aanpassing
This commit is contained in:
John
parent
adf28391f0
commit
55f6d54f76
|
|
@ -5,16 +5,19 @@ created: 2021-05-04 14:58:11Z
|
|||
---
|
||||
|
||||
## show database schema info
|
||||
|
||||
CALL db.schema.visualization()
|
||||
CALL db.schema.relTypeProperties()
|
||||
CALL db.schema.nodeTypeProperties()
|
||||
CALL db.propertyKeys()
|
||||
|
||||
## syntax
|
||||
|
||||
MATCH (variable:Label {propertyKey: propertyValue, propertyKey2: propertyValue2})
|
||||
RETURN variable
|
||||
|
||||
## relationships
|
||||
|
||||
() // a node
|
||||
()--() // 2 nodes have some type of relationship
|
||||
()-[]-() // 2 nodes have some type of relationship
|
||||
|
|
@ -27,31 +30,35 @@ RETURN node1, node2
|
|||
MATCH (node1)-[:REL_TYPEA | REL_TYPEB]->(node2)
|
||||
RETURN node1, node2
|
||||
|
||||
|
||||
|
||||
## show node with name "Tom Hanks"
|
||||
|
||||
MATCH (tom {name: "Tom"}) RETURN tom
|
||||
|
||||
## return all nodes in database
|
||||
|
||||
MATCH (a:Person) WHERE a.name = "Tom" RETURN a
|
||||
MATCH (a:Person) RETURN a.name
|
||||
|
||||
## with where clause
|
||||
|
||||
match (a:Movie)
|
||||
where a.released >= 1990 and a.released < 1999
|
||||
return a.title;
|
||||
|
||||
## a list of all properties that match a string
|
||||
## a list of all properties that match a string
|
||||
|
||||
MATCH (n) WITH keys(n) AS p UNWIND p AS x WITH DISTINCT x WHERE x =~ ".*" RETURN collect(x) AS SET;
|
||||
|
||||
## delete all nodes and relations
|
||||
|
||||
MATCH (n)
|
||||
DETACH DELETE n
|
||||
|
||||
## create
|
||||
|
||||
```cypher
|
||||
create (:Person {name = 'jan', age = 32})
|
||||
```
|
||||
|
||||
|
||||
match(n:Person {age: 32}) return n
|
||||
|
||||
|
|
@ -78,7 +85,6 @@ WHERE directors >= 2
|
|||
OPTIONAL MATCH (p:Person)-[:REVIEWED]->(m)
|
||||
RETURN m.title, p.name
|
||||
|
||||
|
||||
match (a:Person), (m:Movie), (b:Person)
|
||||
where a.name = 'Liam Neeson'
|
||||
and b.name = 'Benjamin Melniker'
|
||||
|
|
@ -120,25 +126,33 @@ return p
|
|||
match (p:Person {name:'Robert Zemeckis'}), (m:Movie {title:'Forrest Gump'})
|
||||
merge (p)-[r:DIRECTED]->(m)
|
||||
return p,r,m
|
||||
|
||||
```
|
||||
|
||||
## constrain uniqueness
|
||||
|
||||
```
|
||||
|
||||
CREATE CONSTRAINT UniqueMovieTitleConstraint
|
||||
ON (m:Movie)
|
||||
ASSERT m.title IS UNIQUE
|
||||
|
||||
```
|
||||
|
||||
## constrain uniqueness over two properties
|
||||
|
||||
## only enterprise edition
|
||||
|
||||
CREATE CONSTRAINT UniqueNameBornConstraint
|
||||
ON (p:Person)
|
||||
ASSERT (p.name, p.born) IS NODE KEY
|
||||
|
||||
## needs enterprise edition of neo4j
|
||||
|
||||
create constraint PersonBornExistsConstraint on (p:Person)
|
||||
assert exists(p.born)
|
||||
|
||||
|
||||
## existence constraint (possible for node
|
||||
|
||||
CREATE CONSTRAINT ExistsMovieTagline
|
||||
ON (m:Movie)
|
||||
ASSERT exists(m.tagline)
|
||||
|
|
@ -146,79 +160,100 @@ CREATE CONSTRAINT ExistsMovieTagline
|
|||
DROP CONSTRAINT MovieTitleConstraint
|
||||
|
||||
## existence constraint for relationship
|
||||
|
||||
## only enterprise edition of neo4j
|
||||
|
||||
CREATE CONSTRAINT ExistsREVIEWEDRating
|
||||
ON ()-[rel:REVIEWED]-()
|
||||
ASSERT exists(rel.rating)
|
||||
|
||||
## drop constraint
|
||||
|
||||
DROP CONSTRAINT ExistsREVIEWEDRating
|
||||
|
||||
CALL db.constraints() better SHOW CONSTRAINTS
|
||||
|
||||
## Indexes
|
||||
|
||||
## Single property index
|
||||
|
||||
CREATE INDEX MovieReleased FOR (m:Movie) ON (m.released)
|
||||
|
||||
## composite index
|
||||
|
||||
CREATE INDEX MovieReleasedVideoFormat
|
||||
FOR (m:Movie)
|
||||
ON (m.released, m.videoFormat)
|
||||
|
||||
## full-text schema index
|
||||
|
||||
CALL db.index.fulltext.createNodeIndex(
|
||||
'MovieTitlePersonName',['Movie', 'Person'], ['title', 'name'])
|
||||
### To use a full-text schema index, you must call the query procedure that uses the index.
|
||||
|
||||
### To use a full-text schema index, you must call the query procedure that uses the index
|
||||
|
||||
CALL db.index.fulltext.queryNodes(
|
||||
'MovieTitlePersonName', 'Jerry')
|
||||
YIELD node, score
|
||||
RETURN node.title, score
|
||||
|
||||
### Searching on a particular property
|
||||
|
||||
CALL db.index.fulltext.queryNodes(
|
||||
'MovieTitlePersonName', 'name: Jerry') YIELD node
|
||||
RETURN node
|
||||
|
||||
## drop index
|
||||
|
||||
DROP INDEX MovieReleasedVideoFormat
|
||||
|
||||
## dropping full-text schema index
|
||||
|
||||
CALL db.index.fulltext.drop('MovieTitlePersonName')
|
||||
|
||||
## search a full-text schema index
|
||||
|
||||
CALL db.index.fulltext.queryNodes('MovieTaglineFTIndex', 'real OR world')
|
||||
YIELD node
|
||||
RETURN node.title, node.tagline
|
||||
|
||||
## set parameters
|
||||
|
||||
:param year => 2000
|
||||
:params {actorName: 'Tom Cruise', movieName: 'Top Gun'}
|
||||
|
||||
## for statement
|
||||
|
||||
MATCH (p:Person)-[:ACTED_IN]->(m:Movie)
|
||||
WHERE p.name = $actorName AND m.title = $movieName
|
||||
RETURN p, m
|
||||
|
||||
## clear
|
||||
|
||||
:params {}
|
||||
|
||||
## view
|
||||
|
||||
:params
|
||||
|
||||
## Analyzing queries
|
||||
|
||||
- EXPLAIN provides estimates of the graph engine processing that will occur, but does not execute the Cypher statement.
|
||||
|
||||
- PROFILE provides real profiling information for what has occurred in the graph engine during the query and executes the Cypher statement. (run-time performance metrics)
|
||||
|
||||
## Monitoring queries
|
||||
|
||||
:queries
|
||||
|
||||
|
||||
## exercise
|
||||
|
||||
:params {year:2006, ratingValue:65}
|
||||
|
||||
match (p:Person)-[r:REVIEWED]->(m:Movie)<-[:ACTED_IN]-(a:Person)
|
||||
where m.released = $year and r.rating = $ratingValue
|
||||
return p.name, m.title, m.released, r.rating, collect(a.name)
|
||||
|
||||
|
||||
:auto USING PERIODIC COMMIT LOAD CSV
|
||||
commit every 1000 rows
|
||||
Eager operators don't act on this command, ie:
|
||||
|
|
@ -241,15 +276,14 @@ MERGE (actor:Person {name: line.name})
|
|||
ON CREATE SET actor.born = toInteger(trim(line.birthYear)), actor.actorId = line.id
|
||||
ON MATCH SET actor.actorId = line.id
|
||||
|
||||
|
||||
|
||||
## before load
|
||||
|
||||
CREATE CONSTRAINT UniqueMovieIdConstraint ON (m:Movie) ASSERT m.id IS UNIQUE;
|
||||
|
||||
## after load
|
||||
|
||||
CREATE INDEX MovieTitleIndex ON (m:Movie) FOR (m.title);
|
||||
|
||||
|
||||
|
||||
// Delete all constraints and indexes
|
||||
CALL apoc.schema.assert({},{},true);
|
||||
// Delete all nodes and relationships
|
||||
|
|
@ -259,19 +293,19 @@ CALL apoc.periodic.iterate(
|
|||
{ batchSize:500 }
|
||||
)
|
||||
|
||||
|
||||
## test apoc
|
||||
|
||||
CALL dbms.procedures()
|
||||
YIELD name WHERE name STARTS WITH "apoc"
|
||||
RETURN name
|
||||
|
||||
|
||||
## Graph modelling
|
||||
|
||||
How does Neo4j support graph data modeling?
|
||||
|
||||
- allows you to create property graphs.
|
||||
- traversing the graph: traversal means anchoring a query based upon a property value, then traversing the graph to satisfy the query
|
||||
|
||||
|
||||
Nodes and relationships are the key components of a graph.
|
||||
Nodes must have labels to categorize entities.
|
||||
A label is used to categorize a set of nodes.
|
||||
|
|
@ -280,22 +314,26 @@ A relationship is only traversed once during a query.
|
|||
Nodes and relationships can have properties.
|
||||
Properties are used to provide specific values to a node or relationship.
|
||||
|
||||
## Your model must address Nodes:
|
||||
## Your model must address Nodes
|
||||
|
||||
- Uniqueness of nodes: always have a property (or set of properties) that uniquely identify a node.
|
||||
- Complex data: balance between number of properties that represent complex data vs. multiple nodes and relationships.
|
||||
|
||||
super nodes = (a node with lots of fan-in or fan-out)
|
||||
|
||||
- Reduce property duplication (no repeating property values)
|
||||
- Reduce gather-and-inspect (traversal)
|
||||
|
||||
## Best practices for modeling relationships
|
||||
|
||||
- Using specific relationship types.
|
||||
- Reducing symmetric relationships.
|
||||
- No semantically identical relationships (PARENT_OF and CHILD_OF)
|
||||
- Not all mutual relationships are semantically symmetric(FOLLOWS)
|
||||
- No semantically identical relationships (PARENT_OF and CHILD_OF)
|
||||
- Not all mutual relationships are semantically symmetric(FOLLOWS)
|
||||
- Using types vs. properties.
|
||||
|
||||
## Property best practices
|
||||
|
||||
In the case of property value complexity, it depends on how the property is used. Anchors and traversal paths that use property values need to be parsed at query time.
|
||||
|
||||
- Property lookups have a cost.
|
||||
|
|
@ -304,6 +342,7 @@ In the case of property value complexity, it depends on how the property is used
|
|||
- Identifiers, outputs, and decoration are OK as complex values.
|
||||
|
||||
## Hierarchy of accessibility
|
||||
|
||||
1. Anchor node label, indexed anchor node properties (cheap)
|
||||
2. Relationship types (cheap)
|
||||
3. Non-indexed anchor node properties
|
||||
|
|
@ -312,26 +351,25 @@ In the case of property value complexity, it depends on how the property is used
|
|||
|
||||
Downstream labels and properties are most expensive.
|
||||
|
||||
## Common graph structures used in modeling:
|
||||
## Common graph structures used in modeling
|
||||
|
||||
1. Intermediate nodes
|
||||
- (solve hyperedge; n-ary relationships)
|
||||
- sharing context (share contextual information)
|
||||
- sharing data (deduplicate information)
|
||||
- organizing data (avoid density of nodes)
|
||||
- (solve hyperedge; n-ary relationships)
|
||||
- sharing context (share contextual information)
|
||||
- sharing data (deduplicate information)
|
||||
- organizing data (avoid density of nodes)
|
||||
2. Linked lists (useful whenever the sequence of objects matters)
|
||||
- Interleaved linked list
|
||||
- Head and tail of linked list (root point to head and tail)
|
||||
- No double linked-lists (redundant symmetrical relationships)
|
||||
- Interleaved linked list
|
||||
- Head and tail of linked list (root point to head and tail)
|
||||
- No double linked-lists (redundant symmetrical relationships)
|
||||
3. Timeline trees
|
||||
- use time as either an anchor or a navigational aid
|
||||
- topmost node in the timeline is an “all time” node
|
||||
- timeline trees consume a lot of space
|
||||
- use time as either an anchor or a navigational aid
|
||||
- topmost node in the timeline is an “all time” node
|
||||
- timeline trees consume a lot of space
|
||||
4. Multiple structures in a single graph
|
||||
|
||||
|
||||
CREATE (:Airport {code: "ABQ"})<-[:CONNECTED_TO {airline: "WN", flightNumber: 500, date: "2019-1-3", depature: 1445, arrival: 1710}]-(:Airport {code: "LAS"})-[:CONNECTED_TO {airline: "WN", flightNumber: 82, date: "2019-1-3", depature: 1715, arrival: 1820}]->(:Airport {code: "LAX"})
|
||||
|
||||
|
||||
LOAD CSV WITH HEADERS FROM 'file:///flights_2019_1k.csv' AS row
|
||||
MERGE (origin:Airport {code: row.Origin})
|
||||
MERGE (destination:Airport {code: row.Dest})
|
||||
|
|
@ -340,4 +378,3 @@ MERGE (origin)-[connection:CONNECTED_TO {
|
|||
flightNumber: row.FlightNum,
|
||||
date: toInteger(row.Year) + '-' + toInteger(row.Month) + '-' + toInteger(row.DayofMonth)}]->(destination)
|
||||
ON CREATE SET connection.departure = toInteger(row.CRSDepTime), connection.arrival = toInteger(row.CRSArrTime)
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue