Skip to content
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

Jump to bottom

fix: pandas 'nan' values when loading csv files #409

Merged
merged 1 commit into from
Nov 10, 2020
Merged

fix: pandas 'nan' values when loading csv files #409

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
8 changes: 4 additions & 4 deletions databuilder/publisher/neo4j_csv_publisher.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -219,7 +219,7 @@ def _create_indices(self, node_file: str) -> None:
LOGGER.info('Creating indices. (Existing indices will be ignored)')

with open(node_file, 'r', encoding='utf8') as node_csv:
for node_record in pandas.read_csv(node_csv).to_dict(orient='records'):
for node_record in pandas.read_csv(node_csv, na_filter=False).to_dict(orient='records'):
label = node_record[NODE_LABEL_KEY]
if label not in self.labels:
self._try_create_index(label)
Expand All @@ -246,7 +246,7 @@ def _publish_node(self, node_file: str, tx: Transaction) -> Transaction:
"""

with open(node_file, 'r', encoding='utf8') as node_csv:
for node_record in pandas.read_csv(node_csv).to_dict(orient="records"):
for node_record in pandas.read_csv(node_csv, na_filter=False).to_dict(orient="records"):
stmt = self.create_node_merge_statement(node_record=node_record)
params = self._create_props_param(node_record)
tx = self._execute_statement(stmt, tx, params)
Expand Down Expand Up @@ -301,7 +301,7 @@ def _publish_relation(self, relation_file: str, tx: Transaction) -> Transaction:

count = 0
with open(relation_file, 'r', encoding='utf8') as relation_csv:
for rel_record in pandas.read_csv(relation_csv).to_dict(orient="records"):
for rel_record in pandas.read_csv(relation_csv, na_filter=False).to_dict(orient="records"):
stmt, params = self._relation_preprocessor.preprocess_cypher(
start_label=rel_record[RELATION_START_LABEL],
end_label=rel_record[RELATION_END_LABEL],
Expand All @@ -317,7 +317,7 @@ def _publish_relation(self, relation_file: str, tx: Transaction) -> Transaction:
LOGGER.info('Executed pre-processing Cypher statement {} times'.format(count))

with open(relation_file, 'r', encoding='utf8') as relation_csv:
for rel_record in pandas.read_csv(relation_csv).to_dict(orient="records"):
for rel_record in pandas.read_csv(relation_csv, na_filter=False).to_dict(orient="records"):
stmt = self.create_relationship_merge_statement(rel_record=rel_record)
params = self._create_props_param(rel_record)
tx = self._execute_statement(stmt, tx, params,
Expand Down