def predict(project_id, model_id, content):
"""Predict."""
# [START automl_language_entity_extraction_predict]
from google.cloud import automl
# TODO(developer): Uncomment and set the following variables
# project_id = "YOUR_PROJECT_ID"
# model_id = "YOUR_MODEL_ID"
# content = "text to predict"
prediction_client = automl.PredictionServiceClient()
# Get the full path of the model.
model_full_id = automl.AutoMlClient.model_path(project_id, "us-central1",
model_id)
# Supported mime_types: 'text/plain', 'text/html'
# https://cloud.google.com/automl/docs/reference/rpc/google.cloud.automl.v1#textsnippet
text_snippet = automl.TextSnippet(content=content, mime_type="text/plain")
payload = automl.ExamplePayload(text_snippet=text_snippet)
response = prediction_client.predict(name=model_full_id, payload=payload)
for annotation_payload in response.payload:
print("Text Extract Entity Types: {}".format(
annotation_payload.display_name))
print("Text Score: {}".format(
annotation_payload.text_extraction.score))
text_segment = annotation_payload.text_extraction.text_segment
print("Text Extract Entity Content: {}".format(text_segment.content))
print("Text Start Offset: {}".format(text_segment.start_offset))
print("Text End Offset: {}".format(text_segment.end_offset))
def predict(project_id, model_id, file_path):
"""Predict."""
# [START automl_translate_predict]
from google.cloud import automl
# TODO(developer): Uncomment and set the following variables
# project_id = "YOUR_PROJECT_ID"
# model_id = "YOUR_MODEL_ID"
# file_path = "path_to_local_file.txt"
prediction_client = automl.PredictionServiceClient()
# Get the full path of the model.
model_full_id = automl.AutoMlClient.model_path(project_id, "us-central1",
model_id)
# Read the file content for translation.
with open(file_path, "rb") as content_file:
content = content_file.read()
content.decode("utf-8")
text_snippet = automl.TextSnippet(content=content)
payload = automl.ExamplePayload(text_snippet=text_snippet)
response = prediction_client.predict(name=model_full_id, payload=payload)
translated_content = response.payload[0].translation.translated_content
print(u"Translated content: {}".format(translated_content.content))
async def process(req: models.Request):
"""
Analyze a given piece of text to find the bias. Any given piece of text will be checked against the database to
check if it has already been processed. If it has not yet been processed, it will be sent for inference on
a GCP NLP trained model.
"""
# Either fetch the content from the site or use the provided text
if req.url != "":
try:
article = Article(req.url)
article.download()
article.parse()
if article.text != "" and article.text is not None:
text = article.text
else:
text = req.text
except ArticleException:
text = req.text
else:
text = req.text
# Calculate hash of id and text
job_hash = compute_job_hash(req.id, text)
# Ensure job has not been computed or is being computed
job_ref = db.collection("text").document(job_hash)
job = job_ref.get()
if job.exists:
job_data = job.to_dict()
return {
"success": True,
"bias": job_data.get("bias"),
"extent": job_data.get("extent")
}
# Process the data
snippet = automl.TextSnippet(content=text, mime_type="text/plain")
payload = automl.ExamplePayload(text_snippet=snippet)
response = predictor.predict(name=MODEL_PATH, payload=payload)
bias, extent = extract_from_categories(response.payload)
# Set the processed data to the database
job_ref.set({
"hash": job_hash,
"bias": bias,
"extent": extent
})
return {
"success": True,
"bias": bias,
"extent": extent
}
def predict():
if request.method == 'POST':
comment = request.form['comment']
#data = [comment]
text_snippet = automl.TextSnippet(content=comment,
mime_type="text/plain")
payload = automl.ExamplePayload(text_snippet=text_snippet)
my_prediction = prediction_client.predict(name=model_full_id,
payload=payload)
return render_template('results.html',
prediction=my_prediction,
comment=comment)
def prediction():
if request.method == 'POST':
commentInput = request.form
for key, item in commentInput.items():
text_snippet = automl.TextSnippet(content=item,
mime_type="text/plain")
payload = automl.ExamplePayload(text_snippet=text_snippet)
response = prediction_client.predict(name=model_full_id,
payload=payload)
for annotation_payload in response.payload:
sentPred = annotation_payload.display_name
break
return render_template('results.html',
sentPred=sentPred,
content=content)
def predict(content):
# Supported mime_types: 'text/plain', 'text/html'
# https://cloud.google.com/automl/docs/reference/rpc/google.cloud.automl.v1#textsnippet
text_snippet = automl.TextSnippet(content=content, mime_type="text/plain")
payload = automl.ExamplePayload(text_snippet=text_snippet)
response = prediction_client.predict(name=model_full_id, payload=payload)
for annotation_payload in response.payload:
# print(
# u"Predicted class name: {}".format(annotation_payload.display_name)
# )
# print(
# u"Predicted class score: {}".format(
# annotation_payload.classification.score
# )
# )
return annotation_payload.display_name
break
def predict(content):
prediction_client = automl.PredictionServiceClient()
# Get the full path of the model.
model_full_id = automl.AutoMlClient.model_path(project_id, "us-central1",
model_id)
# Supported mime_types: 'text/plain', 'text/html'
# https://cloud.google.com/automl/docs/reference/rpc/google.cloud.automl.v1#textsnippet
text_snippet = automl.TextSnippet(content=content, mime_type="text/plain")
payload = automl.ExamplePayload(text_snippet=text_snippet)
response = prediction_client.predict(name=model_full_id, payload=payload)
for annotation_payload in response.payload:
print("Predicted class name: {}".format(
annotation_payload.display_name))
print("Predicted sentiment score: {}".format(
annotation_payload.text_sentiment.sentiment))
return annotation_payload.text_sentiment.sentiment
def predict(content):
from google.cloud import automl
# You must first create a dataset, using the `eu` endpoint, before you can
# call other operations such as: list, get, import, delete, etc.
client_options = {'api_endpoint': 'eu-automl.googleapis.com:443'}
project_id = '685330484131'
# (model AI Crowd) model_id = 'TCN3300918624537018368'
model_id = 'TCN4629621252099670016'
prediction_client = automl.PredictionServiceClient(
client_options=client_options)
# Get the full path of the model.
model_full_id = automl.AutoMlClient.model_path(project_id, "eu", model_id)
text_snippet = automl.TextSnippet(content=content, mime_type="text/plain")
payload = automl.ExamplePayload(text_snippet=text_snippet)
response = prediction_client.predict(name=model_full_id, payload=payload)
return response
def nlp_predict(self, model_id: (str, 'the id of the deployed nlp model'),
content: (str,
'the text to submit to the prediction model')):
response_payload = None
try:
model_full_id = self.automl_client.model_path(
self.project_id, self.region, model_id)
text_snippet = automl.TextSnippet(content=content,
mime_type="text/plain")
payload = automl.ExamplePayload(text_snippet=text_snippet)
#payload = {'text_snippet': {'content': content, 'mime_type': 'text/plain' }}
response = self.prediction_client.predict(name=model_full_id,
payload=payload)
response_payload = response.payload
except Exception:
logger.exception("")
return response_payload
import os
from google.cloud import automl
from dotenv import load_dotenv
load_dotenv()
project_id = os.getenv("PROJECT_ID")
model_id = os.getenv("MODEL_ID")
content = "How does the len() function work?"
prediction_client = automl.PredictionServiceClient()
# Get the full path of the model.
model_full_id = automl.AutoMlClient.model_path(project_id, "us-central1",
model_id)
text_snippet = automl.TextSnippet(content=content, mime_type="text/plain")
payload = automl.ExamplePayload(text_snippet=text_snippet)
response = prediction_client.predict(name=model_full_id, payload=payload)
for annotation_payload in response.payload:
print(u"Predicted question tag: {}".format(
annotation_payload.display_name))
print(u"Predicted score: {}".format(
annotation_payload.classification.score))
