-
Notifications
You must be signed in to change notification settings - Fork 1.5k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
19 changed files
with
1,426 additions
and
11 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
85 changes: 85 additions & 0 deletions
85
packages/google-cloud-language/samples/v1/language_classify_gcs.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,85 @@ | ||
# -*- coding: utf-8 -*- | ||
# | ||
# Copyright 2019 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_gcs") | ||
|
||
# To install the latest published package dependency, execute the following: | ||
# pip install google-cloud-language | ||
|
||
# sample-metadata | ||
# title: Classify Content (GCS) | ||
# description: Classifying Content in text file stored in Cloud Storage | ||
# usage: python3 samples/v1/language_classify_gcs.py [--gcs_content_uri "gs://cloud-samples-data/language/classify-entertainment.txt"] | ||
|
||
# [START language_classify_gcs] | ||
from google.cloud import language_v1 | ||
from google.cloud.language_v1 import enums | ||
|
||
|
||
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_ = 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 = {"gcs_content_uri": gcs_content_uri, "type": type_, "language": language} | ||
|
||
response = client.classify_text(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_gcs] | ||
|
||
|
||
def main(): | ||
import argparse | ||
|
||
parser = argparse.ArgumentParser() | ||
parser.add_argument( | ||
"--gcs_content_uri", | ||
type=str, | ||
default="gs://cloud-samples-data/language/classify-entertainment.txt", | ||
) | ||
args = parser.parse_args() | ||
|
||
sample_classify_text(args.gcs_content_uri) | ||
|
||
|
||
if __name__ == "__main__": | ||
main() |
83 changes: 83 additions & 0 deletions
83
packages/google-cloud-language/samples/v1/language_classify_text.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,83 @@ | ||
# -*- coding: utf-8 -*- | ||
# | ||
# Copyright 2019 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 | ||
from google.cloud.language_v1 import enums | ||
|
||
|
||
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_ = 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} | ||
|
||
response = client.classify_text(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() |
105 changes: 105 additions & 0 deletions
105
packages/google-cloud-language/samples/v1/language_entities_gcs.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,105 @@ | ||
# -*- coding: utf-8 -*- | ||
# | ||
# Copyright 2019 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_entities_gcs") | ||
|
||
# To install the latest published package dependency, execute the following: | ||
# pip install google-cloud-language | ||
|
||
# sample-metadata | ||
# title: Analyzing Entities (GCS) | ||
# description: Analyzing Entities in text file stored in Cloud Storage | ||
# usage: python3 samples/v1/language_entities_gcs.py [--gcs_content_uri "gs://cloud-samples-data/language/entity.txt"] | ||
|
||
# [START language_entities_gcs] | ||
from google.cloud import language_v1 | ||
from google.cloud.language_v1 import enums | ||
|
||
|
||
def sample_analyze_entities(gcs_content_uri): | ||
""" | ||
Analyzing Entities 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_v1.LanguageServiceClient() | ||
|
||
# gcs_content_uri = 'gs://cloud-samples-data/language/entity.txt' | ||
|
||
# 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 = {"gcs_content_uri": gcs_content_uri, "type": type_, "language": language} | ||
|
||
# Available values: NONE, UTF8, UTF16, UTF32 | ||
encoding_type = enums.EncodingType.UTF8 | ||
|
||
response = client.analyze_entities(document, encoding_type=encoding_type) | ||
# Loop through entitites returned from the API | ||
for entity in response.entities: | ||
print(u"Representative name for the entity: {}".format(entity.name)) | ||
# Get entity type, e.g. PERSON, LOCATION, ADDRESS, NUMBER, et al | ||
print(u"Entity type: {}".format(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)) | ||
# 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) | ||
) | ||
|
||
# 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)) | ||
|
||
|
||
# [END language_entities_gcs] | ||
|
||
|
||
def main(): | ||
import argparse | ||
|
||
parser = argparse.ArgumentParser() | ||
parser.add_argument( | ||
"--gcs_content_uri", | ||
type=str, | ||
default="gs://cloud-samples-data/language/entity.txt", | ||
) | ||
args = parser.parse_args() | ||
|
||
sample_analyze_entities(args.gcs_content_uri) | ||
|
||
|
||
if __name__ == "__main__": | ||
main() |
Oops, something went wrong.