SentiNel/Entity_Label_Assist.py at master · ece324-2019/SentiNel · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
from google.cloud import language_v1
from google.cloud.language_v1 import enums
import pandas as pd

def sample_analyze_entity_sentiment(text_content):
    """
    Analyzing Entity Sentiment in a String

    Args:
      text_content The text content to analyze
    """

    client = language_v1.LanguageServiceClient()


    # Available types: PLAIN_TEXT, HTML
    type_ = enums.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}

    # Available values: NONE, UTF8, UTF16, UTF32
    encoding_type = enums.EncodingType.UTF8

    response = client.analyze_entity_sentiment(document, encoding_type=encoding_type)
    # Loop through entitites returned from the API
    result = []
    for entity in response.entities:
        e_result = []
        # print(u"Representative name for the entity: {}".format(entity.name))
        e_result.append(entity.name)
        # Get entity type, e.g. PERSON, LOCATION, ADDRESS, NUMBER, et al
        # print(u"Entity type: {}".format(enums.Entity.Type(entity.type).name))
        e_result.append(enums.Entity.Type(entity.type).name)

        # Get the salience score associated with the entity in the [0, 1.0] range
        # print(u"Salience score: {}".format(entity.salience))
        # Get the aggregate sentiment expressed for this entity in the provided document.
        e_result.append(entity.salience)

        sentiment = entity.sentiment
        e_result.append(entity.sentiment.score)
        #
        # print(u"Entity sentiment score: {}".format(sentiment.score))
        # print(u"Entity sentiment magnitude: {}".format(sentiment.magnitude))
        e_result.append(entity.sentiment.magnitude)

        # Loop over the metadata associated with entity. For many known entities,
        # the metadata is a Wikipedia URL (wikipedia_url) and Knowledge Graph MID (mid).
        # Some entity types may have additional metadata, e.g. ADDRESS entities
        # may have metadata for the address street_name, postal_code, et al.
        # for metadata_name, metadata_value in entity.metadata.items():
            # print(u"{} = {}".format(metadata_name, metadata_value))

        # Loop over the mentions of this entity in the input document.
        # The API currently supports proper noun mentions.
        # for mention in entity.mentions:
            # print(u"Mention text: {}".format(mention.text.content))
            # Get the mention type, e.g. PROPER for proper noun
            # print(
            #     u"Mention type: {}".format(enums.EntityMention.Type(mention.type).name)
            # )
        result.append(e_result)
    return result

    # 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(u"Language of the text: {}".format(response.language))