Iteration 143: Add 8 benchmark pairs (437 total, +8 vs 429)

Add standalone functional-form benchmarks and new operation benchmarks:
- bench_quantile_fn: quantileSeries/quantileDataFrame standalone functions
- bench_pct_change_fn: pctChangeSeries/pctChangeDataFrame standalone functions
- bench_merge_suffixes: merge with custom suffixes option
- bench_expanding_min_periods: Expanding with minPeriods option
- bench_dt_isocalendar: DatetimeAccessor.isocalendar_week
- bench_period_asfreq: Period.asfreq/PeriodIndex.asfreq frequency conversion
- bench_sample_fn: sampleSeries/sampleDataFrame standalone functions
- bench_nunique_fn: nuniqueSeries/nuniqueDataFrame standalone functions

Run: https://github.com/githubnext/tsessebe/actions/runs/24547746540

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

Author: github-actions[bot]

benchmarks/pandas/bench_dt_isocalendar.py

@@ -0,0 +1,27 @@
+"""
+Benchmark: pandas DatetimeIndex.isocalendar().week on 100k dates.
+Outputs JSON: {"function": "dt_isocalendar", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+"""
+import json
+import time
+import pandas as pd
+
+ROWS = 100_000
+WARMUP = 3
+ITERATIONS = 10
+
+dates = pd.date_range("2000-01-01", periods=ROWS, freq="D")
+s = pd.Series(dates)
+
+for _ in range(WARMUP):
+    s.dt.isocalendar()["week"]
+
+times = []
+for _ in range(ITERATIONS):
+    t0 = time.perf_counter()
+    s.dt.isocalendar()["week"]
+    times.append((time.perf_counter() - t0) * 1000)
+
+total_ms = sum(times)
+mean_ms = total_ms / ITERATIONS
+print(json.dumps({"function": "dt_isocalendar", "mean_ms": round(mean_ms, 3), "iterations": ITERATIONS, "total_ms": round(total_ms, 3)}))

benchmarks/pandas/bench_expanding_min_periods.py

@@ -0,0 +1,32 @@
+"""
+Benchmark: pandas Expanding with min_periods option.
+Outputs JSON: {"function": "expanding_min_periods", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+"""
+import json
+import time
+import pandas as pd
+import numpy as np
+
+ROWS = 100_000
+WARMUP = 3
+ITERATIONS = 10
+
+data = [float('nan') if i % 10 == 0 else float(np.sin(i * 0.01)) for i in range(ROWS)]
+s = pd.Series(data)
+
+for _ in range(WARMUP):
+    s.expanding(min_periods=10).mean()
+    s.expanding(min_periods=50).sum()
+    s.expanding(min_periods=5).std()
+
+times = []
+for _ in range(ITERATIONS):
+    t0 = time.perf_counter()
+    s.expanding(min_periods=10).mean()
+    s.expanding(min_periods=50).sum()
+    s.expanding(min_periods=5).std()
+    times.append((time.perf_counter() - t0) * 1000)
+
+total_ms = sum(times)
+mean_ms = total_ms / ITERATIONS
+print(json.dumps({"function": "expanding_min_periods", "mean_ms": round(mean_ms, 3), "iterations": ITERATIONS, "total_ms": round(total_ms, 3)}))

benchmarks/pandas/bench_merge_suffixes.py

@@ -0,0 +1,34 @@
+"""
+Benchmark: pandas merge with custom suffixes option.
+Outputs JSON: {"function": "merge_suffixes", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+"""
+import json
+import time
+import pandas as pd
+
+ROWS = 50_000
+WARMUP = 3
+ITERATIONS = 10
+
+ids = [i % 10_000 for i in range(ROWS)]
+left = pd.DataFrame({"id": ids, "value": [x * 1.1 for x in ids], "score": [x * 0.5 for x in ids]})
+right = pd.DataFrame({
+    "id": list(range(10_000)),
+    "value": [i * 2.0 for i in range(10_000)],
+    "rank": list(range(10_000)),
+})
+
+for _ in range(WARMUP):
+    pd.merge(left, right, on="id", suffixes=("_left", "_right"))
+    pd.merge(left, right, on="id", how="outer", suffixes=("_l", "_r"))
+
+times = []
+for _ in range(ITERATIONS):
+    t0 = time.perf_counter()
+    pd.merge(left, right, on="id", suffixes=("_left", "_right"))
+    pd.merge(left, right, on="id", how="outer", suffixes=("_l", "_r"))
+    times.append((time.perf_counter() - t0) * 1000)
+
+total_ms = sum(times)
+mean_ms = total_ms / ITERATIONS
+print(json.dumps({"function": "merge_suffixes", "mean_ms": round(mean_ms, 3), "iterations": ITERATIONS, "total_ms": round(total_ms, 3)}))

benchmarks/pandas/bench_nunique_fn.py

@@ -0,0 +1,34 @@
+"""
+Benchmark: pandas nunique on Series and DataFrame (functional-form equivalent).
+Outputs JSON: {"function": "nunique_fn", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+"""
+import json
+import time
+import pandas as pd
+import numpy as np
+
+ROWS = 100_000
+WARMUP = 5
+ITERATIONS = 20
+
+low = pd.Series([i % 1000 for i in range(ROWS)])
+high = pd.Series([i % 50_000 for i in range(ROWS)])
+with_nulls = pd.Series([float('nan') if i % 100 == 0 else i % 2000 for i in range(ROWS)])
+df = pd.DataFrame({"a": low, "b": high, "c": with_nulls})
+
+for _ in range(WARMUP):
+    low.nunique()
+    with_nulls.nunique(dropna=False)
+    df.nunique()
+
+times = []
+for _ in range(ITERATIONS):
+    t0 = time.perf_counter()
+    low.nunique()
+    with_nulls.nunique(dropna=False)
+    df.nunique()
+    times.append((time.perf_counter() - t0) * 1000)
+
+total_ms = sum(times)
+mean_ms = total_ms / ITERATIONS
+print(json.dumps({"function": "nunique_fn", "mean_ms": round(mean_ms, 3), "iterations": ITERATIONS, "total_ms": round(total_ms, 3)}))

benchmarks/pandas/bench_pct_change_fn.py

@@ -0,0 +1,32 @@
+"""
+Benchmark: pandas pct_change on Series and DataFrame.
+Outputs JSON: {"function": "pct_change_fn", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+"""
+import json
+import time
+import pandas as pd
+
+ROWS = 100_000
+WARMUP = 3
+ITERATIONS = 10
+
+data = [i * 1.1 + 1.0 for i in range(ROWS)]
+s = pd.Series(data)
+df = pd.DataFrame({"a": data, "b": [x * 2 for x in data]})
+
+for _ in range(WARMUP):
+    s.pct_change()
+    s.pct_change(periods=2)
+    df.pct_change()
+
+times = []
+for _ in range(ITERATIONS):
+    t0 = time.perf_counter()
+    s.pct_change()
+    s.pct_change(periods=2)
+    df.pct_change()
+    times.append((time.perf_counter() - t0) * 1000)
+
+total_ms = sum(times)
+mean_ms = total_ms / ITERATIONS
+print(json.dumps({"function": "pct_change_fn", "mean_ms": round(mean_ms, 3), "iterations": ITERATIONS, "total_ms": round(total_ms, 3)}))

benchmarks/pandas/bench_period_asfreq.py

@@ -0,0 +1,30 @@
+"""
+Benchmark: pandas Period.asfreq and PeriodIndex.asfreq — frequency conversion.
+Outputs JSON: {"function": "period_asfreq", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+"""
+import json
+import time
+import pandas as pd
+
+SIZE = 10_000
+WARMUP = 3
+ITERATIONS = 20
+
+idx = pd.period_range(start="2000-01", periods=SIZE, freq="M")
+
+for _ in range(WARMUP):
+    idx.asfreq("D", how="start")
+    idx.asfreq("D", how="end")
+    idx.asfreq("Q", how="start")
+
+times = []
+for _ in range(ITERATIONS):
+    t0 = time.perf_counter()
+    idx.asfreq("D", how="start")
+    idx.asfreq("D", how="end")
+    idx.asfreq("Q", how="start")
+    times.append((time.perf_counter() - t0) * 1000)
+
+total_ms = sum(times)
+mean_ms = total_ms / ITERATIONS
+print(json.dumps({"function": "period_asfreq", "mean_ms": round(mean_ms, 3), "iterations": ITERATIONS, "total_ms": round(total_ms, 3)}))

benchmarks/pandas/bench_quantile_fn.py

@@ -0,0 +1,33 @@
+"""
+Benchmark: quantileSeries / quantileDataFrame equivalent — pandas Series.quantile / DataFrame.quantile.
+Outputs JSON: {"function": "quantile_fn", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+"""
+import json
+import time
+import pandas as pd
+import numpy as np
+
+ROWS = 100_000
+WARMUP = 3
+ITERATIONS = 10
+
+data = [(i * 1.41) % 10000 for i in range(ROWS)]
+s = pd.Series(data)
+df = pd.DataFrame({"a": data, "b": [x * 2 for x in data], "c": [x * 0.5 for x in data]})
+
+for _ in range(WARMUP):
+    s.quantile(0.25)
+    s.quantile([0.1, 0.5, 0.9])
+    df.quantile(0.5)
+
+times = []
+for _ in range(ITERATIONS):
+    t0 = time.perf_counter()
+    s.quantile(0.25)
+    s.quantile([0.1, 0.5, 0.9])
+    df.quantile(0.5)
+    times.append((time.perf_counter() - t0) * 1000)
+
+total_ms = sum(times)
+mean_ms = total_ms / ITERATIONS
+print(json.dumps({"function": "quantile_fn", "mean_ms": round(mean_ms, 3), "iterations": ITERATIONS, "total_ms": round(total_ms, 3)}))

benchmarks/pandas/bench_sample_fn.py

@@ -0,0 +1,32 @@
+"""
+Benchmark: pandas sample on Series and DataFrame.
+Outputs JSON: {"function": "sample_fn", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+"""
+import json
+import time
+import pandas as pd
+
+ROWS = 100_000
+WARMUP = 3
+ITERATIONS = 20
+
+data = [i * 1.5 for i in range(ROWS)]
+s = pd.Series(data)
+df = pd.DataFrame({"a": data, "b": [x * 2 for x in data], "c": [x + 100 for x in data]})
+
+for _ in range(WARMUP):
+    s.sample(n=1000)
+    s.sample(frac=0.01)
+    df.sample(n=500)
+
+times = []
+for _ in range(ITERATIONS):
+    t0 = time.perf_counter()
+    s.sample(n=1000)
+    s.sample(frac=0.01)
+    df.sample(n=500)
+    times.append((time.perf_counter() - t0) * 1000)
+
+total_ms = sum(times)
+mean_ms = total_ms / ITERATIONS
+print(json.dumps({"function": "sample_fn", "mean_ms": round(mean_ms, 3), "iterations": ITERATIONS, "total_ms": round(total_ms, 3)}))

benchmarks/tsb/bench_dt_isocalendar.ts

@@ -0,0 +1,36 @@
+/**
+ * Benchmark: DatetimeAccessor.isocalendar_week on 100k datetime Series.
+ * Outputs JSON: {"function": "dt_isocalendar", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+ */
+import { Series } from "../../src/index.ts";
+
+const ROWS = 100_000;
+const WARMUP = 3;
+const ITERATIONS = 10;
+
+// Dates spanning ~274 years to cover all ISO week patterns
+const base = new Date("2000-01-01").getTime();
+const dates = Array.from({ length: ROWS }, (_, i) => new Date(base + i * 86_400_000));
+const s = new Series({ data: dates });
+
+for (let i = 0; i < WARMUP; i++) {
+  s.dt.isocalendar_week();
+}
+
+const times: number[] = [];
+for (let i = 0; i < ITERATIONS; i++) {
+  const t0 = performance.now();
+  s.dt.isocalendar_week();
+  times.push(performance.now() - t0);
+}
+
+const totalMs = times.reduce((a, b) => a + b, 0);
+const meanMs = totalMs / ITERATIONS;
+console.log(
+  JSON.stringify({
+    function: "dt_isocalendar",
+    mean_ms: Math.round(meanMs * 1000) / 1000,
+    iterations: ITERATIONS,
+    total_ms: Math.round(totalMs * 1000) / 1000,
+  }),
+);

benchmarks/tsb/bench_expanding_min_periods.ts

@@ -0,0 +1,38 @@
+/**
+ * Benchmark: Expanding with minPeriods option.
+ * Outputs JSON: {"function": "expanding_min_periods", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+ */
+import { Series } from "../../src/index.ts";
+
+const ROWS = 100_000;
+const WARMUP = 3;
+const ITERATIONS = 10;
+
+const data = Array.from({ length: ROWS }, (_, i) => (i % 10 === 0 ? null : Math.sin(i * 0.01)));
+const s = new Series({ data });
+
+for (let i = 0; i < WARMUP; i++) {
+  s.expanding(10).mean();
+  s.expanding(50).sum();
+  s.expanding(5).std();
+}
+
+const times: number[] = [];
+for (let i = 0; i < ITERATIONS; i++) {
+  const t0 = performance.now();
+  s.expanding(10).mean();
+  s.expanding(50).sum();
+  s.expanding(5).std();
+  times.push(performance.now() - t0);
+}
+
+const totalMs = times.reduce((a, b) => a + b, 0);
+const meanMs = totalMs / ITERATIONS;
+console.log(
+  JSON.stringify({
+    function: "expanding_min_periods",
+    mean_ms: Math.round(meanMs * 1000) / 1000,
+    iterations: ITERATIONS,
+    total_ms: Math.round(totalMs * 1000) / 1000,
+  }),
+);