This repository has been archived by the owner on Sep 5, 2023. It is now read-only.
/
language_classify_text.py
81 lines (62 loc) · 2.82 KB
/
language_classify_text.py
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
73
74
75
76
77
78
79
80
81
# -*- coding: utf-8 -*-
#
# Copyright 2020 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# https://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# DO NOT EDIT! This is a generated sample ("Request", "language_classify_text")
# To install the latest published package dependency, execute the following:
# pip install google-cloud-language
# sample-metadata
# title: Classify Content
# description: Classifying Content in a String
# usage: python3 samples/v1/language_classify_text.py [--text_content "That actor on TV makes movies in Hollywood and also stars in a variety of popular new TV shows."]
# [START language_classify_text]
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))
# [END language_classify_text]
def main():
import argparse
parser = argparse.ArgumentParser()
parser.add_argument(
"--text_content",
type=str,
default="That actor on TV makes movies in Hollywood and also stars in a variety of popular new TV shows.",
)
args = parser.parse_args()
sample_classify_text(args.text_content)
if __name__ == "__main__":
main()