def get_conda_depencies():
conda_dep = CondaDependencies()
conda_dep.set_python_version("3.6.2")
with open('compute_pip_requirements.txt') as f:
for requirement in f:
conda_dep.add_pip_package(str(requirement))
with open('compute_conda_requirements.txt') as f:
for requirement in f:
conda_dep.add_conda_package(str(requirement))
return conda_dep
# ***************** 1. CREATE PythonScriptStep1: DATA PREPARATION **************************
# ...which needs a RunConfiguration object that specifies the right Conda/Pip dependencies. So we proceed as follows in 3 steps:
# 1.A) Create PipelineData Object datapreparation_output
from azureml.pipeline.core import PipelineData
is_directory = False # it's a file where we save the prepared dataframe
default_datastore = ws.get_default_datastore()
datapreparation_output = PipelineData('datapreparation_output',
datastore=default_datastore,
is_directory=is_directory)
# 1.B) Create the dependency object with mlextend package https://docs.microsoft.com/en-us/python/api/azureml-core/azureml.core.conda_dependencies.condadependencies?view=azure-ml-py:
from azureml.core.environment import CondaDependencies
conda_dep_prep = CondaDependencies()
conda_dep_prep.add_pip_package(
"mlxtend==0.17.2") # or conda_dep.add_conda_package("mlxtend==0.17.2")
# 1.C) Create the RunConfiguration object:
from azureml.core import RunConfiguration
run_config_prep = RunConfiguration(conda_dependencies=conda_dep_prep)
# 1.D) Create the PythonScriptStep
from azureml.pipeline.steps import PythonScriptStep
data_preparation_step = PythonScriptStep(
name="1: Data preparation",
script_name="1-data_preparation.py",
compute_target=compute_target,
runconfig=run_config_prep,
arguments=[
"--remoteDataFolder", remote_data_folder, "--localDataFolder",
local_data_to_download_folder, "--datapreparation_output",
#création du path complet dans le blob storage
path_model_datastore = "azureml/" + step1_runid + "/outputs/"
#download en local du modele
def_data_store.download(target_path='datastore', prefix=path_model_datastore)
#chargement dans la workspace a partir du modele download en local
model = Model.register(workspace=ws,
model_path='datastore/' + path_model_datastore +
model_pklname + '.pkl',
model_name=model_basename)
#Create environment file
from azureml.core.conda_dependencies import CondaDependencies
myenv = CondaDependencies()
myenv.add_conda_package("scikit-learn")
myenv.add_pip_package("azureml-defaults")
myenv.add_conda_package("numpy")
myenv.add_conda_package("pandas")
# import os
# old_wd = os.getcwd()
# os.chdir(old_wd+"/source")
with open("myenv.yml", "w") as f:
f.write(myenv.serialize_to_string())
#Review the content of the myenv.yml file:
with open("myenv.yml", "r") as f:
print(f.read())
# register image
# In[5]:
get_ipython().run_cell_magic(
'writefile', 'summarizer_service.py',
'\nimport re\nimport nltk\nimport unicodedata\nfrom gensim.summarization import summarize, keywords\n\ndef clean_and_parse_document(document):\n if isinstance(document, str):\n document = document\n elif isinstance(document, unicode):\n return unicodedata.normalize(\'NFKD\', document).encode(\'ascii\', \'ignore\')\n else:\n raise ValueError("Document is not string or unicode.")\n document = document.strip()\n sentences = nltk.sent_tokenize(document)\n sentences = [sentence.strip() for sentence in sentences]\n return sentences\n\ndef summarize_text(text, summary_ratio=None, word_count=30):\n sentences = clean_and_parse_document(text)\n cleaned_text = \' \'.join(sentences)\n summary = summarize(cleaned_text, split=True, ratio=summary_ratio, word_count=word_count)\n return summary \n\ndef init(): \n nltk.download(\'all\')\n return\n\ndef run(input_str):\n try:\n return summarize_text(input_str)\n except Exception as e:\n return (str(e))'
)
# In[7]:
from azureml.core import Environment
from azureml.core.environment import CondaDependencies
myenv = Environment(name="myenv")
conda_dep = CondaDependencies()
conda_dep.add_pip_package("gensim")
conda_dep.add_pip_package("nltk")
myenv.python.conda_dependencies = conda_dep
# In[8]:
myenv.register(workspace=ws)
# In[9]:
from azureml.core.model import InferenceConfig
from azureml.core.webservice import AciWebservice
inference_config = InferenceConfig(entry_script='summarizer_service.py',
environment=myenv)
aci_config = AciWebservice.deploy_configuration(cpu_cores=1,
pickle.dump(model, open(filename, 'wb'))
# register the dummy model
ws = Workspace.from_config()
registration_params = {
'model_path': "dummy.pkl",
'model_name': "dummy-model",
'description': "mock test deployment",
'workspace': ws
}
model = register_model(**registration_params)
myenv = Environment(name='my_env')
myenv.get(workspace=ws, name='ls-ds-ml-env')
conda_dep = CondaDependencies()
conda_dep.add_pip_package("azureml-defaults==1.3.0")
conda_dep.add_pip_package("joblib")
conda_dep.add_pip_package("json")
myenv.python.conda_dependencies = conda_dep
inference_config = InferenceConfig(entry_script="src/dummy_score.py",
environment=myenv)
aci_config = AciWebservice.deploy_configuration(cpu_cores=1, memory_gb=1)
service_name = 'dummy-service'
try:
service = Model.deploy(ws,
service_name, [model],
inference_config,
deployment_config=aci_config)
service.wait_for_deployment(True)
logs = service.get_logs()