def testClassifyKeywordsAsExpected(self):
"""
Tests ClassificationModelKeywords.
Training on the first five samples of the dataset, and testing on the rest,
the model's classifications should match those in the expected classes
data file.
"""
modelName = "Keywords"
runner = Runner(dataPath=os.path.join(DATA_DIR, "responses.csv"),
resultsDir="",
experimentName="keywords_test",
experimentType="incremental",
loadPath=None,
modelName=modelName,
numClasses=3,
plots=0,
orderedSplit=True,
trainSizes=[5],
verbosity=0)
runner.initModel(modelName)
self.runExperiment(runner)
expectedClasses, resultClasses = self.getExpectedClassifications(
runner, os.path.join(DATA_DIR, "responses_expected_classes_keywords.csv"))
for i, (e, r) in enumerate(zip(expectedClasses, resultClasses)):
if i in (7, 9, 12):
# Ties amongst winning labels are handled randomly, which affects the
# third classification in these test samples.
e = e[:2]
r = r[:2]
self.assertEqual(sorted(e), sorted(r),
"Keywords model predicted classes other than what we expect.")
def testClassifyEndpointAsExpected(self):
"""
Tests ClassificationModelEndpoint.
Training on the first five samples of the dataset, and testing on the rest,
the model's classifications should match those in the expected classes
data file.
"""
modelName = "CioEndpoint"
runner = Runner(dataPath=os.path.join(DATA_DIR, "responses.csv"),
resultsDir="",
experimentName="endpoint_test",
experimentType="incremental",
loadPath=None,
modelName=modelName,
numClasses=3,
plots=0,
orderedSplit=True,
trainSizes=[5],
verbosity=0)
runner.initModel(modelName)
self.runExperiment(runner)
expectedClasses, resultClasses = self.getExpectedClassifications(runner,
os.path.join(DATA_DIR, "responses_expected_classes_endpoint.csv"))
[self.assertEqual(sorted(e), sorted(r),
"Endpoint model predicted classes other than what we expect.")
for e, r in zip(expectedClasses, resultClasses)]
def testClassifyEndpointAsExpected(self):
"""
Tests ClassificationModelEndpoint.
Training on the first five samples of the dataset, and testing on the rest,
the model's classifications should match those in the expected classes
data file.
"""
modelName = "CioEndpoint"
runner = Runner(dataPath=os.path.join(DATA_DIR, "responses.csv"),
resultsDir="",
experimentName="endpoint_test",
experimentType="incremental",
loadPath=None,
modelName=modelName,
numClasses=3,
plots=0,
orderedSplit=True,
trainSizes=[5],
verbosity=0)
runner.initModel(modelName)
self.runExperiment(runner)
expectedClasses, resultClasses = self.getExpectedClassifications(
runner,
os.path.join(DATA_DIR, "responses_expected_classes_endpoint.csv"))
[
self.assertEqual(
sorted(e), sorted(r),
"Endpoint model predicted classes other than what we expect.")
for e, r in zip(expectedClasses, resultClasses)
]
def testClassifyKeywordsAsExpected(self):
"""
Tests ClassificationModelKeywords.
Training on the first five samples of the dataset, and testing on the rest,
the model's classifications should match those in the expected classes
data file.
"""
modelName = "Keywords"
runner = Runner(dataPath=os.path.join(DATA_DIR, "responses.csv"),
resultsDir="",
experimentName="keywords_test",
experimentType="incremental",
loadPath=None,
modelName=modelName,
numClasses=3,
plots=0,
orderedSplit=True,
trainSizes=[5],
verbosity=0)
runner.initModel(modelName)
self.runExperiment(runner)
expectedClasses, resultClasses = self.getExpectedClassifications(
runner,
os.path.join(DATA_DIR, "responses_expected_classes_keywords.csv"))
for i, (e, r) in enumerate(zip(expectedClasses, resultClasses)):
if i in (7, 9, 12):
# Ties amongst winning labels are handled randomly, which affects the
# third classification in these test samples.
e = e[:2]
r = r[:2]
self.assertEqual(
sorted(e), sorted(r),
"Keywords model predicted classes other than what we expect.")