Merge pull request #10 from tanishq-ids/relevance_detector

push with code for relevance detector

.coveragerc

@@ -10,6 +10,7 @@ source =
     */site-packages/
 
 [report]
+skip_empty = true
 # Regexes for lines to exclude from consideration
 exclude_lines =
     # Have to re-enable the standard pragma

pyproject.toml

@@ -25,6 +25,14 @@ classifiers = [
   "Topic :: Scientific/Engineering",
   "Topic :: Software Development",
 ]
+dependencies = [
+    "torch>=2.2.2",
+    "pandas>=2.2.2",
+    "tokenizers>=0.19.1",
+    "ipykernel>=6.29.4",
+    "transformers>=4.40.0",
+    "pre-commit>=3.7.0",
+]
 
 [project.urls]
 Homepage = "https://github.com/os-climate/osc-transformer-based-extractor"
@@ -61,14 +69,14 @@ test = [
 [tool.pdm.scripts]
 pre_release = "scripts/dev-versioning.sh"
 release = "scripts/release-versioning.sh"
-test = "pytest"
+test = ["pdm[pytest]", "pytest-cov"]
 tox = "tox"
 docs = { shell = "cd docs && mkdocs serve", help = "Start the dev server for doc preview" }
 lint = "pre-commit run --all-files"
 complete = { call = "tasks.complete:main", help = "Create autocomplete files for bash and fish" }
 
 [tool.pdm.dev-dependencies]
-test = ["pdm[pytest]", "pytest", "pytest-cov"]
+test = ["pdm[pytest]", "pytest-cov"]
 tox = ["tox", "tox-pdm>=0.5"]
 docs = ["sphinx>=7.2.6", "sphinx-copybutton>=0.5.2"]
 dev = ["tox>=4.11.3", "tox-pdm>=0.7.0"]

src/relevance_detector/OSC/kpi_mapping.csv

@@ -0,0 +1,25 @@
+kpi_id,question,sectors,add_year,kpi_category,,
+0,What is the company name?,"OG, CM, CU",FALSE,TEXT,,
+1,In which year was the annual report or the sustainability report published?,"OG, CM, CU",FALSE,TEXT,,
+2,What is the total volume of proven and probable hydrocarbons reserves?,OG,TRUE,"TEXT, TABLE",,
+2.1,What is the volume of estimated proven hydrocarbons reserves?,OG,TRUE,"TEXT, TABLE",,
+2.2,What is the volume of estimated probable hydrocarbons reserves?,OG,TRUE,"TEXT, TABLE",,
+3,What is the total volume of hydrocarbons production?,OG,TRUE,"TEXT, TABLE",,
+3.1,What is the total volume of crude oil liquid production?,OG,TRUE,"TEXT, TABLE",,
+3.2,What is the total volume of natural gas liquid production?,OG,TRUE,"TEXT, TABLE",,
+3.3,What is the total volume of natural gas production?,OG,TRUE,"TEXT, TABLE",,
+4,What is the annual total production from coal?,CU,TRUE,"TEXT, TABLE",,
+4.1,What is the annual total production from lignite (brown coal)?,CU,TRUE,"TEXT, TABLE",,
+4.2,What is the annual total production from hard coal?,CU,TRUE,"TEXT, TABLE",,
+5,What is the total installed capacity from coal?,CU,TRUE,"TEXT, TABLE",,
+5.1,What is the total installed capacity from lignite (brown coal)?,CU,TRUE,"TEXT, TABLE",,
+5.2,What is the total installed capacity from hard coal?,CU,TRUE,"TEXT, TABLE",,
+6,What is the total amount of direct greenhouse gases emissions referred to as scope 1 emissions?,"CU, OG",TRUE,"TEXT, TABLE",,
+7,What is the total amount of energy indirect greenhouse gases emissions referred to as scope 2 emissions?,"CU, OG",TRUE,"TEXT, TABLE",,
+8,What is the total amount of upstream energy indirect greenhouse gases emissions referred to as scope 3 emissions?,"CU, OG",TRUE,"TEXT, TABLE",,
+9,What is the base year for carbon reduction commitment?,"OG, CM, CU",FALSE,"TEXT, TABLE",,
+10,What is the climate commitment scenario considered?,"OG, CM, CU",TRUE,TEXT,,
+11,What is the target year for climate commitment?,"OG, CM, CU",FALSE,TEXT,,
+12,What is the target carbon reduction in percentage?,"OG, CM, CU",TRUE,TEXT,,
+13,What is the total amount of scope 1 and 2 greenhouse gases emissions?,CU,TRUE,"TEXT, TABLE",,
+14,"What is the total amount of scope 1, scope 2 and scope 3 greenhouse gases emissions?",OG,TRUE,"TEXT, TABLE",,