def test_automl_usecase(self):
# train featurization pipeline
featurization_pipe = Pipeline([NGramFeaturizer(keep_diacritics=True, columns={'Features': ['SentimentText']})])
featurization_pipe.fit(train_set)
# train learner pipeline
learner_pipe = Pipeline([DatasetTransformer(featurization_pipe.model),
OneVsRestClassifier(AveragedPerceptronBinaryClassifier(),
feature=['Features'], label='Sentiment')
])
learner_pipe.fit(train_set)
# Export the learner pipeline to ONNX
onnx_path = get_tmp_file('.onnx')
learner_pipe.export_to_onnx(onnx_path, 'com.microsoft.ml', onnx_version='Stable')
# Perform the transform using the standard ML.Net backend
start = time.time()
result_standard = learner_pipe.predict(test_set)
end = time.time()
print('%ss done transform using standard backend' % round(end - start, 3))
# Perform the transform using the ORT backend
df_tool = DFT(onnx_path)
dataset = test_set.to_df()
start = time.time()
result_ort = df_tool.execute(dataset, ['PredictedLabel.output', 'Score.output'])
end = time.time()
print('%ss done transform using ORT backend (excludes df load time)' % round(end - start, 3))
# compare the results
for col_tuple in (('PredictedLabel', 'PredictedLabel.output'),
('Score.0', 'Score.output.0'),
('Score.1', 'Score.output.1'),
):
col_expected = result_standard.loc[:, col_tuple[0]]
col_ort = result_ort.loc[:, col_tuple[1]]
check_kwargs = {
'check_names': False,
'check_exact': False,
'check_dtype': True,
'check_less_precise': True
}
pd.testing.assert_series_equal(col_expected, col_ort, **check_kwargs)
train_data = {'c1': x, 'c2': y}
train_df = pd.DataFrame(train_data).astype({
'c1': np.float32,
'c2': np.float32
})
test_data = {'c1': [2.5, 30.5], 'c2': [1, 1]}
test_df = pd.DataFrame(test_data).astype({'c1': np.float32, 'c2': np.float32})
# Fit a MinMaxScaler Pipeline
r1 = Pipeline([MinMaxScaler()])
r1.fit(train_df)
# Export the pipeline to ONNX
onnx_path = get_tmp_file('.onnx')
r1.export_to_onnx(onnx_path, 'com.microsoft.ml', onnx_version='Stable')
# Perform the transform using the standard ML.Net backend
result_standard = r1.transform(test_df)
print(result_standard)
# c1 c2
# 0 0.025025 0.000998
# 1 0.305305 0.000998
# Perform the transform using the ONNX backend.
# Note, the extra columns and column name differences
# is a known issue with the ML.Net backend.
onnxrunner = OnnxRunner(model_file=onnx_path)
result_onnx = onnxrunner.fit_transform(test_df)
print(result_onnx)
# c1 c2 c12.0 c22.0
