for the data import

constraints and indexes

create constraint ON ( movie:Movie ) ASSERT movie.id IS UNIQUE;
create constraint ON ( person:Person ) ASSERT person.id IS UNIQUE;

create index ON :Movie(title);
create index ON :Person(name);

// migrate genres to nodes
match (m:Movie)
unwind m.genres as genre
merge (g:Genre {name:genre})
merge (m)-[:IN_GENRE]->(g);

// keanu reeves from 1996
match (p:Person)-[:ACTED_IN]->(m:Movie)
where p.name = "Keanu Reeves"
and m.released > 1996
return avg(m.avgVote), collect(m.avgVote), stdev(m.avgVote), collect(m.released)

gistfile1.txt

LOAD CSV WITH HEADERS
FROM "https://raw.githubusercontent.com/mneedham/graphconnect-training/master/new_movies.csv"
AS line
merge (m:Movie {id:line.movieId})
on create set 
m.title=line.title, 
m.avgVote=line.avgVote,
m.released=line.releaseYear,
m.genres=split(line.genres, ':')
return count(m);

LOAD CSV WITH HEADERS
FROM "https://raw.githubusercontent.com/mneedham/graphconnect-training/master/people.csv"
AS line
merge (p:Person {id:line.personId})
on create set 
p.name = line.name, 
p.born = toInt(line.birthYear),
p.died = toInt(line.deathYear)
return count(p);

LOAD CSV WITH HEADERS
FROM "https://raw.githubusercontent.com/mneedham/graphconnect-training/master/directors.csv"
AS line
match (p:Person {id:line.personId})
match (m:Movie {id:line.movieId})
merge (p)-[:DIRECTED]->(m)
return count(p);

LOAD CSV WITH HEADERS
FROM "https://raw.githubusercontent.com/mneedham/graphconnect-training/master/actors.csv"
AS line
match (p:Person {id:line.personId})
match (m:Movie {id:line.movieId})
merge (p)-[r:ACTED_IN]->(m)
on create set r.roles = split(line.characters, ':')
return count(r)