jprdonnelly/MachineLearningNotebooks
1
0
Fork 0
mirror of https://github.com/Azure/MachineLearningNotebooks.git synced 2025-12-19 17:17:04 -05:00
Code Issues Projects Releases Wiki Activity

update samples from Release-240 as a part of 1.57.0 SDK stable release

Browse Source
This commit is contained in:
amlrelsa-ms
2024-08-05 21:57:46 +00:00
parent 2352e458c7
commit aae88e87ea
45 changed files with 113 additions and 2685 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
how-to-use-azureml/explain-model/azure-integration/remote-explanation/train_explain.py
View File

@@ -1,7 +1,7 @@
# Copyright (c) Microsoft. All rights reserved.
# Licensed under the MIT license.
from sklearn import datasets
from sklearn.datasets import fetch_california_housing
from sklearn.linear_model import Ridge
from interpret.ext.blackbox import TabularExplainer
from azureml.interpret import ExplanationClient
@@ -14,20 +14,20 @@ import numpy as np
OUTPUT_DIR = './outputs/'
os.makedirs(OUTPUT_DIR, exist_ok=True)
boston_data = datasets.load_boston()
california_data = fetch_california_housing()
run = Run.get_context()
client = ExplanationClient.from_run(run)
X_train, X_test, y_train, y_test = train_test_split(boston_data.data,
boston_data.target,
X_train, X_test, y_train, y_test = train_test_split(california_data.data,
california_data.target,
test_size=0.2,
random_state=0)
# write x_test out as a pickle file for later visualization
x_test_pkl = 'x_test.pkl'
with open(x_test_pkl, 'wb') as file:
joblib.dump(value=X_test, filename=os.path.join(OUTPUT_DIR, x_test_pkl))
run.upload_file('x_test_boston_housing.pkl', os.path.join(OUTPUT_DIR, x_test_pkl))
run.upload_file('x_test_california_housing.pkl', os.path.join(OUTPUT_DIR, x_test_pkl))
alpha = 0.5
@@ -50,7 +50,7 @@ original_model = run.register_model(model_name='model_explain_model_on_amlcomp',
model_path='original_model.pkl')
# Explain predictions on your local machine
tabular_explainer = TabularExplainer(model, X_train, features=boston_data.feature_names)
tabular_explainer = TabularExplainer(model, X_train, features=california_data.feature_names)
# Explain overall model predictions (global explanation)
# Passing in test dataset for evaluation examples - note it must be a representative sample of the original data
@@ -60,5 +60,5 @@ global_explanation = tabular_explainer.explain_global(X_test)
# Uploading model explanation data for storage or visualization in webUX
# The explanation can then be downloaded on any compute
comment = 'Global explanation on regression model trained on boston dataset'
comment = 'Global explanation on regression model trained on california dataset'
client.upload_model_explanation(global_explanation, comment=comment, model_id=original_model.id)