updates to sampler and zone aggregator

rsm/sampler.py

@@ -40,13 +40,10 @@ def rsm_household_sampler(
     prev_iter_access : Path-like or pandas.DataFrame
         Accessibility in an old (default, no treatment, etc) run is given (preloaded)
         or read in from here. Give as a relative path (from `input_dir`) or an
-        absolute path.  If given as a path and the file does not exist, assume no delta-accessibility update info
-        is available and ignore this aspect of sampling.
+        absolute path.
     curr_iter_access : Path-like or pandas.DataFrame
         Accessibility in the latest run is given (preloaded) or read in from here.
-        Give as a relative path (from `input_dir`) or an absolute path.  If given as a
-        path and the file does not exist, assume no delta-accessibility update info
-        is available and ignore this aspect of sampling.
+        Give as a relative path (from `input_dir`) or an absolute path.
     study_area : array-like
         Array of RSM zone id's in the study area.  These zones are sampled at 100%.
     input_household : Path-like or pandas.DataFrame
@@ -79,7 +76,7 @@ def rsm_household_sampler(
     logger.debug(f"  {input_dir=}")
     logger.debug(f"  {output_dir=}")
 
-    def _resolve_df(x, directory, must_exist=True, make_index=None):
+    def _resolve_df(x, directory, make_index=None):
         if isinstance(x, (str, Path)):
             # read in the file to a pandas DataFrame
             x = Path(x).expanduser()
@@ -88,13 +85,10 @@ def _resolve_df(x, directory, must_exist=True, make_index=None):
             try:
                 result = pd.read_csv(x)
             except FileNotFoundError:
-                if must_exist:
-                    raise
-                else:
-                    result = None
+                raise
         elif isinstance(x, pd.DataFrame):
             result = x
-        elif x is None and not must_exist:
+        elif x is None:
             result = None
         else:
             raise TypeError("must be path-like or DataFrame")
@@ -114,10 +108,10 @@ def _resolve_out_filename(x):
         return x
 
     prev_iter_access_df = _resolve_df(
-        prev_iter_access, input_dir, must_exist=False, make_index="MGRA"
+        prev_iter_access, input_dir, make_index="MGRA"
     )
     curr_iter_access_df = _resolve_df(
-        curr_iter_access, input_dir, must_exist=False, make_index="MGRA"
+        curr_iter_access, input_dir, make_index="MGRA"
     )
     rsm_zones = _resolve_df(taz_crosswalk, input_dir)
     dict_clusters = dict(zip(rsm_zones["taz"], rsm_zones["cluster_id"]))

scripts/rsm_sampler.py

@@ -40,9 +40,9 @@
 logging_start(
     filename=os.path.join(rsm_dir, "logFiles", "rsm-logging.log"), level=logging.INFO
 )
-logging.info(f"start logging rsm_sampler for {iteration}")
+logging.info(f"start logging rsm_sampler for iteration {iteration}")
 
-run_rsm_sampling = get_property(ABM_PROPERTIES, "run.rsm.sampling")
+run_rsm_sampling = int(get_property(ABM_PROPERTIES, "run.rsm.sampling"))
 sampling_rate = float(get_property(ABM_PROPERTIES, "rsm.default.sampling.rate"))
 min_sampling_rate = float(get_property(ABM_PROPERTIES, "rsm.min.sampling.rate"))
 baseline_run_dir = get_property(ABM_PROPERTIES, "rsm.baseline.run.dir")
@@ -66,6 +66,9 @@
     PREV_ITER_ACCESS = None
     CURR_ITER_ACCESS = None
 
+logging.info(f"Current Iteration Accessibility File: {CURR_ITER_ACCESS}")
+logging.info(f"Previous Iteration Accessibility File: {PREV_ITER_ACCESS}")
+
 rsm_household_sampler(
     input_dir=rsm_dir,
     output_dir=rsm_dir,
@@ -81,4 +84,4 @@
     output_person=OUTPUT_RSM_SAMPLED_PERSONS,
 )
 
-logging.info(f"finished logging rsm_sampler for {iteration}")
+logging.info(f"finished logging rsm_sampler for iteration {iteration}")

scripts/rsm_zone_aggregator.py

@@ -68,7 +68,7 @@
 logging.info("loading mgra data")
 mgra = load_mgra_data(
     shapefilename=FULL_ABM_MGRA_SHAPEFILE,
-    supplemental_features=FULL_ABM_MGRA,
+    supplemental_features=FULL_ABM_MGRA_FILE,
     simplify_tolerance=10,
     topo=True,
 )