Amazon SageMaker Pipelines 和 Amazon SageMaker 开发工具包的新功能

print(sagemaker.__version__)
import sys
!{sys.executable} -m pip install "sagemaker>=2.104.0"
!{sys.executable} -m pip install "xlrd >=1.0.0"
 
import sagemaker

import boto3
import pandas as pd
import sagemaker
from sagemaker.workflow.pipeline_context import PipelineSession
 
s3_client = boto3.resource('s3')
pipeline_name = f"ChurnModelPipeline"
sagemaker_session = sagemaker.session.Session()
region = sagemaker_session.boto_region_name
role = sagemaker.get_execution_role()
pipeline_session = PipelineSession()
default_bucket = sagemaker_session.default_bucket()
model_package_group_name = f"ChurnModelPackageGroup"

from sagemaker.workflow.parameters import (
    ParameterInteger,
    ParameterString,
    ParameterFloat,
)
auc_score_threshold = 0.75
base_job_prefix = "churn-example"
model_package_group_name = "churn-job-model-packages"
batch_data = "s3://{}/data/batch/batch.csv".format(default_bucket)

processing_instance_count = ParameterInteger(
    name="ProcessingInstanceCount",
    default_value=1
)
processing_instance_type = ParameterString(
    name="ProcessingInstanceType",
    default_value="ml.m5.xlarge"
)
training_instance_type = ParameterString(
    name="TrainingInstanceType",
    default_value="ml.m5.xlarge"
)
input_data = ParameterString(
    name="InputData",
    default_value="s3://{}/data/storedata_total.csv".format(default_bucket),
)

model_approval_status = ParameterString(
    name="ModelApprovalStatus", default_value="PendingManualApproval"
)

def preprocess_batch_data(file_path):
    df = pd.read_csv(file_path)
    ## Convert to datetime columns
    df["firstorder"]=pd.to_datetime(df["firstorder"],errors='coerce')
    df["lastorder"] = pd.to_datetime(df["lastorder"],errors='coerce')
    ## Drop Rows with null values
    df = df.dropna()
    ## Create Column which gives the days between the last order and the first order
    df["first_last_days_diff"] = (df['lastorder']-df['firstorder']).dt.days
    ## Create Column which gives the days between when the customer record was created and the first order
    df['created'] = pd.to_datetime(df['created'])
    df['created_first_days_diff']=(df['created']-df['firstorder']).dt.days
    ## Drop Columns
    df.drop(['custid','created','firstorder','lastorder'],axis=1,inplace=True)
    ## Apply one hot encoding on favday and city columns
    df = pd.get_dummies(df,prefix=['favday','city'],columns=['favday','city'])
    return df
    
# convert the store_data file into csv format
store_data = pd.read_excel("data/storedata_total.xlsx")
store_data.to_csv("data/storedata_total.csv")
 
# preprocess batch data and save into the data folder
batch_data = preprocess_batch_data("data/storedata_total.csv")
batch_data.pop("retained")
batch_sample = batch_data.sample(frac=0.2)
pd.DataFrame(batch_sample).to_csv("data/batch.csv",header=False,index=False)

s3_client.Bucket(default_bucket).upload_file("data/batch.csv","data/batch/batch.csv")
s3_client.Bucket(default_bucket).upload_file("data/storedata_total.csv","data/storedata_total.csv")

%%writefile pipelines/customerchurn/preprocess.py

import os
import tempfile
import numpy as np
import pandas as pd
import datetime as dt
if __name__ == "__main__":
    base_dir = "/opt/ml/processing"
    #Read Data
    df = pd.read_csv(
        f"{base_dir}/input/storedata_total.csv"
    )
    # convert created column to datetime
    df["created"] = pd.to_datetime(df["created"])
    #Convert firstorder and lastorder to datetime datatype
    df["firstorder"] = pd.to_datetime(df["firstorder"],errors='coerce')
    df["lastorder"] = pd.to_datetime(df["lastorder"],errors='coerce')
    #Drop Rows with Null Values
    df = df.dropna()
    #Create column which gives the days between the last order and the first order
    df['first_last_days_diff'] = (df['lastorder'] - df['firstorder']).dt.days
    #Create column which gives the days between the customer record was created and the first order
    df['created_first_days_diff'] = (df['created'] - df['firstorder']).dt.days
    #Drop columns
    df.drop(['custid', 'created','firstorder','lastorder'], axis=1, inplace=True)
    #Apply one hot encoding on favday and city columns
    df = pd.get_dummies(df, prefix=['favday', 'city'], columns=['favday', 'city'])
    # Split into train, validation and test datasets
    y = df.pop("retained")
    X_pre = df
    y_pre = y.to_numpy().reshape(len(y), 1)
    X = np.concatenate((y_pre, X_pre), axis=1)
    np.random.shuffle(X)
    # Split in Train, Test and Validation Datasets
    train, validation, test = np.split(X, [int(.7*len(X)), int(.85*len(X))])
    train_rows = np.shape(train)[0]
    validation_rows = np.shape(validation)[0]
    test_rows = np.shape(test)[0]
    train = pd.DataFrame(train)
    test = pd.DataFrame(test)
    validation = pd.DataFrame(validation)
    # Convert the label column to integer
    train[0] = train[0].astype(int)
    test[0] = test[0].astype(int)
    validation[0] = validation[0].astype(int)
    # Save the Dataframes as csv files
    train.to_csv(f"{base_dir}/train/train.csv", header=False, index=False)
    validation.to_csv(f"{base_dir}/validation/validation.csv", header=False, index=False)
    test.to_csv(f"{base_dir}/test/test.csv", header=False, index=False)

# Upload processing script to S3
s3_client.Bucket(default_bucket).upload_file("pipelines/customerchurn/preprocess.py","input/code/preprocess.py")

# Define Processing Step for Feature Engineering
from sagemaker.sklearn.processing import SKLearnProcessor
from sagemaker.processing import ProcessingInput, ProcessingOutput
from sagemaker.workflow.steps import ProcessingStep

framework_version = "1.0-1"sklearn_processor = SKLearnProcessor(
    framework_version=framework_version,
    instance_type="ml.m5.xlarge",
    instance_count=processing_instance_count,
    base_job_name="sklearn-churn-process",
    role=role,
    sagemaker_session=pipeline_session,
)
processor_args = sklearn_processor.run(
    inputs=[
      ProcessingInput(source=input_data, destination="/opt/ml/processing/input"),  
    ],
    outputs=[
        ProcessingOutput(output_name="train", source="/opt/ml/processing/train",
                         destination=f"s3://{default_bucket}/output/train" ),
        ProcessingOutput(output_name="validation", source="/opt/ml/processing/validation",
                        destination=f"s3://{default_bucket}/output/validation"),
        ProcessingOutput(output_name="test", source="/opt/ml/processing/test",
                        destination=f"s3://{default_bucket}/output/test")
    ],
    code=f"s3://{default_bucket}/input/code/preprocess.py",
)
step_process = ProcessingStep(name="ChurnModelProcess", step_args=processor_args)

from sagemaker.estimator import Estimator
from sagemaker.inputs import TrainingInput

model_path = f"s3://{default_bucket}/output"
image_uri = sagemaker.image_uris.retrieve(
    framework="xgboost",
    region=region,
    version="1.0-1",
    py_version="py3",
    instance_type="ml.m5.xlarge",
)
xgb_train = Estimator(
    image_uri=image_uri,
    instance_type=training_instance_type,
    instance_count=1,
    output_path=model_path,
    role=role,
    sagemaker_session=pipeline_session,
)
xgb_train.set_hyperparameters(
    objective="reg:linear",
    num_round=50,
    max_depth=5,
    eta=0.2,
    gamma=4,
    min_child_weight=6,
    subsample=0.7,
)

train_args = xgb_train.fit(
    inputs={
            "train": TrainingInput(
                s3_data=step_process.properties.ProcessingOutputConfig.Outputs[
                    "train"
                ].S3Output.S3Uri,
                content_type="text/csv",
            ),
            "validation": TrainingInput(
                s3_data=step_process.properties.ProcessingOutputConfig.Outputs[
                    "validation"
                ].S3Output.S3Uri,
                content_type="text/csv",
            ),
        },
)
from sagemaker.inputs import TrainingInput
from sagemaker.workflow.steps import TrainingStep
step_train = TrainingStep(
    name="ChurnModelTrain",
    step_args=train_args,
    )

%%writefile pipelines/customerchurn/evaluate.py

import json
import pathlib
import pickle
import tarfile
import joblib
import numpy as np
import pandas as pd
import xgboost
import datetime as dt
from sklearn.metrics import roc_curve,auc
if __name__ == "__main__":   
    #Read Model Tar File
    model_path = f"/opt/ml/processing/model/model.tar.gz"
    with tarfile.open(model_path) as tar:
        tar.extractall(path=".")
    model = pickle.load(open("xgboost-model", "rb"))
    #Read Test Data using which we evaluate the model
    test_path = "/opt/ml/processing/test/test.csv"
    df = pd.read_csv(test_path, header=None)
    y_test = df.iloc[:, 0].to_numpy()
    df.drop(df.columns[0], axis=1, inplace=True)
    X_test = xgboost.DMatrix(df.values)
    #Run Predictions
    predictions = model.predict(X_test)
    #Evaluate Predictions
    fpr, tpr, thresholds = roc_curve(y_test, predictions)
    auc_score = auc(fpr, tpr)
    report_dict = {
        "classification_metrics": {
            "auc_score": {
                "value": auc_score,
            },
        },
    }
    #Save Evaluation Report
    output_dir = "/opt/ml/processing/evaluation"
    pathlib.Path(output_dir).mkdir(parents=True, exist_ok=True)
    evaluation_path = f"{output_dir}/evaluation.json"
    with open(evaluation_path, "w") as f:
        f.write(json.dumps(report_dict))

#Upload the evaluation script to S3
s3_client.Bucket(default_bucket).upload_file("pipelines/customerchurn/evaluate.py","input/code/evaluate.py")
from sagemaker.processing import ScriptProcessor
# define model evaluation step to evaluate the trained model
script_eval = ScriptProcessor(
    image_uri=image_uri,
    command=["python3"],
    instance_type=processing_instance_type,
    instance_count=1,
    base_job_name="script-churn-eval",
    role=role,
    sagemaker_session=pipeline_session,
)
eval_args = script_eval.run(
    inputs=[
        ProcessingInput(
            source=step_train.properties.ModelArtifacts.S3ModelArtifacts,
            destination="/opt/ml/processing/model",
        ),
        ProcessingInput(
            source=step_process.properties.ProcessingOutputConfig.Outputs["test"].S3Output.S3Uri,
            destination="/opt/ml/processing/test",
        ),
    ],
    outputs=[
            ProcessingOutput(output_name="evaluation", source="/opt/ml/processing/evaluation",
                             destination=f"s3://{default_bucket}/output/evaluation"),
        ],
    code=f"s3://{default_bucket}/input/code/evaluate.py",
)
from sagemaker.workflow.properties import PropertyFile
evaluation_report = PropertyFile(
    name="ChurnEvaluationReport", output_name="evaluation", path="evaluation.json"
)
step_eval = ProcessingStep(
    name="ChurnEvalModel",
    step_args=eval_args,
    property_files=[evaluation_report],
)

from sagemaker import Model
from sagemaker.inputs import CreateModelInput
from sagemaker.workflow.model_step import ModelStep
# step to create model 
model = Model(
    image_uri=image_uri,        
    model_data=step_train.properties.ModelArtifacts.S3ModelArtifacts,
    sagemaker_session=pipeline_session,
    role=role,
)
step_create_model = ModelStep(
    name="ChurnCreateModel",
    step_args=model.create(instance_type="ml.m5.large", accelerator_type="ml.eia1.medium"),
)

from sagemaker.transformer import Transformer
from sagemaker.inputs import TransformInput
from sagemaker.workflow.steps import TransformStep

transformer = Transformer(
    model_name=step_create_model.properties.ModelName,
    instance_type="ml.m5.xlarge",
    instance_count=1,
    output_path=f"s3://{default_bucket}/ChurnTransform",
    sagemaker_session=pipeline_session
)
                                 
step_transform = TransformStep(
    name="ChurnTransform", 
    step_args=transformer.transform(
                    data=batch_data,
                    content_type="text/csv"
                 )
)

model = Model(
    image_uri=image_uri,
    model_data=step_train.properties.ModelArtifacts.S3ModelArtifacts,
    sagemaker_session=pipeline_session,
    role=role,
)
from sagemaker.model_metrics import MetricsSource, ModelMetrics

model_metrics = ModelMetrics(
    model_statistics=MetricsSource(
        s3_uri="{}/evaluation.json".format(
            step_eval.arguments["ProcessingOutputConfig"]["Outputs"][0]["S3Output"]["S3Uri"]
        ),
        content_type="application/json",
    )
)
register_args = model.register(
    content_types=["text/csv"],
    response_types=["text/csv"],
    inference_instances=["ml.t2.medium", "ml.m5.xlarge"],
    transform_instances=["ml.m5.xlarge"],
    model_package_group_name=model_package_group_name,
    approval_status=model_approval_status,
    model_metrics=model_metrics,
)
step_register = ModelStep(name="ChurnRegisterModel", step_args=register_args)

from sagemaker.workflow.fail_step import FailStep
from sagemaker.workflow.functions import Join
step_fail = FailStep(
    name="ChurnAUCScoreFail",
    error_message=Join(on=" ", values=["Execution failed due to AUC Score >", auc_score_threshold]),
    )

from sagemaker.workflow.conditions import ConditionGreaterThan
from sagemaker.workflow.condition_step import ConditionStep
from sagemaker.workflow.functions import JsonGet
cond_lte = ConditionGreaterThan(
    left=JsonGet(
        step_name=step_eval.name,
        property_file=evaluation_report,
        json_path="classification_metrics.auc_score.value",
    ),
    right=auc_score_threshold,
)
step_cond = ConditionStep(
    name="CheckAUCScoreChurnEvaluation",
    conditions=[cond_lte],
    if_steps=[step_register, step_create_model, step_transform],
    else_steps=[step_fail],
)

import json
from sagemaker.workflow.pipeline import Pipeline

pipeline = Pipeline(
    name=pipeline_name,
    parameters=[
        processing_instance_count,
        processing_instance_type,
        training_instance_type,
        model_approval_status,
        input_data,
        batch_data,
        auc_score_threshold,
    ],
    steps=[step_process, step_train, step_eval, step_cond],
) 
definition = json.loads(pipeline.definition())
print(definition)

pipeline.start()
# Create a new or update existing Pipeline
pipeline.upsert(role_arn=sagemaker_role)
# start Pipeline execution