ltc-code 0.2.22__tar.gz → 0.2.24__tar.gz

{ltc_code-0.2.22 → ltc_code-0.2.24}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: ltc-code
-Version: 0.2.22
+Version: 0.2.24
 Summary: Add your description here
 Requires-Dist: fastexcel>=0.16,<0.20
 Requires-Dist: polars>=1.36.1,<1.42

{ltc_code-0.2.22 → ltc_code-0.2.24}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ltc-code"
-version = "0.2.22"
+version = "0.2.24"
 description = "Add your description here"
 readme = "README.md"
 requires-python = ">=3.9"

ltc_code-0.2.24/pyproject.toml.orig

@@ -0,0 +1,19 @@
+[project]
+name = "ltc-code"
+version = "0.2.24"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.9"
+dependencies = [
+    "fastexcel>=0.16,<0.20",
+    "polars>=1.36.1,<1.42",
+    "polars-readstat>=0.20.2",
+]
+
+[project.scripts]
+ltc-code = "ltc_code:main"
+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"

{ltc_code-0.2.22 → ltc_code-0.2.24}/src/ltc_code/nsc/build_nsc_outcomes.py

@@ -1529,7 +1529,7 @@ nsc_outcomes = (
 )
 
 # Sarah's later cleanup takes medians over the student-level analysis file by
-# tier. Apply the same residual fill only when an attendee is still missing.
+# tier. Use the by-Y4 window for the completion-rate fill.
 tier_medians = (
     nsc_outcomes.group_by("tier_firstinst")
     .agg(
@@ -1555,7 +1555,7 @@ nsc_outcomes = (
         .alias("k_mean"),
         pl.when(
             pl.col("completion_rate_150pct_ip").is_null()
-            & (pl.col("att_any_byY2") == 1)
+            & (pl.col("att_any_byY4") == 1)
         )
         .then(pl.col("completion_rate_150pct_tier_median"))
         .otherwise(pl.col("completion_rate_150pct_ip"))
@@ -1643,83 +1643,58 @@ for age in AGE_ATTENDANCE_RANGE:
     )
 
 
-# Sarah removes the raw school-specific rate for students who were not observed
-# attending by Y2 before creating cmp_rate.
+# Define expected completion over the cumulative by-Y4 attendance window. The
+# detailed measure uses the first institution's rate (with the tier-median fill
+# above), gives observed nonattenders zero, and leaves attendee rates missing
+# when neither the institution rate nor its tier median is available.
 nsc_outcomes = nsc_outcomes.with_columns(
-    pl.when(pl.col("att_any_byY2") == 0)
+    pl.when(pl.col("att_any_byY4") == 0)
     .then(None)
     .otherwise(pl.col("completion_rate_150pct_ip"))
     .alias("completion_rate_150pct_ip")
 )
 
-# Sarah creates cmp_rate as a copy of the restricted raw completion rate, then
-# fills missing cmp_rate values with the late-enrollee/control-group mean.
 nsc_outcomes = nsc_outcomes.with_columns(
     pl.col("completion_rate_150pct_ip").alias("cmp_rate"),
-    pl.when(pl.col("att_any_byY2") == 0)
+    pl.when(pl.col("att_any_byY4").is_null())
     .then(None)
-    .when(pl.col("college_years_firstinst") == 4)
+    .when(pl.col("att_4yr_byY4") == 1)
     .then(cmp_rate_4yr_coarse)
-    .when(pl.col("college_years_firstinst").is_in([1, 2]))
+    .when(pl.col("att_2yr_byY4") == 1)
     .then(cmp_rate_2yr_coarse)
+    .when(pl.col("att_any_byY4") == 0)
+    .then(0.0)
     .otherwise(None)
     .alias("cmp_rate_coarse"),
 )
 
-late_enrollee_means = (
-    nsc_outcomes
-    .filter(
-        (pl.col("att_4yr_inY2") == 0)
-        & (pl.col("att_4yr_inY3") == 1)
-        & (
-            (pl.col("cmp_BA_byY6") == 1)
-            | (pl.col("cmp_BA_byY7") == 1)
-            | (pl.col("cmp_BA_byY8") == 1)
-        )
-        & (pl.col("offer") == 0)
-    )
-    .select(
-        pl.col("cmp_rate").mean().alias("cmp_rate"),
-        pl.col("cmp_rate_coarse").mean().alias("cmp_rate_coarse"),
-    )
-)
-
-late_enrollee_mean = late_enrollee_means.item(0, "cmp_rate")
-late_enrollee_coarse_mean = late_enrollee_means.item(0, "cmp_rate_coarse")
-
-if late_enrollee_mean is None or late_enrollee_coarse_mean is None:
-    raise ValueError(
-        "The late-enrollee control donor group has no usable completion-rate values."
-    )
-
 nsc_outcomes = nsc_outcomes.with_columns(
-    pl.when(pl.col("cmp_rate").is_null())
-    .then(pl.lit(late_enrollee_mean, dtype=pl.Float64))
+    pl.when(pl.col("att_any_byY4").is_null())
+    .then(None)
+    .when(pl.col("att_any_byY4") == 0)
+    .then(0.0)
     .otherwise(pl.col("cmp_rate"))
     .alias("adj_cmp_rate"),
-    pl.when(pl.col("cmp_rate_coarse").is_null())
-    .then(pl.lit(late_enrollee_coarse_mean, dtype=pl.Float64))
-    .otherwise(pl.col("cmp_rate_coarse"))
+    pl.col("cmp_rate_coarse")
     .alias("adj_cmp_rate_coarse"),
 ).with_columns(
-    pl.when(pl.col("att_4yr_byY2").is_null())
+    pl.when(pl.col("att_any_byY4").is_null())
     .then(None)
     .otherwise(pl.col("cmp_rate"))
     .alias("cmp_rate"),
-    pl.when(pl.col("att_4yr_byY2").is_null())
+    pl.when(pl.col("att_any_byY4").is_null())
     .then(None)
     .otherwise(pl.col("adj_cmp_rate"))
     .alias("adj_cmp_rate"),
-    pl.when(pl.col("att_4yr_byY2").is_null())
+    pl.when(pl.col("att_any_byY4").is_null())
     .then(None)
     .otherwise(pl.col("cmp_rate_coarse"))
     .alias("cmp_rate_coarse"),
-    pl.when(pl.col("att_4yr_byY2").is_null())
+    pl.when(pl.col("att_any_byY4").is_null())
     .then(None)
     .otherwise(pl.col("adj_cmp_rate_coarse"))
     .alias("adj_cmp_rate_coarse"),
-    # Preserve the package's existing name as an alias for Sarah's adjusted rate.
-    pl.when(pl.col("att_4yr_byY2").is_null())
+    pl.when(pl.col("att_any_byY4").is_null())
     .then(None)
     .otherwise(pl.col("adj_cmp_rate"))
     .alias("predicted_completion"),
@@ -1809,13 +1784,12 @@ print(
     f"k_mean 4yr={k_mean_4yr_coarse:.2f}, "
     f"k_mean 2yr-or-less={k_mean_2yr_coarse:.2f}, "
     f"completion 4yr={cmp_rate_4yr_coarse:.4f}, "
-    f"completion 2yr-or-less={cmp_rate_2yr_coarse:.4f}, "
-    f"nonattender completion imputation={late_enrollee_mean:.4f}, "
-    f"coarse nonattender imputation={late_enrollee_coarse_mean:.4f}"
+    f"completion 2yr-or-less={cmp_rate_2yr_coarse:.4f}; "
+    "observed by-Y4 nonattender completion=0"
 )
 
-observable_y2 = nsc_outcomes.filter(pl.col("att_4yr_byY2").is_not_null())
-coarse_audit = observable_y2.select(
+observable_y4 = nsc_outcomes.filter(pl.col("att_any_byY4").is_not_null())
+coarse_audit = observable_y4.select(
     pl.len().alias("students"),
     pl.col("k_mean_coarse").null_count().alias("k_mean_coarse_missing"),
     pl.col("k_mean_coarse").min().alias("k_mean_coarse_min"),
@@ -1836,6 +1810,45 @@ if coarse_audit.item(0, "adj_cmp_rate_coarse_missing") > 0:
 
 print("Coarse outcome audit:")
 print(coarse_audit)
+
+attendee_completion_audit = (
+    observable_y4.filter(pl.col("att_any_byY4") == 1)
+    .select(
+        pl.len().alias("by_y4_attendees"),
+        pl.col("completion_rate_150pct_firstinst")
+        .is_null()
+        .sum()
+        .alias("missing_first_institution_rate"),
+        (
+            pl.col("completion_rate_150pct_firstinst").is_null()
+            & pl.col("completion_rate_150pct_ip").is_not_null()
+        )
+        .sum()
+        .alias("filled_by_tier_median"),
+        pl.col("predicted_completion")
+        .is_null()
+        .sum()
+        .alias("missing_after_tier_median"),
+        pl.col("predicted_completion")
+        .is_null()
+        .mean()
+        .alias("missing_after_tier_median_share"),
+        (
+            pl.col("predicted_completion").is_null()
+            & pl.col("tier_firstinst").is_null()
+        )
+        .sum()
+        .alias("missing_after_tier_median_no_tier"),
+        (
+            pl.col("predicted_completion").is_null()
+            & pl.col("tier_firstinst").is_not_null()
+        )
+        .sum()
+        .alias("missing_after_tier_median_with_tier"),
+    )
+)
+print("By-Y4 attendee completion-rate audit:")
+print(attendee_completion_audit)
 print(
     nsc_outcomes.select("sid_cepr", "cohort_lottery", "recovered_nsc_outcome").sort(
         "sid_cepr"

ltc_code-0.2.22/src/ltc_code/nsc/naics.csv

@@ -1,25 +0,0 @@
-naics_code,sector
-11,"Agriculture, Forestry, Fishing and Hunting"
-21,"Mining, Quarrying, and Oil and Gas Extraction"
-22,Utilities
-23,Construction
-31,Manufacturing
-32,Manufacturing
-33,Manufacturing
-42,Wholesale Trade
-44,Retail Trade
-45,Retail Trade
-48,Transportation and Warehousing
-49,Transportation and Warehousing
-51,Information
-52,Finance and Insurance
-53,Real Estate and Rental and Leasing
-54,"Professional, Scientific, and Technical Services"
-55,Management of Companies and Enterprises
-56,Administrative and Support and Waste Management and Remediation Services
-61,Educational Services
-62,Health Care and Social Assistance
-71,"Arts, Entertainment, and Recreation"
-72,Accommodation and Food Services
-81,Other Services (except Public Administration)
-92,Public Administration