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, **kwargs):
mapper = DataFrameMapper([
(["cylinders"], CategoricalDomain()),
(["displacement", "horsepower", "weight",
"acceleration"], [ContinuousDomain(),
StandardScaler()]),
(["model_year"], [CategoricalDomain(),
Binarizer(threshold=77)], {
"alias": "bin(model_year, 77)"
}), # Pre/post 1973 oil crisis effects
(["origin"], OneHotEncoder()),
(["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)
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))
customize(regressor, **kwargs)
store_pkl(pipeline, name + ".pkl")
mpg = DataFrame(pipeline.predict(auto_X), columns=["mpg"])
store_csv(mpg, name + ".csv")
def build_audit_cat(classifier, name, with_proba=True, **fit_params):
mapper = DataFrameMapper(
[([column], ContinuousDomain())
for column in ["Age", "Income"]] + [(["Hours"], [
ContinuousDomain(),
CutTransformer(bins=[0, 20, 40, 60, 80, 100],
labels=False,
right=False,
include_lowest=True)
])] + [(["Employment", "Education", "Marital", "Occupation"], [
MultiDomain([
CategoricalDomain(),
CategoricalDomain(),
CategoricalDomain(),
CategoricalDomain()
]),
OrdinalEncoder()
])] +
[([column], [CategoricalDomain(), LabelEncoder()])
for column in ["Gender", "Deductions"]])
pipeline = Pipeline([("mapper", mapper), ("classifier", classifier)])
pipeline.fit(audit_X, audit_y, **fit_params)
pipeline = make_pmml_pipeline(pipeline, audit_X.columns.values,
audit_y.name)
store_pkl(pipeline, name)
adjusted = DataFrame(pipeline.predict(audit_X), columns=["Adjusted"])
if with_proba == True:
adjusted_proba = DataFrame(
pipeline.predict_proba(audit_X),
columns=["probability(0)", "probability(1)"])
adjusted = pandas.concat((adjusted, adjusted_proba), axis=1)
store_csv(adjusted, name)
def build_auto_na(regressor, name, predict_transformer = None, apply_transformer = None, **pmml_options):
mapper = DataFrameMapper(
[([column], [CategoricalDomain(missing_values = -1), CategoricalImputer(missing_values = -1), PMMLLabelBinarizer()]) for column in ["cylinders", "model_year"]] +
[(["origin"], [CategoricalDomain(missing_values = -1), SimpleImputer(missing_values = -1, strategy = "most_frequent"), OneHotEncoder()])] +
[(["acceleration"], [ContinuousDomain(missing_values = None), CutTransformer(bins = [5, 7.5, 10, 12.5, 15, 17.5, 20, 22.5, 25], labels = False), CategoricalImputer(), LabelBinarizer()])] +
[(["displacement"], [ContinuousDomain(missing_values = None), SimpleImputer(), CutTransformer(bins = [0, 100, 200, 300, 400, 500], labels = ["XS", "S", "M", "L", "XL"]), LabelBinarizer()])] +
[(["horsepower"], [ContinuousDomain(missing_values = None, outlier_treatment = "as_extreme_values", low_value = 50, high_value = 225), SimpleImputer(strategy = "median")])] +
[(["weight"], [ContinuousDomain(missing_values = None, outlier_treatment = "as_extreme_values", low_value = 2000, high_value = 5000), SimpleImputer(strategy = "median")])]
)
pipeline = PMMLPipeline([
("mapper", mapper),
("regressor", regressor)
], predict_transformer = predict_transformer, apply_transformer = apply_transformer)
pipeline.fit(auto_na_X, auto_na_y)
if isinstance(regressor, DecisionTreeRegressor):
tree = regressor.tree_
node_impurity = {node_idx : tree.impurity[node_idx] for node_idx in range(0, tree.node_count) if tree.impurity[node_idx] != 0.0}
pmml_options["node_extensions"] = {regressor.criterion : node_impurity}
pipeline.configure(**pmml_options)
pipeline.verify(auto_na_X.sample(frac = 0.05, random_state = 13))
store_pkl(pipeline, name)
mpg = DataFrame(pipeline.predict(auto_na_X), columns = ["mpg"])
if isinstance(regressor, DecisionTreeRegressor):
Xt = pipeline_transform(pipeline, auto_na_X)
mpg_apply = DataFrame(regressor.apply(Xt), columns = ["nodeId"])
mpg = pandas.concat((mpg, mpg_apply), axis = 1)
store_csv(mpg, name)
def test_fit_string_missing(self):
domain = CategoricalDomain(missing_values="N/A",
missing_value_replacement="0")
domain = clone(domain)
self.assertEqual("N/A", domain.missing_values)
self.assertEqual("0", domain.missing_value_replacement)
self.assertFalse(domain._empty_fit())
X = DataFrame(["1", "N/A", "3", "2", "N/A", "2"])
Xt = domain.fit_transform(X)
self.assertIsInstance(Xt, DataFrame)
self.assertEqual(["1", "2", "3"], domain.data_.tolist())
self.assertEqual({
"totalFreq": 6,
"missingFreq": 2,
"invalidFreq": 0
}, domain.counts_)
self.assertEqual({
"1": 1,
"2": 2,
"3": 1
}, _value_count(domain.discr_stats_))
self.assertEqual(["1", "0", "3", "2", "0", "2"], Xt.ix[:, 0].tolist())
X = numpy.array(["N/A", "N/A"])
Xt = domain.transform(X)
self.assertEqual(["0", "0"], Xt.tolist())
def get_training_data(con):
data = pd.read_sql("""select
user_responses.id as id,
drink_name as drink,
user_responses.question_name as question_name,
question_choices.choice as choice,
session_id
from user_responses inner join question_choices
on user_responses.question_choice = question_choices.id"""
, con=con
, index_col='id')
print(data)
data = data.pivot(index='session_id', columns='question_name', values=['choice', 'drink'])
print(data)
pipeline = PMMLPipeline([
("transformation", DataFrameMapper([
(["hotdog"], [CategoricalDomain(), LabelBinarizer()])
, (["tp"], [CategoricalDomain(), LabelBinarizer()])
, (["personality"], [CategoricalDomain(), LabelBinarizer()])
])),
("classifier", GaussianNB())
])
return data, pipeline
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 = 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_audit_cat(classifier, name, with_proba = True, fit_params = {}):
marital_mapping = {
"Married-spouse-absent" : "Married"
}
mapper = DataFrameMapper(
[([column], ContinuousDomain(display_name = column)) for column in ["Age", "Income"]] +
[(["Hours"], [ContinuousDomain(display_name = "Hours"), CutTransformer(bins = [0, 20, 40, 60, 80, 100], labels = False, right = False, include_lowest = True)])] +
[(["Employment", "Education"], [MultiDomain([CategoricalDomain(display_name = "Employment"), CategoricalDomain(display_name = "Education")]), OrdinalEncoder(dtype = numpy.int_)])] +
[(["Marital"], [CategoricalDomain(display_name = "Marital"), FilterLookupTransformer(marital_mapping), OrdinalEncoder(dtype = numpy.uint16)])] +
[(["Occupation"], [CategoricalDomain(display_name = "Occupation"), OrdinalEncoder(dtype = numpy.float_)])] +
[([column], [CategoricalDomain(display_name = column), LabelEncoder()]) for column in ["Gender", "Deductions"]]
)
pipeline = Pipeline([
("mapper", mapper),
("classifier", classifier)
])
pipeline.fit(audit_X, audit_y, **fit_params)
pipeline = make_pmml_pipeline(pipeline, audit_X.columns.values, audit_y.name)
pipeline.verify(audit_X.sample(frac = 0.05, random_state = 13))
store_pkl(pipeline, name)
adjusted = DataFrame(pipeline.predict(audit_X), columns = ["Adjusted"])
if with_proba == True:
adjusted_proba = DataFrame(pipeline.predict_proba(audit_X), columns = ["probability(0)", "probability(1)"])
adjusted = pandas.concat((adjusted, adjusted_proba), axis = 1)
store_csv(adjusted, name)
def test_fit_string(self):
domain = clone(
CategoricalDomain(with_data=False, with_statistics=False))
self.assertTrue(domain._empty_fit())
domain = clone(
CategoricalDomain(missing_values=None, with_statistics=False))
self.assertIsNone(domain.missing_values)
self.assertEqual("as_is", domain.missing_value_treatment)
self.assertIsNone(domain.missing_value_replacement)
self.assertEqual("return_invalid", domain.invalid_value_treatment)
self.assertIsNone(domain.invalid_value_replacement)
self.assertFalse(domain._empty_fit())
X = DataFrame(["1", None, "3", "2", None, "2"])
Xt = domain.fit_transform(X)
self.assertIsInstance(Xt, DataFrame)
self.assertEqual(["1", "2", "3"], domain.data_.tolist())
self.assertFalse(hasattr(domain, "counts_"))
self.assertFalse(hasattr(domain, "discr_stats_"))
self.assertEqual(["1", None, "3", "2", None, "2"], Xt.iloc[:,
0].tolist())
X = numpy.array([None, None])
Xt = domain.transform(X)
self.assertEqual([None, None], Xt.tolist())
X = numpy.array(["4"])
with self.assertRaises(ValueError):
domain.transform(X)
def test_fit_int(self):
domain = clone(
CategoricalDomain(with_data=False, with_statistics=False))
self.assertTrue(domain._empty_fit())
domain = clone(
CategoricalDomain(missing_value_treatment="as_value",
missing_value_replacement=1,
invalid_value_treatment="as_is",
invalid_value_replacement=0))
self.assertIsNone(domain.missing_values)
self.assertEqual("as_value", domain.missing_value_treatment)
self.assertEqual(1, domain.missing_value_replacement)
self.assertEqual("as_is", domain.invalid_value_treatment)
self.assertEqual(0, domain.invalid_value_replacement)
self.assertFalse(hasattr(domain, "data_"))
self.assertFalse(hasattr(domain, "counts_"))
self.assertFalse(hasattr(domain, "discr_stats_"))
self.assertFalse(domain._empty_fit())
X = DataFrame([1, None, 3, 2, None, 2])
Xt = domain.fit_transform(X)
self.assertIsInstance(Xt, DataFrame)
self.assertEqual([1, 2, 3], domain.data_.tolist())
self.assertEqual({
"totalFreq": 6,
"missingFreq": 2,
"invalidFreq": 0
}, domain.counts_)
self.assertEqual({1: 1, 2: 2, 3: 1}, _value_count(domain.discr_stats_))
self.assertEqual([1, 1, 3, 2, 1, 2], Xt[0].tolist())
X = numpy.array([None, None])
Xt = domain.transform(X)
self.assertEqual([1, 1], Xt.tolist())
def test_fit_string(self):
domain = CategoricalDomain(with_statistics = False)
self.assertEqual("as_is", domain.missing_value_treatment)
self.assertFalse(hasattr(domain, "missing_value_replacement"))
self.assertEqual("return_invalid", domain.invalid_value_treatment)
X = numpy.array(["1", None, "3", "2", None, "2"])
Xt = domain.fit_transform(X)
self.assertEqual(numpy.array(["1", "2", "3"]).tolist(), domain.data_.tolist())
self.assertFalse(hasattr(domain, "counts_"))
self.assertFalse(hasattr(domain, "discr_stats_"))
self.assertEqual(numpy.array(["1", None, "3", "2", None, "2"]).tolist(), Xt.tolist())
def get_sample_data(con):
data = pd.read_sql("select * from sample_training_data"
, con=con
, index_col="id")
pipeline = PMMLPipeline([
("transformation", DataFrameMapper([
(["hotdog"], [CategoricalDomain(), LabelBinarizer()]),
(["tp"], [CategoricalDomain(), LabelBinarizer()])
])),
("classifier", GaussianNB())
])
return data, pipeline
def test_fit_int_missing(self):
domain = CategoricalDomain(missing_values = -1, missing_value_replacement = 0)
self.assertEqual(-1, domain.missing_values)
self.assertEqual(0, domain.missing_value_replacement)
self.assertFalse(domain._empty_fit())
X = DataFrame([1, -1, 3, 2, -1, 2])
Xt = domain.fit_transform(X)
self.assertIsInstance(Xt, DataFrame)
self.assertEqual([1, 2, 3], domain.data_.tolist())
self.assertEqual({"totalFreq" : 6, "missingFreq" : 2, "invalidFreq" : 0}, domain.counts_)
self.assertEqual({1 : 1, 2 : 2, 3 : 1}, _value_count(domain.discr_stats_))
self.assertEqual([1, 0, 3, 2, 0, 2], Xt[0].tolist())
X = numpy.array([-1, -1])
Xt = domain.transform(X)
self.assertEqual([0, 0], Xt.tolist())
def build_auto(regressor, name):
mapper = DataFrameMapper([
(["cylinders"], CategoricalDomain()),
(["displacement", "horsepower", "weight", "acceleration"], [ContinuousDomain(), Imputer(missing_values = "NaN"), StandardScaler()]),
(["model_year"], [CategoricalDomain(), Binarizer(threshold = 77)], {"alias" : "bin(model_year, 77)"}), # Pre/post 1973 oil crisis effects
(["origin"], OneHotEncoder())
])
pipeline = PMMLPipeline([
("mapper", mapper),
("regressor", regressor)
])
pipeline.fit(auto_X, auto_y)
store_pkl(pipeline, name + ".pkl")
mpg = DataFrame(pipeline.predict(auto_X), columns = ["mpg"])
store_csv(mpg, name + ".csv")
def build_visit(regressor, name):
mapper = DataFrameMapper(
[(["edlevel"], [CategoricalDomain(), OneHotEncoder()])] +
[([bin_column], [CategoricalDomain(), OneHotEncoder()]) for bin_column in ["outwork", "female", "married", "kids", "self"]] +
[(["age"], ContinuousDomain())] +
[(["hhninc", "educ"], ContinuousDomain())]
)
pipeline = PMMLPipeline([
("mapper", mapper),
("regressor", regressor)
])
pipeline.fit(visit_X, visit_y)
pipeline.verify(visit_X.sample(frac = 0.05, random_state = 13))
store_pkl(pipeline, name)
docvis = DataFrame(pipeline.predict(visit_X), columns = ["docvis"])
store_csv(docvis, name)
def build_auto_h2o(regressor, name):
transformer = ColumnTransformer(
[(column, CategoricalDomain(), [column])
for column in ["cylinders", "model_year", "origin"]] +
[(column, ContinuousDomain(), [column]) for column in
["displacement", "horsepower", "weight", "acceleration"]])
pipeline = PMMLPipeline([("transformer", transformer),
("uploader",
H2OFrameCreator(column_names=[
"cylinders", "model_year", "origin",
"displacement", "horsepower", "weight",
"acceleration"
],
column_types=[
"enum", "enum", "enum",
"numeric", "numeric",
"numeric", "numeric"
])), ("regressor", regressor)])
pipeline.fit(auto_X, H2OFrame(auto_y.to_frame()))
pipeline.verify(auto_X.sample(frac=0.05, random_state=13))
regressor = pipeline._final_estimator
store_mojo(regressor, name + ".zip")
store_pkl(pipeline, name + ".pkl")
mpg = pipeline.predict(auto_X)
mpg.set_names(["mpg"])
store_csv(mpg.as_data_frame(), name + ".csv")
def test_fit_int(self):
domain = CategoricalDomain(missing_value_treatment="as_value",
missing_value_replacement=-999,
invalid_value_treatment="as_is")
self.assertEqual("as_value", domain.missing_value_treatment)
self.assertEqual(-999, domain.missing_value_replacement)
self.assertEqual("as_is", domain.invalid_value_treatment)
self.assertFalse(hasattr(domain, "data_"))
X = DataFrame(numpy.array([1, None, 3, 2, None, 2]))
Xt = domain.fit_transform(X)
self.assertEqual(
numpy.array([1, 2, 3]).tolist(), domain.data_.tolist())
self.assertEqual(
numpy.array([1, -999, 3, 2, -999, 2]).tolist(), Xt[0].tolist())
X = numpy.array([None, None])
Xt = domain.transform(X)
self.assertEqual(numpy.array([-999, -999]).tolist(), Xt.tolist())
def test_mapper(self):
domain = CategoricalDomain()
df = DataFrame([{"X": "2", "y": 2}, {"X": "1"}, {"X": "3"}])
mapper = DataFrameMapper([("X", [domain, LabelBinarizer()]),
("y", None)])
mapper.fit_transform(df)
self.assertEqual(
numpy.array(["1", "2", "3"]).tolist(), domain.data_.tolist())
def test_fit_int(self):
domain = CategoricalDomain(missing_value_treatment = "as_value", missing_value_replacement = -999, invalid_value_treatment = "as_is")
self.assertEqual("as_value", domain.missing_value_treatment)
self.assertEqual(-999, domain.missing_value_replacement)
self.assertEqual("as_is", domain.invalid_value_treatment)
self.assertFalse(hasattr(domain, "data_"))
self.assertFalse(hasattr(domain, "counts_"))
self.assertFalse(hasattr(domain, "discr_stats_"))
X = DataFrame(numpy.array([1, None, 3, 2, None, 2]))
Xt = domain.fit_transform(X)
self.assertEqual(numpy.array([1, 2, 3]).tolist(), domain.data_.tolist())
self.assertEqual({"totalFreq" : 6, "missingFreq" : 2, "invalidFreq" : 0}, domain.counts_)
self.assertEqual({1 : 1, 2 : 2, 3 : 1}, _value_count(domain.discr_stats_))
self.assertEqual(numpy.array([1, -999, 3, 2, -999, 2]).tolist(), Xt[0].tolist())
X = numpy.array([None, None]);
Xt = domain.transform(X)
self.assertEqual(numpy.array([-999, -999]).tolist(), Xt.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 test_mapper(self):
domain = CategoricalDomain()
df = DataFrame([{"X" : "2", "y" : 2}, {"X" : "1"}, {"X" : "3"}])
mapper = DataFrameMapper([
("X", [domain, LabelBinarizer()]),
("y", None)
])
mapper.fit_transform(df)
self.assertEqual({"totalFreq" : 3, "missingFreq" : 0, "invalidFreq" : 0}, domain.counts_)
self.assertEqual({"1" : 1, "2" : 1, "3" : 1}, _value_count(domain.discr_stats_))
self.assertEqual(["1", "2", "3"], domain.data_.tolist())
def test_fit_transform(self):
domain = MultiDomain([ContinuousDomain(missing_value_replacement = 0.0), CategoricalDomain(missing_value_replacement = "zero")])
X = DataFrame([[-1.0, "minus one"], [float("NaN"), None], [1.0, "one"]], columns = ["x1", "x2"])
Xt = domain.fit_transform(X)
self.assertTrue(isinstance(Xt, DataFrame))
self.assertEqual([-1.0, 0.0, 1.0], Xt["x1"].tolist())
self.assertEqual(["minus one", "zero", "one"], Xt["x2"].tolist())
X = numpy.array([[float("NaN"), None]])
Xt = domain.transform(X)
self.assertTrue(isinstance(Xt, numpy.ndarray))
self.assertTrue([0.0], Xt[:, 0].tolist())
self.assertTrue(["zero"], Xt[:, 1].tolist())
def make_fit_lgbmlr(gbdt, lr):
mapper = DataFrameMapper(
[([cat_column],
[CategoricalDomain(), LabelEncoder()])
for cat_column in cat_columns] + [(cont_columns, ContinuousDomain())])
classifier = GBDTLRClassifier(gbdt, lr)
pipeline = PMMLPipeline([("mapper", mapper), ("classifier", classifier)])
pipeline.fit(df[cat_columns + cont_columns],
df[label_column],
classifier__gbdt__categorical_feature=range(
0, len(cat_columns)))
return pipeline
def build_audit(classifier, name, with_proba = True, **kwargs):
continuous_mapper = DataFrameMapper([
("Age", ContinuousDomain()),
("Income", ContinuousDomain()),
("Hours", ContinuousDomain())
])
categorical_mapper = DataFrameMapper([
("Employment", [CategoricalDomain(), LabelBinarizer(), SelectorProxy(SelectFromModel(EstimatorProxy(DecisionTreeClassifier(random_state = 13))))]),
("Education", [CategoricalDomain(), LabelBinarizer(), SelectorProxy(SelectFromModel(EstimatorProxy(RandomForestClassifier(random_state = 13, n_estimators = 3)), threshold = "1.25 * mean"))]),
("Marital", [CategoricalDomain(), LabelBinarizer(neg_label = -1, pos_label = 1), SelectKBest(k = 3)]),
("Occupation", [CategoricalDomain(), LabelBinarizer(), SelectorProxy(SelectKBest(k = 3))]),
("Gender", [CategoricalDomain(), LabelBinarizer(neg_label = -3, pos_label = 3)]),
("Deductions", [CategoricalDomain(), LabelEncoder()]),
])
pipeline = PMMLPipeline([
("union", FeatureUnion([
("continuous", continuous_mapper),
("categorical", Pipeline([
("mapper", categorical_mapper),
("polynomial", PolynomialFeatures())
]))
])),
("classifier", classifier)
])
pipeline.fit(audit_X, audit_y)
customize(classifier, **kwargs)
store_pkl(pipeline, name + ".pkl")
adjusted = DataFrame(pipeline.predict(audit_X), columns = ["Adjusted"])
if(with_proba == True):
adjusted_proba = DataFrame(pipeline.predict_proba(audit_X), columns = ["probability(0)", "probability(1)"])
adjusted = pandas.concat((adjusted, adjusted_proba), axis = 1)
store_csv(adjusted, name + ".csv")
def build_audit(classifier, name, with_proba = True, fit_params = {}, predict_params = {}, predict_proba_params = {}, **pmml_options):
continuous_mapper = DataFrameMapper([
(["Age", "Income", "Hours"], MultiDomain([ContinuousDomain() for i in range(0, 3)]))
])
categorical_mapper = DataFrameMapper([
(["Employment"], [CategoricalDomain(), SubstringTransformer(0, 3), OneHotEncoder(drop = ["Vol"]), SelectFromModel(DecisionTreeClassifier(random_state = 13))]),
(["Education"], [CategoricalDomain(), ReplaceTransformer("[aeiou]", ""), OneHotEncoder(drop = "first"), SelectFromModel(RandomForestClassifier(n_estimators = 3, random_state = 13), threshold = "1.25 * mean")]),
(["Marital"], [CategoricalDomain(), LabelBinarizer(neg_label = -1, pos_label = 1), SelectKBest(k = 3)]),
(["Occupation"], [CategoricalDomain(), LabelBinarizer(), SelectKBest(k = 3)]),
(["Gender"], [CategoricalDomain(), MatchesTransformer("^Male$"), CastTransformer(int)]),
(["Deductions"], [CategoricalDomain()]),
])
pipeline = Pipeline([
("union", FeatureUnion([
("continuous", continuous_mapper),
("categorical", Pipeline([
("mapper", categorical_mapper),
("polynomial", PolynomialFeatures())
]))
])),
("classifier", classifier)
])
pipeline.fit(audit_X, audit_y, **fit_params)
pipeline = make_pmml_pipeline(pipeline, audit_X.columns.values, audit_y.name)
pipeline.configure(**pmml_options)
if isinstance(classifier, XGBClassifier):
pipeline.verify(audit_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_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_X, **predict_params), columns = ["Adjusted"])
if with_proba == True:
adjusted_proba = DataFrame(pipeline.predict_proba(audit_X, **predict_proba_params), columns = ["probability(0)", "probability(1)"])
adjusted = pandas.concat((adjusted, adjusted_proba), axis = 1)
store_csv(adjusted, name)
def build_audit(classifier, name, with_proba=True, **kwargs):
continuous_mapper = DataFrameMapper([
(["Age", "Income",
"Hours"], MultiDomain([ContinuousDomain() for i in range(0, 3)]))
])
categorical_mapper = DataFrameMapper([
(["Employment"], [
CategoricalDomain(),
LabelBinarizer(),
SelectFromModel(DecisionTreeClassifier(random_state=13))
]),
(["Education"], [
CategoricalDomain(),
LabelBinarizer(),
SelectFromModel(RandomForestClassifier(random_state=13,
n_estimators=3),
threshold="1.25 * mean")
]),
(["Marital"], [
CategoricalDomain(),
LabelBinarizer(neg_label=-1, pos_label=1),
SelectKBest(k=3)
]),
(["Occupation"],
[CategoricalDomain(),
LabelBinarizer(),
SelectKBest(k=3)]),
(["Gender"],
[CategoricalDomain(),
LabelBinarizer(neg_label=-3, pos_label=3)]),
(["Deductions"], [CategoricalDomain(),
LabelEncoder()]),
])
pipeline = Pipeline([
("union",
FeatureUnion([("continuous", continuous_mapper),
("categorical",
Pipeline([("mapper", categorical_mapper),
("polynomial", PolynomialFeatures())]))])),
("classifier", classifier)
])
pipeline.fit(audit_X, audit_y)
pipeline = make_pmml_pipeline(pipeline, audit_X.columns.values,
audit_y.name)
if isinstance(classifier, XGBClassifier):
pipeline.verify(audit_X.sample(frac=0.05, random_state=13),
precision=1e-5,
zeroThreshold=1e-5)
else:
pipeline.verify(audit_X.sample(frac=0.05, random_state=13))
customize(classifier, **kwargs)
store_pkl(pipeline, name + ".pkl")
adjusted = DataFrame(pipeline.predict(audit_X), columns=["Adjusted"])
if with_proba == True:
adjusted_proba = DataFrame(
pipeline.predict_proba(audit_X),
columns=["probability(0)", "probability(1)"])
adjusted = pandas.concat((adjusted, adjusted_proba), axis=1)
store_csv(adjusted, name + ".csv")
def build_auto_na(regressor, name):
mapper = DataFrameMapper(
[([column], [ContinuousDomain(missing_values = None), Imputer()]) for column in ["acceleration", "displacement", "horsepower", "weight"]] +
[([column], [CategoricalDomain(missing_values = -1), CategoricalImputer(missing_values = -1), PMMLLabelBinarizer()]) for column in ["cylinders", "model_year", "origin"]]
)
pipeline = PMMLPipeline([
("mapper", mapper),
("regressor", regressor)
])
pipeline.fit(auto_na_X, auto_na_y)
store_pkl(pipeline, name + ".pkl")
mpg = DataFrame(pipeline.predict(auto_na_X), columns = ["mpg"])
store_csv(mpg, name + ".csv")
def build_audit_na(classifier, name, with_proba=True):
employment_mapping = {
"Consultant": "Private",
"PSFederal": "Public",
"PSLocal": "Public",
"PSState": "Public",
"SelfEmp": "Private",
"Private": "Private"
}
gender_mapping = {"Female": 0, "Male": 1}
mapper = DataFrameMapper(
[([column], [ContinuousDomain(missing_values=None),
Imputer()])
for column in ["Age", "Income", "Hours"]] + [("Employment", [
CategoricalDomain(missing_values=None),
CategoricalImputer(),
LookupTransformer(employment_mapping, "Other"),
PMMLLabelBinarizer()
])] + [([column], [
CategoricalDomain(missing_values=None),
CategoricalImputer(),
PMMLLabelBinarizer()
]) for column in ["Education", "Marital", "Occupation"]] +
[("Gender", [
CategoricalDomain(missing_values=None),
CategoricalImputer(),
LookupTransformer(gender_mapping, None)
])])
pipeline = PMMLPipeline([("mapper", mapper), ("classifier", classifier)])
pipeline.fit(audit_na_X, audit_na_y)
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)
store_csv(adjusted, name + ".csv")
def build_auto_na_hist(regressor, name):
mapper = DataFrameMapper(
[([column], ContinuousDomain()) for column in ["displacement", "horsepower", "weight", "acceleration"]] +
[([column], [CategoricalDomain(), PMMLLabelBinarizer()]) for column in ["cylinders", "model_year", "origin"]]
)
pipeline = PMMLPipeline([
("mapper", mapper),
("regressor", regressor)
])
pipeline.fit(auto_na_X, auto_na_y)
pipeline.verify(auto_na_X.sample(frac = 0.05, random_state = 13))
store_pkl(pipeline, name)
mpg = DataFrame(pipeline.predict(auto_na_X), columns = ["mpg"])
store_csv(mpg, name)
def sklearn_audit(classifier, name):
pipeline = PMMLPipeline([
("mapper",
DataFrameMapper(
[([column],
[CategoricalDomain(), OneHotEncoder()]) for column in
["Employment", "Education", "Marital", "Occupation", "Gender"]] +
[([column], ContinuousDomain())
for column in ["Age", "Income", "Hours"]])),
("classifier", classifier)
])
pipeline.fit(audit_X, audit_y)
pipeline.configure(compact=False)
sklearn2pmml(pipeline, "pmml/" + name + ".pmml", with_repr=False)
def test_fit_int(self):
domain = CategoricalDomain()
self.assertEqual("return_invalid", domain.invalid_value_treatment)
self.assertFalse(hasattr(domain, "data_"))
domain = domain.fit(numpy.array([1, 3, 2, 2]))
self.assertEqual(numpy.array([1, 2, 3]).tolist(), domain.data_.tolist())
def test_fit_string(self): domain = CategoricalDomain() domain = domain.fit(numpy.array(["1", None, "3", "2", None, "2"])) self.assertEqual(numpy.array(["1", "2", "3"]).tolist(), domain.data_.tolist())