def run(self):
'''
Make a key-value map of certain attributes in the Open FDA dataset
'''
print('Acquiring Records')
for record in self.source.acquire_labels():
if 'openfda' in record and 'product_ndc' in record['openfda']:
for entry in record['openfda']['product_ndc']:
ndc = ProductNdc.parse(entry)
id = ndc.format()
for op in self.features:
op['feature'].accumulate(id, record)
print('Writing Features')
for op in self.features:
feature = op['feature']
baseName = '-'.join(feature.fields)
fileName = io.relativeToAbsolute('../../data/'+baseName+'.txt')
with open(fileName, 'w', encoding='utf-8') as f:
print('product_ndc', op['column'], sep='\t', file=f)
for pair in sorted(feature.data, key=itemgetter(0, 1)):
value = pair[1]
for fn in op['transform']:
value = fn(value)
print(pair[0],value,sep='\t',file=f)
def run(self):
'''
Make a key-value map of certain attributes in the Open FDA dataset
'''
print('Acquiring Records')
for record in self.source.acquire_labels():
if 'openfda' in record and 'product_ndc' in record['openfda']:
for entry in record['openfda']['product_ndc']:
ndc = ProductNdc.parse(entry)
id = ndc.format()
for op in self.features:
op['feature'].accumulate(id, record)
print('Writing Features')
for op in self.features:
feature = op['feature']
baseName = '-'.join(feature.fields)
fileName = io.relativeToAbsolute('../../data/' + baseName + '.txt')
with open(fileName, 'w', encoding='utf-8') as f:
print('product_ndc', op['column'], sep='\t', file=f)
for pair in sorted(feature.data, key=itemgetter(0, 1)):
value = pair[1]
for fn in op['transform']:
value = fn(value)
print(pair[0], value, sep='\t', file=f)
def map_fda(self, x):
''' Project an element from the FDA product list
'''
ndc = ProductNdc.parse(x['PRODUCTNDC'])
return {'product_ndc': ndc.format(),
'proprietary_name': self.title(x['PROPRIETARYNAME']),
'nonproprietary_name': self.title(x['NONPROPRIETARYNAME']),
'dea_schedule': x['DEASCHEDULE']
}
def map_fda(self, x):
''' Project an element from the FDA product list
'''
ndc = ProductNdc.parse(x['PRODUCTNDC'])
return {
'product_ndc': ndc.format(),
'proprietary_name': self.title(x['PROPRIETARYNAME']),
'nonproprietary_name': self.title(x['NONPROPRIETARYNAME']),
'dea_schedule': x['DEASCHEDULE']
}
def test_fda(self):
self.suite[4]['formatted'] = '99999-009'
self.suite[9]['formatted'] = '99999-099'
self.suite[14]['formatted'] = '99999-999'
for s in self.suite:
actual = ProductNdc.parse(s['formatted'])
self.assertEqual(s['l'], actual.labeler)
self.assertEqual(s['prc'], actual.productCode)
self.assertEqual(s['formatted'], actual.format_fda())
def test_fda(self):
self.suite[4]['formatted'] = '99999-009'
self.suite[9]['formatted'] = '99999-099'
self.suite[14]['formatted'] = '99999-999'
for s in self.suite:
actual = ProductNdc.parse(s['formatted'])
self.assertEqual(s['l'], actual.labeler)
self.assertEqual(s['prc'], actual.productCode)
self.assertEqual(s['formatted'], actual.format_fda())
def _map(self, label):
''' A generator function that produces multiple elements from each
OpenFDA record
'''
if ('openfda' in label and 'product_ndc' in label['openfda'] and
'brand_name' in label['openfda']):
asString = json.dumps(label)
for x in label['openfda']['brand_name']:
brand = self.sourceNames.title(x)
for y in label['openfda']['product_ndc']:
ndc = ProductNdc.parse(y).format()
yield {'proprietary_name': brand,
'ndc':ndc,
'size':len(asString)}
def _map(self, x):
''' Extend the manufacturer record to include the labeler value from
the product NDC and the partition key to use
'''
ndc = ProductNdc.parse(x['product_ndc'])
partition = x['name']
for fn in [self._stripThe, self._fixEDotFO, self._defaultPartition]:
partition = fn(partition)
return {'name': x['name'],
'labeler': ndc.labeler,
'product_ndc': x['product_ndc'],
'partition' : partition
}
def _map(self, x):
''' Extend the manufacturer record to include the labeler value from
the product NDC and the partition key to use
'''
ndc = ProductNdc.parse(x['product_ndc'])
partition = x['name']
for fn in [self._stripThe, self._fixEDotFO, self._defaultPartition]:
partition = fn(partition)
return {
'name': x['name'],
'labeler': ndc.labeler,
'product_ndc': x['product_ndc'],
'partition': partition
}
def test_nutricel(self):
actual = ProductNdc.parse('53157-AS3')
self.assertEqual(53157, actual.labeler)
self.assertEqual(120, actual.productCode)
self.assertEqual('53157-0120', actual.format())
def test_canon(self):
for s in self.suite:
actual = ProductNdc.parse(s['formatted'])
self.assertEqual(s['l'], actual.labeler)
self.assertEqual(s['prc'], actual.productCode)
self.assertEqual(s['formatted'], actual.format())
def test_nutricel(self):
actual = ProductNdc.parse('53157-AS3')
self.assertEqual(53157, actual.labeler)
self.assertEqual(120, actual.productCode)
self.assertEqual('53157-0120', actual.format())
def test_canon(self):
for s in self.suite:
actual = ProductNdc.parse(s['formatted'])
self.assertEqual(s['l'], actual.labeler)
self.assertEqual(s['prc'], actual.productCode)
self.assertEqual(s['formatted'], actual.format())
