Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Elyra pipeline fixes #13

Merged
merged 4 commits into from
Nov 27, 2024
Merged

Elyra pipeline fixes #13

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
ae9a119
updated pipeline runtime
mamurak Nov 20, 2024
7e5c353
updated pipeline runtime image
mamurak Nov 27, 2024
3d90331
updated elyra pipeline
mamurak Nov 27, 2024
e6aa093
Merge remote-tracking branch 'max/mamurak/industrial-edge-v2' into qu…
mbaldessari Nov 27, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
32 changes: 32 additions & 0 deletions ml-models/anomaly-detection/pipeline/deployment.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,32 @@
def get_deployment_resource(model_artifact_id):
deployment_resource = {
'apiVersion': 'serving.kserve.io/v1beta1',
'kind': 'InferenceService',
'metadata': {
'name': 'inference-service',
'labels': {
'opendatahub.io/dashboard': 'true'
},
'annotations': {
'serving.kserve.io/deploymentMode': 'ModelMesh'
},
},
'spec': {
'predictor': {
'model': {
'modelFormat': {
'name': 'sklearn',
'version': '0',
},
'runtime': 'anomaly-detection-model-server',
'storage': {
'key': 'aws-connection-user-bucket',
'path': model_artifact_id,
}
}
}
}
}
return deployment_resource


17 changes: 6 additions & 11 deletions ml-models/anomaly-detection/pipeline/preprocessing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,8 +7,6 @@
df.set_index('time', inplace=True)
df.drop(columns=['ts'], inplace=True)

df.head(20)

df1 = df.loc[df['id'] == 'pump-1']
df1 = df1.drop(columns=['id', 'label'])

Expand All @@ -18,8 +16,6 @@
df1 = df.loc[df['id'] == 'pump-1']
df1 = df1.drop(columns=['id'])

df1.head(10)

df1 = df.loc[df['id'] == 'pump-1']
df1 = df1.drop(columns=['id'])

Expand All @@ -31,6 +27,8 @@
#

# Get list with column names: F1, F2, Fn, L


def get_columns(n):
f = []
for x in range(1, n+1):
Expand All @@ -55,6 +53,7 @@ def create_df(vals: list, label: int = 0):
dfx = pd.DataFrame([vals+[label]], columns=get_columns(len(vals)))
return dfx


length = 5 # Episode length

df_epis = create_empty_df(length)
Expand All @@ -70,13 +69,9 @@ def create_df(vals: list, label: int = 0):
epi.append(row['value'])
if len(epi) == length:
df_row = create_df(epi, row['label'])
df_epis = df_epis.append(df_row, ignore_index=True)
df_epis = pd.concat([df_epis, df_row], ignore_index=True)
del(epi[0])

df_epis.head(20)

df_epis.describe()

# Calculate number of episodes
n_episodes = df_epis.shape[0]

Expand Down Expand Up @@ -107,7 +102,7 @@ def create_df(vals: list, label: int = 0):

dfi = df_epis.copy()
dfi['F5'] = np.where(dfi['L'] == 1, dfi['F5']*f, dfi['F5'])
dfr = dfr.append(dfi)
dfr = pd.concat([dfr, dfi])

df_epis = dfr.copy()

Expand Down Expand Up @@ -135,4 +130,4 @@ def create_df(vals: list, label: int = 0):

df_epis.to_csv(
'sensor-training-data.csv', index=False, header=True, float_format='%.2f'
)
)
83 changes: 62 additions & 21 deletions ml-models/anomaly-detection/pipeline/push-model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,30 +1,28 @@
from datetime import datetime
import json
import os
from os import environ

import boto3
import git
import yaml

s3_endpoint_url = os.environ.get('S3_ENDPOINT_URL')
s3_access_key = os.environ.get('S3_ACCESS_KEY')
s3_secret_key = os.environ.get('S3_SECRET_KEY')
s3_bucket_name = os.environ.get('S3_BUCKET_NAME')
from deployment import get_deployment_resource

timestamp = datetime.now().strftime('%y%m%d%H%M')
model_name = f'model-{timestamp}.joblib'
s3_model_location = f's3://{s3_bucket_name}/{model_name}'

metrics = {
'metrics': [
{
'name': 'model-version',
'numberValue': timestamp,
'format': 'RAW'
}
]
}
s3_endpoint_url = environ.get('S3_ENDPOINT_URL')
s3_access_key = environ.get('S3_ACCESS_KEY')
s3_secret_key = environ.get('S3_SECRET_KEY')
s3_bucket_name = environ.get('S3_BUCKET_NAME')

with open('mlpipeline-metrics.json', 'w') as f:
json.dump(metrics, f)
timestamp = datetime.now().strftime('%y%m%d%H%M')
git_server_url = 'http://gitea-in-cluster-http.vp-gitea.svc.cluster.local:3000'
git_user = environ.get('username')
git_password = environ.get('password')
git_branch = environ.get('branch', 'main')
ops_repo_location = f'{git_server_url}/{git_user}/industrial-edge.git'
ops_repo_url = (
f'http://{git_user}:{git_password}@{ops_repo_location.lstrip("http://")}'
)
model_artifact_id = 'model.joblib'


print(f'Uploading model to bucket {s3_bucket_name}'
Expand All @@ -33,5 +31,48 @@
's3', endpoint_url=s3_endpoint_url,
aws_access_key_id=s3_access_key, aws_secret_access_key=s3_secret_key
)
try:
s3_client.create_bucket(Bucket=s3_bucket_name)
except Exception:
print(f'Failed to create new bucket with name "{s3_bucket_name}". Continuing.')
with open('model.joblib', 'rb') as model_file:
s3_client.upload_fileobj(model_file, s3_bucket_name, model_name)
s3_client.upload_fileobj(model_file, s3_bucket_name, model_artifact_id)


print(f'Checking out repo at {ops_repo_location} with user {git_user}')
ops_repository_local = '/opt/app-root/src/industrial-edge'
try:
repository = git.Repo.clone_from(ops_repo_url, ops_repository_local)
except git.GitCommandError as error:
print(f'Git clone failed: {error}\nChecking out local repository.')
repository = git.Repo(ops_repository_local)

print(f'Checking out branch {git_branch}.')
repository.git.checkout(git_branch)
with repository.config_writer() as git_config:
git_config.set_value('user', 'name', git_user)

inference_service_cr = get_deployment_resource(model_artifact_id)

print(f'Writing updated Inference Service CR: {inference_service_cr}')

inference_service_manifest_location_dev = (
f'{ops_repository_local}/charts/datacenter/data-science-project/templates/'
f'anomaly-detection/anomaly-detection-service.yaml'
)

with open(inference_service_manifest_location_dev, 'w') as outputfile:
yaml.safe_dump(inference_service_cr, outputfile)

inference_service_manifest_location_tst = (
f'{ops_repository_local}/charts/datacenter/manuela-tst/templates/'
f'anomaly-detection/anomaly-detection-service.yaml'
)

with open(inference_service_manifest_location_tst, 'w') as outputfile:
yaml.safe_dump(inference_service_cr, outputfile)

repository.index.add(inference_service_manifest_location_dev)
repository.index.add(inference_service_manifest_location_tst)
repository.index.commit(f'Model update {timestamp} in test environment.')
repository.remotes.origin.push()
36 changes: 26 additions & 10 deletions ml-models/anomaly-detection/pipeline/training.pipeline
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,7 @@
"label": "",
"ui_data": {
"label": "preprocessing.py",
"image": "/notebook/object-detection/industrial-edge/static/elyra/python.svg",
"image": "/notebook/ml-development/jupyterlab/static/elyra/python.svg",
"x_pos": 61,
"y_pos": 287,
"description": "Run Python script"
Expand Down Expand Up @@ -96,7 +96,7 @@
"label": "",
"ui_data": {
"label": "feature_extraction.py",
"image": "/notebook/object-detection/industrial-edge/static/elyra/python.svg",
"image": "/notebook/ml-development/jupyterlab/static/elyra/python.svg",
"x_pos": 298,
"y_pos": 286,
"description": "Run Python script"
Expand Down Expand Up @@ -160,7 +160,7 @@
"label": "",
"ui_data": {
"label": "training.py",
"image": "/notebook/object-detection/industrial-edge/static/elyra/python.svg",
"image": "/notebook/ml-development/jupyterlab/static/elyra/python.svg",
"x_pos": 539,
"y_pos": 287,
"description": "Run Python script"
Expand Down Expand Up @@ -222,7 +222,7 @@
"label": "",
"ui_data": {
"label": "verification.py",
"image": "/notebook/object-detection/industrial-edge/static/elyra/python.svg",
"image": "/notebook/ml-development/jupyterlab/static/elyra/python.svg",
"x_pos": 471,
"y_pos": 461,
"description": "Run Python script"
Expand Down Expand Up @@ -270,7 +270,9 @@
"op": "execute-python-node",
"app_data": {
"component_parameters": {
"dependencies": [],
"dependencies": [
"deployment.py"
],
"include_subdirectories": false,
"outputs": [],
"env_vars": [],
Expand All @@ -296,18 +298,32 @@
"env_var": "S3_BUCKET_NAME",
"name": "aws-connection-user-bucket",
"key": "AWS_S3_BUCKET"
},
{
"env_var": "username",
"name": "gitea-admin-secret-and-branch",
"key": "username"
},
{
"env_var": "password",
"name": "gitea-admin-secret-and-branch",
"key": "password"
},
{
"env_var": "branch",
"name": "gitea-admin-secret-and-branch",
"key": "branch"
}
],
"kubernetes_shared_mem_size": {},
"kubernetes_tolerations": [],
"mounted_volumes": [],
"filename": "push-model.py",
"runtime_image": "quay.io/mmurakam/runtimes:timeseries-v0.1.0"
"filename": "push-model.py"
},
"label": "",
"ui_data": {
"label": "push-model.py",
"image": "/notebook/object-detection/industrial-edge/static/elyra/python.svg",
"image": "/notebook/ml-development/jupyterlab/static/elyra/python.svg",
"x_pos": 879,
"y_pos": 493,
"description": "Run Python script"
Expand Down Expand Up @@ -393,7 +409,7 @@
"label": "",
"ui_data": {
"label": "data_ingestion.py",
"image": "/notebook/object-detection/industrial-edge/static/elyra/python.svg",
"image": "/notebook/ml-development/jupyterlab/static/elyra/python.svg",
"x_pos": 156,
"y_pos": 176,
"description": "Run Python script"
Expand Down Expand Up @@ -444,7 +460,7 @@
"kubernetes_pod_labels": [],
"env_vars": [],
"kubernetes_secrets": [],
"runtime_image": "quay.io/mmurakam/runtimes:industrial-edge-v0.1.0"
"runtime_image": "quay.io/hybridcloudpatterns/manuela-runtime:main"
},
"name": "training",
"runtime": "Data Science Pipelines"
Expand Down