Address review comments: searchsorted, table[col] indexing, caching, docstring

Author: Copilot

activitysim/core/configuration/network.py

@@ -127,7 +127,7 @@ class TAZ_Settings(PydanticBase):
     is not available.
 
     As an alternative to OMX, skim files can instead be provided in Parquet
-    format (using a ``.parquet`` file extension). The input format is
+    format (using a ``.parquet`` or ``.pq`` file extension). The input format is
     auto-detected from the file extension, so no other settings need to
     change to use Parquet input. Parquet skim files should have an origin
     column and a destination column (the first two columns in the file),

activitysim/core/skim_dict_factory.py

@@ -387,6 +387,7 @@ def _read_skims_from_omx(self, skim_info, skim_data):
                 parquet_skim_file = skim_info.parquet_files.get(omx_file_path)
                 if parquet_skim_file is None:
                     parquet_skim_file = ParquetSkimFile(omx_file_path)
+                    skim_info.parquet_files[omx_file_path] = parquet_skim_file
                 for skim_key, omx_key in omx_keys.items():
                     if omx_manifest[omx_key] == omx_file_path:
                         offset = skim_info.block_offsets[skim_key]

activitysim/core/skim_parquet.py

@@ -64,8 +64,8 @@ def __init__(self, file_path):
         self.data_cols = column_names[2:]
 
         od_table = parquet_file.read(columns=[self.orig_col, self.dest_col])
-        origins = od_table.column(self.orig_col).to_numpy(zero_copy_only=False)
-        destinations = od_table.column(self.dest_col).to_numpy(zero_copy_only=False)
+        origins = od_table[self.orig_col].to_numpy(zero_copy_only=False)
+        destinations = od_table[self.dest_col].to_numpy(zero_copy_only=False)
 
         zone_ids = np.unique(np.concatenate([origins, destinations]))
         self.zone_ids = zone_ids
@@ -76,13 +76,8 @@ def __init__(self, file_path):
         n_rows = len(origins)
         self.is_dense = n_rows == self.n_zones * self.n_zones
 
-        zone_index = {z: i for i, z in enumerate(zone_ids)}
-        orig_idx = np.fromiter(
-            (zone_index[o] for o in origins), dtype=np.int64, count=n_rows
-        )
-        dest_idx = np.fromiter(
-            (zone_index[d] for d in destinations), dtype=np.int64, count=n_rows
-        )
+        orig_idx = np.searchsorted(zone_ids, origins)
+        dest_idx = np.searchsorted(zone_ids, destinations)
         self._orig_idx = orig_idx
         self._dest_idx = dest_idx
 
@@ -134,7 +129,7 @@ def read_matrix(self, column_name, dtype=None):
         np.ndarray, shape (n_zones, n_zones)
         """
         table = pq.read_table(self.file_path, columns=[column_name])
-        values = table.column(column_name).to_numpy(zero_copy_only=False)
+        values = table[column_name].to_numpy(zero_copy_only=False)
         if dtype is not None:
             values = values.astype(dtype, copy=False)