def test_run(self):
# part 1
imputer = MeanImputation(hyperparams=hp)
imputer.set_training_data(inputs=X)
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=X, timeout=self.enough_time).value
self.helper_impute_result_check(X, 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=X, 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)
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'],
'Class': predictedTargets
})
print(predictedTargets.head())
print(trainData.head())
print(trainTargets.head())
print(np.asarray(trainTargets['Class']))
print(testData.head())
enc = Encoder()
enc.set_training_data(inputs=trainData)
enc.set_params(params=Params(n_limit=10, text2int=True))
enc.fit()
encodedData = enc.produce(inputs=trainData)
encodedTestData = enc.produce(inputs=testData)
# Initialize the DSBox imputer
imputer = MeanImputation()
imputer.set_params(verbose=0)
imputer.set_training_data(inputs=encodedData) # unsupervised
imputer.fit(timeout=10) # give 10 seconds to fit
print(imputer.get_call_metadata()) # to see wether fit worked
imputedData = imputer.produce(inputs=encodedData, timeout=10)
print(imputer.get_call_metadata()) # to see wether produce worked
model = BaggingClassifier()
trainedModel = model.fit(imputedData, np.asarray(trainTargets['Class']))
predictedTargets = trainedModel.predict(
imputer.produce(inputs=encodedTestData))
print(predictedTargets)
# Outputs the predicted targets in the location specified in the JSON configuration file
with open(jsonCall['output_file'], 'w') as outputFile: