def test_normalize(self): X = numpy.asarray([" One", " two ", "THRee "]) normalizer = StringNormalizer(function = None) self.assertEqual(["One", "two", "THRee"], normalizer.transform(X).tolist()) normalizer = StringNormalizer(function = "uppercase", trim_blanks = False) self.assertEqual([" ONE", " TWO ", "THREE "], normalizer.transform(X).tolist()) normalizer = StringNormalizer(function = "lowercase") self.assertEqual(["one", "two", "three"], normalizer.transform(X).tolist()) X = Series(X, dtype = str) self.assertEqual(["one", "two", "three"], normalizer.transform(X).tolist())
def test_transform(self): X = numpy.asarray([" One", " two ", "THRee "]) normalizer = StringNormalizer(function = None) self.assertEqual(["One", "two", "THRee"], normalizer.transform(X).tolist()) normalizer = StringNormalizer(function = "uppercase", trim_blanks = False) self.assertEqual([" ONE", " TWO ", "THREE "], normalizer.transform(X).tolist()) normalizer = StringNormalizer(function = "lowercase") self.assertEqual(["one", "two", "three"], normalizer.transform(X).tolist()) X = X.reshape(3, 1) self.assertEqual([["one"], ["two"], ["three"]], normalizer.transform(X).tolist())
def build_audit_na(classifier, name, with_proba = True, fit_params = {}, predict_params = {}, predict_proba_params = {}, predict_transformer = None, predict_proba_transformer = None, apply_transformer = None, **pmml_options):
employment_mapping = {
"CONSULTANT" : "PRIVATE",
"PSFEDERAL" : "PUBLIC",
"PSLOCAL" : "PUBLIC",
"PSSTATE" : "PUBLIC",
"SELFEMP" : "PRIVATE",
"PRIVATE" : "PRIVATE"
}
gender_mapping = {
"FEMALE" : 0.0,
"MALE" : 1.0,
"MISSING_VALUE" : 0.5
}
mapper = DataFrameMapper(
[(["Age"], [ContinuousDomain(missing_values = None, with_data = False), Alias(ExpressionTransformer("X[0] if pandas.notnull(X[0]) else -999", dtype = int), name = "flag_missing(Age, -999)"), SimpleImputer(missing_values = -999, strategy = "constant", fill_value = 38)])] +
[(["Age"], MissingIndicator())] +
[(["Hours"], [ContinuousDomain(missing_values = None, with_data = False), Alias(ExpressionTransformer("-999 if pandas.isnull(X[0]) else X[0]"), name = "flag_missing(Hours, -999)"), SimpleImputer(missing_values = -999, add_indicator = True)])] +
[(["Income"], [ContinuousDomain(missing_values = None, outlier_treatment = "as_missing_values", low_value = 5000, high_value = 200000, with_data = False), SimpleImputer(strategy = "median", add_indicator = True)])] +
[(["Employment"], [CategoricalDomain(missing_values = None, with_data = False), CategoricalImputer(missing_values = None), StringNormalizer(function = "uppercase"), LookupTransformer(employment_mapping, "OTHER"), StringNormalizer(function = "lowercase"), PMMLLabelBinarizer()])] +
[([column], [CategoricalDomain(missing_values = None, missing_value_replacement = "N/A", with_data = False), SimpleImputer(missing_values = "N/A", strategy = "most_frequent"), StringNormalizer(function = "lowercase"), PMMLLabelBinarizer()]) for column in ["Education", "Marital", "Occupation"]] +
[(["Gender"], [CategoricalDomain(missing_values = None, with_data = False), SimpleImputer(strategy = "constant"), StringNormalizer(function = "uppercase"), LookupTransformer(gender_mapping, None)])]
)
pipeline = PMMLPipeline([
("mapper", mapper),
("classifier", classifier)
], predict_transformer = predict_transformer, predict_proba_transformer = predict_proba_transformer, apply_transformer = apply_transformer)
pipeline.fit(audit_na_X, audit_na_y, **fit_params)
pipeline.configure(**pmml_options)
if isinstance(classifier, XGBClassifier):
pipeline.verify(audit_na_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_na_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_na_X, **predict_params), columns = ["Adjusted"])
if with_proba == True:
adjusted_proba = DataFrame(pipeline.predict_proba(audit_na_X, **predict_proba_params), columns = ["probability(0)", "probability(1)"])
adjusted = pandas.concat((adjusted, adjusted_proba), axis = 1)
if isinstance(classifier, DecisionTreeClassifier):
Xt = pipeline_transform(pipeline, audit_na_X)
adjusted_apply = DataFrame(classifier.apply(Xt), columns = ["nodeId"])
adjusted = pandas.concat((adjusted, adjusted_apply), axis = 1)
store_csv(adjusted, name)
def build_audit_na(classifier,
name,
with_proba=True,
predict_proba_transformer=None,
apply_transformer=None,
**pmml_options):
employment_mapping = {
"CONSULTANT": "PRIVATE",
"PSFEDERAL": "PUBLIC",
"PSLOCAL": "PUBLIC",
"PSSTATE": "PUBLIC",
"SELFEMP": "PRIVATE",
"PRIVATE": "PRIVATE"
}
gender_mapping = {"FEMALE": 0, "MALE": 1}
mapper = DataFrameMapper([(["Age"], [
ContinuousDomain(missing_values=None, with_data=False),
Alias(ExpressionTransformer(
"numpy.where(pandas.notnull(X[:, 0]), X[:, 0], -999)"),
name="flag_missing(Age, -999)"),
Imputer(missing_values=-999)
])] + [(["Hours"], [
ContinuousDomain(missing_values=None, with_data=False),
Alias(ExpressionTransformer(
"numpy.where(pandas.isnull(X[:, 0]), -999, X[:, 0])"),
name="flag_missing(Hours, -999)"),
Imputer(missing_values=-999)
])] + [(["Income"], [
ContinuousDomain(missing_values=None,
outlier_treatment="as_missing_values",
low_value=5000,
high_value=200000,
with_data=False),
Imputer()
])] + [(["Employment"], [
CategoricalDomain(missing_values=None, with_data=False),
CategoricalImputer(),
StringNormalizer(function="uppercase"),
LookupTransformer(employment_mapping, "OTHER"),
StringNormalizer(function="lowercase"),
PMMLLabelBinarizer()
])] + [([column], [
CategoricalDomain(missing_values=None, with_data=False),
CategoricalImputer(missing_values=None),
StringNormalizer(function="lowercase"),
PMMLLabelBinarizer()
]) for column in ["Education", "Marital", "Occupation"]] + [(["Gender"], [
CategoricalDomain(missing_values=None, with_data=False),
CategoricalImputer(),
StringNormalizer(function="uppercase"),
LookupTransformer(gender_mapping, None)
])])
pipeline = PMMLPipeline(
[("mapper", mapper), ("classifier", classifier)],
predict_proba_transformer=predict_proba_transformer,
apply_transformer=apply_transformer)
pipeline.fit(audit_na_X, audit_na_y)
pipeline.configure(**pmml_options)
store_pkl(pipeline, name + ".pkl")
adjusted = DataFrame(pipeline.predict(audit_na_X), columns=["Adjusted"])
if with_proba == True:
adjusted_proba = DataFrame(
pipeline.predict_proba(audit_na_X),
columns=["probability(0)", "probability(1)"])
adjusted = pandas.concat((adjusted, adjusted_proba), axis=1)
if isinstance(classifier, DecisionTreeClassifier):
Xt = pipeline_transform(pipeline, audit_na_X)
adjusted_apply = DataFrame(classifier.apply(Xt), columns=["nodeId"])
adjusted = pandas.concat((adjusted, adjusted_apply), axis=1)
store_csv(adjusted, name + ".csv")