def test_fit(self):
regressor = DummyRegressor()
regressor_proxy = EstimatorProxy(regressor, attr_names_=["constant_"])
self.assertFalse(hasattr(regressor_proxy, "constant_"))
regressor_proxy.fit(numpy.array([[0], [0]]), numpy.array([0.0, 2.0]))
self.assertEqual(1.0, regressor.constant_)
self.assertEqual(1.0, regressor_proxy.constant_)
def build_audit(classifier, name, with_proba=True):
mapper = DataFrameMapper([
("Age", ContinuousDomain()),
("Employment", [
LabelBinarizer(),
SelectFromModel(EstimatorProxy(
DecisionTreeClassifier(random_state=13)),
threshold="1.25 * mean")
]),
("Education", [
LabelBinarizer(),
SelectorProxy(
SelectFromModel(EstimatorProxy(
RandomForestClassifier(random_state=13, n_estimators=3)),
threshold="median"))
]), ("Marital", [LabelBinarizer(), SelectKBest(k=3)]),
("Occupation", [LabelBinarizer(),
SelectorProxy(SelectKBest(k=3))]),
("Income", ContinuousDomain()), ("Gender", LabelEncoder()),
("Deductions", LabelEncoder()), ("Hours", ContinuousDomain())
])
pipeline = PMMLPipeline([("mapper", mapper), ("classifier", classifier)])
pipeline.fit(audit_X, audit_y)
store_pkl(pipeline, name + ".pkl")
adjusted = DataFrame(pipeline.predict(audit_X), columns=["Adjusted"])
if (with_proba == True):
adjusted_proba = DataFrame(pipeline.predict_proba(audit_X),
columns=["probability_0", "probability_1"])
adjusted = pandas.concat((adjusted, adjusted_proba), axis=1)
store_csv(adjusted, name + ".csv")
classifier.pmml_feature_importances_ = classifier.feature_importances_
else:
pass
if isinstance(classifier, XGBClassifier):
pipeline.verify(audit_X.sample(frac = 0.05, random_state = 13), predict_params = predict_params, predict_proba_params = predict_proba_params, precision = 1e-5, zeroThreshold = 1e-5)
else:
pipeline.verify(audit_X.sample(frac = 0.05, random_state = 13), predict_params = predict_params, predict_proba_params = predict_proba_params)
store_pkl(pipeline, name)
adjusted = DataFrame(pipeline.predict(audit_X, **predict_params), columns = ["Adjusted"])
if with_proba == True:
adjusted_proba = DataFrame(pipeline.predict_proba(audit_X, **predict_proba_params), columns = ["probability(0)", "probability(1)"])
adjusted = pandas.concat((adjusted, adjusted_proba), axis = 1)
store_csv(adjusted, name)
if "Audit" in datasets:
build_audit(EstimatorProxy(DecisionTreeClassifier(min_samples_leaf = 2, random_state = 13)), "DecisionTreeAudit", compact = False)
build_audit(BaggingClassifier(DecisionTreeClassifier(random_state = 13, min_samples_leaf = 5), n_estimators = 3, max_features = 0.5, random_state = 13), "DecisionTreeEnsembleAudit")
build_audit(DummyClassifier(strategy = "most_frequent"), "DummyAudit")
build_audit(EstimatorProxy(ExtraTreesClassifier(n_estimators = 10, min_samples_leaf = 5, random_state = 13)), "ExtraTreesAudit")
build_audit(GBDTLRClassifier(RandomForestClassifier(n_estimators = 17, random_state = 13), LogisticRegression()), "GBDTLRAudit")
build_audit(GBDTLRClassifier(XGBClassifier(n_estimators = 17, random_state = 13), LogisticRegression()), "XGBLRAudit")
build_audit(GBDTLRClassifier(XGBRFClassifier(n_estimators = 7, max_depth = 6, random_state = 13), SGDClassifier(loss = "log", penalty = "elasticnet", random_state = 13)), "XGBRFLRAudit")
build_audit(EstimatorProxy(GradientBoostingClassifier(loss = "exponential", init = None, random_state = 13)), "GradientBoostingAudit")
build_audit(HistGradientBoostingClassifier(max_iter = 71, random_state = 13), "HistGradientBoostingAudit")
build_audit(LGBMClassifier(objective = "binary", n_estimators = 37), "LGBMAudit", predict_params = {"num_iteration" : 17}, predict_proba_params = {"num_iteration" : 17}, num_iteration = 17)
build_audit(LinearDiscriminantAnalysis(solver = "lsqr"), "LinearDiscriminantAnalysisAudit")
build_audit(LinearSVC(penalty = "l1", dual = False, random_state = 13), "LinearSVCAudit", with_proba = False)
build_audit(LogisticRegression(multi_class = "multinomial", solver = "newton-cg", max_iter = 500), "MultinomialLogisticRegressionAudit")
build_audit(LogisticRegressionCV(cv = 3, multi_class = "ovr"), "OvRLogisticRegressionAudit")
build_audit(BaggingClassifier(LogisticRegression(), n_estimators = 3, max_features = 0.5, random_state = 13), "LogisticRegressionEnsembleAudit")
build_audit(GaussianNB(), "NaiveBayesAudit")
def build_audit(classifier, name, with_proba = True, **kwargs):
continuous_mapper = DataFrameMapper([
("Age", ContinuousDomain()),
("Income", ContinuousDomain()),
("Hours", ContinuousDomain())
])
categorical_mapper = DataFrameMapper([
("Employment", [CategoricalDomain(), LabelBinarizer(), SelectorProxy(SelectFromModel(EstimatorProxy(DecisionTreeClassifier(random_state = 13))))]),
("Education", [CategoricalDomain(), LabelBinarizer(), SelectorProxy(SelectFromModel(EstimatorProxy(RandomForestClassifier(random_state = 13, n_estimators = 3)), threshold = "1.25 * mean"))]),
("Marital", [CategoricalDomain(), LabelBinarizer(neg_label = -1, pos_label = 1), SelectKBest(k = 3)]),
("Occupation", [CategoricalDomain(), LabelBinarizer(), SelectorProxy(SelectKBest(k = 3))]),
("Gender", [CategoricalDomain(), LabelBinarizer(neg_label = -3, pos_label = 3)]),
("Deductions", [CategoricalDomain(), LabelEncoder()]),
])
pipeline = PMMLPipeline([
("union", FeatureUnion([
("continuous", continuous_mapper),
("categorical", Pipeline([
("mapper", categorical_mapper),
("polynomial", PolynomialFeatures())
]))
])),
("classifier", classifier)
])
pipeline.fit(audit_X, audit_y)
customize(classifier, **kwargs)
store_pkl(pipeline, name + ".pkl")
adjusted = DataFrame(pipeline.predict(audit_X), columns = ["Adjusted"])
if(with_proba == True):
adjusted_proba = DataFrame(pipeline.predict_proba(audit_X), columns = ["probability(0)", "probability(1)"])
adjusted = pandas.concat((adjusted, adjusted_proba), axis = 1)
store_csv(adjusted, name + ".csv")