ltc-code 0.2.30__tar.gz → 0.2.31__tar.gz

{ltc_code-0.2.30 → ltc_code-0.2.31}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: ltc-code
-Version: 0.2.30
+Version: 0.2.31
 Summary: Add your description here
 Requires-Dist: fastexcel>=0.16,<0.20
 Requires-Dist: polars>=1.36.1,<1.42

{ltc_code-0.2.30 → ltc_code-0.2.31}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ltc-code"
-version = "0.2.30"
+version = "0.2.31"
 description = "Add your description here"
 readme = "README.md"
 requires-python = ">=3.9"

{ltc_code-0.2.30 → ltc_code-0.2.31}/src/ltc_code/nsc/build_nsc_outcomes_new.py

@@ -1293,11 +1293,34 @@ for column in enrollment_outcomes.columns:
             .alias(column)
         )
 
-# First post-high-school institution is useful for auditing the match. Sarah's
-# final Stata sort keeps the highest ID_FSC when enrollment start dates tie.
+# Use exactly the status and window-overlap rules for att_any_byY4. A spell
+# starting before July 1 can count if it continues into the attendance window.
+qualifying_enroll = enroll.with_columns(
+    pl.date(pl.col("cohort_18"), 7, 1).alias("_window_start"),
+    pl.date(pl.col("cohort_18") + 4, 6, 30).alias("_window_end"),
+).filter(
+    (pl.col("_term_att") == 1)
+    & (pl.col("term_end_date") >= pl.col("_window_start"))
+)
+
+# Before excluding late starts, count students whose first observed qualifying
+# enrollment is after Y4. Denominator: observed qualifying enrollees with a
+# fully observable Y4 window; not all applicants or an eventual-enrollment rate.
+first_enrollment_timing = qualifying_enroll.group_by("sid_cepr").agg(
+    pl.col("term_start_date").min().alias("first_start"),
+    pl.col("_window_end").first().alias("y4_end"),
+).filter(pl.col("y4_end") <= NSC_CUTOFF_DATE)
+
+print("FIRST QUALIFYING ENROLLMENT AFTER Y4", first_enrollment_timing.select(
+    pl.len().alias("observed_enrollees_with_Y4_followup"),
+    (pl.col("first_start") > pl.col("y4_end")).sum().alias("first_after_Y4"),
+    (100 * (pl.col("first_start") > pl.col("y4_end")).mean()).alias("percent_after_Y4"),
+))
+
+# Select the earliest qualifying spell overlapping the by-Y4 window. Preserve
+# Sarah's tie-break: highest ID_FSC when enrollment start dates are equal.
 first_institution = (
-    enroll.with_columns(pl.date(pl.col("cohort_18"), 7, 1).alias("_hs_grad_start"))
-    .filter(pl.col("term_start_date") >= pl.col("_hs_grad_start"))
+    qualifying_enroll.filter(pl.col("term_start_date") <= pl.col("_window_end"))
     .sort(["sid_cepr", "term_start_date", "ID_FSC"], descending=[False, False, True])
     .group_by("sid_cepr", maintain_order=True)
     .agg(