ltc-code 0.2.21__tar.gz → 0.2.23__tar.gz

{ltc_code-0.2.21 → ltc_code-0.2.23}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: ltc-code
-Version: 0.2.21
+Version: 0.2.23
 Summary: Add your description here
 Requires-Dist: fastexcel>=0.16,<0.20
 Requires-Dist: polars>=1.36.1,<1.42

{ltc_code-0.2.21 → ltc_code-0.2.23}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ltc-code"
-version = "0.2.21"
+version = "0.2.23"
 description = "Add your description here"
 readme = "README.md"
 requires-python = ">=3.9"

ltc_code-0.2.23/pyproject.toml.orig

@@ -0,0 +1,19 @@
+[project]
+name = "ltc-code"
+version = "0.2.23"
+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-0.2.21 → ltc_code-0.2.23}/src/ltc_code/nsc/build_nsc_outcomes.py

@@ -86,6 +86,8 @@ NSC_CUTOFF_DATE = date(2026, 12, 31)
 RANDOM_SEED = 3852804
 STEM_CIP_FAMILIES = {11, 14, 15, 26, 27, 40, 41}
 COLLEGE_TYPES = ["any", "4yr", "2yr", "elite"]
+AGE_ATTENDANCE_TYPES = ["any", "4yr", "2yr"]
+AGE_ATTENDANCE_RANGE = range(18, 27)
 
 
 ###########################################################
@@ -1020,6 +1022,40 @@ for year in range(1, N_YEARS_OUT + 1):
                 )
             )
 
+# Build calendar-year attendance indicators for each age. These use birth year
+# plus age, rather than the July-to-June school-year windows above.
+for age in AGE_ATTENDANCE_RANGE:
+    bounded = enroll.with_columns(
+        (pl.col("cohort_lottery") + age).alias("_age_window_year")
+    ).with_columns(
+        pl.date(pl.col("_age_window_year"), 1, 1).alias("_age_window_start"),
+        pl.date(pl.col("_age_window_year"), 12, 31).alias("_age_window_end"),
+    ).with_columns(
+        (
+            (pl.col("term_start_date") <= pl.col("_age_window_end"))
+            & (pl.col("term_end_date") >= pl.col("_age_window_start"))
+            & (pl.col("_term_att") == 1)
+        )
+        .cast(pl.Int8)
+        .alias("_overlaps")
+    )
+
+    enrollment_pieces.append(
+        bounded.group_by("sid_cepr").agg(
+            [
+                (
+                    pl.col("_overlaps")
+                    * pl.col(f"college_{college_type}")
+                    .fill_null(0)
+                    .cast(pl.Int8)
+                )
+                .max()
+                .alias(f"att_{college_type}_{age}")
+                for college_type in AGE_ATTENDANCE_TYPES
+            ]
+        )
+    )
+
 enrollment_outcomes = enrollment_pieces[0]
 for piece in enrollment_pieces[1:]:
     enrollment_outcomes = enrollment_outcomes.join(
@@ -1585,6 +1621,27 @@ for year in range(1, N_YEARS_OUT + 1):
         ]
     )
 
+for age in AGE_ATTENDANCE_RANGE:
+    age_start = pl.date(pl.col("cohort_lottery") + age, 1, 1)
+    age_columns = [
+        column
+        for column in nsc_outcomes.columns
+        if column.startswith("att_") and column.endswith(f"_{age}")
+    ]
+
+    nsc_outcomes = nsc_outcomes.with_columns(
+        [
+            pl.when(age_start > NSC_CUTOFF_DATE)
+            .then(None)
+            .when(pl.col(column).is_null())
+            .then(0)
+            .otherwise(pl.col(column))
+            .cast(pl.Int8)
+            .alias(column)
+            for column in age_columns
+        ]
+    )
+
 
 # Sarah removes the raw school-specific rate for students who were not observed
 # attending by Y2 before creating cmp_rate.
@@ -1684,6 +1741,10 @@ outcome_columns = [
     "att_2yr_byY2", "att_2yr_byY3", "att_2yr_byY4", 
     "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_4yr_{age}" for age in AGE_ATTENDANCE_RANGE],
+    *[f"att_2yr_{age}" for age in AGE_ATTENDANCE_RANGE],
+
     "cmp_any_byY4", "cmp_any_byY5", "cmp_any_byY6", "cmp_any_byY7", "cmp_any_byY8",
     "cmp_AA_byY4", "cmp_AA_byY5", "cmp_AA_byY6", "cmp_AA_byY7", "cmp_AA_byY8",
     "cmp_BA_byY4", "cmp_BA_byY5", "cmp_BA_byY6", "cmp_BA_byY7", "cmp_BA_byY8",

ltc_code-0.2.21/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