def test_binarizer(self):
trfm_obj = Binarizer()
trfm_obj, feature_names, target_name = auto_dataset_for_regression(
trfm_obj)
self.assertEqual(pp.get_class_name(trfm_obj),
trfm_obj.__class__.__name__)
self.assertEqual(
pp.get_derived_colnames('binarizer', ['displacement']),
['binarizer(displacement)'])
self.assertEqual(
pp.binarizer(trfm_obj,
feature_names)['der_fld'][0].__class__.__name__,
pml.DerivedField().__class__.__name__)
self.assertEqual(
pp.binarizer(trfm_obj, feature_names)['der_fld'][0].get_optype(),
"continuous")
self.assertEqual(
pp.binarizer(trfm_obj, feature_names)['der_fld'][0].get_dataType(),
"double")
self.assertEqual(
pp.binarizer(trfm_obj, feature_names)['der_fld']
[0].get_Apply().get_Constant()[0].get_valueOf_(),
trfm_obj.threshold)
def test_max_abs_scaler(self):
trfm_obj = MaxAbsScaler()
trfm_obj, feature_names, target_name = auto_dataset_for_regression(
trfm_obj)
self.assertEqual(pp.get_class_name(trfm_obj),
trfm_obj.__class__.__name__)
self.assertEqual(
pp.get_derived_colnames('max_abs__scaler', ['displacement']),
['max_abs__scaler(displacement)'])
self.assertEqual(
pp.max_abs_scaler(trfm_obj,
feature_names)['der_fld'][0].__class__.__name__,
pml.DerivedField().__class__.__name__)
self.assertEqual(
pp.max_abs_scaler(trfm_obj,
feature_names)['der_fld'][0].get_optype(),
"continuous")
self.assertEqual(
pp.max_abs_scaler(trfm_obj,
feature_names)['der_fld'][0].get_dataType(),
"double")
self.assertEqual(
pp.max_abs_scaler(trfm_obj, feature_names)['der_fld']
[0].get_Apply().get_Constant()[0].get_valueOf_(),
"{:.25f}".format(trfm_obj.max_abs_[0]))
def test_tfidf_vectorizer(self):
trfm_obj = TfidfVectorizer(norm=None)
trfm_obj, feature_names, target_name = auto_dataset_for_tfidf_and_count_vec(
trfm_obj)
self.assertEqual(pp.get_class_name(trfm_obj),
trfm_obj.__class__.__name__)
self.assertEqual(
len(pp.tfidf_vectorizer(trfm_obj, feature_names)['der_col_names']),
len(trfm_obj.get_feature_names()))
self.assertEqual(
pp.tfidf_vectorizer(trfm_obj,
feature_names)['der_col_names'][0], 'tfidf@[' +
feature_names[0] + '](' + trfm_obj.get_feature_names()[0] + ')')
self.assertEqual(
len(pp.tfidf_vectorizer(trfm_obj, feature_names)['der_fld']) - 1,
len(trfm_obj.idf_))
self.assertEqual(
pp.tfidf_vectorizer(
trfm_obj,
feature_names)['der_fld'][0].get_Apply().get_function(),
'lowercase')
self.assertEqual(
pp.tfidf_vectorizer(trfm_obj, feature_names)['pp_feat_name'],
feature_names[0])
self.assertEqual(
len(
pp.tfidf_vectorizer(trfm_obj,
feature_names)['pp_feat_class_lbl']), 0)
self.assertEqual(
pp.tfidf_vectorizer(trfm_obj,
feature_names)['der_fld'][0].get_optype(),
'categorical')
self.assertEqual(
pp.tfidf_vectorizer(trfm_obj,
feature_names)['der_fld'][1].get_optype(),
'continuous')
self.assertEqual(
pp.tfidf_vectorizer(trfm_obj,
feature_names)['der_fld'][0].get_dataType(),
'string')
self.assertEqual(
pp.tfidf_vectorizer(trfm_obj,
feature_names)['der_fld'][1].get_dataType(),
'double')
self.assertEqual(
pp.tfidf_vectorizer(trfm_obj, feature_names)['der_fld']
[1].get_Apply().get_Constant()[0].get_valueOf_(), trfm_obj.idf_[0])
self.assertEqual(
pp.tfidf_vectorizer(trfm_obj, feature_names)['der_fld']
[1].get_Apply().get_TextIndex()[0].get_Constant().get_valueOf_(),
trfm_obj.get_feature_names()[0])
self.assertEqual(
pp.tfidf_vectorizer(trfm_obj, feature_names)['der_fld']
[-1].get_Apply().get_TextIndex()[0].get_Constant().get_valueOf_(),
trfm_obj.get_feature_names()[-1])
def test_lbl_encoder(self):
trfm_obj = LabelEncoder()
trfm_obj, feature_names, target_name = auto_dataset_for_regression(
trfm_obj)
self.assertEqual(pp.get_class_name(trfm_obj),
trfm_obj.__class__.__name__)
self.assertEqual(pp.get_derived_colnames('labelEncoder', ['origin']),
['labelEncoder(origin)'])
self.assertEqual(
pp.lbl_encoder(trfm_obj,
feature_names)['der_fld'][0].__class__.__name__,
pml.DerivedField().__class__.__name__)
self.assertEqual(
pp.lbl_encoder(trfm_obj, feature_names)['der_fld'][0].get_optype(),
"continuous")
self.assertEqual(
pp.lbl_encoder(trfm_obj,
feature_names)['der_fld'][0].get_dataType(),
"double")
self.assertEqual(
pp.lbl_encoder(trfm_obj, feature_names)['der_col_names'][0],
"labelEncoder(origin)")
self.assertEqual(
pp.lbl_encoder(trfm_obj, feature_names)['pp_feat_class_lbl'][0],
trfm_obj.classes_[0])
self.assertEqual(
pp.lbl_encoder(trfm_obj, feature_names)['der_fld']
[0].get_MapValues().get_outputColumn(), "output")
self.assertEqual(
pp.lbl_encoder(trfm_obj, feature_names)['pp_feat_name'], "origin")
def test_lbl_binarizer(self):
trfm_obj = LabelBinarizer()
trfm_obj, feature_names, target_name = auto_dataset_for_regression(
trfm_obj)
self.assertEqual(pp.get_class_name(trfm_obj),
trfm_obj.__class__.__name__)
self.assertEqual(
pp.lbl_binarizer(trfm_obj,
feature_names)['der_fld'][0].__class__.__name__,
pml.DerivedField().__class__.__name__)
self.assertEqual(
pp.lbl_binarizer(trfm_obj,
feature_names)['der_fld'][0].get_optype(),
"categorical")
self.assertEqual(
pp.lbl_binarizer(trfm_obj,
feature_names)['der_fld'][0].get_dataType(),
"double")
self.assertEqual(
pp.lbl_binarizer(trfm_obj, feature_names)['pp_feat_class_lbl'][0],
trfm_obj.classes_[0])
self.assertEqual(
pp.lbl_binarizer(
trfm_obj,
feature_names)['der_fld'][0].get_NormDiscrete().get_field(),
"origin")
self.assertEqual(
pp.lbl_binarizer(trfm_obj, feature_names)['pp_feat_name'],
"origin")