feat: skin substitutes marimo notebook + snippet (refs #245)

Interactive explorer with 6 tabs:
- ASP Pricing: product-level time series with $127.28 flat rate line
- Market: manufacturer revenue bar chart, product category breakdown
- Geographic: state spend/bene, MAC jurisdiction comparison
- Setting: specialty x setting spend analysis
- Anomaly: provider risk scatter (volume vs intensity z-scores)
- Evidence: source distribution, study characteristics summary

Snippet: skin-subs-connect.py for quick DuckDB table inventory.
Updated snippet count test from 10 to 11.

infra/marimo/snippets/skin-subs-connect.py

@@ -0,0 +1,44 @@
+import marimo
+
+__generated_with = "0.20.4"
+app = marimo.App()
+
+
+@app.cell
+def _(mo):
+    mo.md(r"""
+    # Skin Substitutes: Connect to DuckDB
+
+    Load all 17 skin_subs tables for analysis.
+    """)
+    return
+
+
+@app.cell
+def _():
+    import polars as pl
+    from conf import connect
+
+    con = connect.duckdb()
+
+    # Quick inventory
+    tables = con.execute("""
+        SELECT table_name, (
+            SELECT count(*) FROM skin_subs. || table_name
+        ) as row_count
+        FROM information_schema.tables
+        WHERE table_schema = 'skin_subs'
+        ORDER BY table_name
+    """).fetchdf()
+    return con, connect, pl, tables
+
+
+@app.cell
+def _():
+    import marimo as mo
+
+    return (mo,)
+
+
+if __name__ == "__main__":
+    app.run()

notebooks/skin_subs_explorer.py

@@ -0,0 +1,343 @@
+import marimo
+
+__generated_with = "0.20.4"
+app = marimo.App(width="medium")
+
+
+@app.cell(hide_code=True)
+def _():
+    import marimo as mo
+
+    return (mo,)
+
+
+@app.cell(hide_code=True)
+def _(mo):
+    mo.md("""
+    # Skin Substitutes Analysis
+
+    Predatory pricing, distribution, and utilization analysis of skin
+    substitute / cellular tissue products (CTPs) in the Medicare program.
+
+    **Hypothesis:** Certain distributors, products, geographies, and care
+    settings are softer or harder targets for predatory use and pricing.
+
+    Navigate sections using the tabs below.
+    """)
+    return
+
+
+@app.cell
+def _():
+    import altair as alt
+    import polars as pl
+    from conf import connect
+
+    con = connect.duckdb()
+    return alt, con, connect, pl
+
+
+@app.cell(hide_code=True)
+def _(mo):
+    tabs = mo.ui.tabs(
+        {
+            "ASP Pricing": mo.md("Loading..."),
+            "Market": mo.md("Loading..."),
+            "Geographic": mo.md("Loading..."),
+            "Setting": mo.md("Loading..."),
+            "Anomaly": mo.md("Loading..."),
+            "Evidence": mo.md("Loading..."),
+        }
+    )
+    tabs
+    return (tabs,)
+
+
+# ── ASP Pricing Tab ──────────────────────────────────────────────
+
+
+@app.cell(hide_code=True)
+def _(alt, con, mo, pl):
+    asp = pl.from_pandas(
+        con.execute("""
+            SELECT quarter, hcpcs_code, product_name, manufacturer, category,
+                   asp_per_unit, payment_limit, entry_quarter, total_quarters,
+                   qoq_pct_change, cumulative_pct_change,
+                   flat_rate_impact, anomalous_spike
+            FROM skin_subs.asp_trajectories
+            ORDER BY quarter
+        """).fetchdf()
+    )
+
+    products = sorted(asp["hcpcs_code"].unique().to_list())
+    product_select = mo.ui.multiselect(
+        products, label="Products", value=["Q4101", "Q4186", "Q4121"]
+    )
+    product_select
+    return asp, product_select, products
+
+
+@app.cell(hide_code=True)
+def _(alt, asp, mo, pl, product_select):
+    mo.stop(not product_select.value, mo.md("Select products above."))
+    filtered = asp.filter(pl.col("hcpcs_code").is_in(product_select.value))
+    labels = (
+        filtered.select(["hcpcs_code", "product_name"])
+        .unique()
+        .with_columns(
+            (pl.col("hcpcs_code") + " " + pl.col("product_name").fill_null("")).alias("label")
+        )
+    )
+    chart_data = filtered.join(labels, on="hcpcs_code").to_pandas()
+
+    chart = (
+        alt.Chart(chart_data)
+        .mark_line(point=True)
+        .encode(
+            x=alt.X("quarter:N", title="Quarter", axis=alt.Axis(labelAngle=-45)),
+            y=alt.Y("payment_limit:Q", title="Payment Limit ($/cm²)"),
+            color=alt.Color("label:N", title="Product"),
+            tooltip=["quarter", "hcpcs_code", "product_name", "manufacturer",
+                     "asp_per_unit", "payment_limit", "qoq_pct_change"],
+        )
+        .properties(width=700, height=400, title="ASP Payment Limit Over Time")
+    )
+
+    flat_rate_line = (
+        alt.Chart(chart_data.head(1))
+        .mark_rule(color="red", strokeDash=[4, 4])
+        .encode(y=alt.datum(127.28))
+    )
+
+    flat_label = (
+        alt.Chart(chart_data.head(1))
+        .mark_text(align="left", dx=5, dy=-5, color="red", fontSize=10)
+        .encode(y=alt.datum(127.28), text=alt.datum("$127.28 flat rate (Jan 2026)"))
+    )
+
+    mo.ui.altair_chart(chart + flat_rate_line + flat_label)
+    return
+
+
+# ── Market Tab ───────────────────────────────────────────────────
+
+
+@app.cell(hide_code=True)
+def _(alt, con, mo, pl):
+    mfr = pl.from_pandas(
+        con.execute("""
+            SELECT manufacturer, product_count, active_products,
+                   total_revenue, avg_asp, categories
+            FROM skin_subs.manufacturers
+            WHERE total_revenue IS NOT NULL
+            ORDER BY total_revenue DESC LIMIT 15
+        """).fetchdf()
+    )
+
+    mfr_chart = (
+        alt.Chart(mfr.to_pandas())
+        .mark_bar()
+        .encode(
+            x=alt.X("total_revenue:Q", title="Total Revenue ($)"),
+            y=alt.Y("manufacturer:N", sort="-x", title=None),
+            color=alt.Color("avg_asp:Q", scale=alt.Scale(scheme="reds"), title="Avg ASP ($/cm²)"),
+            tooltip=["manufacturer", "product_count", "active_products",
+                     "total_revenue", "avg_asp", "categories"],
+        )
+        .properties(width=600, height=350, title="Top Manufacturers by Revenue")
+    )
+
+    # Category breakdown
+    cat = pl.from_pandas(
+        con.execute("""
+            SELECT category, count(*) as products,
+                   round(avg(latest_asp), 2) as avg_asp,
+                   sum(claim_lines) as claims
+            FROM skin_subs.products_enriched
+            WHERE category IS NOT NULL
+            GROUP BY category ORDER BY products DESC LIMIT 12
+        """).fetchdf()
+    )
+
+    cat_chart = (
+        alt.Chart(cat.to_pandas())
+        .mark_bar()
+        .encode(
+            x=alt.X("products:Q", title="Product Count"),
+            y=alt.Y("category:N", sort="-x", title=None),
+            color=alt.Color("avg_asp:Q", scale=alt.Scale(scheme="blues"), title="Avg ASP"),
+            tooltip=["category", "products", "avg_asp", "claims"],
+        )
+        .properties(width=600, height=300, title="Products by Category")
+    )
+
+    mo.vstack([mo.ui.altair_chart(mfr_chart), mo.ui.altair_chart(cat_chart)])
+    return cat, cat_chart, mfr, mfr_chart
+
+
+# ── Geographic Tab ───────────────────────────────────────────────
+
+
+@app.cell(hide_code=True)
+def _(alt, con, mo, pl):
+    geo = pl.from_pandas(
+        con.execute("""
+            SELECT state, mac_jurisdiction, claim_lines, unique_benes,
+                   unique_providers, total_paid, paid_per_bene,
+                   pct_office, pct_podiatry
+            FROM skin_subs.geographic_summary
+            ORDER BY total_paid DESC
+        """).fetchdf()
+    )
+
+    geo_chart = (
+        alt.Chart(geo.to_pandas())
+        .mark_bar()
+        .encode(
+            x=alt.X("paid_per_bene:Q", title="Paid per Beneficiary ($)"),
+            y=alt.Y("state:N", sort="-x", title=None),
+            color=alt.Color("mac_jurisdiction:N", title="MAC Jurisdiction"),
+            tooltip=["state", "mac_jurisdiction", "unique_benes", "total_paid",
+                     "paid_per_bene", "pct_office", "pct_podiatry"],
+        )
+        .properties(width=600, height=400, title="Spend per Beneficiary by State")
+    )
+
+    mac = pl.from_pandas(
+        con.execute("SELECT * FROM skin_subs.mac_summary ORDER BY total_paid DESC").fetchdf()
+    )
+
+    mac_chart = (
+        alt.Chart(mac.to_pandas())
+        .mark_bar()
+        .encode(
+            x=alt.X("total_paid:Q", title="Total Paid ($)"),
+            y=alt.Y("mac_jurisdiction:N", sort="-x", title=None),
+            color=alt.Color("avg_pct_podiatry:Q", scale=alt.Scale(scheme="oranges"),
+                           title="% Podiatry"),
+            tooltip=["mac_jurisdiction", "states", "claim_lines", "total_paid",
+                     "avg_paid_per_bene", "avg_pct_office", "avg_pct_podiatry"],
+        )
+        .properties(width=600, height=250, title="Total Paid by MAC Jurisdiction")
+    )
+
+    mo.vstack([mo.ui.altair_chart(geo_chart), mo.ui.altair_chart(mac_chart)])
+    return geo, geo_chart, mac, mac_chart
+
+
+# ── Setting Tab ──────────────────────────────────────────────────
+
+
+@app.cell(hide_code=True)
+def _(alt, con, mo, pl):
+    setting = pl.from_pandas(
+        con.execute("""
+            SELECT setting, provider_specialty,
+                   sum(claim_lines) as lines, round(sum(total_paid), 2) as paid
+            FROM skin_subs.setting_analysis
+            GROUP BY setting, provider_specialty
+            ORDER BY paid DESC
+        """).fetchdf()
+    )
+
+    setting_chart = (
+        alt.Chart(setting.to_pandas())
+        .mark_bar()
+        .encode(
+            x=alt.X("paid:Q", title="Total Paid ($)"),
+            y=alt.Y("provider_specialty:N", sort="-x", title=None),
+            color=alt.Color("setting:N", title="Setting"),
+            tooltip=["setting", "provider_specialty", "lines", "paid"],
+        )
+        .properties(width=600, height=300, title="Spend by Specialty and Setting")
+    )
+
+    mo.ui.altair_chart(setting_chart)
+    return setting, setting_chart
+
+
+# ── Anomaly Tab ──────────────────────────────────────────────────
+
+
+@app.cell(hide_code=True)
+def _(alt, con, mo, pl):
+    risk = pl.from_pandas(
+        con.execute("""
+            SELECT rendering_npi, provider_specialty, state, primary_setting,
+                   total_paid, paid_per_patient, unique_patients,
+                   volume_zscore, intensity_zscore, composite_risk,
+                   risk_tier, fraud_pattern_match, benford_chi2
+            FROM skin_subs.provider_risk_profile
+            ORDER BY composite_risk DESC
+        """).fetchdf()
+    )
+
+    scatter = (
+        alt.Chart(risk.to_pandas())
+        .mark_circle(size=60)
+        .encode(
+            x=alt.X("volume_zscore:Q", title="Volume Z-Score (vs specialty peers)"),
+            y=alt.Y("intensity_zscore:Q", title="Intensity Z-Score ($/patient)"),
+            color=alt.Color("risk_tier:N",
+                           scale=alt.Scale(
+                               domain=["critical", "high", "moderate", "low"],
+                               range=["#d62728", "#ff7f0e", "#bcbd22", "#2ca02c"]),
+                           title="Risk Tier"),
+            size=alt.Size("total_paid:Q", title="Total Paid"),
+            shape=alt.Shape("primary_setting:N", title="Setting"),
+            tooltip=["rendering_npi", "provider_specialty", "state",
+                     "primary_setting", "total_paid", "paid_per_patient",
+                     "composite_risk", "risk_tier", "fraud_pattern_match"],
+        )
+        .properties(width=650, height=450, title="Provider Risk: Volume vs Intensity")
+    )
+
+    # Risk tier distribution
+    tier = risk.group_by("risk_tier").agg(
+        pl.col("rendering_npi").count().alias("n"),
+        pl.col("total_paid").mean().round(0).alias("avg_paid"),
+    )
+
+    tier_table = mo.ui.table(tier.to_pandas())
+
+    mo.vstack([mo.ui.altair_chart(scatter), mo.md("### Risk Tier Distribution"), tier_table])
+    return risk, scatter, tier, tier_table
+
+
+# ── Evidence Tab ─────────────────────────────────────────────────
+
+
+@app.cell(hide_code=True)
+def _(con, mo, pl):
+    ev = pl.from_pandas(
+        con.execute("""
+            SELECT source_tag, count(*) as items,
+                   count(*) FILTER (WHERE is_snowball) as snowball
+            FROM skin_subs.evidence_base
+            GROUP BY source_tag ORDER BY items DESC
+        """).fetchdf()
+    )
+
+    study = pl.from_pandas(
+        con.execute("""
+            SELECT pub_type, count(*) as n,
+                   count(*) FILTER (WHERE product_count > 0) as with_products,
+                   count(*) FILTER (WHERE sample_size IS NOT NULL) as with_sample,
+                   round(avg(sample_size), 0) as avg_sample
+            FROM skin_subs.study_characteristics
+            GROUP BY pub_type ORDER BY n DESC
+        """).fetchdf()
+    )
+
+    mo.vstack([
+        mo.md("### Evidence Base by Source"),
+        mo.ui.table(ev.to_pandas()),
+        mo.md("### Study Characteristics by Type"),
+        mo.ui.table(study.to_pandas()),
+        mo.md(f"**Total evidence items:** {ev['items'].sum():,}"),
+    ])
+    return ev, study
+
+
+if __name__ == "__main__":
+    app.run()

tests/test_notebook_layout.py

@@ -77,7 +77,7 @@ class TestInfraMarimo:
         snippets_dir = INFRA_MARIMO / "snippets"
         assert snippets_dir.is_dir()
         snippet_files = list(snippets_dir.glob("*.py"))
-        assert len(snippet_files) == 10
+        assert len(snippet_files) == 11
 
     def test_all_snippets_present(self):
         expected = {
@@ -90,6 +90,7 @@ class TestInfraMarimo:
             "query-pmpm.py",
             "query-schema.py",
             "s3-obstore.py",
+            "skin-subs-connect.py",
             "trino-connect.py",
         }
         actual = {p.name for p in (INFRA_MARIMO / "snippets").iterdir()}