Kubeflow Cheat Sheet

from kfp import dsl, compiler@dsl.component(base_image="python:3.11", packages_to_install=["pandas"])def preprocess(input_path: str, output_path: dsl.Output[dsl.Dataset]):    import pandas as pd    df = pd.read_csv(input_path)    df.dropna().to_csv(output_path.path, index=False)@dsl.component(base_image="python:3.11", packages_to_install=["scikit-learn"])def train(dataset: dsl.Input[dsl.Dataset], model: dsl.Output[dsl.Model]):    import pandas as pd, joblib    from sklearn.ensemble import RandomForestClassifier    df = pd.read_csv(dataset.path)    clf = RandomForestClassifier().fit(df.drop(columns=["label"]), df["label"])    joblib.dump(clf, model.path)@dsl.pipeline(name="train-pipeline")def pipeline(input_path: str = "gs://bucket/data.csv"):    prep = preprocess(input_path=input_path)    train(dataset=prep.outputs["output_path"])compiler.Compiler().compile(pipeline, "pipeline.yaml")

import kfpclient = kfp.Client(host="https://kubeflow.mycompany.com/pipeline")run = client.create_run_from_pipeline_package(    pipeline_file="pipeline.yaml",    arguments={"input_path": "gs://bucket/data.csv"},    experiment_name="fraud-model-training",)print(run.run_id)

apiVersion: kubeflow.org/v1beta1kind: Experimentmetadata:  name: rf-tuningspec:  objective:    type: maximize    goal: 0.95    objectiveMetricName: accuracy  algorithm:    algorithmName: bayesianoptimization  parameters:    - name: n_estimators      parameterType: int      feasibleSpace: { min: "50", max: "500" }    - name: max_depth      parameterType: int      feasibleSpace: { min: "2", max: "20" }  trialTemplate:    primaryContainerName: training-container    trialParameters:      - name: n_estimators        reference: n_estimators      - name: max_depth        reference: max_depth

apiVersion: serving.kserve.io/v1beta1kind: InferenceServicemetadata:  name: fraud-modelspec:  predictor:    sklearn:      storageUri: "gs://bucket/models/fraud-model/"    minReplicas: 1    maxReplicas: 5