def create_directory_children(dirs, parent):
'''Create the following relationship: (p:Directory)<-[:PARENT]-(d:Directory)
where dirs is a list of strings and parent is a py2neo node.'''
batch = WriteBatch(graph_db)
for d in dirs:
dir_node = batch.create({'name': d, '_id': uuid.uuid4().hex})
batch.add_labels(dir_node, "Directory")
batch.create(rel(dir_node, "PARENT", parent))
batch.run()
def create_file_children(files, parent, root_path):
'''Create (p:Directory)<-{:PARENT]-(f:File)
for all files to the given parent. Also stores the file's contents in
the content property.'''
batch = WriteBatch(graph_db)
for f in files:
file_content = get_file_content(f, root_path)
file_node = batch.create({'name': f, '_id': uuid.uuid4().hex,
'content': file_content})
batch.add_labels(file_node, 'File')
batch.create(rel(file_node, "PARENT", parent))
batch.run()
merge_category_query = '''
MATCH (b:Business {id: {business_id}})
MERGE (c:Category {name: {category}})
CREATE UNIQUE (c)<-[:IS_IN]-(b)
'''
print "Beginning business batch"
with open('data/yelp_academic_dataset_business.json', 'r') as f:
business_batch = WriteBatch(db)
count = 0
for b in (json.loads(l) for l in f):
business_batch.append_cypher(create_business_query, b)
count += 1
if count >= 10000:
business_batch.run()
business_batch.clear()
count = 0
if count > 0:
business_batch.run()
print "Beginning category batch"
with open('data/yelp_academic_dataset_business.json', 'r') as f:
category_batch = WriteBatch(db)
count = 0
for b in (json.loads(l) for l in f):
for c in b['categories']:
category_batch.append_cypher(merge_category_query, {'business_id': b['business_id'], 'category': c})
count += 1
if count >= 10000:
category_batch.run()
merge_category_query = '''
MATCH (b:Business {id: {business_id}})
MERGE (c:Category {name: {category}})
CREATE UNIQUE (c)<-[:IS_IN]-(b)
'''
print "Beginning business batch"
with open('data/yelp_academic_dataset_business.json', 'r') as f:
business_batch = WriteBatch(db)
count = 0
for b in (json.loads(l) for l in f):
business_batch.append_cypher(create_business_query, b)
count += 1
if count >= 10000:
business_batch.run()
business_batch.clear()
count = 0
if count > 0:
business_batch.run()
print "Beginning category batch"
with open('data/yelp_academic_dataset_business.json', 'r') as f:
category_batch = WriteBatch(db)
count = 0
for b in (json.loads(l) for l in f):
for c in b['categories']:
category_batch.append_cypher(merge_category_query, {
'business_id': b['business_id'],
'category': c
})
