add statistics-function for variable Final Energy [by Sector]|Agriculture

[maxnutz]

• workflow processes
• output is constant over all investment periods
• tests succeed
• latest version of master is merged into feature branch

Agriculture includes carriers ['agriculture electricity','agriculture heat','agriculture machinery', 'agriculture machinery oil'] evaluated on Load-Components.

The carriers could be easily identified with

carriers = list(n.loads[n.loads.index.str.contains("agriculture")].carrier.unique())

but as other functions are also based on hard-coded carrier names, it seems safer to also keep it static.

Summary by Sourcery

Add support for computing and exposing final energy consumption for the agriculture sector.

New Features:

• Introduce a statistics function to calculate agriculture-sector final energy from PyPSA networks.
• Expose the agriculture-sector final energy metric through the default mapping configuration.

Tests:

• Add a dedicated test suite validating the agriculture final energy statistics function for single and multiple networks.

[sourcery-ai]

Reviewer's Guide

Adds a new statistics function to compute final energy consumption for the agriculture sector, wires it into the mapping configuration, and introduces a focused test suite mirroring the existing transportation-sector tests.

Flow diagram for Final_Energy_by_Sector__Agriculture statistics function

flowchart TD
    Start([Start Final_Energy_by_Sector__Agriculture])
    InputN["Input n: pypsa.Network"]
    DefineCarriers["Define carriers = [agriculture electricity, agriculture heat, agriculture machinery electric, agriculture machinery oil]"]
    CallStats["Call n.statistics.energy_balance with\ncarrier=carriers\ngroupby=[carrier, unit, country]\ncomponents=Load\ndirection=withdrawal"]
    GroupSum["Group result by [country, unit]\nand sum over all carriers"]
    ReturnRes(["Return aggregated pd.Series res"]) 

    Start --> InputN --> DefineCarriers --> CallStats --> GroupSum --> ReturnRes

Loading

File-Level Changes

Change	Details	Files
Introduce Final_Energy_by_Sector__Agriculture statistics function for agriculture-sector final energy calculation.	Define Final_Energy_by_Sector__Agriculture taking a pypsa.Network and returning a pandas Series with MultiIndex ['country','unit']. Specify a static list of agriculture-related carriers and call n.statistics.energy_balance filtered by those carriers, grouped by ['carrier','unit','country'], component 'Load', and direction 'withdrawal'. Aggregate the energy balance by ['country','unit'] and return the summed result.	pypsa_validation_processing/statistics_functions.py
Register the new agriculture-sector statistics function in the default mapping configuration.	Add a mapping entry for 'Final Energy [by Sector]	Agriculture' that points to Final_Energy_by_Sector__Agriculture.
Add tests covering the new Final_Energy_by_Sector__Agriculture function.	Create TestFinalEnergyBySectorAgriculture test class mirroring the transportation tests for a single mock network and a mock network collection. Assert that the function returns a non-empty pandas Series with MultiIndex ['country','unit'], numeric values, and that it includes country 'AT'. Verify behavior across multiple networks by iterating over a MockNetworkCollection and checking the shape and types of the results.	tests/test_statistics_functions.py

Assessment against linked issues

Issue	Objective	Addressed	Explanation
#13	Add a new statistics function Final_Energy_by_Sector__Agriculture to statistics_functions.py, following existing naming/structural conventions and including a comprehensive docstring.	✅
#13	Add the mapping from `Final Energy [by Sector]	AgriculturetoFinal_Energy_by_Sector__Agriculture` in the default mapping configuration file.	✅
#13	Add a testing routine for Final_Energy_by_Sector__Agriculture under tests/ in line with the existing testing structure.	✅

Possibly linked issues

• #0: PR adds Final_Energy_by_Sector__Agriculture, its config mapping, and tests, directly implementing the issue’s requested feature.

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[sourcery-ai]

Hey - I've found 2 issues, and left some high level feedback:

• The docstring for Final_Energy_by_Sector__Agriculture still mentions "transportation sector" in the Returns description, which is misleading for this function and should be updated to refer to the agriculture sector.
• In Final_Energy_by_Sector__Agriculture the notes mention that agriculture machinery oil is also a carrier of Links and Buses, but the actual call uses components="Load"; consider either expanding the components argument or adjusting the note so it matches the implemented behavior.
• The test_numeric_values assertion can be simplified by directly using pd.api.types.is_numeric_dtype(result.dtype) instead of combining it with explicit checks against float and int, which are redundant for pandas dtypes.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- The docstring for `Final_Energy_by_Sector__Agriculture` still mentions "transportation sector" in the Returns description, which is misleading for this function and should be updated to refer to the agriculture sector.
- In `Final_Energy_by_Sector__Agriculture` the notes mention that `agriculture machinery oil` is also a carrier of Links and Buses, but the actual call uses `components="Load"`; consider either expanding the components argument or adjusting the note so it matches the implemented behavior.
- The `test_numeric_values` assertion can be simplified by directly using `pd.api.types.is_numeric_dtype(result.dtype)` instead of combining it with explicit checks against `float` and `int`, which are redundant for pandas dtypes.

## Individual Comments

### Comment 1
<location path="pypsa_validation_processing/statistics_functions.py" line_range="132-133" />
<code_context>
+
+    Notes
+    -----
+    Includes carriers ['agriculture electricity','agriculture heat','agriculture machinery electric',
+    'agriculture machinery oil'] executed on Load-Components. agriculture machinery oil is also carrier
+    of Links and Buses, as Demand is assued fixed. _Timeseries of Agriculture demand are assumed
+    to be constant in PyPSA-EUR._
</code_context>
<issue_to_address>
**question:** Docstring mentions additional components for 'agriculture machinery oil' but implementation only uses Load.

Since `n.statistics.energy_balance` is called with `components="Load"`, this metric excludes Link/Bus usage of `agriculture machinery oil`. Please either adjust the wording about Links/Buses to avoid implying they are included here, or explicitly note that only load-side demand is captured by this statistic.
</issue_to_address>

### Comment 2
<location path="pypsa_validation_processing/statistics_functions.py" line_range="130-135" />
<code_context>
+    Notes
+    -----
+    Includes carriers ['agriculture electricity','agriculture heat','agriculture machinery electric',
+    'agriculture machinery oil'] executed on Load-Components. agriculture machinery oil is also carrier
+    of Links and Buses, as Demand is assued fixed. _Timeseries of Agriculture demand are assumed
+    to be constant in PyPSA-EUR._
+    """
</code_context>
<issue_to_address>
**nitpick (typo):** Clean up spelling and capitalization in the docstring for clarity.

Specifically: change "assued" → "assumed", "Timeseries" → "time series", and capitalize "agriculture machinery oil" at the start of the sentence for consistency.

```suggestion
    Notes
    -----
    Includes carriers ['agriculture electricity','agriculture heat','agriculture machinery electric',
    'agriculture machinery oil'] executed on Load-Components. Agriculture machinery oil is also carrier
    of Links and Buses, as Demand is assumed fixed. _Time series of Agriculture demand are assumed
    to be constant in PyPSA-EUR._
```
</issue_to_address>

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}