def _predict_remotely(
self, ws, experiment, predict_data, model_id, threshold):
input_payload = predict_data.to_json(orient='split', index = False)
remote_run = AutoMLRun(experiment = experiment, run_id = model_id)
model_name = remote_run.properties['model_name']
aci_service_name = self._aci_service_name(model_name)
aci_service = AciWebservice(ws, aci_service_name)
input_payload = json.loads(input_payload)
# If you have a classification model, you can get probabilities by changing this to 'predict_proba'.
method = 'predict'
if threshold is not None:
method = 'predict_proba'
input_payload = {
'method': method,
'data': input_payload['data']
}
input_payload = json.dumps(input_payload)
try:
response = aci_service.run(input_data = input_payload)
print(response)
except Exception as e:
print('err log', aci_service.get_logs())
raise e
results_proba = None
proba_classes = None
return json.loads(response)['result'], results_proba, proba_classes
def _predict_remotely(self, predict_data, model_id, predict_proba):
from azureml.core.webservice import AciWebservice
from azureml.train.automl.run import AutoMLRun
from azureml.core.run import Run
import numpy as np
ws, experiment = self._get_experiment()
model_features = None
target_categories = None
remote_run = AutoMLRun(experiment = experiment, run_id = model_id)
model_features, target_categories = self._get_remote_model_features(remote_run)
if model_id.startswith("AutoML_"):
model_name = remote_run.properties['model_name']
else:
model_name = model_id
if model_features:
predict_data = predict_data[model_features]
input_payload = predict_data.to_json(orient='split', index = False)
aci_service_name = self._aci_service_name(model_name)
aci_service = AciWebservice(ws, aci_service_name)
input_payload = json.loads(input_payload)
# If you have a classification model, you can get probabilities by changing this to 'predict_proba'.
method = 'predict'
if predict_proba:
method = 'predict_proba'
input_payload = {
'data': {'data': input_payload['data'], 'method': method}
}
input_payload = json.dumps(input_payload)
try:
response = aci_service.run(input_data = input_payload)
except Exception as e:
log_file = 'automl_errors.log'
fsclient.write_text_file(log_file, aci_service.get_logs(), mode="a")
raise AzureException("Prediction service error. Please redeploy the model. Log saved to file '%s'. Details: %s"%(log_file, str(e)))
response = json.loads(response)
if "error" in response or not 'result' in response:
raise AzureException('Prediction service return error: %s'%response.get('error'))
results_proba = None
proba_classes = None
results = response['result']
if predict_proba:
results_proba = results
proba_classes = response['proba_classes']
results_proba = np.array(results_proba)
return results, results_proba, proba_classes, target_categories
# Show output of the deployment on stdout
dev_service.wait_for_deployment(show_output=True)
print("State of Service: {}".format(dev_service.state))
# Checking status of web service
print("Checking status of ACI Dev Deployment")
if dev_service.state != "Healthy":
raise Exception(
"Dev Deployment on ACI failed with the following status: {} and logs: \n{}"
.format(dev_service.state, dev_service.get_logs()))
# Testing ACI web service
print("Testing ACI web service")
test_sample = test_functions.get_test_data_sample()
print("Test Sample: ", test_sample)
test_sample_encoded = bytes(test_sample, encoding='utf8')
try:
prediction = dev_service.run(input_data=test_sample)
print(prediction)
except Exception as e:
result = str(e)
logs = dev_service.get_logs()
dev_service.delete()
raise Exception(
"ACI Dev web service is not working as expected: \n{} \nLogs: \n{}".
format(result, logs))
# Delete aci after test
print("Deleting ACI Dev web service after successful test")
dev_service.delete()
import json
import pickle
import numpy as np
import pandas as pd
from azureml.core.workspace import Workspace
import azureml.train.automl
from sklearn.externals import joblib
from azureml.core.model import Model
ws = Workspace.from_config('./config.json')
from azureml.core.webservice import Webservice, AciWebservice, AksWebservice
service = AciWebservice(ws, "sentiment-scorer-korean")
# service = AksWebservice(ws, "sentiment-scorer-korean-aks")
# input_sample = pd.DataFrame({'id': pd.Series(['6471903'], dtype='int64'), 'document': pd.Series(['진짜 별로다 헐 ㅡ'], dtype='object')})
from load_dataset import testdata as input_sample
import json
test = json.dumps({"data": input_sample.values.tolist()})
result = service.run(input_data=bytes(test, encoding="utf8"))
input_sample['predicted'] = list(json.loads(result).values())[0]
print(input_sample)
with open("aml_config/aci_webservice.json") as f:
config = json.load(f)
except:
print('No new model, thus no deployment on ACI')
#raise Exception('No new model to register as production model perform better')
sys.exit(0)
service_name = config['aci_name']
print("Service :", service_name)
# Get the hosted web service
service = AciWebservice(ws, service_name)
# Input for Model with all features
# load the dataset
test_file = os.path.join('..', 'data', 'preprocessed', 'X_test.hkl')
X = hkl.load(test_file)
X_test = X[:10]
json_data = json.dumps({"data": X_test.tolist()})
json_data = bytes(json_data, encoding='utf8')
print("Service URL:", service.scoring_uri)
try:
prediction = service.run(json_data)
print(prediction)
except Exception as e:
result = str(e)
print(result)
raise Exception('ACI service is not working as expected')
import torch
from torchvision import transforms
def preprocess(image_file):
"""Preprocess the input image."""
data_transforms = transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])
image = Image.open(image_file)
image = data_transforms(image).float()
image = image.clone().detach()
image = image.unsqueeze(0)
return image.numpy()
input_data = preprocess('test_img.jpg')
result = service.run(input_data=json.dumps({'data': input_data.tolist()}))
print(result)
# Clean up
# Once you no longer need the web service, you can delete it with a simple API call.
service.delete()
