def test_transform_int(self):
mapping = {(1, 1): "one", (2, 2): "two", (3, 3): "three"}
transformer = MultiLookupTransformer(mapping, None)
X = DataFrame([[1, 0], [1, 1], [2, 0], [2, 1], [2, 2], [3, 0], [3, 1],
[3, 2], [3, 3]])
self.assertEqual([[None], ["one"], [None], [None], ["two"], [None],
[None], [None], ["three"]],
transformer.transform(X).tolist())
def test_transform_int(self):
mapping = {(1, 1): "one", (2, 2): "two", (3, 3): "three"}
transformer = MultiLookupTransformer(mapping, None)
Y = DataFrame([[1, 0], [1, 1], [2, 0], [2, 1], [2, 2], [3, 0], [3, 1],
[3, 2], [3, 3]])
Yt = transformer.transform(Y)
self.assertEqual(
[None, "one", None, None, "two", None, None, None, "three"],
Yt.tolist())
def test_transform_object(self):
mapping = {tuple(["zero"]) : "null", ("one", True) : "ein", ("two", True) : "zwei", ("three", True) : "drei"}
with self.assertRaises(ValueError):
MultiLookupTransformer(mapping, None)
mapping.pop(tuple(["zero"]))
transformer = MultiLookupTransformer(mapping, None)
Y = DataFrame([["one", None], ["one", True], [None, True], ["two", True], ["three", True]])
Yt = transformer.transform(Y)
self.assertEqual([None, "ein", None, "zwei", "drei"], Yt.tolist())
Y = numpy.matrix([["one", True], ["one", None], ["two", True]], dtype = "O")
Yt = transformer.transform(Y)
self.assertEqual(["ein", None, "zwei"], Yt.tolist())
def build_auto(regressor, name, fit_params = {}, predict_params = {}, **pmml_options):
cylinders_origin_mapping = {
(8, 1) : "8/1",
(6, 1) : "6/1",
(4, 1) : "4/1",
(6, 2) : "6/2",
(4, 2) : "4/2",
(4, 3) : "4/3"
}
mapper = DataFrameMapper([
(["cylinders"], [CategoricalDomain(), Alias(ExpressionTransformer("X[0] % 2.0 > 0.0", dtype = numpy.int8), name = "odd(cylinders)", prefit = True)]),
(["cylinders", "origin"], [MultiDomain([None, CategoricalDomain()]), MultiLookupTransformer(cylinders_origin_mapping, default_value = "other"), OneHotEncoder()]),
(["model_year"], [CategoricalDomain(), CastTransformer(str), ExpressionTransformer("'19' + X[0] + '-01-01'"), CastTransformer("datetime64[D]"), DaysSinceYearTransformer(1977), Binarizer(threshold = 0)], {"alias" : "bin(model_year, 1977)"}),
(["model_year", "origin"], [ConcatTransformer("/"), OneHotEncoder(sparse = False), SelectorProxy(SelectFromModel(RandomForestRegressor(n_estimators = 3, random_state = 13), threshold = "1.25 * mean"))]),
(["weight", "displacement"], [ContinuousDomain(), ExpressionTransformer("(X[0] / X[1]) + 0.5", dtype = numpy.float64)], {"alias" : "weight / displacement + 0.5"}),
(["displacement", "horsepower", "weight", "acceleration"], [MultiDomain([None, ContinuousDomain(), None, ContinuousDomain()]), StandardScaler()])
])
pipeline = PMMLPipeline([
("mapper", mapper),
("selector", SelectUnique()),
("regressor", regressor)
])
pipeline.fit(auto_X, auto_y, **fit_params)
pipeline.configure(**pmml_options)
if isinstance(regressor, XGBRegressor):
pipeline.verify(auto_X.sample(frac = 0.05, random_state = 13), predict_params = predict_params, precision = 1e-5, zeroThreshold = 1e-5)
else:
pipeline.verify(auto_X.sample(frac = 0.05, random_state = 13), predict_params = predict_params)
store_pkl(pipeline, name)
mpg = DataFrame(pipeline.predict(auto_X, **predict_params), columns = ["mpg"])
store_csv(mpg, name)
def build_auto(regressor, name, **pmml_options):
cylinders_origin_mapping = {
(8, 1): "8/1",
(6, 1): "6/1",
(4, 1): "4/1",
(6, 2): "6/2",
(4, 2): "4/2",
(4, 3): "4/3"
}
mapper = DataFrameMapper([
(["cylinders", "origin"], [
MultiDomain([CategoricalDomain(),
CategoricalDomain()]),
MultiLookupTransformer(cylinders_origin_mapping,
default_value="other"),
LabelBinarizer()
]),
(["cylinders"],
Alias(ExpressionTransformer("X[0] % 2.0 > 0.0"),
name="odd(cylinders)",
prefit=True)),
(["model_year"], [CategoricalDomain(),
Binarizer(threshold=77)], {
"alias": "bin(model_year, 77)"
}), # Pre/post 1973 oil crisis effects
(["model_year", "origin"], [
MultiDomain([CategoricalDomain(),
CategoricalDomain()]),
ConcatTransformer("/"),
LabelBinarizer(),
SelectorProxy(
SelectFromModel(RandomForestRegressor(random_state=13,
n_estimators=3),
threshold="1.25 * mean"))
]),
(["displacement", "horsepower", "weight",
"acceleration"], [ContinuousDomain(),
StandardScaler()]),
(["weight",
"displacement"], ExpressionTransformer("(X[0] / X[1]) + 0.5"), {
"alias": "weight / displacement + 0.5"
})
])
pipeline = PMMLPipeline([("mapper", mapper), ("selector", SelectUnique()),
("regressor", regressor)])
pipeline.fit(auto_X, auto_y)
pipeline.configure(**pmml_options)
if isinstance(regressor, XGBRegressor):
pipeline.verify(auto_X.sample(frac=0.05, random_state=13),
precision=1e-5,
zeroThreshold=1e-5)
else:
pipeline.verify(auto_X.sample(frac=0.05, random_state=13))
store_pkl(pipeline, name)
mpg = DataFrame(pipeline.predict(auto_X), columns=["mpg"])
store_csv(mpg, name)
def build_auto(regressor, name, **pmml_options):
cylinders_origin_mapping = {
(8, 1): "8/1",
(6, 1): "6/1",
(4, 1): "4/1",
(6, 2): "6/2",
(4, 2): "4/2",
(6, 3): "6/3",
(4, 3): "4/3"
}
mapper = DataFrameMapper([
(["cylinders", "origin"], [
MultiDomain([CategoricalDomain(),
CategoricalDomain()]),
MultiLookupTransformer(cylinders_origin_mapping,
default_value="other"),
LabelBinarizer()
]),
(["model_year"], [CategoricalDomain(),
Binarizer(threshold=77)], {
"alias": "bin(model_year, 77)"
}), # Pre/post 1973 oil crisis effects
(["displacement", "horsepower", "weight",
"acceleration"], [ContinuousDomain(),
StandardScaler()]),
(["weight", "displacement"],
ExpressionTransformer("(X[:, 0] / X[:, 1]) + 0.5"), {
"alias": "weight / displacement + 0.5"
})
])
pipeline = Pipeline([("mapper", mapper), ("regressor", regressor)])
pipeline.fit(auto_X, auto_y)
pipeline = make_pmml_pipeline(pipeline, auto_X.columns.values, auto_y.name)
pipeline.configure(**pmml_options)
if isinstance(regressor, XGBRegressor):
pipeline.verify(auto_X.sample(frac=0.05, random_state=13),
precision=1e-5,
zeroThreshold=1e-5)
else:
pipeline.verify(auto_X.sample(frac=0.05, random_state=13))
store_pkl(pipeline, name + ".pkl")
mpg = DataFrame(pipeline.predict(auto_X), columns=["mpg"])
store_csv(mpg, name + ".csv")
