def test_preprocessing_network(self): feature_value_map = read_data() normalization_parameters = {} for name, values in feature_value_map.items(): normalization_parameters[name] = normalization.identify_parameter( name, values, feature_type=self._feature_type_override(name)) test_features = NumpyFeatureProcessor.preprocess( feature_value_map, normalization_parameters) net = core.Net("PreprocessingTestNet") C2.set_net(net) preprocessor = PreprocessorNet() name_preprocessed_blob_map = {} for feature_name in feature_value_map: workspace.FeedBlob(str(feature_name), np.array([0], dtype=np.int32)) preprocessed_blob, _ = preprocessor.preprocess_blob( str(feature_name), [normalization_parameters[feature_name]]) name_preprocessed_blob_map[feature_name] = preprocessed_blob workspace.CreateNet(net) for feature_name, feature_value in six.iteritems(feature_value_map): feature_value = np.expand_dims(feature_value, -1) workspace.FeedBlob(str(feature_name), feature_value) workspace.RunNetOnce(net) for feature_name in feature_value_map: normalized_features = workspace.FetchBlob( name_preprocessed_blob_map[feature_name]) if feature_name != ENUM_FEATURE_ID: normalized_features = np.squeeze(normalized_features, -1) tolerance = 0.01 if feature_name == BOXCOX_FEATURE_ID: # At the limit, boxcox has some numerical instability tolerance = 0.5 non_matching = np.where( np.logical_not( np.isclose( normalized_features, test_features[feature_name], rtol=tolerance, atol=tolerance, ))) self.assertTrue( np.all( np.isclose( normalized_features, test_features[feature_name], rtol=tolerance, atol=tolerance, )), "{} does not match: {} {}".format( feature_name, normalized_features[non_matching].tolist(), test_features[feature_name][non_matching].tolist(), ), )
def test_preprocessing_network(self): feature_value_map = read_data() normalization_parameters = {} name_preprocessed_blob_map = {} for feature_name, feature_values in feature_value_map.items(): normalization_parameters[ feature_name] = normalization.identify_parameter( feature_values, feature_type=self._feature_type_override(feature_name)) feature_values[ 0] = MISSING_VALUE # Set one entry to MISSING_VALUE to test that preprocessor = Preprocessor( {feature_name: normalization_parameters[feature_name]}, False) feature_values_matrix = np.expand_dims(feature_values, -1) normalized_feature_values = preprocessor.forward( feature_values_matrix) name_preprocessed_blob_map[ feature_name] = normalized_feature_values.numpy() test_features = NumpyFeatureProcessor.preprocess( feature_value_map, normalization_parameters) for feature_name in feature_value_map: normalized_features = name_preprocessed_blob_map[feature_name] if feature_name != ENUM_FEATURE_ID: normalized_features = np.squeeze(normalized_features, -1) tolerance = 0.01 if feature_name == BOXCOX_FEATURE_ID: # At the limit, boxcox has some numerical instability tolerance = 0.5 non_matching = np.where( np.logical_not( np.isclose( normalized_features.flatten(), test_features[feature_name].flatten(), rtol=tolerance, atol=tolerance, ))) self.assertTrue( np.all( np.isclose( normalized_features.flatten(), test_features[feature_name].flatten(), rtol=tolerance, atol=tolerance, )), "{} does not match: {} \n!=\n {}".format( feature_name, normalized_features.flatten()[non_matching], test_features[feature_name].flatten()[non_matching], ), )
def test_preprocessing_network(self): feature_value_map = read_data() normalization_parameters = {} for name, values in feature_value_map.items(): normalization_parameters[name] = normalization.identify_parameter( name, values, feature_type=self._feature_type_override(name) ) test_features = NumpyFeatureProcessor.preprocess( feature_value_map, normalization_parameters ) net = core.Net("PreprocessingTestNet") C2.set_net(net) preprocessor = PreprocessorNet() name_preprocessed_blob_map = {} for feature_name in feature_value_map: workspace.FeedBlob(str(feature_name), np.array([0], dtype=np.int32)) preprocessed_blob, _ = preprocessor.preprocess_blob( str(feature_name), [normalization_parameters[feature_name]] ) name_preprocessed_blob_map[feature_name] = preprocessed_blob workspace.CreateNet(net) for feature_name, feature_value in six.iteritems(feature_value_map): feature_value = np.expand_dims(feature_value, -1) workspace.FeedBlob(str(feature_name), feature_value) workspace.RunNetOnce(net) for feature_name in feature_value_map: normalized_features = workspace.FetchBlob( name_preprocessed_blob_map[feature_name] ) if feature_name != ENUM_FEATURE_ID: normalized_features = np.squeeze(normalized_features, -1) tolerance = 0.01 if feature_name == BOXCOX_FEATURE_ID: # At the limit, boxcox has some numerical instability tolerance = 0.5 non_matching = np.where( np.logical_not( np.isclose( normalized_features, test_features[feature_name], rtol=tolerance, atol=tolerance, ) ) ) self.assertTrue( np.all( np.isclose( normalized_features, test_features[feature_name], rtol=tolerance, atol=tolerance, ) ), "{} does not match: {} {}".format( feature_name, normalized_features[non_matching].tolist(), test_features[feature_name][non_matching].tolist(), ), )
def test_preprocessing_network(self): feature_value_map = read_data() normalization_parameters = {} name_preprocessed_blob_map = {} for feature_name, feature_values in feature_value_map.items(): normalization_parameters[feature_name] = normalization.identify_parameter( feature_name, feature_values, feature_type=self._feature_type_override(feature_name), ) feature_values[ 0 ] = MISSING_VALUE # Set one entry to MISSING_VALUE to test that preprocessor = Preprocessor( {feature_name: normalization_parameters[feature_name]}, False ) feature_values_matrix = np.expand_dims(feature_values, -1) normalized_feature_values = preprocessor.forward(feature_values_matrix) name_preprocessed_blob_map[feature_name] = normalized_feature_values.numpy() test_features = NumpyFeatureProcessor.preprocess( feature_value_map, normalization_parameters ) for feature_name in feature_value_map: normalized_features = name_preprocessed_blob_map[feature_name] if feature_name != ENUM_FEATURE_ID: normalized_features = np.squeeze(normalized_features, -1) tolerance = 0.01 if feature_name == BOXCOX_FEATURE_ID: # At the limit, boxcox has some numerical instability tolerance = 0.5 non_matching = np.where( np.logical_not( np.isclose( normalized_features.flatten(), test_features[feature_name].flatten(), rtol=tolerance, atol=tolerance, ) ) ) self.assertTrue( np.all( np.isclose( normalized_features.flatten(), test_features[feature_name].flatten(), rtol=tolerance, atol=tolerance, ) ), "{} does not match: {} \n!=\n {}".format( feature_name, normalized_features.flatten()[non_matching], test_features[feature_name].flatten()[non_matching], ), )