fix: exclude examples.html from conformance tests and make Python blocks self-contained

- Add "examples.html" to NON_PLAYGROUND_PAGES in tests/playground.test.ts
  and tests-e2e/playground-cells.test.ts (it's an index/gallery page, not
  an interactive playground)
- Prepend data-setup code to each playground-python textarea block so every
  block runs independently without depending on variables from the JS editor
  or other blocks (fixes 18 Python validation failures)

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: github-actions[bot]

playground/example_ab_test.html

@@ -193,6 +193,13 @@ <h2>1 · Conversion rate by variant</h2>
 const lift = ((b - a) / a) * 100;
 console.log(`\nLift in conversion rate: ${lift.toFixed(1)}%`);</textarea>
       <textarea class="playground-python" style="display:none">import pandas as pd
+sessions = pd.DataFrame({
+    "variant": ["A"]*20 + ["B"]*20,
+    "converted": [0,1,0,0,1,0,0,0,1,0,1,0,0,0,1,0,0,1,0,0,
+                  1,1,0,1,0,1,1,0,1,0,1,1,0,1,1,0,0,1,1,1],
+    "order_value": [0,42,0,0,35,0,0,0,51,0,28,0,0,0,60,0,0,33,0,0,
+                    47,51,0,39,0,64,38,0,55,0,41,47,0,33,58,0,0,49,36,52],
+})
 summary = sessions.groupby("variant", as_index=False).agg(
     conv_rate=("converted", "mean"),
     avg_order_value=("order_value", "mean"),
@@ -240,6 +247,11 @@ <h2>2 · Order value distribution per variant</h2>
 console.log("\nVariant B order values:");
 console.log(describe(b).toString());</textarea>
       <textarea class="playground-python" style="display:none">import pandas as pd
+sessions = pd.DataFrame({
+    "variant": ["A"]*20 + ["B"]*20,
+    "order_value": [0,42,0,0,35,0,0,0,51,0,28,0,0,0,60,0,0,33,0,0,
+                    47,51,0,39,0,64,38,0,55,0,41,47,0,33,58,0,0,49,36,52],
+})
 converted = sessions[sessions["order_value"] &gt; 0]
 print(converted[converted["variant"]=="A"]["order_value"].describe())
 print(converted[converted["variant"]=="B"]["order_value"].describe())</textarea>

playground/example_customer_cohorts.html

@@ -194,6 +194,13 @@ <h2>1 · Monthly signups & cumulative growth</h2>
 console.log("");
 console.log(out.toString());</textarea>
       <textarea class="playground-python" style="display:none">import pandas as pd
+events = pd.DataFrame({
+    "customer_id": list(range(1000, 1060)),
+    "signup_month": (
+        ["2024-01"]*4 + ["2024-02"]*6 + ["2024-03"]*5 + ["2024-04"]*8 +
+        ["2024-05"]*7 + ["2024-06"]*9 + ["2024-07"]*11 + ["2024-08"]*10
+    ),
+})
 monthly = events.groupby("signup_month", as_index=False).size()
 monthly["cumulative"] = monthly["size"].cumsum()
 monthly["mom_growth_pct"] = (monthly["size"].pct_change() * 100).round(1)
@@ -241,6 +248,10 @@ <h2>2 · Visualise cohort growth</h2>
 console.log(`\nTotal customers: ${total}`);
 console.log(`Best cohort   : ${best}`);</textarea>
       <textarea class="playground-python" style="display:none">import pandas as pd
+monthly = pd.DataFrame({
+    "month": ["Jan","Feb","Mar","Apr","May","Jun","Jul","Aug"],
+    "signups": [4, 6, 5, 8, 7, 9, 11, 10],
+})
 print(monthly)
 print("Total:", monthly["signups"].sum())
 print("Best :", monthly.loc[monthly["signups"].idxmax(), "month"])</textarea>

playground/example_log_analysis.html

@@ -199,6 +199,20 @@ <h2>1 · Parse and bucket access logs</h2>
 console.log("Requests per hour by status class:");
 console.log(piv.toString());</textarea>
       <textarea class="playground-python" style="display:none">import pandas as pd
+log = pd.DataFrame({
+    "ts": [
+        "10:01","10:03","10:09","10:14","10:22","10:31","10:47","10:55",
+        "11:02","11:04","11:09","11:18","11:25","11:33","11:41","11:50","11:55","11:58",
+        "12:01","12:03","12:08","12:14","12:22","12:31","12:38","12:45",
+        "13:02","13:09","13:14","13:25","13:31","13:48","13:55",
+    ],
+    "status": [
+        200,200,200,404,200,500,200,200,
+        200,500,500,500,200,200,404,500,500,500,
+        200,200,200,200,200,200,404,200,
+        200,500,200,200,200,200,200,
+    ],
+})
 log["hour"] = log["ts"].str.slice(0, 2).astype(int)
 log["cls"]  = log["status"].apply(lambda s: "5xx" if s&gt;=500 else ("4xx" if s&gt;=400 else "2xx"))
 piv = log.groupby(["hour","cls"]).size().unstack(fill_value=0)
@@ -245,6 +259,12 @@ <h2>2 · Error rate per hour & alert threshold</h2>
 }
 if (flagged === 0) console.log("  (all hours healthy)");</textarea>
       <textarea class="playground-python" style="display:none">import pandas as pd
+by_hour = pd.DataFrame({
+    "hour": [10, 11, 12, 13],
+    "2xx": [6, 5, 7, 6],
+    "4xx": [1, 1, 1, 0],
+    "5xx": [1, 6, 0, 1],
+})
 by_hour["total"]   = by_hour[["2xx","4xx","5xx"]].sum(axis=1)
 by_hour["5xx_pct"] = (by_hour["5xx"] / by_hour["total"] * 100).round(1)
 print(by_hour)

playground/example_pricing_buckets.html

@@ -180,6 +180,11 @@ <h2>1 · Bucket products into price tiers</h2>
 console.log("\nProducts per tier:");
 console.log(valueCounts(enriched.col("tier")).toString());</textarea>
       <textarea class="playground-python" style="display:none">import pandas as pd
+catalogue = pd.DataFrame({
+    "sku":    ["A1","A2","A3","B1","B2","B3","C1","C2","C3","D1","D2","D3","E1","E2","E3"],
+    "price":  [9.99,14.50,19.00,22.00,29.50,39.00,49.00,65.00,79.99,99.00,129.00,149.00,199.00,249.00,349.00],
+    "margin": [0.30,0.32,0.28,0.34,0.36,0.40,0.42,0.45,0.46,0.48,0.50,0.52,0.55,0.58,0.60],
+})
 catalogue["tier"] = pd.cut(
     catalogue["price"],
     bins=[0, 25, 75, 150, 1000],
@@ -244,6 +249,13 @@ <h2>2 · Avg margin by tier</h2>
 console.log("");
 chart("Avg margin % per tier", rows);</textarea>
       <textarea class="playground-python" style="display:none">import pandas as pd
+enriched = pd.DataFrame({
+    "sku":    ["A1","A2","A3","B1","B2","B3","C1","C2","C3","D1","D2","D3","E1","E2","E3"],
+    "price":  [9.99,14.50,19.00,22.00,29.50,39.00,49.00,65.00,79.99,99.00,129.00,149.00,199.00,249.00,349.00],
+    "margin": [0.30,0.32,0.28,0.34,0.36,0.40,0.42,0.45,0.46,0.48,0.50,0.52,0.55,0.58,0.60],
+    "tier":   ["Budget","Budget","Budget","Budget","Mid","Mid","Mid","Mid",
+               "Premium","Premium","Premium","Premium","Luxury","Luxury","Luxury"],
+})
 by_tier = enriched.groupby("tier", as_index=False).agg(
     avg_price=("price","mean"),
     avg_margin=("margin","mean"),

playground/example_sales_dashboard.html

@@ -188,7 +188,20 @@ <h2>1 · Load the sales CSV</h2>
 
 csv = """order_id,date,region,product,units,unit_price
 1001,2024-01-03,North,Widget,4,19.99
-..."""
+1002,2024-01-05,South,Gadget,2,49.50
+1003,2024-01-09,East,Widget,7,19.99
+1004,2024-01-12,West,Gizmo,1,129.00
+1005,2024-01-18,North,Gadget,3,49.50
+1006,2024-01-22,South,Widget,5,19.99
+1007,2024-02-02,East,Gizmo,2,129.00
+1008,2024-02-08,North,Widget,6,19.99
+1009,2024-02-14,West,Gadget,4,49.50
+1010,2024-02-19,South,Gizmo,1,129.00
+1011,2024-03-01,East,Widget,8,19.99
+1012,2024-03-05,North,Gizmo,2,129.00
+1013,2024-03-11,West,Widget,3,19.99
+1014,2024-03-17,South,Gadget,6,49.50
+1015,2024-03-25,East,Gadget,2,49.50"""
 sales = pd.read_csv(StringIO(csv))
 print("Rows:", sales.shape[0], "Columns:", list(sales.columns))
 print(sales.head(5))</textarea>
@@ -258,6 +271,25 @@ <h2>2 · Compute revenue & rank regions</h2>
 console.log("");
 chart("Revenue by region ($)", rows);</textarea>
       <textarea class="playground-python" style="display:none">import pandas as pd
+from io import StringIO
+
+csv = """order_id,region,product,units,unit_price
+1001,North,Widget,4,19.99
+1002,South,Gadget,2,49.50
+1003,East,Widget,7,19.99
+1004,West,Gizmo,1,129.00
+1005,North,Gadget,3,49.50
+1006,South,Widget,5,19.99
+1007,East,Gizmo,2,129.00
+1008,North,Widget,6,19.99
+1009,West,Gadget,4,49.50
+1010,South,Gizmo,1,129.00
+1011,East,Widget,8,19.99
+1012,North,Gizmo,2,129.00
+1013,West,Widget,3,19.99
+1014,South,Gadget,6,49.50
+1015,East,Gadget,2,49.50"""
+sales = pd.read_csv(StringIO(csv))
 
 sales["revenue"] = sales["units"] * sales["unit_price"]
 by_region = sales.groupby("region", as_index=False)["revenue"].sum()
@@ -316,6 +348,25 @@ <h2>3 · Top products & best single order</h2>
 console.log("\nTop 3 single orders by revenue:");
 console.log(top3.toString());</textarea>
       <textarea class="playground-python" style="display:none">import pandas as pd
+from io import StringIO
+
+csv = """order_id,region,product,units,unit_price
+1001,North,Widget,4,19.99
+1002,South,Gadget,2,49.50
+1003,East,Widget,7,19.99
+1004,West,Gizmo,1,129.00
+1005,North,Gadget,3,49.50
+1006,South,Widget,5,19.99
+1007,East,Gizmo,2,129.00
+1008,North,Widget,6,19.99
+1009,West,Gadget,4,49.50
+1010,South,Gizmo,1,129.00
+1011,East,Widget,8,19.99
+1012,North,Gizmo,2,129.00
+1013,West,Widget,3,19.99
+1014,South,Gadget,6,49.50
+1015,East,Gadget,2,49.50"""
+sales = pd.read_csv(StringIO(csv))
 
 sales["revenue"] = sales["units"] * sales["unit_price"]
 by_product = sales.groupby("product", as_index=False).agg(

playground/example_sports_standings.html

@@ -205,6 +205,12 @@ <h2>1 · Build the standings table</h2>
 console.log("League table:");
 console.log(withRank.toString());</textarea>
       <textarea class="playground-python" style="display:none">import pandas as pd
+matches = pd.DataFrame({
+    "home": ["Lions","Tigers","Bears","Wolves","Lions","Bears","Tigers","Wolves","Lions","Tigers","Bears","Wolves"],
+    "away": ["Tigers","Bears","Wolves","Lions","Wolves","Tigers","Lions","Bears","Bears","Wolves","Lions","Tigers"],
+    "home_goals": [2,1,3,0,4,2,1,2,1,2,3,1],
+    "away_goals": [1,1,2,2,0,2,3,1,1,1,2,1],
+})
 home = matches.rename(columns={"home":"team","home_goals":"gf","away_goals":"ga"})[["team","gf","ga"]]
 away = matches.rename(columns={"away":"team","away_goals":"gf","home_goals":"ga"})[["team","gf","ga"]]
 team_matches = pd.concat([home, away], ignore_index=True)

playground/example_stock_returns.html

@@ -182,7 +182,15 @@ <h2>1 · Daily prices and returns</h2>
 console.log("\nMean daily return:", meanRet.toFixed(3) + "%");
 console.log("Std  daily return:", stdRet.toFixed(3) + "%");</textarea>
       <textarea class="playground-python" style="display:none">import pandas as pd
-prices = pd.DataFrame({"date": [...], "close": [...]})
+prices = pd.DataFrame({
+    "date": [
+        "2024-01-02","2024-01-03","2024-01-04","2024-01-05","2024-01-08",
+        "2024-01-09","2024-01-10","2024-01-11","2024-01-12","2024-01-16",
+        "2024-01-17","2024-01-18","2024-01-19","2024-01-22","2024-01-23",
+    ],
+    "close": [100.0,101.5,99.8,102.1,103.4,102.7,104.0,105.6,104.9,
+              106.3,107.0,106.2,108.5,109.1,110.0],
+})
 prices["return"] = prices["close"].pct_change()
 print(prices.head(8))
 print("Mean:", prices["return"].mean()*100, "%")
@@ -236,6 +244,11 @@ <h2>2 · Rolling stats & SMA crossover signal</h2>
 if (signals.length === 0) console.log("  (no crossovers in window)");
 for (const s of signals) console.log("  " + s);</textarea>
       <textarea class="playground-python" style="display:none">import pandas as pd
+prices = pd.DataFrame({
+    "day": list(range(1, 16)),
+    "close": [100.0,101.5,99.8,102.1,103.4,102.7,104.0,105.6,104.9,
+              106.3,107.0,106.2,108.5,109.1,110.0],
+})
 close = prices["close"]
 prices["sma3"] = close.rolling(3).mean()
 prices["sma5"] = close.rolling(5).mean()

playground/example_survey_crosstab.html

@@ -176,6 +176,8 @@ <h2>1 · Build the crosstab</h2>
 console.log("Counts (rows = experience, cols = language):");
 console.log(ct.toString());</textarea>
       <textarea class="playground-python" style="display:none">import pandas as pd
+langs = ["Python","JavaScript","Rust","Go","Python","JavaScript","Python","Rust","Go","JavaScript","Python","JavaScript","Rust","Python","Go","JavaScript","Python","Rust","Python","JavaScript","Go","Python","JavaScript","Rust","Python","Go","JavaScript","Python","Python","Rust"]
+exp   = ["Junior","Junior","Senior","Mid","Mid","Senior","Junior","Senior","Junior","Mid","Senior","Junior","Senior","Mid","Senior","Senior","Mid","Mid","Junior","Senior","Mid","Senior","Mid","Senior","Mid","Junior","Senior","Junior","Senior","Mid"]
 survey = pd.DataFrame({"language": langs, "experience": exp})
 ct = pd.crosstab(survey["experience"], survey["language"])
 print(ct)</textarea>
@@ -211,6 +213,9 @@ <h2>2 · Row percentages</h2>
 
 console.log("\nObservation: the largest cell in each row tells you that cohort's favourite language.");</textarea>
       <textarea class="playground-python" style="display:none">import pandas as pd
+langs = ["Python","JavaScript","Rust","Go","Python","JavaScript","Python","Rust","Go","JavaScript","Python","JavaScript","Rust","Python","Go","JavaScript","Python","Rust","Python","JavaScript","Go","Python","JavaScript","Rust","Python","Go","JavaScript","Python","Python","Rust"]
+exp   = ["Junior","Junior","Senior","Mid","Mid","Senior","Junior","Senior","Junior","Mid","Senior","Junior","Senior","Mid","Senior","Senior","Mid","Mid","Junior","Senior","Mid","Senior","Mid","Senior","Mid","Junior","Senior","Junior","Senior","Mid"]
+survey = pd.DataFrame({"language": langs, "experience": exp})
 ct = pd.crosstab(survey["experience"], survey["language"], normalize="index")
 print(ct.round(3))</textarea>
       <div class="playground-output">Click ▶ Run to execute</div>