Improve robustness of check_df and code refinements

.gitignore

@@ -1,9 +1,227 @@
-import_emission_factors/*__pycache__*
-import_emission_factors/mrio_models/*
-import_emission_factors/processed_mrio_resources/*
-import_emission_factors/output/*
-import_emission_factors/response_data/*
-import_emission_factors/API/*API_key.yaml
-!import_emission_factors/output/*import_factors_exiobase_2019*
-!import_emission_factors/output/aggregate*
-!import_emission_factors/output/import_shares_2019*
+# Standard python gitignore from https://github.com/github/gitignore/
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#   Usually these files are written by a python script from a template
+#   before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+*.lcov
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+# Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi/*
+!.pixi/config.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule*
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+# Temporary file for partial code execution
+tempCodeRunnerFile.py
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml
+
+# Add Devcontainer
+.devcontainer/
+.config/
+.idea/

import_emission_factors/README.md

@@ -64,7 +64,18 @@ The environmental flows fields are the same as those used for USEEIO which are f
 ## BEA API Access
 To make calls to BEA for service imports data (by BEA service category, country, and year), users must first register at https://apps.bea.gov/api/signup/.
 After doing so, users will be provided with an API key to the provided email.
-Store this as 'BEA_API_key.yaml' in the API subfolder of the import_emission_factors directory.
+
+Set the key as an environment variable before running scripts:
+
+- `BEA_API_KEY` (preferred)
+- `BEA_API_key` (backward compatible)
+
+Optional: use a local `.env` file in the repository root with:
+
+- `BEA_API_KEY=<your key>`
+- Install `python-dotenv` to auto-load `.env` values.
+
+Do not store API secrets in tracked files.
 
 ## Package requirements
 - pandas

import_emission_factors/download_imports_data.py

@@ -7,6 +7,7 @@
 import yaml
 import numpy as np
 import requests
+import os
 from pathlib import Path
 
 apiPath = Path(__file__).parent / 'API'
@@ -112,15 +113,38 @@ def create_Reqs(file, d, year):
     return reqs
 
 def get_api_key(file):
+    # Load .env values if python-dotenv is available.
     try:
-        with open(apiPath / f'{file}_key.yaml') as f:
-            api_key = yaml.safe_load(f)
-        return api_key
-    except FileNotFoundError:
-        raise FileNotFoundError(
-            f'API key required for {file}. Create the file '
-            f'"../import_emission_factors/API/{file}_key.yaml" and add your '
-            f'API key')
+        from dotenv import load_dotenv  # type: ignore
+        for env_path in (
+            Path(__file__).parent / '.env',
+            Path(__file__).parents[1] / '.env',
+        ):
+            if env_path.exists():
+                load_dotenv(dotenv_path=env_path, override=False)
+    except ImportError:
+        pass
+
+    env_var_candidates = list(dict.fromkeys([
+        file,
+        f'{file}_KEY',
+        f'{file}_key',
+        file.upper(),
+        f'{file.upper()}_KEY',
+        f'{file.upper()}_key',
+        file.lower(),
+        f'{file.lower()}_key',
+    ]))
+
+    for env_var in env_var_candidates:
+        api_key = os.getenv(env_var)
+        if api_key and api_key.strip():
+            return api_key.strip()
+
+    raise EnvironmentError(
+        f'API key required for {file}. Set an environment variable '
+        f'(for example: {file}, {file}_KEY, or {file}_key).'
+    )
 
 
 def complete_URLs(req_url, year, d):

import_emission_factors/generate_import_factors.py

@@ -148,8 +148,12 @@ def generate_import_emission_factors(years: list, schema=2012, calc_tiva=False):
         ##       is unable to distinguish and sort out mismatches by detail/
         ##       summary sectors.
         multiplier_df = df_prepare(multiplier_df, year)
-        check = (multiplier_df
-                 .query('Flow == @multiplier_df["Flow"][0]')
+        check_df = multiplier_df.copy()
+        if 'Flow' in check_df.columns:
+            check_df = check_df.query('Flow == @check_df["Flow"][0]')
+        elif 'Flowable' in check_df.columns:
+            check_df = check_df.query('Flowable == @check_df["Flowable"][0]')
+        check = (check_df
                  .groupby(['BEA Summary']).agg({'cntry_cntrb_to_national_summary':'sum'})
                  .rename(columns={'cntry_cntrb_to_national_summary': 'contrib'})
                  .query('contrib > 0 and contrib <= 0.9999')

pyproject.toml

@@ -0,0 +1,32 @@
+[project]
+name = "useeio"
+version = "0.1.0"
+description = "United States Environmentally-Extended Input-Output (USEEIO) Modeling Framework."
+readme = "README.md"
+requires-python = ">=3.12"
+dependencies = [
+  "bibtexparser",
+  "currencyconverter",
+  "esupy",
+  "fedelemflowlist",
+  "numpy",
+  "openpyxl",
+  "pandas",
+  "pymrio",
+  "pyyaml",
+  "requests",
+  "tqdm",
+]
+
+
+[dependency-groups]
+dev = [
+    "pytest>=8",
+]
+
+[tool.uv]
+exclude-newer = "1 week"
+
+[tool.uv.sources]
+fedelemflowlist = { git = "https://github.com/FLCAC-admin/fedelemflowlist", rev = "v1.3.1" }
+esupy = { git = "https://github.com/USEPA/esupy.git" }