def generate_nutrition_image_insights():
logger.info("Starting nutrition image insight generation")
logger.info("Deleting previous nutrition image insights...")
deleted = (ProductInsight.delete().where(
ProductInsight.annotation.is_null(),
ProductInsight.type == InsightType.nutrition_image.name,
ProductInsight.server_domain == settings.OFF_SERVER_DOMAIN,
).execute())
logger.info("{} insights deleted".format(deleted))
product_store: DBProductStore = get_product_store()
added = 0
seen_set: Set[str] = set()
latent_insight: ProductInsight
for latent_insight in (ProductInsight.select().where(
ProductInsight.type == InsightType.nutrient_mention.name).order_by(
ProductInsight.source_image.desc()).iterator()):
barcode = latent_insight.barcode
if barcode in seen_set:
continue
mentions = latent_insight.data["mentions"]
nutrition_image_langs = find_nutrition_image_lang(mentions)
if not nutrition_image_langs:
continue
image_id = get_image_id(latent_insight.source_image)
rotation = get_image_orientation(barcode, image_id)
if rotation is None:
continue
product = product_store.get_product(barcode, ["images"])
if product is None:
continue
images = product.get("images", {})
if not has_nutrition_image(images):
for lang in nutrition_image_langs:
if not (ProductInsight.select().where(
ProductInsight.type
== InsightType.nutrition_image.name,
ProductInsight.barcode == barcode,
ProductInsight.value_tag == lang,
ProductInsight.server_domain
== settings.OFF_SERVER_DOMAIN,
).count()):
ProductInsight.create_from_latent(
latent_insight,
type=InsightType.nutrition_image.name,
value_tag=lang,
data={
"from_latent": str(latent_insight.id),
"languages": nutrition_image_langs,
"rotation": rotation or None,
},
id=str(uuid.uuid4()),
)
added += 1
logger.info("Added: {}".format(added))
timestamp = peewee.DateTimeField(null=True)
value_tag = peewee.TextField(null=True, index=True)
value = peewee.TextField(null=True, index=True)
source_image = peewee.TextField(null=True, index=True)
server_domain = peewee.TextField(
null=True, help_text="server domain linked to the insight", index=True)
server_type = peewee.CharField(
null=True,
max_length=10,
help_text="project associated with the server_domain, "
"one of 'off', 'obf', 'opff', 'opf'",
index=True,
)
insight_types = [
InsightType.image_lang.name,
InsightType.image_orientation.name,
InsightType.nutrient_mention.name,
InsightType.nutrient.name,
]
moved = 0
for insight in tqdm.tqdm(LatentProductInsight.select().where(
LatentProductInsight.type.in_(insight_types)).iterator()):
ProductInsight.create_from_latent(insight)
moved += 1
print("{} insights moved".format(moved))