def shap_values(model, x_train, x_text, features, initialization_examples):
"""
Provides feature importances to explain the model.
Parameters:
x_train: input dataset to train the model
x_test: test dataset
model: trained model
features: list of feature names. Optional, used if doing classification
classes: list of output class labels or names. Optional, used if doing classification
Returns:
explainer (object): provides the feature importances that determines the prediction of the model
global_explanation (object): provides the global feature importances that determines the prediction of the model
local_explanation (object): provides the global feature importances that determines the prediction of the model
"""
explainer = TabularExplainer(model, x_train, features=features)
# you can use the training data or the test data here
global_explanation = explainer.explain_global(x_test)
# explain the selected data point in the test set
local_explanation = explainer.explain_local(x_test)
return explainer, global_explanation, local_explanation
x_train, x_test, y_train, y_test = train_test_split(
X, y, test_size=0.2, random_state=0)
clf = svm.SVC(gamma=0.001, C=100., probability=True)
model = clf.fit(x_train, y_train)
explainer = TabularExplainer(model,
x_train,
features=feature_names,
classes=classes)
global_explanation = explainer.explain_global(x_test)
instance_num = 0
local_explanation = explainer.explain_local(x_test[instance_num, :])
prediction_value = clf.predict(x_test)[instance_num]
sorted_local_importance_values = local_explanation.get_ranked_local_values()[
prediction_value]
sorted_local_importance_names = local_explanation.get_ranked_local_names()[
prediction_value]
ExplanationDashboard(global_explanation, model, dataset=x_test, true_y=y_test)
ModelPerformanceDashboard(model, dataset=x_test, true_y=y_test)
input("Press Enter to continue...")
# Evaluate the RFC model
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(Y_test, Y_predict)
score = rfc.score(X_test, Y_test)
#explainability
from interpret.ext.blackbox import TabularExplainer
classes = ['Not Greater than 50k', "Greater than 50k"]
features = list(X.columns)
tab_explainer = TabularExplainer(trained_model,
X_train,
features=features,
classes=classes)
#global
global_explaination = tab_explainer.explain_global(X_train)
global_fi = global_explaination.get_feature_importance_dict()
#local
X_explain = X_test[:5]
local_explaination = tab_explainer.explain_local(X_explain)
local_f = local_explaination.get_ranked_local_names()
local_importance = local_explaination.get_ranked_local_values()
global_tab_feature_importance = global_tab_explanation.get_feature_importance_dict() # PFIExplainer global_pfi_explanation = pfi_explainer.explain_global(X_train, y_train) global_pfi_feature_importance = global_pfi_explanation.get_feature_importance_dict() # MimicExplainer local_mim_explanation = mim_explainer.explain_local(X_test[0:5]) local_mim_features = local_mim_explanation.get_ranked_local_names() local_mim_importance = local_mim_explanation.get_ranked_local_values() # TabularExplainer local_tab_explanation = tab_explainer.explain_local(X_test[0:5]) local_tab_features = local_tab_explanation.get_ranked_local_names() local_tab_importance = local_tab_explanation.get_ranked_local_values() #for showing it on client interface # Import Azure ML run library from azureml.core.run import Run from azureml.contrib.interpret.explanation.explanation_client import ExplanationClient from interpret.ext.blackbox import TabularExplainer # other imports as required # Get the experiment run context run = Run.get_context() # code to train model goes here
