Skip to content

Commit

Permalink
General cleanup: docs, code optimization, and project structure (#411)
Browse files Browse the repository at this point in the history
  • Loading branch information
caufieldjh authored Jul 19, 2024
2 parents 399dd22 + 1cb4563 commit 1ac2f36
Show file tree
Hide file tree
Showing 2,134 changed files with 811 additions and 142,598 deletions.
2 changes: 2 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,7 @@
# OntoGPT

![OntoGPT Logo](/images/ontogpt_logo_3.jpg)

[![DOI](https://zenodo.org/badge/13996/monarch-initiative/ontogpt.svg)](https://zenodo.org/badge/latestdoi/13996/monarch-initiative/ontogpt)
![PyPI](https://img.shields.io/pypi/v/ontogpt)

Expand Down
612 changes: 0 additions & 612 deletions disease_cp_output.yaml

This file was deleted.

Binary file added images/ontogpt_logo_3.jpg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
2,873 changes: 0 additions & 2,873 deletions long_output.yaml

This file was deleted.

2 changes: 0 additions & 2 deletions notebooks/Makefile

This file was deleted.

2 changes: 1 addition & 1 deletion notebooks/Quick-Examples.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"Last updated May 28, 2024"
"Last updated Jul 19, 2024"
]
},
{
Expand Down
File renamed without changes.
File renamed without changes.
106 changes: 106 additions & 0 deletions notebooks/output1.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,106 @@
---
input_text: Spain is a significant contributor to the global agricultural sector,
with its primary exports demonstrating the country's diverse climate and agricultural
capacity. The nation leads the world in olive oil production and export, renowned
for its quality. Spain is also one of the top wine producers globally, with notable
regions including Rioja and Ribera del Duero. It exports a wide range of fruits,
particularly citrus fruits such as oranges and lemons from Valencia, as well as
peaches, strawberries, melons, and apples. Vegetable exports are substantial, with
tomatoes, peppers, cucumbers, and lettuce being predominant, especially from the
Almería region known for its greenhouse production. Spain is recognized for its
premium pork products, notably jamón ibérico and jamón serrano, and is a leading
exporter of nuts, particularly almonds and hazelnuts. Additionally, Spain exports
significant quantities of fish and seafood, including sardines, tuna, and shrimp,
facilitated by its extensive coastline and fishing traditions.
raw_completion_output: |-
terms: Olive oil;Wine;Citrus fruits;Oranges;Lemons;Peaches;Strawberries;Melons;Apples;Tomatoes;Peppers;Cucumbers;Lettuce;Pork products;Jamón ibérico;Jamón serrano;Nuts;Almonds;Hazelnuts;Fish;Seafood;Sardines;Tuna;Shrimp
label: Spain
prompt: |+
From the text below, extract the following entities in the following format:
terms: <A semicolon-separated list of any Food Ontology terms.>
label: <The label (name) of the named thing>
Text:
Spain is a significant contributor to the global agricultural sector, with its primary exports demonstrating the country's diverse climate and agricultural capacity. The nation leads the world in olive oil production and export, renowned for its quality. Spain is also one of the top wine producers globally, with notable regions including Rioja and Ribera del Duero. It exports a wide range of fruits, particularly citrus fruits such as oranges and lemons from Valencia, as well as peaches, strawberries, melons, and apples. Vegetable exports are substantial, with tomatoes, peppers, cucumbers, and lettuce being predominant, especially from the Almería region known for its greenhouse production. Spain is recognized for its premium pork products, notably jamón ibérico and jamón serrano, and is a leading exporter of nuts, particularly almonds and hazelnuts. Additionally, Spain exports significant quantities of fish and seafood, including sardines, tuna, and shrimp, facilitated by its extensive coastline and fishing traditions.
===
extracted_object:
id: c2a2b5c7-c262-46b7-a3d7-a733a5a83c7a
label: Spain
terms:
- FOODON:03301826
- AUTO:Wine
- FOODON:00003324
- FOODON:03315106
- FOODON:03315104
- FOODON:03315502
- FOODON:00003443
- FOODON:00003597
- FOODON:00002473
- FOODON:03301453
- FOODON:00003520
- FOODON:00003415
- FOODON:00001998
- AUTO:Pork%20products
- AUTO:Jam%C3%B3n%20ib%C3%A9rico
- AUTO:Jam%C3%B3n%20serrano
- FOODON:03303171
- FOODON:00003523
- FOODON:00002933
- FOODON:03411222
- AUTO:Seafood
- FOODON:03411558
- FOODON:03411269
- FOODON:03411237
named_entities:
- id: FOODON:03301826
label: Olive oil
- id: AUTO:Wine
label: Wine
- id: FOODON:00003324
label: Citrus fruits
- id: FOODON:03315106
label: Oranges
- id: FOODON:03315104
label: Lemons
- id: FOODON:03315502
label: Peaches
- id: FOODON:00003443
label: Strawberries
- id: FOODON:00003597
label: Melons
- id: FOODON:00002473
label: Apples
- id: FOODON:03301453
label: Tomatoes
- id: FOODON:00003520
label: Peppers
- id: FOODON:00003415
label: Cucumbers
- id: FOODON:00001998
label: Lettuce
- id: AUTO:Pork%20products
label: Pork products
- id: AUTO:Jam%C3%B3n%20ib%C3%A9rico
label: Jamón ibérico
- id: AUTO:Jam%C3%B3n%20serrano
label: Jamón serrano
- id: FOODON:03303171
label: Nuts
- id: FOODON:00003523
label: Almonds
- id: FOODON:00002933
label: Hazelnuts
- id: FOODON:03411222
label: Fish
- id: AUTO:Seafood
label: Seafood
- id: FOODON:03411558
label: Sardines
- id: FOODON:03411269
label: Tuna
- id: FOODON:03411237
label: Shrimp
175 changes: 175 additions & 0 deletions notebooks/output2.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,175 @@
---
input_text: Zambia and the DR Congo are situated in the central African Copperbelt,
which is part of the Lufilian geological structure arc stretching over from Kolwezi
in Katanga Province in the DRC to Luanshya in Copperbelt Province in Zambia. The
area has large copper-cobalt deposits of which the extraction causes severe ecosystem
damage due to pollution of water, food crops, and the ambient air negatively impacting
population health. Contamination of drinking water for domestic use and foods (cereals,
roots and tubers, vegetables, and fruits) was determined by assessing the contents
of trace metals including Mn, Ni, Pb, Zn, Co, As, U, Cd, and Cu and through a questionnaire
for environmental damage. Food samples were analyzed by inductively coupled argon
plasma/optical emission spectroscopy (ICP-OES), while water and urine samples were
analyzed by inductively coupled argon plasma mass spectrometry (ICP-MS). Concentrations
of Ni, Pb, and Cd were higher in almost all food crops, although Cu was more in
samples of Cucurbita maxima and Amaranthus hybridus. Mean contents (μg/L) of Mn,
Zn, Cd, Pb, and U were, respectively, 5,454.6, 2552.2, 138.7, 39.7, 2361.1, and
21.4 in the DRC and 108.9, 543.3, 0.3, 0.2, 1.5, and 0.5 in Zambia, being significantly
higher and always far above World Health Organization maximum limits in the DRC.
Urine samples taken only from the DRC contained trace metals with children's samples
being more contaminated than adult ones. Our results conclusively echo the most
critical challenges of toxic pollutants causing numerous health issues among the
population. Given an outcry among households adjacent to mines about land degradation
and food spoilage, and health problems over years, joint efforts are needed from
public and private sectors for stringent mining exploitation monitoring for sustainable
governance to protect the environment and ensure food and nutrition safety, and
population well-being in Zambia and the DR Congo.
raw_completion_output: |-
location: Kolwezi;Katanga Province;Luanshya;Copperbelt Province
environmental_material: water;food crops;ambient air;drinking water;cereals;roots and tubers;vegetables;fruits;food samples;urine samples
environments: Copperbelt;Lufilian geological structure arc
causal_relationships: effect of extraction on ecosystem damage;effect of pollution on population health;effect of trace metals on contamination of drinking water and foods;effect of pollutants on health issues
variables: Mn;Ni;Pb;Zn;Co;As;U;Cd;Cu;toxic pollutants;health issues;land degradation;food spoilage;children's samples;adult samples
measurements: Mn-5454.6 μg/L;Zn-2552.2 μg/L;Cd-138.7 μg/L;Pb-39.7 μg/L;U-2361.1 μg/L;Mn-108.9 μg/L;Zn-543.3 μg/L;Cd-0.3 μg/L;Pb-0.2 μg/L;U-1.5 μg/L;U-0.5 μg/L
prompt: |+
Split the following piece of text into fields in the following format:
value: <the value of the measurement>
unit: <the unit of the measurement>
Text:
U-0.5 μg/L
===
extracted_object:
location:
- AUTO:Kolwezi
- AUTO:Katanga%20Province
- AUTO:Luanshya
- GAZ:00009425
environmental_material:
- ENVO:00002006
- ENVTHES:20523
- ENVTHES:23
- ENVO:00003064
- AUTO:cereals
- AUTO:roots%20and%20tubers
- AUTO:vegetables
- ENVTHES:20576
- ENVTHES:20523
- ENVTHES:10152
environments:
- AUTO:Copperbelt
- ENVTHES:10358
causal_relationships:
- cause: AUTO:extraction
effect: ENVO:01001110
- cause: ENVO:02500036
effect: ENVTHES:20715
- cause: ENVO:01001069
effect: ENVO:00003064
- cause: ENVTHES:20893
effect: AUTO:health%20issues
variables:
- AUTO:Mn
- AUTO:Ni
- AUTO:Pb
- AUTO:Zn
- AUTO:Co
- AUTO:As
- AUTO:U
- AUTO:Cd
- AUTO:Cu
- ENVTHES:20893
- AUTO:health%20issues
- ENVO:02500005
- ENVTHES:20523
- ENVTHES:10152
- ENVTHES:10152
measurements:
- value: '5454.6'
unit: AUTO:%CE%BCg/L
- value: '2552.2'
unit: AUTO:%CE%BCg/L
- value: '39.7'
unit: AUTO:%CE%BCg/L
- value: '2361.1'
unit: AUTO:%CE%BCg/L
- value: '108.9'
unit: AUTO:%CE%BCg/L
- value: '0.3'
unit: AUTO:%CE%BCg/L
- value: '0.2'
unit: AUTO:%CE%BCg/L
- value: '1.5'
unit: AUTO:%CE%BCg/L
- value: '0.5'
unit: AUTO:%CE%BCg/L
named_entities:
- id: AUTO:Kolwezi
label: Kolwezi
- id: AUTO:Katanga%20Province
label: Katanga Province
- id: AUTO:Luanshya
label: Luanshya
- id: GAZ:00009425
label: Copperbelt Province
- id: ENVO:00002006
label: water
- id: ENVTHES:20523
label: food crops
- id: ENVTHES:23
label: ambient air
- id: ENVO:00003064
label: drinking water
- id: AUTO:cereals
label: cereals
- id: AUTO:roots%20and%20tubers
label: roots and tubers
- id: AUTO:vegetables
label: vegetables
- id: ENVTHES:20576
label: fruits
- id: ENVTHES:10152
label: urine samples
- id: AUTO:Copperbelt
label: Copperbelt
- id: ENVTHES:10358
label: Lufilian geological structure arc
- id: AUTO:extraction
label: extraction
- id: ENVO:01001110
label: ecosystem damage
- id: ENVO:02500036
label: pollution
- id: ENVTHES:20715
label: population health
- id: ENVO:01001069
label: trace metals
- id: ENVTHES:20893
label: pollutants
- id: AUTO:health%20issues
label: health issues
- id: AUTO:Mn
label: Mn
- id: AUTO:Ni
label: Ni
- id: AUTO:Pb
label: Pb
- id: AUTO:Zn
label: Zn
- id: AUTO:Co
label: Co
- id: AUTO:As
label: As
- id: AUTO:U
label: U
- id: AUTO:Cd
label: Cd
- id: AUTO:Cu
label: Cu
- id: ENVO:02500005
label: land degradation
- id: AUTO:%CE%BCg/L
label: μg/L
Loading

0 comments on commit 1ac2f36

Please sign in to comment.