RNeo4j is Neo4j's R driver. It allows you to read and write data from / to Neo4j directly from your R environment.
- Install
- Connect
- Nodes
- Relationships
- Cypher
- Shortest Paths
- Weighted Shortest Paths
- Graph Algorithms
- Visualizations
- Import
- Connection Issues
- Contribute
Download Neo4j community edition.
If you're on Windows, just download the .exe and follow the instructions. You'll get a GUI where you simply press "Start" to start Neo4j.
If you're on OS X, you can download either the .dmg or the .tar.gz. The .dmg is currently offered under the "beta program." This will give you a GUI where you simply press "Start" to start Neo4j. Otherwise, download the .tar.gz, unzip, navigate to the directory and execute ./bin/neo4j start.
If you're on Linux, you have to use the .tar.gz. Download the .tar.gz, unzip, navigate to the directory and execute ./bin/neo4j start.
install.packages("RNeo4j")devtools::install_github("nicolewhite/RNeo4j")Go to the latest release and download the source code. You can then install with install.packages.
install.packages("/path/to/file.tar.gz", repos=NULL, type="source")library(RNeo4j)graph = startGraph("http://localhost:7474/db/data/")If you have authentication enabled, pass your username and password.
graph = startGraph("http://localhost:7474/db/data/", username="neo4j", password="password")nicole = createNode(graph, "Person", name="Nicole", age=24)
greta = createNode(graph, "Person", name="Greta", age=24)
kenny = createNode(graph, "Person", name="Kenny", age=27)
shannon = createNode(graph, "Person", name="Shannon", age=23)r1 = createRel(greta, "LIKES", nicole, weight=7)
r2 = createRel(nicole, "LIKES", kenny, weight=1)
r3 = createRel(kenny, "LIKES", shannon, weight=3)
r4 = createRel(nicole, "LIKES", shannon, weight=5)If you're returning tabular results, use cypher, which will give you a data.frame.
query = "
MATCH (nicole:Person)-[r:LIKES]->(p:Person)
WHERE nicole.name = 'Nicole'
RETURN nicole.name, r.weight, p.name
"
cypher(graph, query)## nicole.name r.weight p.name
## 1 Nicole 5 Shannon
## 2 Nicole 1 Kenny
For anything more complicated, use cypherToList, which will give you a list.
query = "
MATCH (nicole:Person)-[:LIKES]->(p:Person)
WHERE nicole.name = 'Nicole'
RETURN nicole, COLLECT(p.name) AS friends
"
cypherToList(graph, query)## [[1]]
## [[1]]$nicole
## < Node >
## Person
##
## $name
## [1] "Nicole"
##
## $age
## [1] 24
##
##
## [[1]]$friends
## [[1]]$friends[[1]]
## [1] "Shannon"
##
## [[1]]$friends[[2]]
## [1] "Kenny"
Both cypher and cypherToList accept parameters. These parameters can be passed individually or as a list.
query = "
MATCH (p1:Person)-[r:LIKES]->(p2:Person)
WHERE p1.name = {name1} AND p2.name = {name2}
RETURN p1.name, r.weight, p2.name
"
cypher(graph, query, name1="Nicole", name2="Shannon")## p1.name r.weight p2.name
## 1 Nicole 5 Shannon
cypher(graph, query, list(name1="Nicole", name2="Shannon"))## p1.name r.weight p2.name
## 1 Nicole 5 Shannon
p = shortestPath(greta, "LIKES", shannon, max_depth=4)
n = nodes(p)
sapply(n, "[[", "name")## [1] "Greta" "Nicole" "Shannon"
p = shortestPath(greta, "LIKES", shannon, max_depth=4, cost_property="weight")
n = nodes(p)
sapply(n, "[[", "name")## [1] "Greta" "Nicole" "Kenny" "Shannon"
p$weight## [1] 11
library(igraph)
query = "
MATCH (n)-->(m)
RETURN n.name, m.name
"
edgelist = cypher(graph, query)
ig = graph.data.frame(edgelist, directed=F)
betweenness(ig)## Nicole Greta Kenny Shannon
## 2 0 0 0
closeness(ig)## Nicole Greta Kenny Shannon
## 0.3333333 0.2000000 0.2500000 0.2500000
plot(ig)
library(network)
library(GGally)
net = network(edgelist)
ggnet(net, label.nodes=TRUE)
Read this blog post and check out this slide deck.
library(hflights)
hflights = hflights[sample(nrow(hflights), 1000), ]
row.names(hflights) = NULL
head(hflights)## Year Month DayofMonth DayOfWeek DepTime ArrTime UniqueCarrier FlightNum
## 1 2011 12 9 5 2059 2313 CO 1615
## 2 2011 8 4 4 NA NA MQ 2870
## 3 2011 2 17 4 1057 1416 WN 9
## 4 2011 12 10 6 1325 1628 CO 1151
## 5 2011 11 20 7 1922 2100 XE 4370
## 6 2011 10 25 2 1033 1143 WN 183
## TailNum ActualElapsedTime AirTime ArrDelay DepDelay Origin Dest Distance
## 1 N14629 194 168 -8 -1 IAH SLC 1195
## 2 N692MQ NA NA NA NA HOU DFW 247
## 3 N511SW 139 123 36 32 HOU FLL 957
## 4 N57852 123 102 -18 -5 IAH MCO 854
## 5 N15948 98 76 64 62 IAH LBB 458
## 6 N368SW 70 57 -7 -2 HOU LIT 393
## TaxiIn TaxiOut Cancelled CancellationCode Diverted
## 1 10 16 0 0
## 2 NA NA 1 A 0
## 3 3 13 0 0
## 4 7 14 0 0
## 5 5 17 0 0
## 6 4 9 0 0
addConstraint(graph, "Carrier", "name")
addConstraint(graph, "Airport", "name")
query = "
CREATE (flight:Flight {number: {FlightNum} })
SET flight.year = TOINT({Year}),
flight.month = TOINT({DayofMonth}),
flight.day = TOINT({DayOfWeek})
MERGE (carrier:Carrier {name: {UniqueCarrier} })
CREATE (flight)-[:OPERATED_BY]->(carrier)
MERGE (origin:Airport {name: {Origin} })
MERGE (dest:Airport {name: {Dest} })
CREATE (flight)-[o:ORIGIN]->(origin)
CREATE (flight)-[d:DESTINATION]->(dest)
SET o.delay = TOINT({DepDelay}),
o.taxi_time = TOINT({TaxiOut})
SET d.delay = TOINT({ArrDelay}),
d.taxi_time = TOINT({TaxiIn})
"
tx = newTransaction(graph)
for(i in 1:nrow(hflights)) {
row = hflights[i, ]
appendCypher(tx, query,
FlightNum=row$FlightNum,
Year=row$Year,
DayofMonth=row$DayofMonth,
DayOfWeek=row$DayOfWeek,
UniqueCarrier=row$UniqueCarrier,
Origin=row$Origin,
Dest=row$Dest,
DepDelay=row$DepDelay,
TaxiOut=row$TaxiOut,
ArrDelay=row$ArrDelay,
TaxiIn=row$TaxiIn)
}
commit(tx)
summary(graph)## This To That
## 1 Flight OPERATED_BY Carrier
## 2 Flight ORIGIN Airport
## 3 Flight DESTINATION Airport
Error in curl::curl_fetch_memory(url, handle = handle) :
Couldn't connect to server
Neo4j probably isn't running. Make sure Neo4j is running first. It's also possible you have localhost resolution issues; try connecting to http://127.0.0.1:7474/db/data/ instead.
Error: client error: (401) Unauthorized
Neo.ClientError.Security.AuthorizationFailed
No authorization header supplied.
You have auth enabled on Neo4j and either didn't provide your username and password or they were invalid. You can pass a username and password to startGraph.
graph = startGraph("http://localhost:7474/db/data/", username="neo4j", password="password")
You can also disable auth by editing the following line in conf/neo4j-server.properties.
# Require (or disable the requirement of) auth to access Neo4j
dbms.security.auth_enabled=false
Check out the contributing doc if you'd like to contribute!