Files
visual_critical_discourse_a…/src/database/utils.py
T

91 lines
2.2 KiB
Python

from pymongo.collection import Collection
import logging
from .classes import (
VisualCommunication,
NoDocumentFoundException,
ModelOutputs
)
def total_documents(
collection: Collection
) -> int:
"""Get total number of documents in database."""
return collection.count_documents(filter={})
def total_annotated(
collection: Collection
) -> int:
"""Get total number of annotated documents in database."""
query = {
"annotation": { "$ne": None }
}
return collection.count_documents(filter=query)
def get_visual_communication(
collection: Collection,
with_annotation: bool = False
) -> VisualCommunication:
"""Get a random visual communication from the database."""
query = {}
if with_annotation:
query["annotation"] = {"$ne": None}
else:
query["annotation"] = None
data = collection.aggregate([
{ "$match": query }, # find using filters
{ "$sample": { "size": 1 } } # get one random
])
data = list(data) # read data from cursor object
if len(data) == 0:
logging.error("failed getting visual communication")
raise NoDocumentFoundException()
data = data[0]
logging.info("finished")
return VisualCommunication.model_validate(data)
def upsert_predictions(
collection: Collection,
vis_com_name: str,
predictions: ModelOutputs,
) -> None:
"""Upsert prediction data in the database."""
query = {
"name": vis_com_name
}
update = {
"$set": { "prediction": predictions.model_dump() }
}
res = collection.update_one(
filter=query,
update=update,
upsert=True,
)
logging.debug("upserted document: %s", res)
logging.info("finished")
def upsert_annotations(
collection: Collection,
vis_com_name: str,
annotations: ModelOutputs,
) -> None:
"""Upserts annotation data in the database."""
query = {
"name": vis_com_name
}
update = {
"$set": { "annotation": annotations.model_dump() }
}
res = collection.update_one(
filter=query,
update=update,
upsert=True,
)
logging.info("upserted document: %s", res)
logging.info("finished")