feat: regenerate fixture corpus from Phase P publish tree + committed regen script
Adds data-raw/regenerate_fixture_corpus.R, parameterized by publish-cache path, so the fixture is never a manual rebuild again. Regenerates the 2019/2020 long partitions (byte-for-byte copy), the full 39,377-row canonical_fips_xwalk master, the new 117,503-row canonical_alias lookup table, and summary_categories from the Phase P publish tree; resyncs the four fixture docs; and hand-builds manifest.json with schema_version 4 and freshly computed sha256/row_count/size_bytes for every shipped file. Fixture grows from 3.7MB to 5.5MB, well under the 25MB budget.
This commit is contained in:
+18
-46
@@ -1,54 +1,21 @@
|
||||
{
|
||||
"schema_version": 3,
|
||||
"built_at": "2026-04-29T18:57:18Z",
|
||||
"pipeline_commit": "bd3e744",
|
||||
"fixture_note": "Two-year (2019-2020) fixture for uscogdata tests. Full corpus available via USCOGDATA_URL. Regenerated with Layer 1 (canonical_govid resolver gate) + Layer 2 (PID-era extended xwalk).",
|
||||
"schema_version": 4,
|
||||
"built_at": "2026-07-11T13:24:01Z",
|
||||
"pipeline_commit": "1a00925",
|
||||
"fixture_note": "Two-year (2019-2020) fixture for uscogdata tests. Full corpus available via USCOGDATA_URL. Regenerated for Phase P (schema_version 4, uniformly 12-char canonical_govid) with the full canonical_fips_xwalk master and the new canonical_alias lookup table via data-raw/regenerate_fixture_corpus.R.",
|
||||
"data_vintage": {
|
||||
"census_source_downloaded": "unknown",
|
||||
"cpi_vintage": "FRED CPIAUCSL",
|
||||
"acs_vintage": "ACS 2018-2022 5-year"
|
||||
},
|
||||
"scope": {
|
||||
"gov_types_included": [
|
||||
0,
|
||||
1,
|
||||
2,
|
||||
3
|
||||
],
|
||||
"gov_types_excluded": [
|
||||
4,
|
||||
5
|
||||
],
|
||||
"gov_types_included": [0, 1, 2, 3],
|
||||
"gov_types_excluded": [4, 5],
|
||||
"scope_note": "v0.1 covers state, county, city/municipality, and township governments. Special districts (type 4) and school districts (type 5) are excluded pending validation in a future cycle."
|
||||
},
|
||||
"schema": {
|
||||
"long_column_count": 24,
|
||||
"long_columns": [
|
||||
"fips_state",
|
||||
"type",
|
||||
"fips_county",
|
||||
"govid",
|
||||
"gov_blank",
|
||||
"gov_name",
|
||||
"county_name",
|
||||
"fips_state_code",
|
||||
"fips_county_code",
|
||||
"fips_place_code",
|
||||
"population",
|
||||
"popyear",
|
||||
"enrollment",
|
||||
"enrollyear",
|
||||
"function_code",
|
||||
"sch_level_code",
|
||||
"fiscal_year_end",
|
||||
"srvy_year",
|
||||
"item_code",
|
||||
"amt",
|
||||
"srv_data",
|
||||
"impute_flag",
|
||||
"is_aggregate",
|
||||
"canonical_govid"
|
||||
],
|
||||
"long_columns": ["fips_state", "type", "fips_county", "govid", "gov_blank", "gov_name", "county_name", "fips_state_code", "fips_county_code", "fips_place_code", "population", "popyear", "enrollment", "enrollyear", "function_code", "sch_level_code", "fiscal_year_end", "srvy_year", "item_code", "amt", "srv_data", "impute_flag", "is_aggregate", "canonical_govid"],
|
||||
"data_dictionary": "docs/data_dictionary.md"
|
||||
},
|
||||
"files": {
|
||||
@@ -56,27 +23,32 @@
|
||||
{
|
||||
"year": 2019,
|
||||
"path": "data/long/year=2019/part-0.parquet",
|
||||
"sha256": "d93affbbf9c46bd193fa5e07d89dfa9b08ad4f6fc2442fe7a27e6e4ef28f8bd9",
|
||||
"sha256": "c0a2bf0758af129d5dfddb6ff6665cc435ddee87fd6879e788fb56ed53ab22b8",
|
||||
"row_count": 318139,
|
||||
"size_bytes": 1425125
|
||||
"size_bytes": 1441404
|
||||
},
|
||||
{
|
||||
"year": 2020,
|
||||
"path": "data/long/year=2020/part-0.parquet",
|
||||
"sha256": "c9224833bd914cc85efb2ec62f83f75c34dfa469d4398f5cb1789fd028c03389",
|
||||
"sha256": "92570b9d55ec3425d034db37838f91c3b8359d0454d3d98730a6016b62e4bb48",
|
||||
"row_count": 317500,
|
||||
"size_bytes": 1428049
|
||||
"size_bytes": 1444011
|
||||
}
|
||||
],
|
||||
"metadata": [
|
||||
{
|
||||
"path": "data/canonical_alias.parquet",
|
||||
"sha256": "db784d4ec9e5abb4b033405627d8bdd6f8d8ff96b3033a5b2587b4b59113ec9c",
|
||||
"description": "canonical_alias.parquet"
|
||||
},
|
||||
{
|
||||
"path": "data/canonical_fips_xwalk.parquet",
|
||||
"sha256": "4bbdf0415b0ae1a24927869bb9e8e75eca5d7bcceebdf8c26346c7cbf8472d34",
|
||||
"sha256": "c0b1295e779b601f2782de40ab143556324e74d30d214fc10997c2244c109389",
|
||||
"description": "canonical_fips_xwalk.parquet"
|
||||
},
|
||||
{
|
||||
"path": "data/summary_categories.parquet",
|
||||
"sha256": "60045e22bc2723318fa2cb73f8e5038250dc54d24b3447c6750dfe29035335b8",
|
||||
"sha256": "dd59e7f58a022679ad43511c8c8e938b8dd4be81196bbeeee21e67bdcca2295b",
|
||||
"description": "summary_categories.parquet"
|
||||
}
|
||||
]
|
||||
|
||||
Reference in New Issue
Block a user