def testDeleteInstancesWithMissing2(self):
# Deletes instances and checks arrays for correctness
dataPath = os.path.join(THIS_DIR, "test/DataSets/Tests/StringData.csv")
se = StringEnumerator(dataPath, "phenotype")
se.change_header_name("N1", "gender")
se.delete_all_instances_without_header_data("gender")
se.delete_all_instances_without_header_data("N2")
se.delete_all_instances_without_header_data("N3")
se.add_attribute_converter_random("gender")
se.add_attribute_converter_random("N3")
se.add_class_converter_random()
se.convert_all_attributes()
cHeaders = np.array(["gender", "N2", "N3"])
cMap = {
"phenotype": {
"china": "0"
},
"gender": {
"male": "0",
"female": "1"
},
"N3": {
"young": "0",
"old": "1"
}
}
cArray = np.array([["0", "1.2", "0"], ["1", "-0.4", "1"]])
cPArray = np.array(["0", "0"])
self.assertTrue(np.array_equal(cHeaders, se.dataHeaders))
self.assertTrue(np.array_equal("phenotype", se.classLabel))
self.assertTrue(np.array_equal(cArray, se.dataFeatures))
self.assertTrue(np.array_equal(cPArray, se.dataPhenotypes))
self.assertTrue(se.map == cMap)
def testNumericCheck(self):
# Checks non missing numeric
dataPath = os.path.join(THIS_DIR, "test/DataSets/Tests/StringData.csv")
se = StringEnumerator(dataPath, "phenotype")
self.assertFalse(se.check_is_full_numeric())
se.add_attribute_converter_random("N1")
se.convert_all_attributes()
self.assertFalse(se.check_is_full_numeric())
se.add_attribute_converter_random("N3")
se.add_class_converter_random()
se.convert_all_attributes()
self.assertTrue(se.check_is_full_numeric())
dataPath = os.path.join(THIS_DIR,
"test/DataSets/Tests/MissingFeatureData.csv")
se2 = StringEnumerator(dataPath, "phenotype")
self.assertTrue(se2.check_is_full_numeric())
def testget_params2(self):
# Get Params Test
dataPath = os.path.join(THIS_DIR, "test/DataSets/Tests/StringData.csv")
se = StringEnumerator(dataPath, "phenotype")
se.change_header_name("N1", "gender")
se.change_header_name("N2", "floats")
se.change_header_name("N3", "age")
se.change_class_name("country")
se.add_attribute_converter("gender",
np.array(["female", "male", "NA", "other"]))
se.add_attribute_converter("age", np.array(["old", "young"]))
se.add_class_converter_random()
se.convert_all_attributes()
dataHeaders, classLabel, dataFeatures, dataPhenotypes = se.get_params()
cHeaders = np.array(["gender", "floats", "age"])
cFeatures = np.array([[1, 1.2, 1], [0, 0.3, np.nan], [0, -0.4, 0],
[np.nan, 0, 1]])
cPhenotypes = np.array([0, 1, 0, 2])
self.assertEqual("country", classLabel)
self.assertTrue(np.array_equal(cHeaders, dataHeaders))
self.assertTrue(np.allclose(cFeatures, dataFeatures, equal_nan=True))
self.assertTrue(
np.allclose(cPhenotypes, dataPhenotypes, equal_nan=True))