def calculate(neo4j: Neo4JConnection, config: Config):
nodetypes = ["Event", "Common", "Entity", "Log"]
relationtypes = ["E_C", "DF", "E_EN", "L_E"]
results = []
volume = neo4j.query(
f"""
MATCH()-[e:{functools.reduce(lambda a,b : f'{a}|{b}', relationtypes)}]->()
return count(e)
""", "Calculating Volume")[0][0]
nr_vertices = neo4j.query(f"""
MATCH (n)
WHERE {functools.reduce(lambda a,b : f'n:{a} OR n:{b}', nodetypes)}
return count(n)
""")[0][0]
results.append(["volume", volume, "edges"])
results.append(["nr_vertices", nr_vertices, "vertices"])
results.append(["size", volume + nr_vertices, "vertices + edges"])
results.append(
["fill", volume / (nr_vertices * nr_vertices), "edges/vertices^2"])
csv.write(results, ["Statistic", "Value", "Unit"], "basic")
def calculate(neo4j: Neo4JConnection):
edges = neo4j.query(
"""
match ()-[n]->() return type(n), count(n)
""", "calculating counts per edge type")
csv.write(edges, ["type", "count"], "counts-per-edge-type")
nodes = neo4j.query(
"""
match (n) return labels(n), count(n)
""", "calculating counts per node type")
csv.write(nodes, ["labels", "count"], "counts-per-node-type")
def __retrieve_relationship_data(neo4j: Neo4JConnection):
results = neo4j.query("""
match (s)-[r]->(t)
return ID(s) as sourceID, labels(s) as sourceLabels, ID(t) as targetID, labels(t) as targetLabels, type(r) as relationType
""")
for result in results:
result[1] = result[1][0]
result[3] = result[3][0]
csv.write(
results,
['source_id', 'source_label', 'target_id', 'target_label', 'rel_type'],
'relationships')
def calculate(neo4j: Neo4JConnection, config: Config):
nodetypes = ["Event", "Common", "Entity", "Log"]
simple_results = []
histogram_results = []
for nodetype in nodetypes:
for dir in ["<", ">"]:
direction = "in" if dir == "<" else "out"
simple_result = __simple(neo4j, nodetype, dir)
simple_results.append([f'{nodetype}', direction] +
simple_result[0])
histogram_result = __histogram_query_data(neo4j, nodetype, dir)
for entree in histogram_result:
histogram_results.append([f'{nodetype}', direction] + entree)
if nodetype in ["Event", "Entity"]:
for entity_type in config['entity']:
simple_result = __simple(neo4j, nodetype, dir,
entity_type['label'])
simple_results.append(
[f'{nodetype}: {entity_type["label"]}', direction] +
simple_result[0])
histogram_result = __histogram_query_data(
neo4j, nodetype, dir, entity_type['label'])
for entree in histogram_result:
histogram_results.append(
[f'{nodetype}: {entity_type["label"]}', direction
] + entree)
simple_results.sort(key=lambda a: a[0])
histogram_results.sort(key=lambda a: a[2])
histogram_results.sort(key=lambda a: a[1], reverse=True)
histogram_results.sort(key=lambda a: a[0])
csv.write(simple_results,
['node type', 'direction', 'average', 'stdev', 'max', 'min'],
"degrees")
csv.write(histogram_results, ['node type', 'direction', 'degree', 'count'],
"degrees_histogram")
def calculate(neo4j: Neo4JConnection, config: Config):
results = []
results_histogram = []
for entitytype in config['entity']:
label = entitytype['label']
result = __simple(neo4j, label)
results.append([label] + result[0])
result_histogram = __histogram(neo4j, label)
for entree in result_histogram:
results_histogram.append([label] + entree)
csv.write(results, ['entity type', 'average', 'stdev', 'max', 'min'],
'df-path-length')
results_histogram.sort(key=lambda a: a[1])
results_histogram.sort(key=lambda a: a[0])
csv.write(results_histogram, ['entity type', 'df_path_length', 'count'],
'df-path-length_histogram')
def calculate(neo4j: Neo4JConnection):
if not path.exists("statistics-csv.bpi14/relationships.csv"):
__retrieve_relationship_data(neo4j)
else:
print("Found existing relationship data, not retrieving new data")
print(
"Delete the file 'statistics/relationships.csv' and rerun the diameter calculation to retrieve new data"
)
diameters = []
relationships = pd.read_csv('statistics-csv.bpi14/relationships.csv')
rel_filter = ~relationships['rel_type'].str.contains('-')
relationships = relationships[rel_filter]
# diameters.append(['none', __calc(relationships)])
le_filter = ~(relationships['rel_type'].str.contains('L_E'))
relationships = relationships[le_filter]
diameters.append(['no L_E', __calc(relationships)])
csv.write(diameters, ['restriction', 'diameter'], 'diameter')