def test_run(self):
# part 1
imputer = MeanImputation(hyperparams=hp)
imputer.set_training_data(inputs=data)
imputer.fit(timeout=self.enough_time)
print(imputer.get_params())
self.assertEqual(imputer._has_finished, True)
self.assertEqual(imputer._iterations_done, True)
result = imputer.produce(inputs=data, timeout=self.enough_time).value
self.helper_impute_result_check(data, result)
# part2: test set_params()
imputer2 = MeanImputation(hyperparams=hp)
imputer2.set_params(params=imputer.get_params())
self.assertEqual(imputer2._has_finished, True)
self.assertEqual(imputer2._iterations_done, True)
result2 = imputer2.produce(inputs=data, timeout=self.enough_time).value
self.assertEqual(result2.equals(result),
True) # two imputers' results should be same
self.assertEqual(imputer2._has_finished, True)
self.assertEqual(imputer2._iterations_done, True)
def test_noMV(self):
"""
test on the dataset has no missing values
"""
imputer = MeanImputation(hyperparams=hp)
imputer.set_training_data(inputs=data)
imputer.fit(timeout=self.enough_time)
result = imputer.produce(inputs=data, timeout=self.enough_time).value
# 1. check produce(): `result` contains no missing value
result2 = imputer.produce(inputs=result,
timeout=self.enough_time).value
self.assertEqual(result.equals(result2), True)
# 2. check fit() & get_params() try fit on no-missing-value dataset
imputer2 = MeanImputation(hyperparams=hp)
imputer.set_training_data(inputs=result)
imputer.fit(timeout=self.enough_time)
print(imputer.get_params())
print(testData.head())
hp = EncHyperparameter.sample()
enc = Encoder(hyperparams=hp)
enc.set_training_data(inputs=trainData)
enc.fit()
encodedData = enc.produce(inputs=trainData).value
encodedTestData = enc.produce(inputs=testData).value
# Initialize the DSBox imputer
hp = MeanHyperparameter.sample()
imputer = MeanImputation(hyperparams=hp)
imputer.set_training_data(inputs=encodedData) # unsupervised
imputer.fit(timeout=100) # give 100 seconds to fit
print("\nParams:")
print(imputer.get_params())
imputer2 = MeanImputation(hyperparams=hp)
imputer2.set_params(params=imputer.get_params())
imputedData = imputer2.produce(inputs=encodedData, timeout=100).value
model = BaggingClassifier()
trainedModel = model.fit(imputedData, np.asarray(trainTargets['Class']))
predictedTargets = trainedModel.predict(
imputer.produce(inputs=encodedTestData).value)
# Append the d3mindex column to the predicted targets
predictedTargets = pd.DataFrame({
'd3mIndex': d3mIndex['d3mIndex'],