def test_seconds_transform(self):
X = numpy.array([
datetime(1960, 1, 1),
datetime(1960, 1, 1, 0, 0, 1),
datetime(1960, 1, 1, 0, 1, 0),
datetime(1959, 12, 31, 23, 59, 59),
datetime(1960, 1, 3, 3, 30, 3)
])
transformer = SecondsSinceYearTransformer(year=1960)
self.assertEqual([0, 1, 60, -1, 185403],
transformer.transform(X).tolist())
def test_timedelta_seconds(self):
X = DataFrame([["2018-12-31T23:59:59", "2019-01-01T00:00:00"], ["2019-01-01T03:30:03", "2019-01-01T00:00:00"]], columns = ["left", "right"])
mapper = DataFrameMapper([
(["left", "right"], [DateTimeDomain(), SecondsSinceYearTransformer(year = 2010), ExpressionTransformer("X[0] - X[1]")])
])
Xt = mapper.fit_transform(X)
self.assertEqual([[-1], [12603]], Xt.tolist())
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")