Prova Gemini 1.5 Pro, il nostro modello multimodale più avanzato di Vertex AI e scopri cosa puoi creare con una finestra di contesto dei token da 1 milione. Prova Gemini 1.5 Pro, il nostro modello multimodale più avanzato di Vertex AI e scopri cosa puoi creare con una finestra di contesto di 1 milione di token.

Analisi del sentiment in un file Cloud Storage

Esamina un file archiviato in Cloud Storage e identifica l'opinione emotiva prevalente all'interno del testo.

Per saperne di più

Per la documentazione dettagliata che include questo esempio di codice, vedi quanto segue:

Analisi del sentiment

Esempio di codice

Go

Per scoprire come installare e utilizzare la libreria client per Natural Language, consulta Librerie client di Natural Language. Per maggiori informazioni, consulta la documentazione di riferimento dell'API Natural Language Go.

Per eseguire l'autenticazione in Natural Language, imposta Credenziali predefinite dell'applicazione. Per maggiori informazioni, consulta Configurare l'autenticazione per un ambiente di sviluppo locale.


func analyzeSentimentFromGCS(ctx context.Context, gcsURI string) (*languagepb.AnalyzeSentimentResponse, error) {
	return client.AnalyzeSentiment(ctx, &languagepb.AnalyzeSentimentRequest{
		Document: &languagepb.Document{
			Source: &languagepb.Document_GcsContentUri{
				GcsContentUri: gcsURI,
			},
			Type: languagepb.Document_PLAIN_TEXT,
		},
	})
}

Java

// Instantiate the Language client com.google.cloud.language.v2.LanguageServiceClient
try (LanguageServiceClient language = LanguageServiceClient.create()) {
  Document doc =
      Document.newBuilder().setGcsContentUri(gcsUri).setType(Type.PLAIN_TEXT).build();
  AnalyzeSentimentResponse response = language.analyzeSentiment(doc);
  Sentiment sentiment = response.getDocumentSentiment();
  if (sentiment == null) {
    System.out.println("No sentiment found");
  } else {
    System.out.printf("Sentiment magnitude : %.3f\n", sentiment.getMagnitude());
    System.out.printf("Sentiment score : %.3f\n", sentiment.getScore());
  }
  return sentiment;
}

Node.js

// Imports the Google Cloud client library
const language = require('@google-cloud/language').v2;

// 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',
};

// Detects the sentiment of the document
const [result] = await client.analyzeSentiment({document});

const sentiment = result.documentSentiment;
console.log('Document sentiment:');
console.log(`  Score: ${sentiment.score}`);
console.log(`  Magnitude: ${sentiment.magnitude}`);

const sentences = result.sentences;
sentences.forEach(sentence => {
  console.log(`Sentence: ${sentence.text.content}`);
  console.log(`  Score: ${sentence.sentiment.score}`);
  console.log(`  Magnitude: ${sentence.sentiment.magnitude}`);
});

PHP

Per scoprire come installare e utilizzare la libreria client per Natural Language, consulta Librerie client di Natural Language.

use Google\Cloud\Language\V1\AnalyzeSentimentRequest;
use Google\Cloud\Language\V1\Client\LanguageServiceClient;
use Google\Cloud\Language\V1\Document;
use Google\Cloud\Language\V1\Document\Type;

/**
 * @param string $uri The cloud storage object to analyze (gs://your-bucket-name/your-object-name)
 */
function analyze_sentiment_from_file(string $uri): void
{
    $languageServiceClient = new LanguageServiceClient();

    // Create a new Document, pass GCS URI and set type to PLAIN_TEXT
    $document = (new Document())
        ->setGcsContentUri($uri)
        ->setType(Type::PLAIN_TEXT);

    // Call the analyzeSentiment function
    $request = (new AnalyzeSentimentRequest())
        ->setDocument($document);
    $response = $languageServiceClient->analyzeSentiment($request);
    $document_sentiment = $response->getDocumentSentiment();
    // Print document information
    printf('Document Sentiment:' . PHP_EOL);
    printf('  Magnitude: %s' . PHP_EOL, $document_sentiment->getMagnitude());
    printf('  Score: %s' . PHP_EOL, $document_sentiment->getScore());
    printf(PHP_EOL);
    $sentences = $response->getSentences();
    foreach ($sentences as $sentence) {
        printf('Sentence: %s' . PHP_EOL, $sentence->getText()->getContent());
        printf('Sentence Sentiment:' . PHP_EOL);
        $sentiment = $sentence->getSentiment();
        if ($sentiment) {
            printf('Entity Magnitude: %s' . PHP_EOL, $sentiment->getMagnitude());
            printf('Entity Score: %s' . PHP_EOL, $sentiment->getScore());
        }
        print(PHP_EOL);
    }
}

Python

from google.cloud import language_v2

def sample_analyze_sentiment(
    gcs_content_uri: str = "gs://cloud-samples-data/language/sentiment-positive.txt",
) -> None:
    """
    Analyzes Sentiment 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]
    """

    client = language_v2.LanguageServiceClient()

    # Available types: PLAIN_TEXT, HTML
    document_type_in_plain_text = language_v2.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_code = "en"
    document = {
        "gcs_content_uri": gcs_content_uri,
        "type_": document_type_in_plain_text,
        "language_code": language_code,
    }

    # Available values: NONE, UTF8, UTF16, UTF32
    # See https://cloud.google.com/natural-language/docs/reference/rest/v2/EncodingType.
    encoding_type = language_v2.EncodingType.UTF8

    response = client.analyze_sentiment(
        request={"document": document, "encoding_type": encoding_type}
    )
    # Get overall sentiment of the input document
    print(f"Document sentiment score: {response.document_sentiment.score}")
    print(f"Document sentiment magnitude: {response.document_sentiment.magnitude}")
    # Get sentiment for all sentences in the document
    for sentence in response.sentences:
        print(f"Sentence text: {sentence.text.content}")
        print(f"Sentence sentiment score: {sentence.sentiment.score}")
        print(f"Sentence sentiment magnitude: {sentence.sentiment.magnitude}")

    # Get the language of the text, which will be the same as
    # the language specified in the request or, if not specified,
    # the automatically-detected language.
    print(f"Language of the text: {response.language_code}")

Passaggi successivi

Per cercare e filtrare esempi di codice per altri prodotti Google Cloud, consulta il browser di esempio Google Cloud.