %s, Confidence : %.3f\n",
        category.getName(), category.getConfidence());
  }
}

Node.js

// Imports the Google Cloud client library
const language = require('@google-cloud/language');

// Creates a client
const client = new language.LanguageServiceClient();

/**
 * TODO(developer): Uncomment the following line to run this code.
 */
// const text = 'Your text to analyze, e.g. Hello, world!';

// Prepares a document, representing the provided text
const document = {
  content: text,
  type: 'PLAIN_TEXT',
};

// Classifies text in the document
const [classification] = await client.classifyText({document});
console.log('Categories:');
classification.categories.forEach(category => {
  console.log(`Name: ${category.name}, Confidence: ${category.confidence}`);
});

Python

from google.cloud import language_v1

def sample_classify_text(text_content):
    """
    Classifying Content in a String

    Args:
      text_content The text content to analyze. Must include at least 20 words.
    """

    client = language_v1.LanguageServiceClient()

    # text_content = 'That actor on TV makes movies in Hollywood and also stars in a variety of popular new TV shows.'

    # Available types: PLAIN_TEXT, HTML
    type_ = language_v1.Document.Type.PLAIN_TEXT

    # Optional. If not specified, the language is automatically detected.
    # For list of supported languages:
    # https://cloud.google.com/natural-language/docs/languages
    language = "en"
    document = {"content": text_content, "type_": type_, "language": language}

    response = client.classify_text(request = {'document': document})
    # Loop through classified categories returned from the API
    for category in response.categories:
        # Get the name of the category representing the document.
        # See the predefined taxonomy of categories:
        # https://cloud.google.com/natural-language/docs/categories
        print(u"Category name: {}".format(category.name))
        # Get the confidence. Number representing how certain the classifier
        # is that this category represents the provided text.
        print(u"Confidence: {}".format(category.confidence))

Como classificar o conteúdo do Cloud Storage

Veja um exemplo de classificação de conteúdo armazenado em um arquivo de texto no Cloud Storage:

Protocolo

Para classificar o conteúdo de um documento armazenado no Cloud Storage, crie uma solicitação POST para o método REST documents:classifyText e forneça a solicitação apropriada body com o caminho para o documento, como no exemplo a seguir.

curl -X POST \
     -H "Authorization: Bearer "$(gcloud auth application-default print-access-token) \
     -H "Content-Type: application/json; charset=utf-8" \
     --data "{
  'document':{
    'type':'PLAIN_TEXT',
    'gcsContentUri':'gs://<bucket-name>/<object-name>'
  }
}" "https://language.googleapis.com/v1/documents:classifyText"

Go


func classifyTextFromGCS(ctx context.Context, gcsURI string) (*languagepb.ClassifyTextResponse, error) {
	return client.ClassifyText(ctx, &languagepb.ClassifyTextRequest{
		Document: &languagepb.Document{
			Source: &languagepb.Document_GcsContentUri{
				GcsContentUri: gcsURI,
			},
			Type: languagepb.Document_PLAIN_TEXT,
		},
	})
}

Java

// Instantiate the Language client com.google.cloud.language.v1.LanguageServiceClient
try (LanguageServiceClient language = LanguageServiceClient.create()) {
  // set the GCS content URI path
  Document doc =
      Document.newBuilder().setGcsContentUri(gcsUri).setType(Type.PLAIN_TEXT).build();
  ClassifyTextRequest request = ClassifyTextRequest.newBuilder().setDocument(doc).build();
  // detect categories in the given file
  ClassifyTextResponse response = language.classifyText(request);

  for (ClassificationCategory category : response.getCategoriesList()) {
    System.out.printf(
        "Category name : %s, Confidence : %.3f\n",
        category.getName(), category.getConfidence());
  }
}

Node.js

// Imports the Google Cloud client library.
const language = require('@google-cloud/language');

// Creates a client.
const client = new language.LanguageServiceClient();

/**
 * TODO(developer): Uncomment the following lines to run this code
 */
// const bucketName = 'Your bucket name, e.g. my-bucket';
// const fileName = 'Your file name, e.g. my-file.txt';

// Prepares a document, representing a text file in Cloud Storage
const document = {
  gcsContentUri: `gs://${bucketName}/${fileName}`,
  type: 'PLAIN_TEXT',
};

// Classifies text in the document
const [classification] = await client.classifyText({document});

console.log('Categories:');
classification.categories.forEach(category => {
  console.log(`Name: ${category.name}, Confidence: ${category.confidence}`);
});

Python

from google.cloud import language_v1

def sample_classify_text(gcs_content_uri):
    """
    Classifying Content in text file stored in Cloud Storage

    Args:
      gcs_content_uri Google Cloud Storage URI where the file content is located.
      e.g. gs://[Your Bucket]/[Path to File]
      The text file must include at least 20 words.
    """

    client = language_v1.LanguageServiceClient()

    # gcs_content_uri = 'gs://cloud-samples-data/language/classify-entertainment.txt'

    # Available types: PLAIN_TEXT, HTML
    type_ = language_v1.Document.Type.PLAIN_TEXT

    # Optional. If not specified, the language is automatically detected.
    # For list of supported languages:
    # https://cloud.google.com/natural-language/docs/languages
    language = "en"
    document = {"gcs_content_uri": gcs_content_uri, "type_": type_, "language": language}

    response = client.classify_text(request = {'document': document})
    # Loop through classified categories returned from the API
    for category in response.categories:
        # Get the name of the category representing the document.
        # See the predefined taxonomy of categories:
        # https://cloud.google.com/natural-language/docs/categories
        print(u"Category name: {}".format(category.name))
        # Get the confidence. Number representing how certain the classifier
        # is that this category represents the provided text.
        print(u"Confidence: {}".format(category.confidence))