ltc-code 0.2.14__tar.gz → 0.2.16__tar.gz

{ltc_code-0.2.14 → ltc_code-0.2.16}/PKG-INFO

@@ -1,9 +1,9 @@
 Metadata-Version: 2.3
 Name: ltc-code
-Version: 0.2.14
+Version: 0.2.16
 Summary: Add your description here
-Requires-Dist: fastexcel>=0.20.2
-Requires-Dist: polars>=1.42.1
+Requires-Dist: fastexcel>=0.16,<0.20
+Requires-Dist: polars>=1.36.1,<1.42
 Requires-Dist: polars-readstat>=0.20.2
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown

{ltc_code-0.2.14 → ltc_code-0.2.16}/pyproject.toml

@@ -1,12 +1,12 @@
 [project]
 name = "ltc-code"
-version = "0.2.14"
+version = "0.2.16"
 description = "Add your description here"
 readme = "README.md"
 requires-python = ">=3.9"
 dependencies = [
-    "fastexcel>=0.20.2",
-    "polars>=1.42.1",
+    "fastexcel>=0.16,<0.20",
+    "polars>=1.36.1,<1.42",
     "polars-readstat>=0.20.2",
 ]
 

{ltc_code-0.2.14 → ltc_code-0.2.16}/src/ltc_code/nsc/build_nsc_outcomes.py

@@ -43,6 +43,17 @@ CHETTY_MRC_TABLE2 = next(
 )
 # Chetty/Barron college tier lookup. Numeric tier 1/2 identifies elite colleges.
 
+CHETTY_MRC_TABLE11_CANDIDATES = [
+    RAW_NSC / "chetty" / "mrc_table11.dta",
+    RAW_NSC / "mrc_table11.dta",
+    PACKAGE_NSC.parents[3] / "College" / "chetty" / "mrc_table11.dta",
+]
+CHETTY_MRC_TABLE11 = next(
+    (path for path in CHETTY_MRC_TABLE11_CANDIDATES if path.exists()),
+    CHETTY_MRC_TABLE11_CANDIDATES[0],
+)
+# Chetty OPE-to-super-OPE crosswalk used to attach tier to NSC schools.
+
 INPUT_NSC = PACKAGE_NSC / "input"
 # Folder for secured Census inputs that are not packaged with the code.
 
@@ -85,21 +96,31 @@ COLLEGE_TYPES = ["any", "4yr", "2yr", "elite"]
 college_crosswalk = (
     pl.read_excel(
         COLLEGE_CROSSWALK,
-        columns=["ID_IPEDS", "ID_OPE", "ID_FSC_long", "name"],
+        columns=["ID_IPEDS", "ID_OPE", "ID_FSC", "ID_FSC_long", "name"],
     )
     .with_columns(
-        pl.col("ID_FSC_long")
-        .cast(pl.String)
-        .str.strip_chars()
-        .str.replace(r"\.0$", "")
+        pl.when(
+            pl.col("ID_FSC_long").is_not_null()
+            & (pl.col("ID_FSC_long").cast(pl.String).str.strip_chars() != "")
+        )
+        .then(pl.col("ID_FSC_long").cast(pl.String).str.strip_chars())
+        .when(pl.col("ID_FSC").is_not_null())
+        .then(
+            pl.col("ID_FSC").cast(pl.String).str.strip_chars().str.replace(r"\.0$", "")
+            + pl.lit("-00")
+        )
+        .otherwise(None)
         .alias("ID_FSC"),
         pl.col("ID_IPEDS").cast(pl.Int64, strict=False).alias("unitid"),
         pl.col("ID_OPE").cast(pl.Int64, strict=False),
     )
     .select("ID_FSC", "unitid", "ID_OPE", "name")
     .rename({"name": "college_name_crosswalk"})
-    .drop_nulls("ID_FSC")
+    .drop_nulls(["ID_FSC", "unitid"])
     .unique("ID_FSC", keep="first")
+    .with_columns(
+        pl.col("ID_FSC").str.slice(0, 6).cast(pl.Int64, strict=False).alias("opeid")
+    )
 )
 
 
@@ -210,24 +231,42 @@ directory = (
     .select("unitid", "college_name_directory", "years_directory", "ownership_directory")
 )
 
-# Chetty/Barron tiers are keyed at the super-OPE level. The NSC college
-# crosswalk carries OPE IDs, so joining tier onto college_ref makes the tier
-# available on each enrollment spell.
+# Chetty/Barron tiers are keyed at super-OPE level. Table 11 maps school OPE IDs
+# to those super-OPE groups, which is the same route Sarah's Stata code uses.
 chetty_tiers = (
     scan_readstat(
         CHETTY_MRC_TABLE2,
         missing_string_as_null=True,
         value_labels_as_strings=False,
     )
-    .select("super_opeid", "tier")
+    .select("super_opeid", "tier", "tier_name")
     .collect()
     .with_columns(
-        pl.col("super_opeid").cast(pl.Int64, strict=False).alias("ID_OPE"),
+        pl.col("super_opeid").cast(pl.Int64, strict=False),
         pl.col("tier").cast(pl.Int8, strict=False),
     )
-    .select("ID_OPE", "tier")
-    .drop_nulls("ID_OPE")
-    .unique("ID_OPE", keep="first")
+    .drop_nulls("super_opeid")
+    .unique("super_opeid", keep="first")
+)
+
+chetty_ope_crosswalk = (
+    scan_readstat(
+        CHETTY_MRC_TABLE11,
+        missing_string_as_null=True,
+        value_labels_as_strings=False,
+    )
+    .select("opeid", "super_opeid", "superopeid_name")
+    .collect()
+    .with_columns(
+        pl.col("opeid").cast(pl.Int64, strict=False),
+        pl.col("super_opeid").cast(pl.Int64, strict=False),
+    )
+    .drop_nulls("opeid")
+)
+
+chetty_by_opeid = (
+    chetty_ope_crosswalk.join(chetty_tiers, on="super_opeid", how="left")
+    .unique("opeid", keep="first")
 )
 
 
@@ -240,7 +279,7 @@ college_ref = (
     college_crosswalk.join(ipeds_2013, on="unitid", how="left")
     .join(ipeds_manual, on="unitid", how="left")
     .join(directory, on="unitid", how="left")
-    .join(chetty_tiers, on="ID_OPE", how="left", validate="m:1")
+    .join(chetty_by_opeid, on="opeid", how="left", validate="m:1")
     .with_columns(
         pl.coalesce(
             [
@@ -279,6 +318,8 @@ college_ref = (
         "ID_FSC",
         "unitid",
         "ID_OPE",
+        "opeid",
+        "super_opeid",
         "college_name",
         "college_years",
         "college_ownership",
@@ -286,6 +327,8 @@ college_ref = (
         "college_4yr",
         "college_2yr",
         "tier",
+        "tier_name",
+        "superopeid_name",
         "college_elite",
     )
 )
@@ -415,12 +458,12 @@ nsc_new = (
     .with_row_index("origsrt", offset=1)
     .filter(pl.col("studyid").is_not_null())
     .with_columns(
-        pl.col("studyid").cast(pl.String).str.replace_all("_", "").alias("sid_cepr")
+        pl.col("studyid").cast(pl.String).str.split("_").alias("sid_cepr")
     )
     .explode("sid_cepr")
     .filter(pl.col("sid_cepr") != "")
     .with_columns(
-        pl.col("sid_cepr").cast(pl.String).str.replace_all("_", "").cast(pl.Int64, strict=False)
+        pl.col("sid_cepr").cast(pl.Int64, strict=False)
     )
     .filter(
         pl.col("sid_cepr").is_not_null()
@@ -759,8 +802,15 @@ for year in range(1, N_YEARS_OUT + 1):
                 end_month, end_day = 6, 30
 
             bounded = enroll.with_columns(
-                pl.date(start_year, start_month, start_day).alias("_window_start"),
-                pl.date(end_year, end_month, end_day).alias("_window_end"),
+                start_year.alias("_window_start_year"),
+                end_year.alias("_window_end_year"),
+            ).with_columns(
+                pl.date(pl.col("_window_start_year"), start_month, start_day).alias(
+                    "_window_start"
+                ),
+                pl.date(pl.col("_window_end_year"), end_month, end_day).alias(
+                    "_window_end"
+                ),
             ).with_columns(
                 (
                     (pl.col("term_start_date") <= pl.col("_window_end"))
@@ -1211,9 +1261,15 @@ nsc_outcomes = (
 )
 
 for year in range(1, N_YEARS_OUT + 1):
-    in_start = pl.date(pl.col("cohort_18") + year - 1, 7, 1)
-    by_start = pl.date(pl.col("cohort_18"), 7, 1)
-    by_end = pl.date(pl.col("cohort_18") + year, 6, 30)
+    nsc_outcomes = nsc_outcomes.with_columns(
+        (pl.col("cohort_18") + year - 1).alias("_in_start_year"),
+        pl.col("cohort_18").alias("_by_start_year"),
+        (pl.col("cohort_18") + year).alias("_by_end_year"),
+    ).with_columns(
+        pl.date(pl.col("_in_start_year"), 7, 1).alias("_in_start"),
+        pl.date(pl.col("_by_start_year"), 7, 1).alias("_by_start"),
+        pl.date(pl.col("_by_end_year"), 6, 30).alias("_by_end"),
+    )
 
     att_in_columns = [
         column
@@ -1235,7 +1291,7 @@ for year in range(1, N_YEARS_OUT + 1):
 
     nsc_outcomes = nsc_outcomes.with_columns(
         [
-            pl.when(in_start > NSC_CUTOFF_DATE)
+            pl.when(pl.col("_in_start") > NSC_CUTOFF_DATE)
             .then(None)
             .when(pl.col(column).is_null())
             .then(0)
@@ -1246,7 +1302,7 @@ for year in range(1, N_YEARS_OUT + 1):
         ]
         +
         [
-            pl.when(by_start > NSC_CUTOFF_DATE)
+            pl.when(pl.col("_by_start") > NSC_CUTOFF_DATE)
             .then(None)
             .when(pl.col(column).is_null())
             .then(0)
@@ -1257,7 +1313,7 @@ for year in range(1, N_YEARS_OUT + 1):
         ]
         +
         [
-            pl.when(by_end > NSC_CUTOFF_DATE)
+            pl.when(pl.col("_by_end") > NSC_CUTOFF_DATE)
             .then(None)
             .when(pl.col(column).is_null())
             .then(0)