Skip to content

dataloader #28

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
runyangxu merged 1 commit into from
Feb 26, 2026
Merged

dataloader #28

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Binary file modified docs/.doctrees/environment.pickle
View file
Open in desktop
Binary file not shown.
Binary file modified docs/.doctrees/pyhazards_datasets.doctree
View file
Open in desktop
Binary file not shown.
39 changes: 0 additions & 39 deletions docs/_sources/modules/models_hydrographnet.rst.txt
View file
Open in desktop

This file was deleted.

32 changes: 0 additions & 32 deletions docs/_sources/modules/models_wildfire_aspp.rst.txt
View file
Open in desktop

This file was deleted.

33 changes: 1 addition & 32 deletions docs/_sources/pyhazards_datasets.rst.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,42 +81,11 @@ Notes (MERRA-2)
- ``--var T2M`` to choose the plotted surface variable (default: ``T2M``)


Dataloader (v3)
Dataloader
---------------

Minimal API with a structured request object for multi-source fusion
(e.g., FIRMS + ERA5).

API
~~~

.. literalinclude:: ../../pyhazards/datasets/dataloader/README.md
:language: markdown
:start-after: ## API
:end-before: ## `GeoLoadInput`

GeoLoadInput
~~~~~~~~~~~~

.. literalinclude:: ../../pyhazards/datasets/dataloader/README.md
:language: markdown
:start-after: ## `GeoLoadInput`
:end-before: ## Optional

Optional fields
~~~~~~~~~~~~~~~

.. literalinclude:: ../../pyhazards/datasets/dataloader/README.md
:language: markdown
:start-after: ## Optional
:end-before: ## Example

Example
~~~~~~~

.. literalinclude:: ../../pyhazards/datasets/dataloader/README.md
:language: markdown
:start-after: ## Example


Example skeleton
Expand Down
51 changes: 18 additions & 33 deletions docs/pyhazards_datasets.html
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -355,13 +355,14 @@ <h3>Notes (MERRA-2)<a class="headerlink" href="#notes-merra-2" title="Link to th
</ul>
</section>
</section>
<section id="dataloader-v3">
<h2>Dataloader (v3)<a class="headerlink" href="#dataloader-v3" title="Link to this heading">¶</a></h2>
<p>Minimal API with a structured request object for multi-source fusion
(e.g., FIRMS + ERA5).</p>
<section id="api">
<h3>API<a class="headerlink" href="#api" title="Link to this heading">¶</a></h3>
<div class="highlight-markdown notranslate"><div class="highlight"><pre><span></span><span class="sb">```python</span>
<section id="dataloader">
<h2>Dataloader<a class="headerlink" href="#dataloader" title="Link to this heading">¶</a></h2>
<div class="highlight-markdown notranslate"><div class="highlight"><pre><span></span><span class="gh"># Dataloader V3</span>

Minimal API with a structured request object.

<span class="gu">## API</span>
<span class="sb">```python</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">dataloader_v3</span><span class="w"> </span><span class="kn">import</span> <span class="p">(</span>
<span class="n">GeoLoadInput</span><span class="p">,</span>
<span class="n">load_data</span><span class="p">,</span>
Expand All @@ -370,35 +371,26 @@ <h3>API<a class="headerlink" href="#api" title="Link to this heading">¶</a></h3
<span class="n">to_torch_batch</span><span class="p">,</span>
<span class="p">)</span>
<span class="sb">```</span>
</pre></div>
</div>
</section>
<section id="geoloadinput">
<h3>GeoLoadInput<a class="headerlink" href="#geoloadinput" title="Link to this heading">¶</a></h3>
<div class="highlight-markdown notranslate"><div class="highlight"><pre><span></span><span class="k">-</span><span class="w"> </span><span class="sb">`data_sources: list[str]`</span>

<span class="gu">## `GeoLoadInput` (required format)</span>
<span class="k">-</span><span class="w"> </span><span class="sb">`data_sources: list[str]`</span>
Example: <span class="sb">`[&quot;FIRMS&quot;, &quot;ERA5&quot;]`</span>
<span class="k">-</span><span class="w"> </span><span class="sb">`temporal_window: tuple[str, str]`</span>
Format: <span class="sb">`(&quot;YYYY-MM-DD&quot;, &quot;YYYY-MM-DD&quot;)`</span> or <span class="sb">`(&quot;YYYY-MM-DD HH:MM:SS&quot;, &quot;...&quot;)`</span>
<span class="k">-</span><span class="w"> </span><span class="sb">`area_of_interest_bbox: tuple[float, float, float, float]`</span>
Order: <span class="sb">`(min_lon, min_lat, max_lon, max_lat)`</span>
</pre></div>
</div>
</section>
<section id="optional-fields">
<h3>Optional fields<a class="headerlink" href="#optional-fields" title="Link to this heading">¶</a></h3>
<div class="highlight-markdown notranslate"><div class="highlight"><pre><span></span><span class="k">-</span><span class="w"> </span><span class="sb">`spatial_resolution_deg: float = 0.1`</span>

<span class="gu">## Optional</span>
<span class="k">-</span><span class="w"> </span><span class="sb">`spatial_resolution_deg: float = 0.1`</span>
<span class="k">-</span><span class="w"> </span><span class="sb">`root_dir: str = &quot;/home/yangshuang&quot;`</span>
<span class="k">-</span><span class="w"> </span><span class="sb">`synthetic_time: bool = False`</span>
<span class="k">-</span><span class="w"> </span><span class="sb">`temporal_cadence: str = &quot;D&quot;`</span> (<span class="sb">`&quot;D&quot;`</span>, <span class="sb">`&quot;H&quot;`</span>, <span class="sb">`&quot;15min&quot;`</span>, ...)
<span class="k">-</span><span class="w"> </span><span class="sb">`target_hazards: list[str] | None = None`</span> (if set and no mapping, default code is <span class="sb">`1`</span>)
<span class="k">-</span><span class="w"> </span><span class="sb">`label_source: str | None = None`</span> (<span class="sb">`&quot;firms&quot; | &quot;noaa&quot; | &quot;mtbs&quot;`</span>, else auto-infer)
<span class="k">-</span><span class="w"> </span><span class="sb">`label_mapping: dict[str, int] | None = None`</span>
</pre></div>
</div>
</section>
<section id="example">
<h3>Example<a class="headerlink" href="#example" title="Link to this heading">¶</a></h3>
<div class="highlight-markdown notranslate"><div class="highlight"><pre><span></span><span class="sb">```python</span>

<span class="gu">## Example</span>
<span class="sb">```python</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">dataloader_v3</span><span class="w"> </span><span class="kn">import</span> <span class="n">GeoLoadInput</span><span class="p">,</span> <span class="n">load_data</span><span class="p">,</span> <span class="n">save_sample_h5</span>

<span class="n">req</span> <span class="o">=</span> <span class="n">GeoLoadInput</span><span class="p">(</span>
Expand All @@ -418,7 +410,6 @@ <h3>Example<a class="headerlink" href="#example" title="Link to this heading">¶
</pre></div>
</div>
</section>
</section>
<section id="example-skeleton">
<h2>Example skeleton<a class="headerlink" href="#example-skeleton" title="Link to this heading">¶</a></h2>
<p>A “nice” skeleton should make it explicit <strong>what data you load</strong> and how it flows into
Expand Down Expand Up @@ -546,13 +537,7 @@ <h2>Developer note<a class="headerlink" href="#developer-note" title="Link to th
<li><a class="reference internal" href="#notes-merra-2">Notes (MERRA-2)</a></li>
</ul>
</li>
<li><a class="reference internal" href="#dataloader-v3">Dataloader (v3)</a><ul>
<li><a class="reference internal" href="#api">API</a></li>
<li><a class="reference internal" href="#geoloadinput">GeoLoadInput</a></li>
<li><a class="reference internal" href="#optional-fields">Optional fields</a></li>
<li><a class="reference internal" href="#example">Example</a></li>
</ul>
</li>
<li><a class="reference internal" href="#dataloader">Dataloader</a></li>
<li><a class="reference internal" href="#example-skeleton">Example skeleton</a></li>
<li><a class="reference internal" href="#inspection-entrypoints-convention-for-all-datasets">Inspection entrypoints (convention for all datasets)</a></li>
<li><a class="reference internal" href="#developer-note">Developer note</a></li>
Expand Down
2 changes: 1 addition & 1 deletion docs/searchindex.js
View file
Open in desktop

Large diffs are not rendered by default.

33 changes: 1 addition & 32 deletions docs/source/pyhazards_datasets.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,42 +81,11 @@ Notes (MERRA-2)
- ``--var T2M`` to choose the plotted surface variable (default: ``T2M``)


Dataloader (v3)
Dataloader
---------------

Minimal API with a structured request object for multi-source fusion
(e.g., FIRMS + ERA5).

API
~~~

.. literalinclude:: ../../pyhazards/datasets/dataloader/README.md
:language: markdown
:start-after: ## API
:end-before: ## `GeoLoadInput`

GeoLoadInput
~~~~~~~~~~~~

.. literalinclude:: ../../pyhazards/datasets/dataloader/README.md
:language: markdown
:start-after: ## `GeoLoadInput`
:end-before: ## Optional

Optional fields
~~~~~~~~~~~~~~~

.. literalinclude:: ../../pyhazards/datasets/dataloader/README.md
:language: markdown
:start-after: ## Optional
:end-before: ## Example

Example
~~~~~~~

.. literalinclude:: ../../pyhazards/datasets/dataloader/README.md
:language: markdown
:start-after: ## Example


Example skeleton
Expand Down