def __set_up_model_explanations(self, best_model, X_train, X_test, y_train,
y_test):
return automl_setup_model_explanations(best_model,
X=X_train,
X_test=X_test,
y=y_train,
task='classification')
def run(raw_data):
# Get predictions and explanations for each data point
data = pd.read_json(raw_data, orient="records")
# Make prediction
predictions = automl_model.predict(data)
# Setup for inferencing explanations
automl_explainer_setup_obj = automl_setup_model_explanations(
automl_model, X_test=data, task="regression")
# Retrieve model explanations for engineered explanations
engineered_local_importance_values = scoring_explainer.explain(
automl_explainer_setup_obj.X_test_transform)
# Retrieve model explanations for raw explanations
raw_local_importance_values = scoring_explainer.explain(
automl_explainer_setup_obj.X_test_transform, get_raw=True)
# You can return any data type as long as it is JSON-serializable
return {
"predictions": predictions.tolist(),
"engineered_local_importance_values":
engineered_local_importance_values,
"raw_local_importance_values": raw_local_importance_values,
}
def run(raw_data):
try:
columns = deploy_parameters.get("dataset_columns")
data = json.loads(raw_data)["data"]
input_data = pd.DataFrame.from_records(
data, columns=columns)
inputs_dc.collect(input_data)
pred_array = heart_disease_model.predict(input_data)
automl_explainer_setup_obj = automl_setup_model_explanations(heart_disease_model,
X_test=input_data, task='classification')
local_importance_values = explainer_model.explain(
automl_explainer_setup_obj.X_test_transform)
iterator = map(lambda x, y: {"prediction": HeartDiseaseTreatment(x).name, "local_importance": dict(
zip(columns, y))}, pred_array.tolist(), local_importance_values)
return json.dumps({"results": [*iterator]})
except Exception as e:
result = str(e)
return json.dumps({"error": result})
def run(raw_data):
data = pd.read_json(raw_data)
# Make prediction
pred = model.predict(data)
# Get raw feature importance values
automl_explainer_setup_obj = automl_setup_model_explanations(
model, X_test=data, task='classification')
raw_local_importance_values = scoring_explainer.explain(
automl_explainer_setup_obj.X_test_transform, get_raw=True)
# Combine explanations with feature names, reverse sorted by importance score
num_records = data.shape[0]
explanations = []
for i in range(num_records):
exp_dict = dict(
zip(automl_explainer_setup_obj.raw_feature_names,
raw_local_importance_values[i]))
sorted_exp_dict = dict(
sorted(exp_dict.items(), key=lambda item: item[1], reverse=True))
explanations.append(sorted_exp_dict)
return {"result": pred.tolist(), "explanations": explanations}
train_dataset = Dataset.get_by_name(workspace=ws,
name='<<train_dataset_name>>')
# Drop the lablled column to get the training set.
X_train = train_dataset.drop_columns(columns=['<<target_column_name>>'])
y_train = train_dataset.keep_columns(columns=['<<target_column_name>>'],
validate=True)
# Get the train dataset from the workspace
test_dataset = Dataset.get_by_name(workspace=ws, name='<<test_dataset_name>>')
# Drop the lablled column to get the testing set.
X_test = test_dataset.drop_columns(columns=['<<target_column_name>>'])
# Setup the class for explaining the AtuoML models
automl_explainer_setup_obj = automl_setup_model_explanations(fitted_model,
'<<task>>',
X=X_train,
X_test=X_test,
y=y_train)
# Initialize the Mimic Explainer
explainer = MimicWrapper(
ws,
automl_explainer_setup_obj.automl_estimator,
LGBMExplainableModel,
init_dataset=automl_explainer_setup_obj.X_transform,
run=automl_run,
features=automl_explainer_setup_obj.engineered_feature_names,
feature_maps=[automl_explainer_setup_obj.feature_map],
classes=automl_explainer_setup_obj.classes)
# Compute the engineered explanations
name="<<train_dataset_name>>")
# Drop the labeled column to get the training set.
X_train = train_dataset.drop_columns(columns=["<<target_column_name>>"])
y_train = train_dataset.keep_columns(columns=["<<target_column_name>>"],
validate=True)
# Get the test dataset from the workspace
test_dataset = Dataset.get_by_name(workspace=ws, name="<<test_dataset_name>>")
# Drop the labeled column to get the testing set.
X_test = test_dataset.drop_columns(columns=["<<target_column_name>>"])
# Setup the class for explaining the AutoML models
automl_explainer_setup_obj = automl_setup_model_explanations(
fitted_model,
"<<task>>",
X=X_train,
X_test=X_test,
y=y_train,
automl_run=automl_run)
# Initialize the Mimic Explainer
explainer = MimicWrapper(
ws,
automl_explainer_setup_obj.automl_estimator,
LGBMExplainableModel,
init_dataset=automl_explainer_setup_obj.X_transform,
run=automl_explainer_setup_obj.automl_run,
features=automl_explainer_setup_obj.engineered_feature_names,
feature_maps=[automl_explainer_setup_obj.feature_map],
classes=automl_explainer_setup_obj.classes,
)
train_dataset = Dataset.get_by_name(workspace=ws,
name='machineData_train_dataset')
# Drop the lablled column to get the training set.
X_train = train_dataset.drop_columns(columns=['<<target_column_name>>'])
y_train = train_dataset.keep_columns(columns=['<<target_column_name>>'],
validate=True)
# Get the train dataset from the workspace
test_dataset = Dataset.get_by_name(workspace=ws, name='<<test_dataset_name>>')
# Drop the lablled column to get the testing set.
X_test = test_dataset.drop_columns(columns=['<<target_column_name>>'])
# Setup the class for explaining the AtuoML models
automl_explainer_setup_obj = automl_setup_model_explanations(fitted_model,
'classification',
X=X_train,
X_test=X_test,
y=y_train)
# Initialize the Mimic Explainer
explainer = MimicWrapper(
ws,
automl_explainer_setup_obj.automl_estimator,
LGBMExplainableModel,
init_dataset=automl_explainer_setup_obj.X_transform,
run=automl_run,
features=automl_explainer_setup_obj.engineered_feature_names,
feature_maps=[automl_explainer_setup_obj.feature_map],
classes=automl_explainer_setup_obj.classes)
# Compute the engineered explanations
