Azure ML Studio 未在模型下显示数据集

Question

我在 Azure ML 笔记本中注册了一个模型及其数据集。在 ML Studio 中，我可以看到数据集下列出的模型，但模型下没有列出任何数据集。我应该怎么做才能在模型下列出数据集？

数据集下列出的模型：

模型下未列出的数据集：

笔记本代码：

import pickle
import sys
from azureml.core import Workspace, Dataset, Model
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.utils import assert_all_finite

workspace = Workspace('<snip>', '<snip>', '<snip>')
dataset = Dataset.get_by_name(workspace, name='creditcard')
data = dataset.to_pandas_dataframe()
data.dropna(inplace=True)
X = data.drop(labels=["Class"], axis=1, inplace=False)
y = data["Class"]

model = make_pipeline(StandardScaler(), GradientBoostingClassifier())
model.fit(X, y)

with open('creditfraud_sklearn_model.pkl', 'wb') as outfile:
    pickle.dump(model, outfile)

Model.register(
    Workspace = workspace,
    model_name = 'creditfraud_sklearn_model',
    model_path = 'creditfraud_sklearn_model.pkl',
    description = 'Gradient Boosting classifier for Kaggle credit-card fraud',
    model_framework = Model.Framework.SCIKITLEARN,
    model_framework_version = sys.modules['sklearn'].__version__,
    sample_input_dataset = dataset,
    sample_output_dataset = dataset)

Answer 1

看起来需要调用 add_dataset_references() 才能在模型下显示数据集：

model_registration.add_dataset_references([("input dataset", dataset)])

Azure ML Studio 未在模型下显示数据集

Azure ML Studio not showing datasets under models

azure-machine-learning-studio