def testInfinitysOnly(self):
examples = []
example = tf.train.Example()
example.features.feature['num'].float_list.value.append(float('inf'))
examples.append(example)
example = tf.train.Example()
example.features.feature['num'].float_list.value.append(float('-inf'))
examples.append(example)
entries = {}
for i, example in enumerate(examples):
fs._ParseExample(example.features.feature, [], entries, i)
datasets = [{
'entries': entries,
'size': len(examples),
'name': 'test'
}]
p = gfsg.GetDatasetsProto(datasets)
numfeat = p.datasets[0].features[0]
hist = buckets = numfeat.num_stats.histograms[0]
buckets = hist.buckets
self.assertEqual(gfsg.GetHistogramProtoDef().STANDARD, hist.type)
self.assertEqual(10, len(buckets))
self.assertEqual(float('-inf'), buckets[0].low_value)
self.assertEqual(0.1, buckets[0].high_value)
self.assertEqual(1, buckets[0].sample_count)
self.assertEquals(0.9, buckets[9].low_value)
self.assertEqual(float('inf'), buckets[9].high_value)
self.assertEqual(1, buckets[9].sample_count)
def testQuantiles(self):
examples = []
for i in range(50):
example = tf.train.Example()
example.features.feature['num'].int64_list.value.append(i)
examples.append(example)
for i in range(50):
example = tf.train.Example()
example.features.feature['num'].int64_list.value.append(100)
examples.append(example)
entries = {}
for i, example in enumerate(examples):
fs._ParseExample(example.features.feature, [], entries, i)
datasets = [{
'entries': entries,
'size': len(examples),
'name': 'test'
}]
p = gfsg.GetDatasetsProto(datasets)
numfeat = p.datasets[0].features[0]
self.assertEqual(2, len(numfeat.num_stats.histograms))
self.assertEqual(gfsg.GetHistogramProtoDef().QUANTILES,
numfeat.num_stats.histograms[1].type)
buckets = numfeat.num_stats.histograms[1].buckets
self.assertEqual(10, len(buckets))
self.assertEqual(0, buckets[0].low_value)
self.assertEqual(9.9, buckets[0].high_value)
self.assertEqual(10, buckets[0].sample_count)
self.assertEqual(100, buckets[9].low_value)
self.assertEqual(100, buckets[9].high_value)
self.assertEqual(10, buckets[9].sample_count)
def testParseExampleSequenceFeatureList(self):
examples = []
for i in range(50):
example = tf.train.SequenceExample()
feat = example.feature_lists.feature_list['num'].feature.add()
feat.int64_list.value.append(i)
examples.append(example)
entries = {}
for i, example in enumerate(examples):
fs._ParseExample(example.context.feature,
example.feature_lists.feature_list, entries, i)
self._check_sequence_example_entries(entries, 50, 1, 1)
def testParseExampleSequenceContext(self):
# Tests parsing examples of integers in context field
examples = []
for i in range(50):
example = tf.train.SequenceExample()
example.context.feature['num'].int64_list.value.append(i)
examples.append(example)
entries = {}
for i, example in enumerate(examples):
fs._ParseExample(example.context.feature,
example.feature_lists.feature_list, entries, i)
self._check_sequence_example_entries(entries, 50, 1)
self.assertEqual(1, len(entries))
def testParseExamplesTypeMismatch(self):
examples = []
example = tf.train.Example()
example.features.feature['feat'].int64_list.value.append(0)
examples.append(example)
example = tf.train.Example()
example.features.feature['feat'].bytes_list.value.append(b'str')
examples.append(example)
entries = {}
fs._ParseExample(examples[0].features.feature, [], entries, 0)
with self.assertRaises(TypeError):
fs._ParseExample(examples[1].features.feature, [], entries, 1)
def testInfinityAndNan(self):
examples = []
for i in range(50):
example = tf.train.Example()
example.features.feature['num'].float_list.value.append(i)
examples.append(example)
example = tf.train.Example()
example.features.feature['num'].float_list.value.append(float('inf'))
examples.append(example)
example = tf.train.Example()
example.features.feature['num'].float_list.value.append(float('-inf'))
examples.append(example)
example = tf.train.Example()
example.features.feature['num'].float_list.value.append(float('nan'))
examples.append(example)
entries = {}
for i, example in enumerate(examples):
fs._ParseExample(example.features.feature, [], entries, i)
datasets = [{
'entries': entries,
'size': len(examples),
'name': 'test'
}]
p = gfsg.GetDatasetsProto(datasets)
numfeat = p.datasets[0].features[0]
self.assertEqual('num', numfeat.name)
self.assertEqual(gfsg.GetFeatureStatsProtoDef().FLOAT, numfeat.type)
self.assertTrue(np.isnan(numfeat.num_stats.min))
self.assertTrue(np.isnan(numfeat.num_stats.max))
self.assertTrue(np.isnan(numfeat.num_stats.mean))
self.assertTrue(np.isnan(numfeat.num_stats.median))
self.assertEqual(1, numfeat.num_stats.num_zeros)
self.assertTrue(np.isnan(numfeat.num_stats.std_dev))
self.assertEqual(53, numfeat.num_stats.common_stats.num_non_missing)
hist = buckets = numfeat.num_stats.histograms[0]
buckets = hist.buckets
self.assertEqual(gfsg.GetHistogramProtoDef().STANDARD, hist.type)
self.assertEqual(1, hist.num_nan)
self.assertEqual(10, len(buckets))
self.assertEqual(float('-inf'), buckets[0].low_value)
self.assertEqual(4.9, buckets[0].high_value)
self.assertEqual(6, buckets[0].sample_count)
self.assertEquals(44.1, buckets[9].low_value)
self.assertEqual(float('inf'), buckets[9].high_value)
self.assertEqual(6, buckets[9].sample_count)
def testParseExampleSequenceFeatureListMultipleEntriesOuter(self):
# Tests parsing examples of integers in context field
examples = []
for i in range(2):
example = tf.train.SequenceExample()
for j in range(25):
feat = example.feature_lists.feature_list['num'].feature.add()
feat.int64_list.value.append(i * 25 + j)
examples.append(example)
entries = {}
for i, example in enumerate(examples):
fs._ParseExample(example.context.feature,
example.feature_lists.feature_list, entries, i)
self._check_sequence_example_entries(entries, 2, 25, 25)
def testGetProtoMultipleDatasets(self):
# Tests converting multiple datsets into the feature stats proto
# including ensuring feature order is consistent in the protos.
examples1 = []
for i in range(2):
example = tf.train.Example()
example.features.feature['str'].bytes_list.value.append(b'one')
example.features.feature['num'].int64_list.value.append(0)
examples1.append(example)
examples2 = []
example = tf.train.Example()
example.features.feature['num'].int64_list.value.append(1)
example.features.feature['str'].bytes_list.value.append(b'two')
examples2.append(example)
entries1 = {}
for i, example1 in enumerate(examples1):
fs._ParseExample(example1.features.feature, [], entries1, i)
entries2 = {}
for i, example2 in enumerate(examples2):
fs._ParseExample(example2.features.feature, [], entries2, i)
datasets = [{
'entries': entries1,
'size': len(examples1),
'name': 'test1'
}, {
'entries': entries2,
'size': len(examples2),
'name': 'test2'
}]
p = gfsg.GetDatasetsProto(datasets)
self.assertEqual(2, len(p.datasets))
test_data_1 = p.datasets[0]
self.assertEqual('test1', test_data_1.name)
self.assertEqual(2, test_data_1.num_examples)
num_feat_index = 0 if test_data_1.features[0].name == 'num' else 1
self.assertEqual(0, test_data_1.features[num_feat_index].num_stats.max)
test_data_2 = p.datasets[1]
self.assertEqual('test2', test_data_2.name)
self.assertEqual(1, test_data_2.num_examples)
self.assertEqual(1, test_data_2.features[num_feat_index].num_stats.max)
def testParseExampleInt(self):
# Tests parsing examples of integers
examples = []
for i in range(50):
example = tf.train.Example()
example.features.feature['num'].int64_list.value.append(i)
examples.append(example)
entries = {}
for i, example in enumerate(examples):
fs._ParseExample(example.features.feature, [], entries, i)
self.assertEqual(1, len(entries))
self.assertIn('num', entries)
info = entries['num']
self.assertEqual(0, info['missing'])
self.assertEqual(gfsg.GetFeatureStatsProtoDef().INT, info['type'])
for i in range(len(examples)):
self.assertEqual(1, info['counts'][i])
self.assertEqual(i, info['vals'][i])
def testParseExampleMissingValueList(self):
# Tests parsing examples of integers
examples = []
example = tf.train.Example()
# pylint: disable=pointless-statement
example.features.feature['str']
# pylint: enable=pointless-statement
examples.append(example)
example = tf.train.Example()
example.features.feature['str'].bytes_list.value.append(b'test')
examples.append(example)
entries = {}
for i, example in enumerate(examples):
fs._ParseExample(example.features.feature, [], entries, i)
self.assertEqual(1, len(entries))
self.assertIn('str', entries)
info = entries['str']
self.assertEqual(1, info['missing'])
self.assertEqual(gfsg.GetFeatureStatsProtoDef().STRING, info['type'])
self.assertEqual(0, info['counts'][0])
self.assertEqual(1, info['counts'][1])
def testVaryingCountsAndMissing(self):
# Tests parsing examples of when some examples have missing features
examples = []
for i in range(5):
example = tf.train.Example()
example.features.feature['other'].int64_list.value.append(0)
for _ in range(i):
example.features.feature['num'].int64_list.value.append(i)
examples.append(example)
example = tf.train.Example()
example.features.feature['other'].int64_list.value.append(0)
examples.append(example)
entries = {}
for i, example in enumerate(examples):
fs._ParseExample(example.features.feature, [], entries, i)
info = entries['num']
self.assertEqual(2, info['missing'])
self.assertEquals(4, len(info['counts']))
for i in range(4):
self.assertEqual(i + 1, info['counts'][i])
self.assertEqual(10, len(info['vals']))
def testParseExampleStringsAndFloats(self):
# Tests parsing examples of string and float features
examples = []
for i in range(50):
example = tf.train.Example()
example.features.feature['str'].bytes_list.value.append(b'hi')
example.features.feature['float'].float_list.value.append(i)
examples.append(example)
entries = {}
for i, example in enumerate(examples):
fs._ParseExample(example.features.feature, [], entries, i)
self.assertEqual(2, len(entries))
self.assertEqual(gfsg.GetFeatureStatsProtoDef().FLOAT,
entries['float']['type'])
self.assertEqual(gfsg.GetFeatureStatsProtoDef().STRING,
entries['str']['type'])
for i in range(len(examples)):
self.assertEqual(1, entries['str']['counts'][i])
self.assertEqual(1, entries['float']['counts'][i])
self.assertEqual(i, entries['float']['vals'][i])
self.assertEqual(
'hi', entries['str']['vals'][i].decode('UTF-8', 'strict'))
def testGetProtoStrings(self):
# Tests converting string examples into the feature stats proto
examples = []
for i in range(2):
example = tf.train.Example()
example.features.feature['str'].bytes_list.value.append(b'hello')
examples.append(example)
for i in range(3):
example = tf.train.Example()
example.features.feature['str'].bytes_list.value.append(b'hi')
examples.append(example)
example = tf.train.Example()
example.features.feature['str'].bytes_list.value.append(b'hey')
examples.append(example)
entries = {}
for i, example in enumerate(examples):
fs._ParseExample(example.features.feature, [], entries, i)
datasets = [{
'entries': entries,
'size': len(examples),
'name': 'test'
}]
p = gfsg.GetDatasetsProto(datasets)
self.assertEqual(1, len(p.datasets))
test_data = p.datasets[0]
self.assertEqual('test', test_data.name)
self.assertEqual(6, test_data.num_examples)
strfeat = test_data.features[0]
self.assertEqual('str', strfeat.name)
self.assertEqual(gfsg.GetFeatureStatsProtoDef().STRING, strfeat.type)
self.assertEqual(3, strfeat.string_stats.unique)
self.assertAlmostEqual(19 / 6.0, strfeat.string_stats.avg_length, 4)
self.assertEqual(0, strfeat.string_stats.common_stats.num_missing)
self.assertEqual(6, strfeat.string_stats.common_stats.num_non_missing)
self.assertEqual(1, strfeat.string_stats.common_stats.min_num_values)
self.assertEqual(1, strfeat.string_stats.common_stats.max_num_values)
self.assertEqual(1, strfeat.string_stats.common_stats.avg_num_values)
hist = strfeat.string_stats.common_stats.num_values_histogram
buckets = hist.buckets
self.assertEqual(gfsg.GetHistogramProtoDef().QUANTILES, hist.type)
self.assertEqual(10, len(buckets))
self.assertEqual(1, buckets[0].low_value)
self.assertEqual(1, buckets[0].high_value)
self.assertEqual(.6, buckets[0].sample_count)
self.assertEquals(1, buckets[9].low_value)
self.assertEqual(1, buckets[9].high_value)
self.assertEqual(.6, buckets[9].sample_count)
self.assertEqual(2, len(strfeat.string_stats.top_values))
self.assertEqual(3, strfeat.string_stats.top_values[0].frequency)
self.assertEqual('hi', strfeat.string_stats.top_values[0].value)
self.assertEqual(2, strfeat.string_stats.top_values[1].frequency)
self.assertEqual('hello', strfeat.string_stats.top_values[1].value)
buckets = strfeat.string_stats.rank_histogram.buckets
self.assertEqual(3, len(buckets))
self.assertEqual(0, buckets[0].low_rank)
self.assertEqual(0, buckets[0].high_rank)
self.assertEqual(3, buckets[0].sample_count)
self.assertEqual('hi', buckets[0].label)
self.assertEqual(2, buckets[2].low_rank)
self.assertEqual(2, buckets[2].high_rank)
self.assertEqual(1, buckets[2].sample_count)
self.assertEqual('hey', buckets[2].label)
def testGetProtoNums(self):
# Tests converting int examples into the feature stats proto
examples = []
for i in range(50):
example = tf.train.Example()
example.features.feature['num'].int64_list.value.append(i)
examples.append(example)
example = tf.train.Example()
example.features.feature['other'].int64_list.value.append(0)
examples.append(example)
entries = {}
for i, example in enumerate(examples):
fs._ParseExample(example.features.feature, [], entries, i)
datasets = [{
'entries': entries,
'size': len(examples),
'name': 'test'
}]
p = gfsg.GetDatasetsProto(datasets)
self.assertEqual(1, len(p.datasets))
test_data = p.datasets[0]
self.assertEqual('test', test_data.name)
self.assertEqual(51, test_data.num_examples)
numfeat = test_data.features[0] if (
test_data.features[0].name == 'num') else test_data.features[1]
self.assertEqual('num', numfeat.name)
self.assertEqual(gfsg.GetFeatureStatsProtoDef().INT, numfeat.type)
self.assertEqual(0, numfeat.num_stats.min)
self.assertEqual(49, numfeat.num_stats.max)
self.assertEqual(24.5, numfeat.num_stats.mean)
self.assertEqual(24.5, numfeat.num_stats.median)
self.assertEqual(1, numfeat.num_stats.num_zeros)
self.assertAlmostEqual(14.430869689, numfeat.num_stats.std_dev, 4)
self.assertEqual(1, numfeat.num_stats.common_stats.num_missing)
self.assertEqual(50, numfeat.num_stats.common_stats.num_non_missing)
self.assertEqual(1, numfeat.num_stats.common_stats.min_num_values)
self.assertEqual(1, numfeat.num_stats.common_stats.max_num_values)
self.assertAlmostEqual(1,
numfeat.num_stats.common_stats.avg_num_values,
4)
hist = numfeat.num_stats.common_stats.num_values_histogram
buckets = hist.buckets
self.assertEqual(gfsg.GetHistogramProtoDef().QUANTILES, hist.type)
self.assertEqual(10, len(buckets))
self.assertEqual(1, buckets[0].low_value)
self.assertEqual(1, buckets[0].high_value)
self.assertEqual(5, buckets[0].sample_count)
self.assertEquals(1, buckets[9].low_value)
self.assertEqual(1, buckets[9].high_value)
self.assertEqual(5, buckets[9].sample_count)
self.assertEqual(2, len(numfeat.num_stats.histograms))
buckets = numfeat.num_stats.histograms[0].buckets
self.assertEqual(gfsg.GetHistogramProtoDef().STANDARD,
numfeat.num_stats.histograms[0].type)
self.assertEqual(10, len(buckets))
self.assertEqual(0, buckets[0].low_value)
self.assertEqual(4.9, buckets[0].high_value)
self.assertEqual(5, buckets[0].sample_count)
self.assertAlmostEqual(44.1, buckets[9].low_value)
self.assertEqual(49, buckets[9].high_value)
self.assertEqual(5, buckets[9].sample_count)
buckets = numfeat.num_stats.histograms[1].buckets
self.assertEqual(gfsg.GetHistogramProtoDef().QUANTILES,
numfeat.num_stats.histograms[1].type)
self.assertEqual(10, len(buckets))
self.assertEqual(0, buckets[0].low_value)
self.assertEqual(4.9, buckets[0].high_value)
self.assertEqual(5, buckets[0].sample_count)
self.assertAlmostEqual(44.1, buckets[9].low_value)
self.assertEqual(49, buckets[9].high_value)
self.assertEqual(5, buckets[9].sample_count)