def test_transform(self):
X = numpy.asarray([
"January", "February", "March", "April", "May", "June", "July",
"August", "September", "October", "November", "December"
])
transformer = MatchesTransformer("ar?y")
self.assertEqual(
[[True], [True], [False], [False], [True], [False], [False],
[False], [False], [False], [False], [False]],
transformer.transform(X).tolist())
def test_transform(self):
X = numpy.asarray([
"January", "February", "March", "April", "May", "June", "July",
"August", "September", "October", "November", "December"
])
Xt_exp = [
True, True, False, False, True, False, False, False, False, False,
False, False
]
transformer = MatchesTransformer("ar?y")
self.assertEqual(Xt_exp, transformer.transform(X).tolist())
X = DataFrame(X.reshape(-1, 1), columns=["month"])
Xt = transformer.transform(X)
self.assertTrue((12, 1), Xt.shape)
self.assertEqual(Xt_exp, Xt.tolist())
def build_audit(classifier, name, with_proba = True, fit_params = {}, predict_params = {}, predict_proba_params = {}, **pmml_options):
continuous_mapper = DataFrameMapper([
(["Age", "Income", "Hours"], MultiDomain([ContinuousDomain() for i in range(0, 3)]))
])
categorical_mapper = DataFrameMapper([
(["Employment"], [CategoricalDomain(), SubstringTransformer(0, 3), OneHotEncoder(drop = ["Vol"]), SelectFromModel(DecisionTreeClassifier(random_state = 13))]),
(["Education"], [CategoricalDomain(), ReplaceTransformer("[aeiou]", ""), OneHotEncoder(drop = "first"), SelectFromModel(RandomForestClassifier(n_estimators = 3, random_state = 13), threshold = "1.25 * mean")]),
(["Marital"], [CategoricalDomain(), LabelBinarizer(neg_label = -1, pos_label = 1), SelectKBest(k = 3)]),
(["Occupation"], [CategoricalDomain(), LabelBinarizer(), SelectKBest(k = 3)]),
(["Gender"], [CategoricalDomain(), MatchesTransformer("^Male$"), CastTransformer(int)]),
(["Deductions"], [CategoricalDomain()]),
])
pipeline = Pipeline([
("union", FeatureUnion([
("continuous", continuous_mapper),
("categorical", Pipeline([
("mapper", categorical_mapper),
("polynomial", PolynomialFeatures())
]))
])),
("classifier", classifier)
])
pipeline.fit(audit_X, audit_y, **fit_params)
pipeline = make_pmml_pipeline(pipeline, audit_X.columns.values, audit_y.name)
pipeline.configure(**pmml_options)
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)