ltc-code 0.2.26__tar.gz → 0.2.27__tar.gz

{ltc_code-0.2.26 → ltc_code-0.2.27}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: ltc-code
-Version: 0.2.26
+Version: 0.2.27
 Summary: Add your description here
 Requires-Dist: fastexcel>=0.16,<0.20
 Requires-Dist: polars>=1.36.1,<1.42

{ltc_code-0.2.26 → ltc_code-0.2.27}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ltc-code"
-version = "0.2.26"
+version = "0.2.27"
 description = "Add your description here"
 readme = "README.md"
 requires-python = ">=3.9"

{ltc_code-0.2.26 → ltc_code-0.2.27}/pyproject.toml.orig

@@ -1,6 +1,6 @@
 [project]
 name = "ltc-code"
-version = "0.2.26"
+version = "0.2.27"
 description = "Add your description here"
 readme = "README.md"
 requires-python = ">=3.9"

{ltc_code-0.2.26 → ltc_code-0.2.27}/src/ltc_code/nsc/build_nsc_outcomes.py

@@ -1860,6 +1860,37 @@ nsc_outcomes = nsc_outcomes.with_columns(
 )
 
 
+# Split the existing prediction by first institution, preserving missing rates.
+nsc_outcomes = nsc_outcomes.with_columns(
+    pl.when(
+        pl.col("adj_cmp_rate").is_not_null()
+        & pl.col("college_years_firstinst").is_in([1, 2])
+    )
+    .then(0.0)
+    .otherwise(pl.col("adj_cmp_rate"))
+    .alias("adj_cmp_rate_4yr"),
+    pl.when(
+        pl.col("adj_cmp_rate").is_not_null()
+        & (pl.col("college_years_firstinst") == 4)
+    )
+    .then(0.0)
+    .otherwise(pl.col("adj_cmp_rate"))
+    .alias("adj_cmp_rate_2yr"),
+)
+
+# Match the available 1098-T calendar years, including the missing 2015 year.
+tax_years = list(range(2011, 2015)) + list(range(2016, 2023))
+nsc_outcomes = nsc_outcomes.with_columns(
+    [
+        pl.when((pl.col("cohort_lottery") + age).is_in(tax_years))
+        .then(pl.col(f"att_any_{age}"))
+        .otherwise(None)
+        .alias(f"att_any_1098_{age}")
+        for age in AGE_ATTENDANCE_RANGE
+    ]
+)
+
+
 ###########################################################
 # Write final outcomes
 ###########################################################
@@ -1876,6 +1907,7 @@ outcome_columns = [
     "att_elite_byY2", "att_elite_byY3", "att_elite_byY4", "att_elite_byY5", "att_elite_byY6",
 
     *[f"att_any_{age}" for age in AGE_ATTENDANCE_RANGE],
+    *[f"att_any_1098_{age}" for age in AGE_ATTENDANCE_RANGE],
     *[f"att_4yr_{age}" for age in AGE_ATTENDANCE_RANGE],
     *[f"att_2yr_{age}" for age in AGE_ATTENDANCE_RANGE],
 
@@ -1932,6 +1964,8 @@ keep_columns = [
     "completion_rate_150pct_ip",
     "cmp_rate",
     "adj_cmp_rate",
+    "adj_cmp_rate_2yr",
+    "adj_cmp_rate_4yr",
     "adj_cmp_rate_coarse",
     "adj_cmp_rate_coarse_sample",
     "adj_cmp_rate_coarsen_4yr",
@@ -2067,3 +2101,18 @@ print(
         "sid_cepr"
     )
 )
+
+# Nonmissing year-eight completion identifies students with the full Y8 window.
+year8_attendance_audit = (
+    nsc_outcomes.filter(pl.col("cmp_BA_byY8").is_not_null())
+    .select(
+        pl.len().alias("N_year8_sample"),
+        (pl.col("att_any_byY4") == 0).sum().alias("N_no_attendance_byY4"),
+        (
+            (pl.col("att_any_byY4") == 0)
+            & (pl.col("cmp_BA_byY8") == 1)
+        ).sum().alias("N_no_attendance_byY4_BA_byY8"),
+    )
+)
+print("Year-eight sample attendance and late BA completion check:")
+print(year8_attendance_audit)