Config files in output file attributes

README.rst

@@ -152,6 +152,21 @@ Option 2: Clone repo (recommended for developers)
         - ``reV``
 
 
+reV Ecosystem
+=============
+The reV model suite comes with a set of tools that can be used alongside the core model
+to assist with data preparation and analysis:
+
+- `reVX <https://nrel.github.io/reVX/>`_ - Collection of helper methods to pre- and post- process geospatial reV data (e.g. setback layers, inclusion masks, etc.)
+- `rex <https://nrel.github.io/rex/>`_ - Library to assist with reV-style data I/O, especially resource data
+- reVRt (Coming soon!) - reV routing tool used to compute transmission costs
+- `reVReports <https://github.com/NREL/reVReports>`_ - Tool for generating publication-ready maps of reV supply curve outputs
+- `reView <https://github.com/NREL/reView>`_ - Dashboard for interactive visualization of reV supply curve outputs
+- `reV tutorial <https://github.com/NREL/reV-tutorial>`_ - Collection of tutorials for learning how to use reV
+- `gaps <https://nrel.github.io/gaps/>`_ - Underlying reV pipeline job submission and management system
+
+
+
 reV command line tools
 ======================
 
@@ -218,6 +233,6 @@ Potential (reV) Model: A Geospatial Platform for Technical Potential and Supply
 Curve Modeling.” Golden, Colorado, United States: National Renewable Energy
 Laboratory. NREL/TP-6A20-73067. https://doi.org/10.2172/1563140.
 
-Grant Buster, Michael Rossol, Paul Pinchuk, Brandon N Benton, Robert Spencer,
-Mike Bannister, & Travis Williams. (2023).
-NREL/reV: reV 0.8.0 (v0.8.0). Zenodo. https://doi.org/10.5281/zenodo.8247528
+Buster, G., Pinchuk, P., Rossol, M., Benton, B., Gleason, M., Stanley, A. P.,
+Spencer, R., Bannister, M., & Williams, T. (2020). reV (Version 0.14.5)
+[Computer software]. https://github.com/NREL/reV

pyproject.toml

@@ -31,7 +31,7 @@ classifiers=[
   "Programming Language :: Python :: 3.13",
 ]
 dependencies = [
-  "NREL-gaps>=0.8.0",
+  "NREL-gaps>=0.8.11",
   "NREL-NRWAL>=0.0.11",
   "NREL-PySAM~=7.0.0",
   "NREL-rex>=0.4.0",

reV/bespoke/bespoke.py

@@ -41,6 +41,7 @@
     SupplyCurveField,
     log_versions,
 )
+from reV.utilities.cli_functions import add_to_run_attrs
 from reV.utilities.exceptions import EmptySupplyCurvePointError, FileInputError
 
 logger = logging.getLogger(__name__)
@@ -2381,7 +2382,7 @@ def sam_sys_inputs_with_site_data(self, gid):
         )
         return site_sys_inputs
 
-    def _init_fout(self, out_fpath, sample):
+    def _init_fout(self, out_fpath, sample, config_file=None):
         """Initialize the bespoke output h5 file with meta and time index dsets
 
         Parameters
@@ -2392,12 +2393,21 @@ def _init_fout(self, out_fpath, sample):
         sample : dict
             A single sample BespokeSinglePlant output dict that has been run
             and has output data.
+        config_file : str, optional
+            Path to config file used for this bespoke run (if
+            applicable). This is used to store information about the run
+            in the output file attrs. By default, ``None``.
         """
         out_dir = os.path.dirname(out_fpath)
         if not os.path.exists(out_dir):
             create_dirs(out_dir)
 
+        global_attrs = add_to_run_attrs(config_file=config_file,
+                                        module=ModuleName.BESPOKE)
+
         with Outputs(out_fpath, mode="w") as f:
+            for key, value in global_attrs.items():
+                f.h5.attrs[key] = value
             f._set_meta("meta", self.meta, attrs={})
             ti_dsets = [
                 d for d in sample.keys() if d.startswith("time_index-")
@@ -2459,14 +2469,18 @@ def _collect_out_arr(self, dset, sample):
 
         return full_arr
 
-    def save_outputs(self, out_fpath):
+    def save_outputs(self, out_fpath, config_file=None):
         """Save Bespoke Wind Plant optimization outputs to disk.
 
         Parameters
         ----------
         out_fpath : str
             Full filepath to an output .h5 file to save Bespoke data to. The
             parent directories will be created if they do not already exist.
+        config_file : str, optional
+            Path to config file used for this bespoke run (if
+            applicable). This is used to store information about the run
+            in the output file attrs. By default, ``None``.
 
         Returns
         -------
@@ -2491,7 +2505,7 @@ def save_outputs(self, out_fpath):
             return out_fpath
 
         sample = self.outputs[self.completed_gids[0]]
-        self._init_fout(out_fpath, sample)
+        self._init_fout(out_fpath, sample, config_file=config_file)
 
         dsets = [
             d
@@ -2725,7 +2739,7 @@ def run_parallel(self, max_workers=None):
 
         return out
 
-    def run(self, out_fpath=None, max_workers=None):
+    def run(self, out_fpath=None, max_workers=None, config_file=None):
         """Run the bespoke wind plant optimization in serial or parallel.
 
         Parameters
@@ -2738,6 +2752,10 @@ def run(self, out_fpath=None, max_workers=None):
         max_workers : int, optional
             Number of local workers to run on. If ``None``, uses all
             available cores (typically 36). By default, ``None``.
+        config_file : str, optional
+            Path to config file used for this bespoke run (if
+            applicable). This is used to store information about the run
+            in the output file attrs. By default, ``None``.
 
         Returns
         -------
@@ -2800,6 +2818,6 @@ def run(self, out_fpath=None, max_workers=None):
             self._outputs = self.run_parallel(max_workers=max_workers)
 
         if out_fpath is not None:
-            out_fpath = self.save_outputs(out_fpath)
+            out_fpath = self.save_outputs(out_fpath, config_file=config_file)
 
         return out_fpath

reV/econ/econ.py

@@ -497,7 +497,8 @@ def _get_data_shape(self, dset, n_sites):
 
         return data_shape
 
-    def run(self, out_fpath=None, max_workers=1, timeout=1800, pool_size=None):
+    def run(self, out_fpath=None, max_workers=1, timeout=1800, pool_size=None,
+            config_file=None):
         """Execute a parallel reV econ run with smart data flushing.
 
         Parameters
@@ -519,6 +520,10 @@ def run(self, out_fpath=None, max_workers=1, timeout=1800, pool_size=None):
             Number of futures to submit to a single process pool for
             parallel futures. If ``None``, the pool size is set to
             ``os.cpu_count() * 2``. By default, ``None``.
+        config_file : str, optional
+            Path to config file used for this econ run (if applicable).
+            This is used to store information about the run in the
+            output file attrs. By default, ``None``.
 
         Returns
         -------
@@ -535,7 +540,8 @@ def run(self, out_fpath=None, max_workers=1, timeout=1800, pool_size=None):
         else:
             self._init_fpath(out_fpath, ModuleName.ECON)
 
-        self._init_h5(mode="a" if self._append else "w")
+        self._init_h5(mode="a" if self._append else "w",
+                      config_file=config_file, module=ModuleName.ECON)
         self._init_out_arrays()
 
         diff = list(set(self.points_control.sites)

reV/generation/base.py

@@ -28,6 +28,7 @@
     OutputWarning,
     ParallelExecutionWarning,
 )
+from reV.utilities.cli_functions import add_to_run_attrs
 
 logger = logging.getLogger(__name__)
 
@@ -994,7 +995,8 @@ def _init_fpath(self, out_fpath, module):
         self._out_fpath = os.path.join(project_dir, out_fn)
         self._run_attrs["out_fpath"] = out_fpath
 
-    def _init_h5(self, mode="w"):
+    def _init_h5(self, mode="w", config_file=None,
+                 module=ModuleName.GENERATION):
         """Initialize the single h5 output file with all output requests.
 
         Parameters
@@ -1048,6 +1050,9 @@ def _init_h5(self, mode="w"):
         else:
             ti = None
 
+        run_attrs = add_to_run_attrs(run_attrs=self.run_attrs,
+                                     config_file=config_file, module=module)
+
         Outputs.init_h5(
             self._out_fpath,
             self.output_request,
@@ -1058,7 +1063,7 @@ def _init_h5(self, mode="w"):
             self.meta,
             time_index=ti,
             configs=self.sam_metas,
-            run_attrs=self.run_attrs,
+            run_attrs=run_attrs,
             mode=mode,
         )
 

reV/generation/generation.py

@@ -455,6 +455,7 @@ def __init__(
         self._sam_module = self.OPTIONS[self.tech]
         self._run_attrs["sam_module"] = self._sam_module.MODULE
         self._run_attrs["res_file"] = resource_file
+        self._run_attrs["low_res_resource_file"] = str(low_res_resource_file)
 
         self._multi_h5_res, self._hsds = check_res_file(resource_file)
         self._gid_map = self._parse_gid_map(gid_map)
@@ -1043,7 +1044,8 @@ def _reduce_kwargs(self, pc, **kwargs):
 
         return kwargs
 
-    def run(self, out_fpath=None, max_workers=1, timeout=1800, pool_size=None):
+    def run(self, out_fpath=None, max_workers=1, timeout=1800, pool_size=None,
+            config_file=None):
         """Execute a parallel reV generation run with smart data flushing.
 
         Parameters
@@ -1067,6 +1069,10 @@ def run(self, out_fpath=None, max_workers=1, timeout=1800, pool_size=None):
             Number of futures to submit to a single process pool for
             parallel futures. If ``None``, the pool size is set to
             ``os.cpu_count() * 2``. By default, ``None``.
+        config_file : str, optional
+            Path to config file used for this generation run (if
+            applicable). This is used to store information about the run
+            in the output file attrs. By default, ``None``.
 
         Returns
         -------
@@ -1076,7 +1082,7 @@ def run(self, out_fpath=None, max_workers=1, timeout=1800, pool_size=None):
         """
         # initialize output file
         self._init_fpath(out_fpath, module=ModuleName.GENERATION)
-        self._init_h5()
+        self._init_h5(config_file=config_file, module=ModuleName.GENERATION)
         self._init_out_arrays()
         if pool_size is None:
             pool_size = os.cpu_count() * 2