def test_timedelta_days(self):
X = DataFrame(
[["2018-12-31", "2019-01-01"], ["2019-01-31", "2019-01-01"]],
columns=["left", "right"])
pipeline = Pipeline([
("union",
FeatureUnion([
("left_mapper",
DataFrameMapper([
("left",
[DateDomain(),
DaysSinceYearTransformer(year=2010)])
])),
("right_mapper",
DataFrameMapper([
("right",
[DateDomain(),
DaysSinceYearTransformer(year=2010)])
]))
])),
("expression",
Alias(ExpressionTransformer("X[0] - X[1]"),
"delta(left, right)",
prefit=True))
])
Xt = pipeline.fit_transform(X)
self.assertEqual([[-1], [30]], Xt.tolist())
def test_days_transform(self):
X = numpy.array([
datetime(1960, 1, 1),
datetime(1960, 1, 2),
datetime(1960, 2, 1),
datetime(1959, 12, 31),
datetime(2003, 4, 1)
])
transformer = DaysSinceYearTransformer(year=1960)
self.assertEqual([0, 1, 31, -1, 15796],
transformer.transform(X).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)
store_csv(df, "Apollo")
def build_apollo(mapper, name):
pipeline = PMMLPipeline([("mapper", mapper),
("classifier", DecisionTreeClassifier())])
pipeline.fit(df, df["success"])
store_pkl(pipeline, name)
success = DataFrame(pipeline.predict(df), columns=["success"])
success_proba = DataFrame(
pipeline.predict_proba(df),
columns=["probability(false)", "probability(true)"])
success = pandas.concat((success, success_proba), axis=1)
store_csv(success, name)
mapper = DataFrameMapper([(["launch", "return"], [
DateTimeDomain(),
DaysSinceYearTransformer(year=1968),
ExpressionTransformer("X[1] - X[0]")
])])
build_apollo(mapper, "DurationInDaysApollo")
mapper = DataFrameMapper([(["launch", "return"], [
DateTimeDomain(),
SecondsSinceYearTransformer(year=1968),
ExpressionTransformer("X[1] - X[0]")
])])
build_apollo(mapper, "DurationInSecondsApollo")