def test_beacon_request(self):
"""
Check that current Clinvar/Variants returns correct
fields for beacon
"""
dataset = Dataset.retrieve('ClinVar/Variants')
beacon = dataset.beacon(genome_build='GRCh37',
chromosome='6',
coordinate=50432798,
allele='G')
check_fields = ['query', 'exist', 'total']
for f in check_fields:
self.assertTrue(f in beacon)
"""
Check that Clinvar/Variants version 3.7.0-2015-12-06
returns true for specific case
"""
dataset = Dataset.retrieve('ClinVar/3.7.0-2015-12-06/Variants')
beacontwo = dataset.beacon(genome_build='GRCh37',
chromosome='13',
coordinate=113803460,
allele='T')
self.assertTrue(beacontwo['exist'])
self.assertEqual(beacontwo['total'], 1)
def __getattr__(self, name):
"""Shortcut to access attributes of the underlying Dataset resource"""
from solvebio.resource import Dataset
# Valid override attributes that let Object act like a Dataset
valid_dataset_attrs = [
# query data
'query',
'lookup',
'beacon',
# transform data
'import_file',
'export',
'migrate',
# dataset meta
'fields',
'template',
'imports',
'commits',
# helpers
'activity',
'saved_queries'
]
try:
return self[name]
except KeyError as err:
# If the Object has a dataset_id, it is of object_type "dataset"
# If there is no dataset_id, either this Object is a file or folder
# or the resource has not yet been retrieved from the API.
if name in valid_dataset_attrs and self.dataset_id:
return getattr(Dataset(self.dataset_id, client=self._client),
name)
raise AttributeError(*err.args)
def test_dataset_fields(self):
fields = Dataset.retrieve(self.TEST_DATASET_NAME).fields()
dataset_field = fields.data[0]
self.assertTrue('id' in dataset_field,
'Should be able to get id in list of dataset fields')
check_fields = set([
'class_name', 'created_at', 'data_type', 'dataset_id',
'description', 'facets_url', 'ordering', 'is_hidden', 'is_valid',
'is_list', 'entity_type', 'name', 'updated_at', 'is_read_only',
'id', 'url'
])
self.assertSetEqual(set(dataset_field.keys()), check_fields)
expected = """
| Field | Data Type | Description |
|------------------------------+-------------+---------------|
| accession_numbers | string | |
| approved_name | string | |
| approved_symbol | string | |
| ccds_ids | string | |
| chromosome | string | |
| date_approved | date | |
| date_modified | date | |
| date_name_changed | date | |
| date_symbol_changed | date | |
| ensembl_gene_id | string | |
| ensembl_id_ensembl | string | |
| entrez_gene_id | string | |
| entrez_gene_id_ncbi | string | |
| enzyme_ids | string | |
| gene_family_description | string | |
| gene_family_tag | string | |
| hgnc_id | long | |
| locus | string | |
| locus_group | string | |
| locus_specific_databases | string | |
| locus_type | string | |
| mouse_genome_database_id | long | |
| mouse_genome_database_id_mgi | long | |
| name_synonyms | string | |
| omim_id_ncbi | string | |
| omim_ids | long | |
| previous_names | string | |
| previous_symbols | string | |
| pubmed_ids | string | |
| rat_genome_database_id_rgd | long | |
| record_type | string | |
| refseq_id_ncbi | string | |
| refseq_ids | string | |
| specialist_database_id | string | |
| specialist_database_links | string | |
| status | string | |
| synonyms | string | |
| ucsc_id_ucsc | string | |
| uniprot_id_uniprot | string | |
| vega_ids | string | |
"""
self.assertEqual("{0}".format(fields), expected[1:-1],
'tabulated dataset fields')
def test_csv_exporter(self):
dataset = Dataset.retrieve(self.TEST_DATASET_NAME)
query = dataset.query()[:10]
query.export('csv', filename='/tmp/test.csv')
self.assertTrue(path.isfile('/tmp/test.csv'))
remove('/tmp/test.csv')
def dataset(self):
""" Returns the dataset object """
from solvebio import Dataset
if not self.is_dataset:
raise SolveError(
"Only dataset objects have a Dataset resource. This is a {}".
format(self.object_type))
return Dataset.retrieve(self.dataset_id, client=self._client)
def get_dataset(cls, alias):
assert alias, 'Dataset alias argument cannot be None'
if alias in app_settings.DATASET_ALIASES:
return Dataset(app_settings.DATASET_ALIASES[alias])
try:
return Dataset(DatasetAlias.objects.get(alias=alias).dataset_id)
except DatasetAlias.DoesNotExist:
pass
# if the alias_or_id matches the Dataset regex, return it
if isinstance(alias, six.integer_types) or \
re.match(Dataset.FULL_NAME_REGEX, alias):
return Dataset(alias)
raise SolveError('Cannot find the SolveBio dataset by alias "%s"' %
alias)
def test_dataset_retrieval(self):
dataset = Dataset.retrieve(self.TEST_DATASET_NAME)
self.assertTrue('id' in dataset, 'Should be able to get id in dataset')
check_fields = [
'class_name', 'created_at', 'data_url', 'depository',
'depository_id', 'depository_version', 'depository_version_id',
'description', 'fields_url', 'full_name', 'genome_builds',
'is_genomic', 'id', 'name', 'title', 'updated_at', 'url',
'documents_count'
]
for f in check_fields:
self.assertTrue(f in dataset)
def test_changelog_dataset(self):
"""
First check if version 3.7.0-2015-12-06 returns a suitable
changelog compared to its most current version
"""
dataset = Dataset.retrieve('ClinVar/3.7.0-2015-12-06/Clinvar')
clog = dataset.changelog()
check_fields = ['attributes', 'to_dataset', 'from_dataset', 'fields']
for f in check_fields:
self.assertTrue(f in clog)
"""
Check if changelog between 3.7.0-2015-12-06 and 3.6.0-2015-09-04
returns
correct dictionary
"""
clogtwo = dataset.changelog('3.6.0-2015-09-04')
final_changelog = {
"attributes": {
"documents_count": [145359, 157003]
},
"to_dataset": "ClinVar/3.7.0-2015-12-06/ClinVar",
"from_dataset": "ClinVar/3.6.0-2015-09-04/ClinVar",
"fields": {
"removed": [],
"added": ["sbid"],
"changed": {}
}
}
self.assertEqual(final_changelog, clogtwo)
def setUp(self):
super(LookupTests, self).setUp()
self.dataset = Dataset.retrieve(self.TEST_DATASET_NAME)
def test_dataset_facets(self):
field = Dataset.retrieve(self.TEST_DATASET_NAME).fields('status')
facets = field.facets()
self.assertTrue(len(facets['facets']) >= 0)
def setUp(self):
self.dataset = Dataset.retrieve(self.TEST_DATASET_NAME)
super(BatchQueryTest, self).setUp()