Iteration 153: Add 5 benchmark pairs (483 total, +5 vs best 478)

github-actions[bot] · Copilot · web-flow · commit 3e8972583e95 · 2026-04-17T12:35:56.000Z
Added 5 new benchmark pairs: - datetime_index_ops: DatetimeIndex sort/unique/toStrings/slice/contains/concat - datetime_index_snap: DatetimeIndex.snap(freq) to month-start and week boundaries - period_index_query: PeriodIndex.getLoc/contains querying operations - series_groupby_agg_all: SeriesGroupBy all aggregations (sum/mean/std/min/max/count/first/last) - dataframe_rolling_median: DataFrameRolling.median and DataFrameExpanding.median Run: https://github.com/githubnext/tsessebe/actions/runs/24564770860 Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
diff --git a/benchmarks/pandas/bench_dataframe_rolling_median.py b/benchmarks/pandas/bench_dataframe_rolling_median.py
@@ -0,0 +1,36 @@
+"""
+Benchmark: pandas DataFrame.rolling(10).median() / DataFrame.expanding(1).median() — rolling and expanding median on DataFrame.
+Outputs JSON: {"function": "dataframe_rolling_median", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+"""
+import json
+import time
+import pandas as pd
+
+ROWS = 10_000
+WARMUP = 3
+ITERATIONS = 20
+
+df = pd.DataFrame({
+    "a": [i * 0.1 for i in range(ROWS)],
+    "b": [(i * 0.3) % 500 for i in range(ROWS)],
+})
+
+for _ in range(WARMUP):
+    df.rolling(10).median()
+    df.expanding(1).median()
+
+times = []
+for _ in range(ITERATIONS):
+    t0 = time.perf_counter()
+    df.rolling(10).median()
+    df.expanding(1).median()
+    times.append((time.perf_counter() - t0) * 1000)
+
+total_ms = sum(times)
+mean_ms = total_ms / ITERATIONS
+print(json.dumps({
+    "function": "dataframe_rolling_median",
+    "mean_ms": round(mean_ms, 3),
+    "iterations": ITERATIONS,
+    "total_ms": round(total_ms, 3),
+}))
diff --git a/benchmarks/pandas/bench_datetime_index_ops.py b/benchmarks/pandas/bench_datetime_index_ops.py
@@ -0,0 +1,43 @@
+"""
+Benchmark: pandas DatetimeIndex sort_values / unique / strftime / slice / isin / append — DatetimeIndex operations.
+Outputs JSON: {"function": "datetime_index_ops", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+"""
+import json
+import time
+import pandas as pd
+
+SIZE = 10_000
+WARMUP = 5
+ITERATIONS = 50
+
+idx = pd.date_range(start="2020-01-01", periods=SIZE, freq="h")
+idx2 = pd.date_range(start="2021-01-01", periods=SIZE, freq="h")
+ref_date = pd.Timestamp("2020-06-15T00:00:00Z")
+
+for _ in range(WARMUP):
+    idx.sort_values()
+    idx.unique()
+    idx.strftime("%Y-%m-%dT%H:%M:%SZ")
+    idx[:100]
+    ref_date in idx
+    idx.append(idx2)
+
+times = []
+for _ in range(ITERATIONS):
+    t0 = time.perf_counter()
+    idx.sort_values()
+    idx.unique()
+    idx.strftime("%Y-%m-%dT%H:%M:%SZ")
+    idx[:100]
+    ref_date in idx
+    idx.append(idx2)
+    times.append((time.perf_counter() - t0) * 1000)
+
+total_ms = sum(times)
+mean_ms = total_ms / ITERATIONS
+print(json.dumps({
+    "function": "datetime_index_ops",
+    "mean_ms": round(mean_ms, 3),
+    "iterations": ITERATIONS,
+    "total_ms": round(total_ms, 3),
+}))
diff --git a/benchmarks/pandas/bench_datetime_index_snap.py b/benchmarks/pandas/bench_datetime_index_snap.py
@@ -0,0 +1,34 @@
+"""
+Benchmark: pandas DatetimeIndex.snap(freq) — snap index to frequency boundaries (round to nearest).
+Outputs JSON: {"function": "datetime_index_snap", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+"""
+import json
+import time
+import pandas as pd
+
+SIZE = 5_000
+WARMUP = 5
+ITERATIONS = 50
+
+# Dates that are not on month/week boundaries
+idx = pd.date_range(start="2020-01-15", periods=SIZE, freq="D")
+
+for _ in range(WARMUP):
+    idx.snap("MS")  # snap to month start
+    idx.snap("W")   # snap to week
+
+times = []
+for _ in range(ITERATIONS):
+    t0 = time.perf_counter()
+    idx.snap("MS")
+    idx.snap("W")
+    times.append((time.perf_counter() - t0) * 1000)
+
+total_ms = sum(times)
+mean_ms = total_ms / ITERATIONS
+print(json.dumps({
+    "function": "datetime_index_snap",
+    "mean_ms": round(mean_ms, 3),
+    "iterations": ITERATIONS,
+    "total_ms": round(total_ms, 3),
+}))
diff --git a/benchmarks/pandas/bench_period_index_query.py b/benchmarks/pandas/bench_period_index_query.py
@@ -0,0 +1,42 @@
+"""
+Benchmark: pandas PeriodIndex.get_loc / isin — querying a PeriodIndex.
+Outputs JSON: {"function": "period_index_query", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+"""
+import json
+import time
+import pandas as pd
+
+SIZE = 1_000
+WARMUP = 5
+ITERATIONS = 100
+
+base = pd.Period("2020-01", freq="M")
+periods = [base + i for i in range(SIZE)]
+idx = pd.PeriodIndex(periods)
+
+query_period = base + 500
+mid_period = base + 250
+
+for _ in range(WARMUP):
+    idx.get_loc(query_period)
+    query_period in idx
+    idx.get_loc(mid_period)
+    mid_period in idx
+
+times = []
+for _ in range(ITERATIONS):
+    t0 = time.perf_counter()
+    idx.get_loc(query_period)
+    query_period in idx
+    idx.get_loc(mid_period)
+    mid_period in idx
+    times.append((time.perf_counter() - t0) * 1000)
+
+total_ms = sum(times)
+mean_ms = total_ms / ITERATIONS
+print(json.dumps({
+    "function": "period_index_query",
+    "mean_ms": round(mean_ms, 3),
+    "iterations": ITERATIONS,
+    "total_ms": round(total_ms, 3),
+}))
diff --git a/benchmarks/pandas/bench_series_groupby_agg_all.py b/benchmarks/pandas/bench_series_groupby_agg_all.py
@@ -0,0 +1,48 @@
+"""
+Benchmark: pandas SeriesGroupBy — all aggregation operations (sum/mean/std/min/max/count/first/last) on 100k Series.
+Outputs JSON: {"function": "series_groupby_agg_all", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+"""
+import json
+import time
+import numpy as np
+import pandas as pd
+
+SIZE = 100_000
+WARMUP = 3
+ITERATIONS = 10
+
+s = pd.Series((np.arange(SIZE) * 1.5) % 9999)
+by = pd.Series(np.arange(SIZE) % 100)
+gb = s.groupby(by)
+
+for _ in range(WARMUP):
+    gb.sum()
+    gb.mean()
+    gb.std()
+    gb.min()
+    gb.max()
+    gb.count()
+    gb.first()
+    gb.last()
+
+times = []
+for _ in range(ITERATIONS):
+    t0 = time.perf_counter()
+    gb.sum()
+    gb.mean()
+    gb.std()
+    gb.min()
+    gb.max()
+    gb.count()
+    gb.first()
+    gb.last()
+    times.append((time.perf_counter() - t0) * 1000)
+
+total_ms = sum(times)
+mean_ms = total_ms / ITERATIONS
+print(json.dumps({
+    "function": "series_groupby_agg_all",
+    "mean_ms": round(mean_ms, 3),
+    "iterations": ITERATIONS,
+    "total_ms": round(total_ms, 3),
+}))
diff --git a/benchmarks/tsb/bench_dataframe_rolling_median.ts b/benchmarks/tsb/bench_dataframe_rolling_median.ts
@@ -0,0 +1,38 @@
+/**
+ * Benchmark: DataFrameRolling.median / DataFrameExpanding.median — rolling and expanding median on DataFrame.
+ * Outputs JSON: {"function": "dataframe_rolling_median", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+ */
+import { DataFrame } from "../../src/index.ts";
+
+const ROWS = 10_000;
+const WARMUP = 3;
+const ITERATIONS = 20;
+
+const df = DataFrame.fromColumns({
+  a: Array.from({ length: ROWS }, (_, i) => i * 0.1),
+  b: Array.from({ length: ROWS }, (_, i) => (i * 0.3) % 500),
+});
+
+for (let i = 0; i < WARMUP; i++) {
+  df.rolling(10).median();
+  df.expanding(1).median();
+}
+
+const times: number[] = [];
+for (let i = 0; i < ITERATIONS; i++) {
+  const t0 = performance.now();
+  df.rolling(10).median();
+  df.expanding(1).median();
+  times.push(performance.now() - t0);
+}
+
+const totalMs = times.reduce((a, b) => a + b, 0);
+const meanMs = totalMs / ITERATIONS;
+console.log(
+  JSON.stringify({
+    function: "dataframe_rolling_median",
+    mean_ms: Math.round(meanMs * 1000) / 1000,
+    iterations: ITERATIONS,
+    total_ms: Math.round(totalMs * 1000) / 1000,
+  }),
+);
diff --git a/benchmarks/tsb/bench_datetime_index_ops.ts b/benchmarks/tsb/bench_datetime_index_ops.ts
@@ -0,0 +1,45 @@
+/**
+ * Benchmark: DatetimeIndex sort / unique / toStrings / slice / contains / concat — DatetimeIndex operations.
+ * Outputs JSON: {"function": "datetime_index_ops", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+ */
+import { date_range } from "../../src/index.ts";
+
+const SIZE = 10_000;
+const WARMUP = 5;
+const ITERATIONS = 50;
+
+const idx = date_range({ start: "2020-01-01", periods: SIZE, freq: "h" });
+const idx2 = date_range({ start: "2021-01-01", periods: SIZE, freq: "h" });
+const refDate = new Date("2020-06-15T00:00:00Z");
+
+for (let i = 0; i < WARMUP; i++) {
+  idx.sort();
+  idx.unique();
+  idx.toStrings();
+  idx.slice(0, 100);
+  idx.contains(refDate);
+  idx.concat(idx2);
+}
+
+const times: number[] = [];
+for (let i = 0; i < ITERATIONS; i++) {
+  const t0 = performance.now();
+  idx.sort();
+  idx.unique();
+  idx.toStrings();
+  idx.slice(0, 100);
+  idx.contains(refDate);
+  idx.concat(idx2);
+  times.push(performance.now() - t0);
+}
+
+const totalMs = times.reduce((a, b) => a + b, 0);
+const meanMs = totalMs / ITERATIONS;
+console.log(
+  JSON.stringify({
+    function: "datetime_index_ops",
+    mean_ms: Math.round(meanMs * 1000) / 1000,
+    iterations: ITERATIONS,
+    total_ms: Math.round(totalMs * 1000) / 1000,
+  }),
+);
diff --git a/benchmarks/tsb/bench_datetime_index_snap.ts b/benchmarks/tsb/bench_datetime_index_snap.ts
@@ -0,0 +1,36 @@
+/**
+ * Benchmark: DatetimeIndex.snap(freq) — snap index dates to frequency boundaries.
+ * Outputs JSON: {"function": "datetime_index_snap", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+ */
+import { date_range } from "../../src/index.ts";
+
+const SIZE = 5_000;
+const WARMUP = 5;
+const ITERATIONS = 50;
+
+// Dates that are not on month/week boundaries
+const idx = date_range({ start: "2020-01-15", periods: SIZE, freq: "D" });
+
+for (let i = 0; i < WARMUP; i++) {
+  idx.snap("MS"); // snap to month start
+  idx.snap("W"); // snap to week
+}
+
+const times: number[] = [];
+for (let i = 0; i < ITERATIONS; i++) {
+  const t0 = performance.now();
+  idx.snap("MS");
+  idx.snap("W");
+  times.push(performance.now() - t0);
+}
+
+const totalMs = times.reduce((a, b) => a + b, 0);
+const meanMs = totalMs / ITERATIONS;
+console.log(
+  JSON.stringify({
+    function: "datetime_index_snap",
+    mean_ms: Math.round(meanMs * 1000) / 1000,
+    iterations: ITERATIONS,
+    total_ms: Math.round(totalMs * 1000) / 1000,
+  }),
+);
diff --git a/benchmarks/tsb/bench_period_index_query.ts b/benchmarks/tsb/bench_period_index_query.ts
@@ -0,0 +1,44 @@
+/**
+ * Benchmark: PeriodIndex.getLoc / contains — querying a PeriodIndex.
+ * Outputs JSON: {"function": "period_index_query", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+ */
+import { Period, PeriodIndex } from "../../src/index.ts";
+
+const SIZE = 1_000;
+const WARMUP = 5;
+const ITERATIONS = 100;
+
+const base = Period.fromDate(new Date(Date.UTC(2020, 0, 1)), "M");
+const periods = Array.from({ length: SIZE }, (_, i) => base.add(i));
+const idx = PeriodIndex.fromPeriods(periods);
+
+const queryPeriod = base.add(500);
+const midPeriod = base.add(250);
+
+for (let i = 0; i < WARMUP; i++) {
+  idx.getLoc(queryPeriod);
+  idx.contains(queryPeriod);
+  idx.getLoc(midPeriod);
+  idx.contains(midPeriod);
+}
+
+const times: number[] = [];
+for (let i = 0; i < ITERATIONS; i++) {
+  const t0 = performance.now();
+  idx.getLoc(queryPeriod);
+  idx.contains(queryPeriod);
+  idx.getLoc(midPeriod);
+  idx.contains(midPeriod);
+  times.push(performance.now() - t0);
+}
+
+const totalMs = times.reduce((a, b) => a + b, 0);
+const meanMs = totalMs / ITERATIONS;
+console.log(
+  JSON.stringify({
+    function: "period_index_query",
+    mean_ms: Math.round(meanMs * 1000) / 1000,
+    iterations: ITERATIONS,
+    total_ms: Math.round(totalMs * 1000) / 1000,
+  }),
+);
diff --git a/benchmarks/tsb/bench_series_groupby_agg_all.ts b/benchmarks/tsb/bench_series_groupby_agg_all.ts
