ltc-code 0.2.26__tar.gz → 0.2.28__tar.gz

{ltc_code-0.2.26 → ltc_code-0.2.28}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: ltc-code
-Version: 0.2.26
+Version: 0.2.28
 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-0.2.28}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ltc-code"
-version = "0.2.26"
+version = "0.2.28"
 description = "Add your description here"
 readme = "README.md"
 requires-python = ">=3.9"

{ltc_code-0.2.26 → ltc_code-0.2.28}/pyproject.toml.orig

@@ -1,6 +1,6 @@
 [project]
 name = "ltc-code"
-version = "0.2.26"
+version = "0.2.28"
 description = "Add your description here"
 readme = "README.md"
 requires-python = ">=3.9"

{ltc_code-0.2.26 → ltc_code-0.2.28}/src/ltc_code/nsc/build_nsc_outcomes.py

@@ -1198,9 +1198,10 @@ for year in range(1, N_YEARS_OUT + 1):
                     [
                         (
                             pl.col("_overlaps")
-                            * pl.col(f"college_{college_type}")
-                            .fill_null(0)
-                            .cast(pl.Int8)
+                            * (
+                                pl.lit(1) if college_type == "any"
+                                else pl.col(f"college_{college_type}").fill_null(0).cast(pl.Int8)
+                            )
                         )
                         .max()
                         .alias(f"att_{college_type}_{label}")
@@ -1258,9 +1259,10 @@ for age in AGE_ATTENDANCE_RANGE:
             [
                 (
                     pl.col("_overlaps")
-                    * pl.col(f"college_{college_type}")
-                    .fill_null(0)
-                    .cast(pl.Int8)
+                    * (
+                        pl.lit(1) if college_type == "any"
+                        else pl.col(f"college_{college_type}").fill_null(0).cast(pl.Int8)
+                    )
                 )
                 .max()
                 .alias(f"att_{college_type}_{age}")
@@ -1860,6 +1862,86 @@ 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"),
+)
+
+# Separate the fully coarse prediction by first-institution sector.
+nsc_outcomes = nsc_outcomes.with_columns(
+    pl.when(
+        pl.col("adj_cmp_rate_coarse").is_not_null()
+        & pl.col("college_years_firstinst").is_in([1, 2])
+    )
+    .then(0.0)
+    .otherwise(pl.col("adj_cmp_rate_coarse"))
+    .alias("adj_cmp_rate_coarse_4yr"),
+    pl.when(
+        pl.col("adj_cmp_rate_coarse").is_not_null()
+        & (pl.col("college_years_firstinst") == 4)
+    )
+    .then(0.0)
+    .otherwise(pl.col("adj_cmp_rate_coarse"))
+    .alias("adj_cmp_rate_coarse_2yr"),
+)
+
+# Give each IPEDS institution one tier, excluding missing crosswalk tiers.
+ipeds_tiers = college_ref.select("unitid", "tier").drop_nulls().unique()
+ipeds_tier_completion = ipeds_completion_with_sector.join(
+    ipeds_tiers, on="unitid", how="left", validate="1:1"
+).filter(pl.col("college_sector") == "4yr")
+
+# Coarsen one bucket at a time, always starting from the detailed prediction.
+tier_buckets = {"t12": [1, 2], "t34": [3, 4], "t58": [5, 6, 7, 8]}
+for label, tiers in tier_buckets.items():
+    bucket_rate = (
+        ipeds_tier_completion.filter(pl.col("tier").is_in(tiers))
+        .select(
+            pl.col("completers_150pct_ip").sum()
+            / pl.col("cohort_adj_150pct_ip").sum()
+        )
+        .item()
+    )
+    nsc_outcomes = nsc_outcomes.with_columns(
+        pl.when(
+            (pl.col("college_years_firstinst") == 4)
+            & pl.col("tier_firstinst").is_in(tiers)
+            & (pl.col("att_any_byY4") == 1)
+            & pl.col("adj_cmp_rate_4yr").is_not_null()
+        )
+        .then(bucket_rate)
+        .otherwise(pl.col("adj_cmp_rate_4yr"))
+        .alias(f"adj_cmp_rate_4yr_coarse_{label}")
+    )
+    print(f"Four-year IPEDS-cohort-weighted completion rate, {label}: {bucket_rate}")
+
+# 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 +1958,7 @@ 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 +2015,11 @@ keep_columns = [
     "completion_rate_150pct_ip",
     "cmp_rate",
     "adj_cmp_rate",
+    "adj_cmp_rate_2yr",
+    "adj_cmp_rate_4yr",
+    "adj_cmp_rate_coarse_2yr",
+    "adj_cmp_rate_coarse_4yr",
+    *[f"adj_cmp_rate_4yr_coarse_{label}" for label in tier_buckets],
     "adj_cmp_rate_coarse",
     "adj_cmp_rate_coarse_sample",
     "adj_cmp_rate_coarsen_4yr",
@@ -2012,15 +2100,8 @@ coarse_audit = observable_y4.select(
 
 if coarse_audit.item(0, "k_mean_coarse_missing") > 0:
     raise ValueError("k_mean_coarse is unexpectedly missing for observable students.")
-if coarse_audit.item(0, "adj_cmp_rate_coarse_missing") > 0:
-    raise ValueError(
-        "adj_cmp_rate_coarse is unexpectedly missing for observable students."
-    )
-if coarse_audit.item(0, "adj_cmp_rate_coarse_sample_missing") > 0:
-    raise ValueError(
-        "adj_cmp_rate_coarse_sample is unexpectedly missing for observable students."
-    )
-
+# Attendees without a classified first college can have missing coarse rates.
+# Report those counts below rather than treating them as a build failure.
 print("Coarse outcome audit:")
 print(coarse_audit)
 
@@ -2067,3 +2148,18 @@ 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)

ltc_code-0.2.28/src/ltc_code/plot_bars.py

@@ -0,0 +1,84 @@
+# --- Import necessary packages ---
+# Required libraries: polars (input DataFrame), pandas, plotnine, oi-tools.
+# Install in your analysis project: uv add polars pandas plotnine oi-tools
+from typing import Optional
+import pandas as pd
+from oi_tools.figures import theme_oi
+from plotnine import (
+    aes, annotate, coord_cartesian, geom_col, geom_errorbar, geom_text,
+    geom_vline, ggplot, labs, scale_x_continuous, theme,
+)
+
+
+def plot_bars(
+    df,
+    y_col: str,
+    plot_label: str,
+    which_control: str = "ccm",
+    scale: float = 1,
+    sample_col: Optional[str] = None,
+):
+    """Use the first row, or one pair per row when sample_col is provided.
+
+    df is a Polars DataFrame containing ccm (or which_control), coef, se,
+    and N_ppl. scale=1/1000 adds K; scale=100 adds %; otherwise no suffix.
+    y_col is the axis title; sample_col may label samples or outcomes.
+    The treated interval is control + coef +/- 1.96 * se, as before.
+    """
+    suffix = "K" if scale == 1 / 1000 else "%" if scale == 100 else ""
+    n_samples = df.height if sample_col is not None else 1
+    frames, notes = [], []
+
+    for i in range(n_samples):
+        control = df.item(i, which_control) * scale
+        effect = df.item(i, "coef") * scale
+        se = df.item(i, "se") * abs(scale)
+        n_ppl = df.item(i, "N_ppl") / 1000
+
+        frames.append(pd.DataFrame({
+            "group": ["Control", "Treated"],
+            "x": [3 * i + 1, 3 * i + 2],
+            "value": [control, control + effect],
+            "ci_lo": [None, control + effect - 1.96 * se],
+            "ci_hi": [None, control + effect + 1.96 * se],
+            "label": [f"{control:.1f}{suffix}",
+                      f"{control + effect:.1f}{suffix}"],
+        }))
+        sample = f"{df.item(i, sample_col)}\n" if sample_col is not None else ""
+        notes.append({
+            "x": 3 * i + 1.5,
+            "label": (f"{sample}Delta = {effect:.1f}{suffix} (se = {se:.1f}{suffix})"
+                      f"\n(N_ppl = {n_ppl:.1f}K)"),
+        })
+
+    plot_data = pd.concat(frames, ignore_index=True)
+    treated = plot_data.iloc[1::2]
+    y_min = min(0.5 * plot_data["value"].min(), treated["ci_lo"].min(),
+                plot_data["value"].min())
+    top = max(plot_data["value"].max(), treated["ci_hi"].max())
+    span = max(top - y_min, 1e-6)
+    y_max = top + 0.35 * span
+    plot_data["label_y"] = plot_data[["value", "ci_hi"]].max(axis=1) + 0.025 * span
+
+    p = (
+        ggplot(plot_data, aes(x="x", y="value"))
+        + theme_oi()
+        + geom_col(width=0.5, fill="#F8766D")
+        + geom_errorbar(
+            data=treated, mapping=aes(ymin="ci_lo", ymax="ci_hi"), width=0.15,
+        )
+        + labs(title=plot_label, x="", y=y_col)
+        + geom_text(aes(y="label_y", label="label"), va="bottom", size=10)
+        + scale_x_continuous(breaks=plot_data["x"].tolist(),
+                             labels=plot_data["group"].tolist())
+        + coord_cartesian(ylim=(y_min, y_max))
+        + theme(figure_size=(max(6, 3 * n_samples), 5.5))
+    )
+    for note in notes:
+        p += annotate("text", x=note["x"], y=top + 0.23 * span,
+                      label=note["label"], size=10, fontweight="bold")
+    if n_samples > 1:
+        p += geom_vline(xintercept=[3 * i for i in range(1, n_samples)],
+                        linetype="dashed", color="grey", size=0.5)
+
+    return p