Skip to content

fix(interactive): fix ldbc data importing in Groot #4583

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 6 commits into
base: main
Choose a base branch
from
Open

fix(interactive): fix ldbc data importing in Groot #4583

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
631dc5a
fix ldbc schema
BingqingLyu Mar 17, 2025
d1c728a
fix test conf
BingqingLyu Mar 18, 2025
112890f
fix a bug when eval empty string
BingqingLyu Mar 18, 2025
7355b25
fix in data import: do not convert '' to nan
BingqingLyu Mar 18, 2025
02dd6f1
Revert "fix a bug when eval empty string"
BingqingLyu Mar 25, 2025
eba64e7
Revert "fix test conf"
BingqingLyu Mar 25, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
100 changes: 50 additions & 50 deletions interactive_engine/groot-server/src/main/resources/import_data.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,11 +92,11 @@ def create_ldbc_graph_schema(graph):
schema.add_vertex_label('PERSON').add_primary_key('id', 'long').add_property('firstName', 'str').add_property('lastName', 'str').add_property('gender', 'str').add_property('birthday', 'long').add_property('creationDate', 'long').add_property('locationIP', 'str').add_property('browserUsed', 'str').add_property('language', 'str').add_property('email', 'str')
schema.add_vertex_label('COMMENT').add_primary_key('id', 'long').add_property('creationDate', 'long').add_property('locationIP', 'str').add_property('browserUsed', 'str').add_property('content', 'str').add_property('length','int')
schema.add_vertex_label('POST').add_primary_key('id', 'long').add_property('imageFile', 'str').add_property('creationDate', 'long').add_property('locationIP', 'str').add_property('browserUsed', 'str').add_property('language', 'str').add_property('content', 'str').add_property('length', 'int')
schema.add_vertex_label('FORUM').add_primary_key('id', 'long').add_property('title', 'str').add_property('creationDate', 'str')
schema.add_vertex_label('FORUM').add_primary_key('id', 'long').add_property('title', 'str').add_property('creationDate', 'long')
schema.add_vertex_label('ORGANISATION').add_primary_key('id', 'long').add_property('type', 'str').add_property('name', 'str').add_property('url', 'str')
schema.add_vertex_label('TAGCLASS').add_primary_key('id', 'long').add_property('name', 'str').add_property('url', 'str')
schema.add_vertex_label('TAG').add_primary_key('id', 'long').add_property('name', 'str').add_property('url', 'str')
schema.add_edge_label('HASCREATOR').source('COMMENT').destination('PERSON').source('POST').destination('PERSON')
schema.add_edge_label('HASCREATOR').source('COMMENT').destination('PERSON').source('POST').destination('PERSON').add_property('creationDate','long')
schema.add_edge_label('HASTAG').source('COMMENT').destination('TAG').source('POST').destination('TAG').source('FORUM').destination('TAG')
schema.add_edge_label('ISLOCATEDIN').source('COMMENT').destination('PLACE').source('POST').destination('PLACE').source('PERSON').destination('PLACE').source('ORGANISATION').destination('PLACE')
schema.add_edge_label('REPLYOF').source('COMMENT').destination('COMMENT').source('COMMENT').destination('POST')
Expand All @@ -106,8 +106,8 @@ def create_ldbc_graph_schema(graph):
schema.add_edge_label('HASINTEREST').source('PERSON').destination('TAG')
schema.add_edge_label('KNOWS').source('PERSON').destination('PERSON').add_property('creationDate','long')
schema.add_edge_label('LIKES').source('PERSON').destination('COMMENT').source('PERSON').destination('POST').add_property('creationDate','long')
schema.add_edge_label('STUDYAT').source('PERSON').destination('ORGANISATION').add_property('classYear','long')
schema.add_edge_label('WORKAT').source('PERSON').destination('ORGANISATION').add_property('workFrom','long')
schema.add_edge_label('STUDYAT').source('PERSON').destination('ORGANISATION').add_property('classYear','int')
schema.add_edge_label('WORKAT').source('PERSON').destination('ORGANISATION').add_property('workFrom','int')
schema.add_edge_label('ISPARTOF').source('PLACE').destination('PLACE')
schema.add_edge_label('ISSUBCLASSOF').source('TAGCLASS').destination('TAGCLASS')
schema.add_edge_label('HASTYPE').source('TAG').destination('TAGCLASS')
Expand All @@ -127,10 +127,10 @@ def create_movie_graph_schema(graph):
schema.update()

def load_data_of_modern_graph(conn, graph, prefix):
person = pd.read_csv(os.path.join(prefix, "person.csv"), sep="|")
software = pd.read_csv(os.path.join(prefix, "software.csv"), sep="|")
knows = pd.read_csv(os.path.join(prefix, "knows.csv"), sep="|")
created = pd.read_csv(os.path.join(prefix, "created.csv"), sep="|")
person = pd.read_csv(os.path.join(prefix, "person.csv"), sep="|", na_filter=False)
software = pd.read_csv(os.path.join(prefix, "software.csv"), sep="|", na_filter=False)
knows = pd.read_csv(os.path.join(prefix, "knows.csv"), sep="|", na_filter=False)
created = pd.read_csv(os.path.join(prefix, "created.csv"), sep="|", na_filter=False)
vertices = []
vertices.extend(
[
Expand Down Expand Up @@ -279,37 +279,37 @@ def prepare_edges(edges, data, edge_type, source_type, destination_type, propert


def load_data_of_ldbc_graph(conn, graph, prefix):
place = pd.read_csv(os.path.join(prefix, "place_0_0.csv"), sep="|")
person = pd.read_csv(os.path.join(prefix, "person_0_0.csv"), sep="|")
comment = pd.read_csv(os.path.join(prefix, "comment_0_0.csv"), sep="|")
post = pd.read_csv(os.path.join(prefix, "post_0_0.csv"), sep="|")
forum = pd.read_csv(os.path.join(prefix, "forum_0_0.csv"), sep="|")
organisation = pd.read_csv(os.path.join(prefix, "organisation_0_0.csv"), sep="|")
tagclass = pd.read_csv(os.path.join(prefix, "tagclass_0_0.csv"), sep="|")
tag = pd.read_csv(os.path.join(prefix, "tag_0_0.csv"), sep="|")
comment_hascreator = pd.read_csv(os.path.join(prefix, "comment_hasCreator_person_0_0.csv"), sep="|")
post_hascreator = pd.read_csv(os.path.join(prefix, "post_hasCreator_person_0_0.csv"), sep="|")
comment_hastag = pd.read_csv(os.path.join(prefix, "comment_hasTag_tag_0_0.csv"), sep="|")
post_hastag = pd.read_csv(os.path.join(prefix, "post_hasTag_tag_0_0.csv"), sep="|")
forum_hastag = pd.read_csv(os.path.join(prefix, "forum_hasTag_tag_0_0.csv"), sep="|")
comment_islocatedin = pd.read_csv(os.path.join(prefix, "comment_isLocatedIn_place_0_0.csv"), sep="|")
post_islocatedin = pd.read_csv(os.path.join(prefix, "post_isLocatedIn_place_0_0.csv"), sep="|")
person_islocatedin = pd.read_csv(os.path.join(prefix, "person_isLocatedIn_place_0_0.csv"), sep="|")
organisation_islocatedin = pd.read_csv(os.path.join(prefix, "organisation_isLocatedIn_place_0_0.csv"), sep="|")
comment_replyof_comment = pd.read_csv(os.path.join(prefix, "comment_replyOf_comment_0_0.csv"), sep="|")
comment_replyof_post = pd.read_csv(os.path.join(prefix, "comment_replyOf_post_0_0.csv"), sep="|")
forum_containerof_post = pd.read_csv(os.path.join(prefix, "forum_containerOf_post_0_0.csv"), sep="|")
forum_hasmember_person = pd.read_csv(os.path.join(prefix, "forum_hasMember_person_0_0.csv"), sep="|")
forum_hasmoderator_person = pd.read_csv(os.path.join(prefix, "forum_hasModerator_person_0_0.csv"), sep="|")
person_hasinterest_tag = pd.read_csv(os.path.join(prefix, "person_hasInterest_tag_0_0.csv"), sep="|")
person_knows_person = pd.read_csv(os.path.join(prefix, "person_knows_person_0_0.csv"), sep="|")
person_likes_comment = pd.read_csv(os.path.join(prefix, "person_likes_comment_0_0.csv"), sep="|")
person_likes_post = pd.read_csv(os.path.join(prefix, "person_likes_post_0_0.csv"), sep="|")
person_studyat_organisation = pd.read_csv(os.path.join(prefix, "person_studyAt_organisation_0_0.csv"), sep="|")
person_workat_organisation = pd.read_csv(os.path.join(prefix, "person_workAt_organisation_0_0.csv"), sep="|")
place_ispartof_place = pd.read_csv(os.path.join(prefix, "place_isPartOf_place_0_0.csv"), sep="|")
tagclass_isSubclassOf_tagclass = pd.read_csv(os.path.join(prefix, "tagclass_isSubclassOf_tagclass_0_0.csv"), sep="|")
tag_hastype_tagclass = pd.read_csv(os.path.join(prefix, "tag_hasType_tagclass_0_0.csv"), sep="|")
place = pd.read_csv(os.path.join(prefix, "place_0_0.csv"), sep="|", na_filter=False)
person = pd.read_csv(os.path.join(prefix, "person_0_0.csv"), sep="|", na_filter=False)
comment = pd.read_csv(os.path.join(prefix, "comment_0_0.csv"), sep="|", na_filter=False)
post = pd.read_csv(os.path.join(prefix, "post_0_0.csv"), sep="|", na_filter=False)
forum = pd.read_csv(os.path.join(prefix, "forum_0_0.csv"), sep="|", na_filter=False)
organisation = pd.read_csv(os.path.join(prefix, "organisation_0_0.csv"), sep="|", na_filter=False)
tagclass = pd.read_csv(os.path.join(prefix, "tagclass_0_0.csv"), sep="|", na_filter=False)
tag = pd.read_csv(os.path.join(prefix, "tag_0_0.csv"), sep="|", na_filter=False)
comment_hascreator = pd.read_csv(os.path.join(prefix, "comment_hasCreator_person_0_0.csv"), sep="|", na_filter=False)
post_hascreator = pd.read_csv(os.path.join(prefix, "post_hasCreator_person_0_0.csv"), sep="|", na_filter=False)
comment_hastag = pd.read_csv(os.path.join(prefix, "comment_hasTag_tag_0_0.csv"), sep="|", na_filter=False)
post_hastag = pd.read_csv(os.path.join(prefix, "post_hasTag_tag_0_0.csv"), sep="|", na_filter=False)
forum_hastag = pd.read_csv(os.path.join(prefix, "forum_hasTag_tag_0_0.csv"), sep="|", na_filter=False)
comment_islocatedin = pd.read_csv(os.path.join(prefix, "comment_isLocatedIn_place_0_0.csv"), sep="|", na_filter=False)
post_islocatedin = pd.read_csv(os.path.join(prefix, "post_isLocatedIn_place_0_0.csv"), sep="|", na_filter=False)
person_islocatedin = pd.read_csv(os.path.join(prefix, "person_isLocatedIn_place_0_0.csv"), sep="|", na_filter=False)
organisation_islocatedin = pd.read_csv(os.path.join(prefix, "organisation_isLocatedIn_place_0_0.csv"), sep="|", na_filter=False)
comment_replyof_comment = pd.read_csv(os.path.join(prefix, "comment_replyOf_comment_0_0.csv"), sep="|", na_filter=False)
comment_replyof_post = pd.read_csv(os.path.join(prefix, "comment_replyOf_post_0_0.csv"), sep="|", na_filter=False)
forum_containerof_post = pd.read_csv(os.path.join(prefix, "forum_containerOf_post_0_0.csv"), sep="|", na_filter=False)
forum_hasmember_person = pd.read_csv(os.path.join(prefix, "forum_hasMember_person_0_0.csv"), sep="|", na_filter=False)
forum_hasmoderator_person = pd.read_csv(os.path.join(prefix, "forum_hasModerator_person_0_0.csv"), sep="|", na_filter=False)
person_hasinterest_tag = pd.read_csv(os.path.join(prefix, "person_hasInterest_tag_0_0.csv"), sep="|", na_filter=False)
person_knows_person = pd.read_csv(os.path.join(prefix, "person_knows_person_0_0.csv"), sep="|", na_filter=False)
person_likes_comment = pd.read_csv(os.path.join(prefix, "person_likes_comment_0_0.csv"), sep="|", na_filter=False)
person_likes_post = pd.read_csv(os.path.join(prefix, "person_likes_post_0_0.csv"), sep="|", na_filter=False)
person_studyat_organisation = pd.read_csv(os.path.join(prefix, "person_studyAt_organisation_0_0.csv"), sep="|", na_filter=False)
person_workat_organisation = pd.read_csv(os.path.join(prefix, "person_workAt_organisation_0_0.csv"), sep="|", na_filter=False)
place_ispartof_place = pd.read_csv(os.path.join(prefix, "place_isPartOf_place_0_0.csv"), sep="|", na_filter=False)
tagclass_isSubclassOf_tagclass = pd.read_csv(os.path.join(prefix, "tagclass_isSubclassOf_tagclass_0_0.csv"), sep="|", na_filter=False)
tag_hastype_tagclass = pd.read_csv(os.path.join(prefix, "tag_hasType_tagclass_0_0.csv"), sep="|", na_filter=False)
vertices = []
prepare_vertices(vertices, place, "PLACE", ["name", "url", "type"])
prepare_vertices(vertices, person, "PERSON", ["firstName", "lastName", "gender", "birthday", "creationDate", "locationIP", "browserUsed", "language", "email"])
Expand All @@ -320,8 +320,8 @@ def load_data_of_ldbc_graph(conn, graph, prefix):
prepare_vertices(vertices, tagclass, "TAGCLASS", ["name", "url"])
prepare_vertices(vertices, tag, "TAG", ["name", "url"])
edges = []
prepare_edges(edges, comment_hascreator, "HASCREATOR", "COMMENT", "PERSON", [])
prepare_edges(edges, post_hascreator, "HASCREATOR", "POST", "PERSON", [])
prepare_edges(edges, comment_hascreator, "HASCREATOR", "COMMENT", "PERSON", ["creationDate"])
prepare_edges(edges, post_hascreator, "HASCREATOR", "POST", "PERSON", ["creationDate"])
prepare_edges(edges, comment_hastag, "HASTAG", "COMMENT", "TAG", [])
prepare_edges(edges, post_hastag, "HASTAG", "POST", "TAG", [])
prepare_edges(edges, forum_hastag, "HASTAG", "FORUM", "TAG", [])
Expand Down Expand Up @@ -349,15 +349,15 @@ def load_data_of_ldbc_graph(conn, graph, prefix):
print("load ldbc graph done")

def load_data_of_movie_graph(conn, graph, prefix):
movie = pd.read_csv(os.path.join(prefix, "Movie.csv"), sep="|")
person = pd.read_csv(os.path.join(prefix, "Person.csv"), sep="|")
user = pd.read_csv(os.path.join(prefix, "User.csv"), sep="|")
acted_in = pd.read_csv(os.path.join(prefix, "ACTED_IN.csv"), sep="|")
directed = pd.read_csv(os.path.join(prefix, "DIRECTED.csv"), sep="|")
review = pd.read_csv(os.path.join(prefix, "REVIEWED.csv"), sep="|")
follows = pd.read_csv(os.path.join(prefix, "FOLLOWS.csv"), sep="|")
wrote = pd.read_csv(os.path.join(prefix, "WROTE.csv"), sep="|")
produced = pd.read_csv(os.path.join(prefix, "PRODUCED.csv"), sep="|")
movie = pd.read_csv(os.path.join(prefix, "Movie.csv"), sep="|", na_filter=False)
person = pd.read_csv(os.path.join(prefix, "Person.csv"), sep="|", na_filter=False)
user = pd.read_csv(os.path.join(prefix, "User.csv"), sep="|", na_filter=False)
acted_in = pd.read_csv(os.path.join(prefix, "ACTED_IN.csv"), sep="|", na_filter=False)
directed = pd.read_csv(os.path.join(prefix, "DIRECTED.csv"), sep="|", na_filter=False)
review = pd.read_csv(os.path.join(prefix, "REVIEWED.csv"), sep="|", na_filter=False)
follows = pd.read_csv(os.path.join(prefix, "FOLLOWS.csv"), sep="|", na_filter=False)
wrote = pd.read_csv(os.path.join(prefix, "WROTE.csv"), sep="|", na_filter=False)
produced = pd.read_csv(os.path.join(prefix, "PRODUCED.csv"), sep="|", na_filter=False)
vertices = []
prepare_vertices(vertices, movie, "Movie", ["released", "tagline", "title"])
prepare_vertices(vertices, person, "Person", ["born", "name"])
Expand Down
Loading