def test_transform(self):
X = numpy.asarray([-2, -1, 0, 1, 2])
transformer = PowerFunctionTransformer(power=1)
self.assertEqual(X.tolist(), transformer.transform(X).tolist())
transformer = PowerFunctionTransformer(power=2)
self.assertEqual([4, 1, 0, 1, 4], transformer.transform(X).tolist())
transformer = PowerFunctionTransformer(power=3)
self.assertEqual([-8, -1, 0, 1, 8], transformer.transform(X).tolist())
def test_power(self):
X = numpy.asarray([-2, -1, 0, 1, 2])
pow = PowerFunctionTransformer(power=1)
self.assertEquals(X.tolist(), pow.transform(X).tolist())
pow = PowerFunctionTransformer(power=2)
self.assertEquals([4, 1, 0, 1, 4], pow.transform(X).tolist())
pow = PowerFunctionTransformer(power=3)
self.assertEquals([-8, -1, 0, 1, 8], pow.transform(X).tolist())
def build_iris(classifier, name, with_proba = True, fit_params = {}, predict_params = {}, predict_proba_params = {}, **pmml_options):
pipeline = Pipeline([
("pipeline", Pipeline([
("mapper", DataFrameMapper([
(iris_X.columns.values, ContinuousDomain()),
(["Sepal.Length", "Petal.Length"], Aggregator(function = "mean")),
(["Sepal.Width", "Petal.Width"], Aggregator(function = "mean"))
])),
("transform", FeatureUnion([
("normal_scale", FunctionTransformer(None, validate = True)),
("log_scale", FunctionTransformer(numpy.log10, validate = True)),
("power_scale", PowerFunctionTransformer(power = 2))
]))
])),
("pca", IncrementalPCA(n_components = 3, whiten = True)),
("classifier", classifier)
])
pipeline.fit(iris_X, iris_y, **fit_params)
pipeline = make_pmml_pipeline(pipeline, iris_X.columns.values, iris_y.name)
pipeline.configure(**pmml_options)
if isinstance(classifier, XGBClassifier):
pipeline.verify(iris_X.sample(frac = 0.10, random_state = 13), predict_params = predict_params, predict_proba_params = predict_proba_params, precision = 1e-5, zeroThreshold = 1e-5)
else:
pipeline.verify(iris_X.sample(frac = 0.10, random_state = 13), predict_params = predict_params, predict_proba_params = predict_proba_params)
store_pkl(pipeline, name)
species = DataFrame(pipeline.predict(iris_X, **predict_params), columns = ["Species"])
if with_proba == True:
species_proba = DataFrame(pipeline.predict_proba(iris_X, **predict_proba_params), columns = ["probability(setosa)", "probability(versicolor)", "probability(virginica)"])
species = pandas.concat((species, species_proba), axis = 1)
store_csv(species, name)