Merge pull request #9 from SCAI-BIO/poetry-integration

Poetry integration

index/mapping.py

@@ -2,7 +2,7 @@
 import numpy as np
 
 from index.embedding import EmbeddingModel
-from index.parsing import MappingSource, DataDictionarySource, EmbeddingSource
+from index.process.parsing import MappingSource, DataDictionarySource, EmbeddingSource
 
 
 class Terminology:

index/process/ols.py

@@ -0,0 +1,2 @@
+OLS_BASE_URL = "https://www.ebi.ac.uk/ols4"
+

pyproject.toml

@@ -0,0 +1,40 @@
+[tool.poetry]
+name = "index"
+version = "0.0.1"
+description = "Intelligent data steward toolbox using Large Language Model embeddings for automated Data-Harmonization"
+authors = ["TimAdams84 <[email protected]>"]
+license = "Apache-2.0 license"
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = "^3.9"
+matplotlib = ">=3.8.1,<3.9.0"
+numpy = "1.25.2"
+openai = ">=0.28.0,<0.29.0"
+openpyxl = "^3.1.2"
+pandas = "2.1.0"
+pip = "21.3.1"
+plotly = ">=5.17.0,<5.18.0"
+python-dateutil = "2.8.2"
+python-dotenv = ">=1.0.0,<1.1.0"
+pytz = "2023.3"
+seaborn = ">=0.13.0,<0.14.0"
+sentence-transformers = "2.3.1"
+setuptools = "60.2.0"
+scikit-learn = "1.3.2"
+six = "1.16.0"
+thefuzz = ">=0.20.0,<0.21.0"
+tzdata = "2023.3"
+wheel = "0.37.1"
+aiofiles = ">=0.7.0,<0.8.0"
+uvicorn = ">=0.15.0"
+python-multipart = "^0.0.9"
+fastapi = ">=0.87.0,<0.88.0"
+sqlalchemy = ">=2.0.27,<2.1.0"
+starlette = ">=0.21.0,<0.22.0"
+scipy = ">=1.11.4,<1.12.0"
+
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

tests/test_evaluation.py

@@ -5,7 +5,7 @@
 
 from index.evaluation import match_closest_descriptions, MatchingMethod, enrichment_analysis, score_mappings
 from index.mapping import MappingTable
-from index.parsing import MappingSource, DataDictionarySource
+from index.process.parsing import MappingSource, DataDictionarySource
 
 
 class Test(TestCase):

tests/test_parser.py

@@ -2,7 +2,7 @@
 from unittest import TestCase
 
 from index.mapping import MappingTable
-from index.parsing import MappingSource, DataDictionarySource
+from index.process.parsing import MappingSource, DataDictionarySource
 
 
 class Test(TestCase):

tests/test_visualisation.py

@@ -4,9 +4,8 @@
 import numpy as np
 import pandas as pd
 
-from index.evaluation import evaluate
 from index.mapping import MappingTable
-from index.parsing import MappingSource, DataDictionarySource
+from index.process.parsing import MappingSource, DataDictionarySource
 from index.visualisation import scatter_plot_two_distributions, enrichment_plot, scatter_plot_all_cohorts, \
     bar_chart_average_acc_two_distributions