def test_write_output(self):
print('++ テスト開始')
aaa = AITManifestGenerator('./')
aaa.set_ait_name("set_ait_name")
aaa.set_ait_description("set_ait_description")
aaa.set_ait_author("set_ait_author")
aaa.set_ait_email("set_ait_email")
aaa.set_ait_version("0.1")
aaa.set_ait_quality("set_ait_quality")
aaa.set_ait_reference("set_ait_reference")
aaa.add_ait_inventories('name1', 'type1', 'description1', ['csv'],
'schema1')
aaa.add_ait_inventories('name2', 'type2', 'description2',
['gz', 'zip'], 'schema')
aaa.add_ait_parameters('name1', 'type1', 'description1',
'default_val1')
aaa.add_ait_parameters('name2', 'type2', 'description2')
aaa.add_ait_measures('name1', 'type1', 'description1', 'structure1')
aaa.add_ait_measures('name2', 'type2', 'description2', 'structure2')
aaa.add_ait_resources('name1', 'type1', 'description1')
aaa.add_ait_resources('name2', 'type2', 'description2')
aaa.add_ait_downloads('name1', 'description1')
aaa.add_ait_downloads('name2', 'description2')
aaa.write()
print('++ テスト終了')
''')
manifest_genenerator.set_ait_author('AIST')
manifest_genenerator.set_ait_email('')
manifest_genenerator.set_ait_version('0.1')
manifest_genenerator.set_ait_quality(
'https://airc.aist.go.jp/aiqm/quality/internal/Distribution_of_training_data'
)
manifest_genenerator.set_ait_reference('')
manifest_genenerator.add_ait_inventories(
name='Data',
type_='dataset',
description='german credit data',
format_=['csv'],
schema='https://archive.ics.uci.edu/ml/datasets/')
manifest_genenerator.add_ait_parameters(name='protected_attribute',
type_='str',
description='protected attributee',
default_val='age')
manifest_genenerator.add_ait_parameters(name='privileged_classes',
type_='float',
description='privileged classes',
default_val='25.0')
manifest_genenerator.add_ait_measures(
name='mean_difference',
type_='float',
description='mean difference of metric fairness',
structure='single',
min='-1',
max='1')
manifest_genenerator.add_ait_resources(
name='metric_fairness_plot',
type_='picture',
manifest_genenerator.set_ait_author('AIST')
manifest_genenerator.set_ait_email('')
manifest_genenerator.set_ait_version('0.1')
manifest_genenerator.set_ait_quality(
'https://airc.aist.go.jp/aiqm/quality/internal/Coverage_for_distinguished_problem_cases'
)
manifest_genenerator.set_ait_reference('')
manifest_genenerator.add_ait_inventories(
name='iris_data',
type_='dataset',
description='アヤメの分類データです',
format_=['csv'],
schema='https://archive.ics.uci.edu/ml/datasets/iris')
manifest_genenerator.add_ait_parameters(
name='mean_column_name',
type_='str',
description='sepal.width\nsepal.length\npetal.width\npetal.length',
default_val='sepal.width')
manifest_genenerator.add_ait_measures(name='mean',
type_='float',
description='mean of select column',
structure='single',
min='0')
manifest_genenerator.add_ait_resources(name='pairplot',
type_='picture',
description='pairplot')
manifest_genenerator.add_ait_downloads(name='Log', description='AIT実行ログ')
manifest_path = manifest_genenerator.write()
# In[9]:
manifest_genenerator.add_ait_inventories(
name='mnist_dataset',
type_='dataset',
description=
'MNIST_dataset are train image, train label, test image, test label',
format_=['zip'],
schema='http://yann.lecun.com/exdb/mnist/')
manifest_genenerator.add_ait_inventories(
name='mnist_model',
type_='model',
description='MNIST_model',
format_=['zip'],
schema='https://github.com/hitachi-rd-yokohama/deep_saucer')
manifest_genenerator.add_ait_parameters(
name='Lap',
type_='int',
description='Input Data Conversion Number',
default_val='10')
manifest_genenerator.add_ait_parameters(
name='NumTest',
type_='int',
description='Number of Test Data to be Used',
default_val='500')
manifest_genenerator.add_ait_parameters(
name='mnist_type',
type_='str',
description=
'train = Training_data, test = test_data, validation = validation_data',
default_val='train')
manifest_genenerator.add_ait_measures(
name='average',
manifest_genenerator.set_ait_quality(
'https://airc.aist.go.jp/aiqm/quality/internal/Coverage_for_distinguished_problem_cases'
)
manifest_genenerator.set_ait_reference('')
manifest_genenerator.add_ait_inventories(
name='pair_wise_model',
type_='dataset',
description='''
Model of pair-wise.
Define factors and constraints.
''',
format_=['txt'],
schema='https://github.com/Microsoft/pict/blob/master/doc/pict.md')
manifest_genenerator.add_ait_parameters(
name='order_combination',
type_='int',
description='Order of combinations.',
default_val='2')
manifest_genenerator.add_ait_parameters(name='seed',
type_='int',
description='''
Randomize generation, N - seed.
if you fix seed, please set it to 1 or more.
''',
default_val='-1')
manifest_genenerator.add_ait_resources(
name='generated_paie_wise',
type_='table',
description='PICT generate pair-wise.')
manifest_genenerator.add_ait_downloads(name='Log',
description='AIT execute log')
manifest_genenerator.set_ait_email('')
manifest_genenerator.set_ait_version('0.1')
manifest_genenerator.set_ait_quality('https://airc.aist.go.jp/aiqm/quality/internal/Accuracy_of_trained_model')
manifest_genenerator.set_ait_reference('')
manifest_genenerator.add_ait_inventories(name='trained_model',
type_='model',
description='Tensorflow 2.3 model',
format_=['h5'],
schema='HDF5')
manifest_genenerator.add_ait_inventories(name='dataset_for_verification',
type_='dataset',
description='Data set for verification requires label',
format_=['csv'],
schema='csv for verification')
manifest_genenerator.add_ait_parameters(name='target_variable',
type_='str',
description='target variable',
default_val='')
manifest_genenerator.add_ait_measures(name='RMSE',
type_='float',
description='The closer to 0, the smaller prediction error.',
structure='single',
min='0')
manifest_genenerator.add_ait_measures(name='MAE',
type_='float',
description='The closer to 0, the smaller prediction error.',
structure='single',
min='0')
manifest_genenerator.add_ait_resources(name='evaluation_index_matrix',
type_='table',
description='Table of evaluation indicators summary.')
manifest_genenerator.add_ait_resources(name='observed_predicted_plot',
manifest_genenerator.add_ait_inventories(
name='label',
type_='dataset',
description='MNIST label data',
format_=['gz'],
schema='http://yann.lecun.com/exdb/mnist/')
manifest_genenerator.add_ait_inventories(
name='tf_ckpt',
type_='model',
description='''Tensorflow model datas.\n
This is loaded by `tf.train.import_meta_graph`.''',
format_=['*'],
schema='https://github.com/tensorflow/models/tree/master/official')
manifest_genenerator.add_ait_parameters(name='mnist_image_px_size',
type_='int',
description='''
MNIST Imagge pixel size.
''',
default_val='28')
manifest_genenerator.add_ait_parameters(name='determination_on_activation',
type_='int',
description='''
Neuron Activity/Inactivity\n
Determination Type\n
0: Threshold Determination\n
1: Upper/Lower Limit Determination\n
2: N Cases of Maximum Value Determination
''',
default_val='0')
manifest_genenerator.add_ait_parameters(name='threshold',
type_='float',
description='''
description='Tensorflow 2.3で学習したモデル',
format_=['h5'],
schema='https://support.hdfgroup.org/HDF5/doc/')
manifest_genenerator.add_ait_inventories(name='test_set_images',
type_='dataset',
description='テスト画像セット（MNISTフォーマット）',
format_=['gz'],
schema='http://yann.lecun.com/exdb/mnist/')
manifest_genenerator.add_ait_inventories(name='test_set_labels',
type_='dataset',
description='テスト画像ラベル（MNISTフォーマット）',
format_=['gz'],
schema='http://yann.lecun.com/exdb/mnist/')
manifest_genenerator.add_ait_parameters(name='class_count',
type_='int',
description='multiple classification class number',
default_val='10')
manifest_genenerator.add_ait_parameters(name='image_px_size',
type_='int',
description='prediction image pixel size',
default_val='28')
manifest_genenerator.add_ait_parameters(name='auc_average',
type_='string',
description='{‘micro’, ‘macro’, ‘samples’, ‘weighted’}\r\nref:\r\nhttps://scikit-learn.org/stable/modules/generated/sklearn.metrics.roc_auc_score.html',
default_val='macro')
manifest_genenerator.add_ait_parameters(name='auc_multi_class',
type_='string',
description='{‘raise’, ‘ovr’, ‘ovo’}\nref:\nhttps://scikit-learn.org/stable/modules/generated/sklearn.metrics.roc_auc_score.html',
default_val='raise')
manifest_genenerator.add_ait_measures(name='Accuracy',
manifest_genenerator.set_ait_name('eval_ca_distribution')
manifest_genenerator.set_ait_description(
'Evaluating distribution of dataset with expected distribution')
manifest_genenerator.set_ait_author('AIST')
manifest_genenerator.set_ait_email('')
manifest_genenerator.set_ait_version('0.1')
manifest_genenerator.set_ait_quality(
'https://airc.aist.go.jp/aiqm/quality/internal/Distribution_of_training_data'
)
manifest_genenerator.set_ait_reference('')
manifest_genenerator.add_ait_inventories(
'Data', 'dataset',
'Classification of different attributes related to autonomous driving scenarios',
['csv'], 'https://bdd-data.berkeley.edu/')
manifest_genenerator.add_ait_parameters(
'attribute_no', 'int',
'Total number of attribute for distibution analysis', '6')
manifest_genenerator.add_ait_parameters(
'dimension', 'int',
'Dimensions of how many attributes to combine for distibution analysis',
'2')
manifest_genenerator.add_ait_resources(
'distibution_csv', 'table',
'Table of distribution for each combination')
manifest_genenerator.add_ait_resources(
'distibution_plot', 'picture',
'Plot of distribution for each combination')
manifest_genenerator.add_ait_downloads('Log', 'AITLog')
manifest_path = manifest_genenerator.write()
# In[6]:
name='images',
type_='dataset',
description='MNIST images',
format_=['gz'],
schema='http://fashion-mnist.s3-website.eu-central-1.amazonaws.com')
manifest_genenerator.add_ait_inventories(
name='labels',
type_='dataset',
description='MNIST labels',
format_=['gz'],
schema='http://fashion-mnist.s3-website.eu-central-1.amazonaws.com')
manifest_genenerator.add_ait_parameters(name='coverage_category',
type_='str',
description='''
Specify what coverage rate to be calculated.\n
Area = Tire area\n
ArcLength = contour perimeter length\n
Mean = Average pixel value\n"
''',
default_val='Area')
manifest_genenerator.add_ait_parameters(
name='interval',
type_='int',
description='The interval factor used to calculate coverage.',
default_val='100')
manifest_genenerator.add_ait_parameters(
name='max_range',
type_='int',
description='The max_range factor used in coverage calculations.',
default_val='800')
manifest_genenerator.add_ait_measures(
'''Classification of different attributes related to autonomous driving scenarios.
Need header.
Include header for Unsound_CA_combinations.
''',
format_=['csv'],
schema='CSV')
manifest_genenerator.add_ait_inventories(
name='Unsound_CA_combinations',
type_='attribute set',
description=
'Combinations of different attribute values that are not possible in real life',
format_=['csv'],
schema='User given data')
manifest_genenerator.add_ait_parameters(
name='PCA',
type_='str',
description='Primary conditional attribute',
default_val='Road type')
manifest_genenerator.add_ait_parameters(
name='PCV',
type_='str',
description='Primary conditional value',
default_val='Highway')
manifest_genenerator.add_ait_parameters(
name='SCA',
type_='str',
description='Secondary conditional attribute',
default_val='Signal')
manifest_genenerator.add_ait_parameters(
name='SCV',
type_='str',