Python Query.ids方法代码示例

# 需要导入模块: from elastic.query import Query [as 别名]
# 或者: from elastic.query.Query import ids [as 别名]
    def test_region_attributes(self):
        ''' test region attributes '''
        idx = ElasticSettings.idx(RegionDataTest.IDX_KEY, 'REGION')
        (idx, idx_type) = idx.split('/')
        docs = ElasticUtils.get_rdm_docs(idx, idx_type, qbool=Query.match_all(), sources=[], size=1)
        newRegion = utils.Region.pad_region_doc(docs[0])

        if len(getattr(newRegion, "genes")) > 0:
            query = ElasticQuery(Query.ids(getattr(newRegion, "genes")))
            resultObject = Search(query, idx=ElasticSettings.idx('GENE', 'GENE'),
                                  size=len(getattr(newRegion, "genes"))).search()
            self.assertEqual(len(getattr(newRegion, "genes")), resultObject.hits_total,
                             "All genes on region found in GENE index")

        if len(getattr(newRegion, "studies")) > 0:
            query = ElasticQuery(Query.ids(getattr(newRegion, "studies")))
            resultObject = Search(query, idx=ElasticSettings.idx('STUDY', 'STUDY'),
                                  size=len(getattr(newRegion, "studies"))).search()
            self.assertEqual(len(getattr(newRegion, "studies")), resultObject.hits_total,
                             "All study ids for region found in STUDY index")

        if len(getattr(newRegion, "pmids")) > 0:
            query = ElasticQuery(Query.ids(getattr(newRegion, "pmids")))
            resultObject = Search(query, idx=ElasticSettings.idx('PUBLICATION', 'PUBLICATION'),
                                  size=len(getattr(newRegion, "pmids"))).search()
            self.assertEqual(len(getattr(newRegion, "pmids")), resultObject.hits_total,
                             "All PMIDs for region found in PUBLICATION index")

# 需要导入模块: from elastic.query import Query [as 别名]
# 或者: from elastic.query.Query import ids [as 别名]
    def gene2ensembl_parse(cls, gene2ens, idx, idx_type):
        ''' Parse gene2ensembl file from NCBI and add entrez to gene index. '''
        genes = {}
        for gene in gene2ens:
            if gene.startswith('9606\t'):
                parts = gene.split('\t')
                gene_id = parts[1]
                ens_id = parts[2]
#                 prot_acc = parts[5]
                if ens_id not in genes:
                    genes[ens_id] = {'dbxrefs': {'entrez': gene_id}}

        def process_hits(resp_json):
            hits = resp_json['hits']['hits']
            docs = [Document(hit) for hit in hits]
            chunk_size = 450
            for i in range(0, len(docs), chunk_size):
                docs_chunk = docs[i:i+chunk_size]
                json_data = ''
                for doc in docs_chunk:
                    ens_id = doc._meta['_id']
                    idx_type = doc.type()
                    doc_data = {"update": {"_id": ens_id, "_type": idx_type,
                                           "_index": idx, "_retry_on_conflict": 3}}
                    json_data += json.dumps(doc_data) + '\n'
                    json_data += json.dumps({'doc': genes[ens_id]}) + '\n'
                if json_data != '':
                    Loader().bulk_load(idx, idx_type, json_data)

        query = ElasticQuery(Query.ids(list(genes.keys())))
        ScanAndScroll.scan_and_scroll(idx, idx_type=idx_type, call_fun=process_hits, query=query)

# 需要导入模块: from elastic.query import Query [as 别名]
# 或者: from elastic.query.Query import ids [as 别名]
def _get_pub_docs_by_pmid(pmids, sources=None):
    """ Get the gene symbols for the corresponding array of ensembl IDs.
    A dictionary is returned with the key being the ensembl ID and the
    value the gene document. """
    query = ElasticQuery(Query.ids(pmids), sources=sources)
    elastic = Search(query, idx=ElasticSettings.idx("PUBLICATION"), size=len(pmids))
    return {doc.doc_id(): doc for doc in elastic.search().docs}

# 需要导入模块: from elastic.query import Query [as 别名]
# 或者: from elastic.query.Query import ids [as 别名]
 def get_gene_docs_by_ensembl_id(cls, ens_ids, sources=None):
     ''' Get the gene symbols for the corresponding array of ensembl IDs.
     A dictionary is returned with the key being the ensembl ID and the
     value the gene document. '''
     query = ElasticQuery(Query.ids(ens_ids), sources=sources)
     elastic = Search(query, idx=ElasticSettings.idx('GENE', idx_type='GENE'), size=len(ens_ids))
     return {doc.doc_id(): doc for doc in elastic.search().docs}

# 需要导入模块: from elastic.query import Query [as 别名]
# 或者: from elastic.query.Query import ids [as 别名]
    def gene2ensembl_parse(cls, gene2ens, idx, idx_type):
        ''' Parse gene2ensembl file from NCBI and add entrez to gene index. '''
        genes = {}
        for gene in gene2ens:
            if gene.startswith('9606\t'):
                parts = gene.split('\t')
                gene_id = parts[1]
                ens_id = parts[2]
#                 prot_acc = parts[5]
                if ens_id not in genes:
                    genes[ens_id] = {'dbxrefs': {'entrez': gene_id}}

        query = ElasticQuery(Query.ids(list(genes.keys())))
        docs = Search(query, idx=idx, idx_type=idx_type, size=80000).search().docs

        chunk_size = 450
        for i in range(0, len(docs), chunk_size):
            docs_chunk = docs[i:i+chunk_size]
            json_data = ''
            for doc in docs_chunk:
                ens_id = doc._meta['_id']
                idx_type = doc.type()
                doc_data = {"update": {"_id": ens_id, "_type": idx_type,
                                       "_index": idx, "_retry_on_conflict": 3}}
                json_data += json.dumps(doc_data) + '\n'
                json_data += json.dumps({'doc': genes[ens_id]}) + '\n'
            if json_data != '':
                Loader().bulk_load(idx, idx_type, json_data)

# 需要导入模块: from elastic.query import Query [as 别名]
# 或者: from elastic.query.Query import ids [as 别名]
 def get_publications(cls, pmids, sources=[]):
     ''' Get publications from the list of PMIDs. '''
     if pmids is None or not pmids:
         return None
     from elastic.search import Search, ElasticQuery
     pubs = Search(ElasticQuery(Query.ids(pmids), sources=sources),
                   idx=ElasticSettings.idx('PUBLICATION', 'PUBLICATION'), size=2).search().docs
     return pubs

# 需要导入模块: from elastic.query import Query [as 别名]
# 或者: from elastic.query.Query import ids [as 别名]
    def ensmart_gene_parse(cls, ensmart_f, idx, idx_type):
        ''' For those gene docs missing a dbxrefs.entrez use Ensembl Mart to
        fill in. '''
        genes = {}
        for ensmart in ensmart_f:
            parts = ensmart.split('\t')
            ens_id = parts[0]
            gene_id = parts[1]
            swissprot = parts[2].strip()
            trembl = parts[3].strip()
            if gene_id == '':
                continue
            if ens_id in genes:
                if genes[ens_id]['dbxrefs']['entrez'] != gene_id:
                    genes[ens_id]['dbxrefs']['entrez'] = None
                else:
                    if swissprot != '':
                        cls._add_to_dbxref(genes[ens_id], 'swissprot', swissprot)
                    if trembl != '':
                        cls._add_to_dbxref(genes[ens_id], 'trembl', trembl)
            else:
                genes[ens_id] = {'dbxrefs': {'entrez': gene_id}}
                if swissprot != '':
                    genes[ens_id]['dbxrefs'].update({'swissprot': swissprot})
                if trembl != '':
                    genes[ens_id]['dbxrefs'].update({'trembl': trembl})

        '''  search for the entrez ids '''
        def process_hits(resp_json):
            hits = resp_json['hits']['hits']
            docs = [Document(hit) for hit in hits]
            chunk_size = 450
            for i in range(0, len(docs), chunk_size):
                docs_chunk = docs[i:i+chunk_size]
                json_data = ''
                for doc in docs_chunk:
                    ens_id = doc._meta['_id']
                    if 'dbxrefs' in doc.__dict__:
                        dbxrefs = getattr(doc, 'dbxrefs')
                    else:
                        dbxrefs = {}

                    if ('entrez' in genes[ens_id]['dbxrefs'] and
                        'entrez' in dbxrefs and
                       dbxrefs['entrez'] != genes[ens_id]['dbxrefs']['entrez']):
                        logger.warn('Multiple entrez ids for ensembl id: '+ens_id)
                        continue

                    idx_type = doc.type()
                    doc_data = {"update": {"_id": ens_id, "_type": idx_type,
                                           "_index": idx, "_retry_on_conflict": 3}}
                    json_data += json.dumps(doc_data) + '\n'
                    json_data += json.dumps({'doc': genes[ens_id]}) + '\n'
                if json_data != '':
                    Loader().bulk_load(idx, idx_type, json_data)

        query = ElasticQuery(Query.ids(list(genes.keys())))
        ScanAndScroll.scan_and_scroll(idx, idx_type=idx_type, call_fun=process_hits, query=query)

# 需要导入模块: from elastic.query import Query [as 别名]
# 或者: from elastic.query.Query import ids [as 别名]
    def is_region_for_disease(cls, hit, section=None, config=None, result_container={}):

        result_container_populated = result_container
        feature_doc = hit['_source']
        feature_doc['_id'] = hit['_id']
        disease_loci = feature_doc['disease_loci']
        region_id = feature_doc['region_id']

        diseases = set()
        for disease_locus_id in disease_loci:

            query = ElasticQuery(Query.ids([disease_locus_id]), sources=['hits'])
            elastic = Search(query, idx=ElasticSettings.idx('REGION', idx_type='DISEASE_LOCUS'))
            disease_locus_hits = elastic.search().docs

            for disease_locus_hit in disease_locus_hits:
                hits = getattr(disease_locus_hit, 'hits')
                for hit in hits:
                    query = ElasticQuery(Query.ids([hit]))
                    elastic = Search(query, idx=ElasticSettings.idx('REGION', idx_type='STUDY_HITS'))
                    hit_doc = elastic.search().docs[0]

                    disease = getattr(hit_doc, "disease")
                    status = getattr(hit_doc, "status")

                    if status != 'N':
                        return result_container

                    disease_loci = getattr(hit_doc, "disease_locus").lower()

                    if disease_loci == 'tbc':
                        return result_container

                    diseases.add(disease)

        for disease in diseases:

            result_container_populated = cls.populate_container(disease,
                                                                disease,
                                                                fnotes=None, features=[region_id],
                                                                diseases=[disease],
                                                                result_container=result_container_populated)
        return result_container_populated

# 需要导入模块: from elastic.query import Query [as 别名]
# 或者: from elastic.query.Query import ids [as 别名]
 def get_disease_loci(self):
     ''' Returns the disease loci for requested hit docs '''
     regions_idx = ElasticSettings.idx('REGION', 'DISEASE_LOCUS')
     disease_loci = getattr(self, "disease_loci")
     if len(disease_loci) == 0:
         logger.warning("no disease_locus attributes found/given")
         return
     resultObj = Search(search_query=ElasticQuery(Query.ids(disease_loci)),
                        idx=regions_idx).search()
     return resultObj.docs

# 需要导入模块: from elastic.query import Query [as 别名]
# 或者: from elastic.query.Query import ids [as 别名]
 def test_chrom(self):
     ''' Check correct number of chromosomes. '''
     ids = ['X', 'Y']
     for i in range(22):
         ids.append(i+1)
     idx = ElasticSettings.idx('BAND', idx_type='CHROM')
     docs = Search(ElasticQuery(Query.ids(ids)), idx=idx, size=len(ids)).search().docs
     self.assertEqual(len(ids), len(docs), 'Check for chromosomes')
     for doc in docs:
         self.assertGreater(getattr(doc, 'length'), 1000000, 'Chromosome length')

# 需要导入模块: from elastic.query import Query [as 别名]
# 或者: from elastic.query.Query import ids [as 别名]
 def get_studies(cls, study_ids=None, disease_code=None, sources=[], split_name=True):
     studies_query = ElasticQuery(Query.match_all(), sources=sources)
     if disease_code is not None:
         studies_query = ElasticQuery(BoolQuery(must_arr=Query.term("diseases", disease_code)), sources=sources)
     elif study_ids:
         studies_query = ElasticQuery(Query.ids(study_ids), sources=sources)
     studies = Search(studies_query, idx=ElasticSettings.idx('STUDY', 'STUDY'), size=200).search().docs
     for doc in studies:
         if split_name and getattr(doc, 'study_name') is not None:
             setattr(doc, 'study_name', getattr(doc, 'study_name').split(':', 1)[0])
     return Document.sorted_alphanum(studies, "study_id")

# 需要导入模块: from elastic.query import Query [as 别名]
# 或者: from elastic.query.Query import ids [as 别名]
def get_gene_docs_by_ensembl_id(ens_ids, sources=None):
    ''' Get the gene symbols for the corresponding array of ensembl IDs.
    A dictionary is returned with the key being the ensembl ID and the
    value the gene document. '''
    genes = {}

    def get_genes(resp_json):
        hits = resp_json['hits']['hits']
        for hit in hits:
            genes[hit['_id']] = GeneDocument(hit)
    query = ElasticQuery(Query.ids(ens_ids), sources=sources)
    ScanAndScroll.scan_and_scroll(ElasticSettings.idx('GENE'), call_fun=get_genes, query=query)
    return genes

# 需要导入模块: from elastic.query import Query [as 别名]
# 或者: from elastic.query.Query import ids [as 别名]
    def get_object(self):
        q = ElasticQuery(Query.ids(self.kwargs[self.lookup_field]))
        s = Search(search_query=q, idx=getattr(self, 'idx'))
        try:
            result = s.get_json_response()['hits']['hits'][0]
            obj = ElasticObject(initial=result['_source'])
            obj.uuid = result['_id']
            obj.criteria_type = result['_type']

            # May raise a permission denied
            self.check_object_permissions(self.request, obj)
            return obj
        except (TypeError, ValueError, IndexError):
            raise Http404

# 需要导入模块: from elastic.query import Query [as 别名]
# 或者: from elastic.query.Query import ids [as 别名]
    def get_pub_docs_by_pmid(cls, pmids, sources=None):
        ''' Get the publication documents for a list of PMIDs.
        A dictionary is returned with the key being the PMID and the
        value the publication document. '''
        pubs = {}

        def get_pubs(resp_json):
            hits = resp_json['hits']['hits']
            for hit in hits:
                pubs[hit['_id']] = PublicationDocument(hit)
        from elastic.search import ElasticQuery, ScanAndScroll
        query = ElasticQuery(Query.ids(pmids), sources=sources)
        ScanAndScroll.scan_and_scroll(ElasticSettings.idx('PUBLICATION'), call_fun=get_pubs, query=query)
        return pubs

# 需要导入模块: from elastic.query import Query [as 别名]
# 或者: from elastic.query.Query import ids [as 别名]
def study_page(request, study):
    ''' Renders a study page. '''
    if study is None:
        messages.error(request, 'No study id given.')
        raise Http404()
    query = ElasticQuery(Query.ids(study.split(',')))
    elastic = Search(query, idx=ElasticSettings.idx('STUDY', 'STUDY'), size=5)
    res = elastic.search(obj_document=StudyDocument)
    if res.hits_total == 0:
        messages.error(request, 'Study(s) '+study+' not found.')
    elif res.hits_total < 9:
        names = ', '.join([getattr(doc, 'study_name') for doc in res.docs])
        context = {'features': res.docs, 'title': names}
        return render(request, 'study/study.html', context, content_type='text/html')
    raise Http404()