Modernize repository, add tests, and update version

.pre-commit-config.yaml

@@ -0,0 +1,7 @@
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.5.5
+    hooks:
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix]
+      - id: ruff-format

CHANGELOG.md

@@ -1,4 +1,13 @@
 # Changelog
+## 0.10.0 (2025-11-18)
+- Modernized the repository by migrating to `uv` for dependency management and `Ruff` for code formatting and linting.
+- Replaced `setup.cfg` with a modern `pyproject.toml` using `hatchling`.
+- Defined all project dependencies in `pyproject.toml`.
+- Generated a `uv.lock` file for reproducible environments.
+- Added a `.pre-commit-config.yaml` to run `Ruff` automatically.
+- Formatted the entire codebase with `Ruff`.
+- Updated versioning to use `importlib.metadata`.
+
 ## 0.9.0 (2022-07-25)
 - Files containing CFs information are now stored in .yaml format (instead of .xlsx)
   - `add_aesa_pbs()` still reads .xlsx files, which are generated in the background on execution with the help of the functionality added by the `DataConverter` class

pyproject.toml

@@ -1,7 +1,49 @@
 [build-system]
-requires = [
-    "setuptools>=58",
-    "wheel",
-    "bw2io >= 0.8.6",
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "aesa_pbs"
+version = "0.10.0"
+authors = [
+    { name = "Victor Tulus", email = "vtulus@ethz.ch" },
 ]
-build-backend = "setuptools.build_meta"
+description = "Implementation of Absolute Environmental Sustainability Assessment (AESA) methods in brightway"
+readme = "README.md"
+license = { file = "LICENSE" }
+requires-python = ">=3.8"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: BSD License",
+    "Operating System :: Microsoft :: Windows",
+    "Topic :: Scientific/Engineering",
+    "Topic :: Scientific/Engineering :: Mathematics",
+    "Topic :: Scientific/Engineering :: Information Analysis",
+]
+dependencies = [
+    "brightway2",
+    "bw2io",
+    "bw2data",
+    "prettytable",
+    "pandas",
+    "PyYAML",
+    "openpyxl",
+]
+
+[project.urls]
+"Homepage" = "https://github.com/vtulus/AESAmethods"
+
+[project.optional-dependencies]
+test = [
+    "pytest",
+    "pytest-cov",
+]
+
+[tool.ruff]
+line-length = 88
+
+[tool.ruff.lint]
+select = ["E", "F", "W"]
+
+[tool.ruff.format]
+quote-style = "double"

src/aesa_pbs/__init__.py

@@ -1,3 +1,5 @@
+import importlib.metadata
+
 __all__ = [
     "add_aesa_pbs",
     "get_nitrogenous_fertilizers",
@@ -6,11 +8,12 @@
     "DataConverter",
 ]
 
+__version__ = importlib.metadata.version("aesa_pbs")
+
 from .aesa_pbs import add_aesa_pbs
 from .n_direct_fixation import (
     get_nitrogenous_fertilizers,
     remove_nitrogen_fertilizer_exchanges,
     update_nitrogen_fertilizer_exchanges,
 )
 from .data_converter import DataConverter
-from .version import __version__

src/aesa_pbs/aesa_pbs.py

@@ -8,13 +8,14 @@
 
 from .biosphere import get_biosphere_database
 from .data_converter import DataConverter
-from .version import __version__
+from . import __version__
 
 DATA_DIR = Path(__file__).resolve().parent / "data"
 DATA_EXCELS = Path(DATA_DIR).resolve() / "excels"
 
 
-# write_methods() does not write metadata other than "description", "unit" and "filename"
+# write_methods() does not write metadata other than "description",
+# "unit" and "filename"
 # store everything in the description using json.dumps()
 # later can be retrieved with json.loads()
 def add_aesa_pbs(verbose=True):
@@ -189,7 +190,10 @@ def add_aesa_pbs(verbose=True):
             "Tg N",
             json.dumps(
                 {
-                    "overview": "direct quantification of industrial and intentional biological fixation of N fertilizer",
+                    "overview": (
+                        "direct quantification of industrial and intentional"
+                        " biological fixation of N fertilizer"
+                    ),
                     "authors": MAINTAINER,
                     "doi": None,
                     "current_version": "v" + __version__,
@@ -204,7 +208,10 @@ def add_aesa_pbs(verbose=True):
             "% forested land",
             json.dumps(
                 {
-                    "overview": "Unit: area of forested land as % of original forest cover",
+                    "overview": (
+                        "Unit: area of forested land as % of original forest"
+                        " cover"
+                    ),
                     "authors": RYBERG_ET_AL,
                     "doi": DOI_RYBERG,
                     "current_version": "v" + __version__,
@@ -219,7 +226,10 @@ def add_aesa_pbs(verbose=True):
             "km3",
             json.dumps(
                 {
-                    "overview": "Unit: Maximum amount of consumptive blue water use per year",
+                    "overview": (
+                        "Unit: Maximum amount of consumptive blue water use per"
+                        " year"
+                    ),
                     "authors": RYBERG_ET_AL,
                     "doi": DOI_RYBERG,
                     "current_version": "v" + __version__,
@@ -352,9 +362,9 @@ def add_aesa_pbs(verbose=True):
             )
 
         # confirm that everything is correctly linked
-        assert (
-            len(list(method.unlinked)) == 0
-        ), f"{cat[0]} method contains unlinked flows. Method could not be installed."
+        assert len(list(method.unlinked)) == 0, (
+            f"{cat[0]} method contains unlinked flows. Method could not be installed."
+        )
 
         # write method
         method.write_methods(overwrite=True, verbose=verbose)
@@ -375,8 +385,13 @@ def add_aesa_pbs(verbose=True):
 
 
 # refs
-RYBERG_ET_AL = "Ryberg, M. W.; Owsianiak, M.; Richardson, K.; Hauschild, M. Z."
-GALAN_ET_AL = "Galán-Martín, Á.; Tulus, V.; Díaz, I.; Pozo, C.; Pérez-Ramírez, J.; Guillén-Gosálbez, G."
+RYBERG_ET_AL = (
+    "Ryberg, M. W.; Owsianiak, M.; Richardson, K.; Hauschild, M. Z."
+)
+GALAN_ET_AL = (
+    "Galán-Martín, Á.; Tulus, V.; Díaz, I.; Pozo, C.; Pérez-Ramírez, J.;"
+    " Guillén-Gosálbez, G."
+)
 DOI_RYBERG = "https://doi.org/10.1016/j.ecolind.2017.12.065"
 DOI_GALAN = "https://doi.org/10.1016/j.oneear.2021.04.001"
 MAINTAINER = "Tulus, V."
@@ -396,8 +411,7 @@ def drop_empty_lines(data):
 
 # TODO: substitute the print with logging?
 def warning_directly_fixated_n() -> None:
-    """Printing a warning regarding a missing database.
-    """
+    """Printing a warning regarding a missing database."""
     message = PrettyTable(["Warning"])
     message.add_row(
         [

src/aesa_pbs/biosphere.py

@@ -1,6 +1,10 @@
 import bw2data as bd
 
+
 def get_biosphere_database():
-    ERROR = "AESA methods work with ecoinvent biosphere flows only. Install base ecoinvent data."
+    ERROR = (
+        "AESA methods work with ecoinvent biosphere flows only. Install base"
+        " ecoinvent data."
+    )
     assert "biosphere3" in bd.databases, ERROR
-    return list(bd.Database("biosphere3"))
+    return list(bd.Database("biosphere3"))

src/aesa_pbs/data_converter.py

@@ -74,7 +74,8 @@ def to_yaml(self, outfilepath: str = None, verbose=True) -> None:
         Parameters
         ----------
         outfilepath : str, optional
-            Absolute file path. If None is provided, uses input file name and default directory.
+            Absolute file path. If None is provided, uses input file name
+            and default directory.
         verbose : bool, optional
             Print completion message, by default True
         """
@@ -107,7 +108,8 @@ def to_excel(self, outfilepath: str = None, verbose=True) -> None:
         Parameters
         ----------
         outfilepath : str, optional
-            Absolute file path. If None is provided, uses input file name and default directory.
+            Absolute file path. If None is provided, uses input file name
+            and default directory.
         verbose : bool, optional
             Print completion message, by default True
         """
@@ -138,9 +140,10 @@ def _validate_extension(filepath: str, extension: str) -> None:
     extension : str
         Desired extension of the file.
     """
-    assert (
-        Path(filepath).suffix == extension
-    ), f"Filepath extension ('{Path(filepath).suffix}') is not valid. Must be '{extension}'."
+    assert Path(filepath).suffix == extension, (
+        f"Filepath extension ('{Path(filepath).suffix}') is not valid. Must be"
+        f" '{extension}'."
+    )
 
 
 def _sanitize(data: pd.DataFrame, filename: str) -> pd.DataFrame:
@@ -160,9 +163,9 @@ def _sanitize(data: pd.DataFrame, filename: str) -> pd.DataFrame:
     pd.DataFrame
         Sanitized data without missing values, nor duplicates
     """
-    assert {"name", "categories", "amount"}.issubset(
-        data.columns
-    ), "Data must contain 'name', 'categories' and 'amount' column labels."
+    assert {"name", "categories", "amount"}.issubset(data.columns), (
+        "Data must contain 'name', 'categories' and 'amount' column labels."
+    )
     data = data[["name", "categories", "amount"]]  # the extra columns are dropped
 
     # "amount" column should have only numeric values,
@@ -233,19 +236,28 @@ def _remove_duplicates(data: pd.DataFrame, filename: str) -> pd.DataFrame:
     ValueError
         If the resulting DataFrame is empty
     """
-    duplicates = data[
-        data.duplicated(subset=["name", "categories", "amount"], keep="first")
-    ]
+    # Create a temporary series with string-ified categories for duplicate check
+    categories_as_str = data["categories"].astype(str)
+
+    # Identify duplicates based on the original columns, but using the stringified
+    # categories
+    is_duplicated = data.assign(categories=categories_as_str).duplicated(
+        subset=["name", "categories", "amount"], keep="first"
+    )
+
+    duplicates = data[is_duplicated]
     if duplicates.empty:
         clean_data = data
     else:
-        message_duplicate = f"Duplicated flows found in {filename} (see below):\n"
+        message_duplicate = (
+            f"Duplicated flows found in {filename} (see below):\n"
+        )
         message_duplicate += duplicates.to_markdown(
             index=False, tablefmt="pretty", stralign="left"
         )
         message_duplicate += "\nNote: All duplicates will be removed.\n"
         logging.warning(message_duplicate)
-        clean_data = data.drop_duplicates(keep="first", ignore_index=True)
+        clean_data = data[~is_duplicated].reset_index(drop=True)
     if clean_data.empty:
         raise ValueError(f"Data in {filename} is not valid.")
     return clean_data

src/aesa_pbs/n_direct_fixation.py

@@ -5,7 +5,7 @@ def get_nitrogenous_fertilizers(db_name: str) -> list:
     """Get list of nitrogenous fertilizers
 
     Get all activities classified according to CPC as
-    "Class 3461: Mineral of chemical fertilizers, nitrogenous", 
+    "Class 3461: Mineral of chemical fertilizers, nitrogenous",
     except "market"-type activities
 
     Parameters
@@ -30,7 +30,7 @@ def get_nitrogenous_fertilizers(db_name: str) -> list:
 
 
 def update_nitrogen_fertilizer_exchanges(activities: list, show_updated=True) -> None:
-    """Create exchanges for 'nitrogen fertilizer' in `activities` if they don't exist already.
+    """Create new exchanges for 'nitrogen fertilizer' in `activities`.
 
     Does not return anything, but modified `activities` inplace.
 
@@ -100,7 +100,8 @@ def is_exchange(exc):
         )
 
     print(
-        "Cleaning 'nitrogen fertilizer' exchanges from the activities that produce nitrogen fertilizer..."
+        "Cleaning 'nitrogen fertilizer' exchanges from the activities that produce"
+        " nitrogen fertilizer..."
     )
     cleaned_act = set()
     for act in activities:
@@ -110,7 +111,8 @@ def is_exchange(exc):
                 cleaned_act.add(act)
     if show_cleaned:
         print(
-            f"These {len(cleaned_act)} activities have been cleaned: \n{list(cleaned_act)}."
+            f"These {len(cleaned_act)} activities have been cleaned:"
+            f" \n{list(cleaned_act)}."
         )
     else:
         print(f"{len(cleaned_act)} activities have been cleaned.")

src/aesa_pbs/utils/utils.py

@@ -59,7 +59,7 @@ def progressbar(itobj: list, **kwargs):
     ----------
     itobj : list-like
         Iterable object
-        
+
     **kwargs
     --------
     total : int, default len(itobj)
@@ -74,11 +74,13 @@ def progressbar(itobj: list, **kwargs):
         str-like symbol to be used as "done"-icon
     icon_todo : str, default "🔳"
         str-like symbol to be used as "to do"-icon
-        
+
     Example
     -------
     lst = [5, 3, 4]
-    for i in progressbar(itobj=lst, total=len(lst), prefix="Progress: ", size=5, unit="datapoint"):
+    for i in progressbar(
+        itobj=lst, total=len(lst), prefix="Progress: ", size=5, unit="datapoint"
+    ):
         # do_something
     """
     start_time = datetime.now()
@@ -111,7 +113,8 @@ def show(j):
         # some ASCII symbol or emoji alternatives
 
         # |, *, #, %, ▒. ▓, █, ■, ♢, ⚃ ⚄ ⚅
-        # 🦾, 👍, 🔴, 🟡 🟢 🔵 🟣 ⚫️ ⚪️, 🔸 🔹 🔶 🔷 🔳 🔲 ▪️ ▫️ ◾️ ◽️ ◼️ ◻️ 🟥 🟧 🟨 🟩 🟦 🟪 ⬛️ ⬜️, ▶️
+        # 🦾, 👍, 🔴, 🟡 🟢 🔵 🟣 ⚫️ ⚪️, 🔸 🔹 🔶 🔷 🔳 🔲 ▪️ ▫️ ◾️ ◽️ ◼️ ◻️ 🟥 🟧 🟨 🟩
+        # 🟦 🟪 ⬛️ ⬜️, ▶️
 
         file.write(
             "%s[%s%s] %i/%i %s\r"