ltc-code 0.2.28__tar.gz → 0.2.29__tar.gz

{ltc_code-0.2.28 → ltc_code-0.2.29}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: ltc-code
-Version: 0.2.28
+Version: 0.2.29
 Summary: Add your description here
 Requires-Dist: fastexcel>=0.16,<0.20
 Requires-Dist: polars>=1.36.1,<1.42

{ltc_code-0.2.28 → ltc_code-0.2.29}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ltc-code"
-version = "0.2.28"
+version = "0.2.29"
 description = "Add your description here"
 readme = "README.md"
 requires-python = ">=3.9"
@@ -17,3 +17,7 @@ ltc-summary-stats = "ltc_code.make_summary_stats_table:main"
 [build-system]
 requires = ["uv_build>=0.11.16,<0.12.0"]
 build-backend = "uv_build"
+
+[tool.uv.build-backend]
+source-exclude = ["**/.DS_Store", "**/__pycache__/**", "**/*.pyc", "src/ltc_code/nsc/input/**", "src/ltc_code/nsc/output/**"]
+wheel-exclude = ["**/.DS_Store", "**/__pycache__/**", "**/*.pyc", "ltc_code/nsc/input/**", "ltc_code/nsc/output/**"]

ltc_code-0.2.29/src/ltc_code/nsc/NEW_CROSSWALK.md

@@ -0,0 +1,24 @@
+# New NSC crosswalk build
+
+Run the new variant explicitly with `python -m ltc_code.nsc.build_nsc_outcomes_new` after providing the student input files. The original build remains available. The new variant writes to `nsc/output/new_crosswalk/` to keep its outputs separate.
+
+The official April 2023 NSC crosswalk is primary. Append mapped legacy codes only when their full lookup key is absent from the official file. Do not fill the 108 present-but-blank official keys using Sarah's mappings. Existing 18 sole-rate candidate choices and 24 Calhoun branch assignments are explicit and documented in the code. Preserve full branch codes and deterministic legacy selection.
+
+Institution type uses IPEDS 2013, then the latest nonmissing directory classification, then three inline exceptions formerly loaded from the manual spreadsheet. Less-than-two-year labels are parsed before broader two-year labels. Treat Missing/not reported as null before choosing the latest directory record. The existing two-year-or-less outcome grouping is retained. The 5–8 tier bucket lookup counts Nevada State once despite its tier 5/7 aliases.
+
+All student outcome formulas, eligibility windows, completion-rate imputation, and the existing within-bucket coarse-rate exercise remain unchanged. The change affects their institutional inputs. No annual enrollment-year classification is introduced.
+
+Expected counts with the audited files: 24,166 keys; 21,315 with UNITID; 21,204 matching a UNITID in the 2013/directory files (99.479%); 7,867 matched institutions with no missing type. Distinct institution types: 3,329 four-year, 2,440 two-year, 2,098 less-than-two-year. These are reference-table counts, not secure-sample match rates or completeness of completion rates.
+
+Required files in `nsc/raw/`:
+- NSC_SCHOOL_CODE_TO_IPEDS_UNIT_ID_XWALK_APR-2023.xlsx (official workbook, NSC_to_IPEDS_UNIT_ID sheet)
+- college_crosswalk.xls (legacy fallback)
+- IPEDS_IC_2013.csv
+- directory.dta
+- CREDENTIAL_LEVEL_LOOKUP_TABLE.xlsx
+- ipeds_data.dta
+- chetty/mrc_table2.dta and chetty/mrc_table11.dta
+
+The old IPEDS_IC_manual.xlsx is not needed by this variant. Student inputs remain input/apps.csv, input/nsc_records_old.dta, and input/nsc_records_new.csv. Do not supply synthetic records for actual analysis. Institutional support files are bundled in the locally built wheel and source distribution but are Git-ignored. GitHub Actions publishes these verified distributions from release assets; it does not rebuild from a checkout that lacks the data. Student inputs are never bundled.
+
+Institution-only audit CSVs are written alongside the outcomes, including mapping choices, appended candidates, missing UNITIDs, and missing classifications. The 99.48% matched subset is an audit denominator, not a filter that drops student records from the build.

{ltc_code-0.2.28 → ltc_code-0.2.29}/src/ltc_code/nsc/build_nsc_outcomes.py

@@ -1898,8 +1898,14 @@ nsc_outcomes = nsc_outcomes.with_columns(
     .alias("adj_cmp_rate_coarse_2yr"),
 )
 
-# Give each IPEDS institution one tier, excluding missing crosswalk tiers.
-ipeds_tiers = college_ref.select("unitid", "tier").drop_nulls().unique()
+# Only tiers 1-8 enter these four-year bucket averages. Other-tier branch
+# mappings can share a UNITID and must not duplicate the institution's cohort.
+ipeds_tiers = (
+    college_ref.select("unitid", "tier")
+    .drop_nulls()
+    .filter(pl.col("tier").is_in(range(1, 9)))
+    .unique()
+)
 ipeds_tier_completion = ipeds_completion_with_sector.join(
     ipeds_tiers, on="unitid", how="left", validate="1:1"
 ).filter(pl.col("college_sector") == "4yr")