[A-00093]pythonでNatural Language API(GCP)を使用する

Google Cloudが提供するNatural Language APIをpythonで使用する方法を記載する。

公式ドキュメントは下記

https://cloud.google.com/natural-language?hl=ja

・セットアップ

pythonライブラリをインストールします。

pip install --upgrade google-cloud-language

・簡単な感情分析を行う

お決まりの[Hello,world!]をAPIに読み込ませてみます。

# Imports the Google Cloud client library
from google.cloud import language_v1

# Instantiates a client
client = language_v1.LanguageServiceClient()

# The text to analyze
text = "Hello, world!"
document = language_v1.types.Document(
    content=text, type_=language_v1.types.Document.Type.PLAIN_TEXT
)

# Detects the sentiment of the text
sentiment = client.analyze_sentiment(
    request={"document": document}
).document_sentiment

print(f"Text: {text}")
print(f"Sentiment: {sentiment.score}, {sentiment.magnitude}")

(.venv)MacBook-Pro:test2_project$ python3 languagetest.py 
Text: Hello, world!
Sentiment: 0.6000000238418579, 0.6000000238418579

・文章の分析を行う

次に文章の分析を行います。

サンプルテキストは下記のとおりです。

中身は英語ですが、「退屈」「感傷的」「とても悪い」などのネガティブワードを入れています。

import argparse

from google.cloud import language_v1


def print_result(annotations):
    score = annotations.document_sentiment.score
    magnitude = annotations.document_sentiment.magnitude

    for index, sentence in enumerate(annotations.sentences):
        sentence_sentiment = sentence.sentiment.score
        print(f"Sentence {index} has a sentiment score of {sentence_sentiment}")

    print(f"Overall Sentiment: score of {score} with magnitude of {magnitude}")
    return 0


def analyze(movie_review_filename):
    """Run a sentiment analysis request on text within a passed filename."""
    client = language_v1.LanguageServiceClient()

    with open(movie_review_filename) as review_file:
        # Instantiates a plain text document.
        content = review_file.read()

    document = language_v1.Document(
        content=content, type_=language_v1.Document.Type.PLAIN_TEXT
    )
    annotations = client.analyze_sentiment(request={"document": document})

    # Print the results
    print_result(annotations)


if __name__ == "__main__":
    parser = argparse.ArgumentParser(
        description=__doc__, 
        formatter_class=argparse.RawDescriptionHelpFormatter
    )
    parser.add_argument(
        "movie_review_filename",
        help="The filename of the movie review you'd like to analyze.",
    )
    args = parser.parse_args()

    analyze(args.movie_review_filename)

python3 languagetest2.py ./docs/movie_review.txt

(.venv)MacBook-Pro:test2_project$ python3 languagetest2.py ./docs/movie_review.txt
Sentence 0 has a sentiment score of -0.800000011920929
Sentence 1 has a sentiment score of -0.6000000238418579
Sentence 2 has a sentiment score of -0.800000011920929
Overall Sentiment: score of -0.800000011920929 with magnitude of 2.4000000953674316

上記の通り、感情分析を数値で表示してくれました。ちなみに表示は行ごとに行われるようです。