fix:ruff

Author: Dinghye

CHANGELOG.md

@@ -26,6 +26,7 @@ This release rolls up upstream-alignment work and correctness fixes that may cha
 ### Changed
 
 - Standardised NumPy docstrings across all public functions and classes in `export.py`, `inspect.py`, `writers.py`, and the `tools/` and `providers/` layers. No behaviour changes.
+
 ### Added
 
 - Versioned documentation with a version selector powered by `mike` and MkDocs Material. Each release tag deploys a pinned version; pushes to `main` update a `dev` alias. The `mike`, `mkdocs-material`, and `pymdown-extensions` packages are now included in the `[dev]` optional group.

docs/api_load.md

@@ -20,7 +20,7 @@ Use `load_export(...)` to read any export produced by [`export_batch`](api_expor
 
 ### Mental Model
 
-`load_export(...)` answers one question: *where is the export?*
+`load_export(...)` answers one question: _where is the export?_
 
 - Pass a **file** (`.npz`, `.nc`, or `.json`) to load a **combined** export.
 - Pass a **directory** to load a **per-item** export.
@@ -43,17 +43,17 @@ result = load_export("exports/per_item_run/")
 
 ## Parameters
 
-| Parameter | Meaning                                                                           |
-| --------- | --------------------------------------------------------------------------------- |
+| Parameter | Meaning                                                                          |
+| --------- | -------------------------------------------------------------------------------- |
 | `path`    | Path to a `.npz`/`.nc`/`.json` file (combined) or a directory (per-item export). |
 
 ### Raises
 
-| Exception         | When                                                                  |
-| ----------------- | --------------------------------------------------------------------- |
-| `FileNotFoundError` | Path does not exist.                                                |
-| `ValueError`      | Path exists but cannot be interpreted as an rs-embed export.          |
-| `ImportError`     | NetCDF export requested but `xarray` is not installed.                |
+| Exception           | When                                                         |
+| ------------------- | ------------------------------------------------------------ |
+| `FileNotFoundError` | Path does not exist.                                         |
+| `ValueError`        | Path exists but cannot be interpreted as an rs-embed export. |
+| `ImportError`       | NetCDF export requested but `xarray` is not installed.       |
 
 ---
 
@@ -102,11 +102,11 @@ class ModelResult:
 
 **Status values:**
 
-| Status    | Meaning                                          |
-| --------- | ------------------------------------------------ |
-| `"ok"`    | All points succeeded.                            |
+| Status      | Meaning                                                              |
+| ----------- | -------------------------------------------------------------------- |
+| `"ok"`      | All points succeeded.                                                |
 | `"partial"` | Some points succeeded; failed points are NaN-filled in `embeddings`. |
-| `"failed"` | All points failed; `embeddings` is `None`.      |
+| `"failed"`  | All points failed; `embeddings` is `None`.                           |
 
 ---
 
@@ -190,5 +190,5 @@ emb = result.embedding("remoteclip")   # shape (1, dim)
 ```
 
 !!! tip "Simple rule"
-    Pass a file path for combined exports, a directory path for per-item exports.
-    Everything else is automatic.
+Pass a file path for combined exports, a directory path for per-item exports.
+Everything else is automatic.

docs/index.md

@@ -46,7 +46,7 @@ Most workflows revolve around three functions: `get_embedding(...)` for one ROI,
 | Get one embedding for one ROI    | [Quickstart](quickstart.md)   | `get_embedding(...)`          |
 | Compute embeddings for many ROIs | [Quickstart](quickstart.md)   | `get_embeddings_batch(...)`   |
 | Build an export dataset          | [Quickstart](quickstart.md)   | `export_batch(...)`           |
-| Compare model assumptions        | [Models](models.md)           | model tables + detail pages    |
+| Compare model assumptions        | [Models](models.md)           | model tables + detail pages   |
 | Inspect a raw provider patch     | [Inspect API](api_inspect.md) | `inspect_provider_patch(...)` |
 
 ---

docs/models/scalemae.md

@@ -4,19 +4,19 @@
 
 ## Quick Facts
 
-| Field | Value |
-|---|---|
-| Model ID | `scalemae` |
-| Aliases | `scalemae_rgb` |
-| Family / Backbone | ScaleMAE via `rshf.scalemae.ScaleMAE` |
-| Adapter type | `on-the-fly` |
-| Typical backend | provider backend (`gee`) |
-| Primary input | S2 RGB (`B4,B3,B2`) + `input_res_m` |
-| Default resolution | 10m default provider fetch / source scale (`sensor.scale_m`) |
-| Temporal mode | range window in practice (normalized via shared helper) |
-| Output modes | `pooled`, `grid` |
-| Extra side inputs | **required effective scale** (`input_res_m` derived from `sensor.scale_m` after preprocess) |
-| Training alignment (adapter path) | High when `sensor.scale_m` matches the source patch resolution semantics |
+| Field                             | Value                                                                                       |
+| --------------------------------- | ------------------------------------------------------------------------------------------- |
+| Model ID                          | `scalemae`                                                                                  |
+| Aliases                           | `scalemae_rgb`                                                                              |
+| Family / Backbone                 | ScaleMAE via `rshf.scalemae.ScaleMAE`                                                       |
+| Adapter type                      | `on-the-fly`                                                                                |
+| Typical backend                   | provider backend (`gee`)                                                                    |
+| Primary input                     | S2 RGB (`B4,B3,B2`) + `input_res_m`                                                         |
+| Default resolution                | 10m default provider fetch / source scale (`sensor.scale_m`)                                |
+| Temporal mode                     | range window in practice (normalized via shared helper)                                     |
+| Output modes                      | `pooled`, `grid`                                                                            |
+| Extra side inputs                 | **required effective scale** (`input_res_m` derived from `sensor.scale_m` after preprocess) |
+| Training alignment (adapter path) | High when `sensor.scale_m` matches the source patch resolution semantics                    |
 
 ---