Iteration 244: 5 new benchmark pairs (539 total, +5 vs best 534)

Add benchmark pairs: str_swapcase_capitalize, dt_strftime, series_reflected_arith,
dataframe_reflected_arith, any_all.

Run: https://github.com/githubnext/tsessebe/actions/runs/24644387987

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

Author: github-actions[bot]

benchmarks/pandas/bench_any_all.py

@@ -0,0 +1,36 @@
+"""Benchmark: any_all — Series.any / all and DataFrame.any / all on 100k rows."""
+import json, time
+import numpy as np
+import pandas as pd
+
+SIZE = 100_000
+WARMUP = 5
+ITERATIONS = 50
+
+s = pd.Series(np.arange(SIZE) % 2 == 0)
+df = pd.DataFrame({
+    "a": np.arange(SIZE) % 3 != 0,
+    "b": np.arange(SIZE) > 0,
+    "c": np.ones(SIZE, dtype=bool),
+})
+
+for _ in range(WARMUP):
+    s.any()
+    s.all()
+    df.any()
+    df.all()
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    s.any()
+    s.all()
+    df.any()
+    df.all()
+total = (time.perf_counter() - start) * 1000
+
+print(json.dumps({
+    "function": "any_all",
+    "mean_ms": total / ITERATIONS,
+    "iterations": ITERATIONS,
+    "total_ms": total,
+}))

benchmarks/pandas/bench_dataframe_reflected_arith.py

@@ -0,0 +1,35 @@
+"""Benchmark: dataframe_reflected_arith — DataFrame.radd / rsub / rmul / rdiv."""
+import json, time
+import numpy as np
+import pandas as pd
+
+ROWS = 10_000
+WARMUP = 5
+ITERATIONS = 30
+
+df = pd.DataFrame({
+    "a": np.arange(ROWS) * 1.5,
+    "b": (np.arange(ROWS) % 100) + 1.0,
+    "c": np.arange(ROWS) * 0.25,
+})
+
+for _ in range(WARMUP):
+    df.radd(10)
+    df.rsub(1000)
+    df.rmul(3)
+    df.rdiv(100)
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    df.radd(10)
+    df.rsub(1000)
+    df.rmul(3)
+    df.rdiv(100)
+total = (time.perf_counter() - start) * 1000
+
+print(json.dumps({
+    "function": "dataframe_reflected_arith",
+    "mean_ms": total / ITERATIONS,
+    "iterations": ITERATIONS,
+    "total_ms": total,
+}))

benchmarks/pandas/bench_dt_strftime.py

@@ -0,0 +1,27 @@
+"""Benchmark: dt_strftime — dt.strftime formatting on 100k datetime values."""
+import json, time
+import pandas as pd
+
+ROWS = 100_000
+WARMUP = 3
+ITERATIONS = 10
+
+dates = pd.date_range("2024-01-01", periods=ROWS, freq="1min")
+s = pd.Series(dates)
+
+for _ in range(WARMUP):
+    s.dt.strftime("%Y-%m-%d")
+    s.dt.strftime("%H:%M:%S")
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    s.dt.strftime("%Y-%m-%d")
+    s.dt.strftime("%H:%M:%S")
+total = (time.perf_counter() - start) * 1000
+
+print(json.dumps({
+    "function": "dt_strftime",
+    "mean_ms": total / ITERATIONS,
+    "iterations": ITERATIONS,
+    "total_ms": total,
+}))

benchmarks/pandas/bench_series_reflected_arith.py

@@ -0,0 +1,32 @@
+"""Benchmark: series_reflected_arith — Series.radd / rsub / rmul / rdiv."""
+import json, time
+import numpy as np
+import pandas as pd
+
+SIZE = 100_000
+WARMUP = 5
+ITERATIONS = 50
+
+a = pd.Series(np.arange(SIZE) * 1.5)
+b = pd.Series((np.arange(SIZE) % 1000) + 1.0)
+
+for _ in range(WARMUP):
+    a.radd(10)
+    a.rsub(1000)
+    a.rmul(3)
+    b.rdiv(100)
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    a.radd(10)
+    a.rsub(1000)
+    a.rmul(3)
+    b.rdiv(100)
+total = (time.perf_counter() - start) * 1000
+
+print(json.dumps({
+    "function": "series_reflected_arith",
+    "mean_ms": total / ITERATIONS,
+    "iterations": ITERATIONS,
+    "total_ms": total,
+}))

benchmarks/pandas/bench_str_swapcase_capitalize.py

@@ -0,0 +1,27 @@
+"""Benchmark: str_swapcase_capitalize — str.swapcase and str.capitalize on 100k strings."""
+import json, time
+import pandas as pd
+
+ROWS = 100_000
+WARMUP = 3
+ITERATIONS = 10
+
+data = [f"Hello World {i % 500} EXAMPLE" for i in range(ROWS)]
+s = pd.Series(data)
+
+for _ in range(WARMUP):
+    s.str.swapcase()
+    s.str.capitalize()
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    s.str.swapcase()
+    s.str.capitalize()
+total = (time.perf_counter() - start) * 1000
+
+print(json.dumps({
+    "function": "str_swapcase_capitalize",
+    "mean_ms": total / ITERATIONS,
+    "iterations": ITERATIONS,
+    "total_ms": total,
+}))

benchmarks/tsb/bench_any_all.ts

@@ -0,0 +1,41 @@
+/**
+ * Benchmark: any_all — anySeries / allSeries / anyDataFrame / allDataFrame on 100k rows.
+ * Outputs JSON: {"function": "any_all", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+ */
+import { Series, DataFrame, anySeries, allSeries, anyDataFrame, allDataFrame } from "../../src/index.ts";
+
+const SIZE = 100_000;
+const WARMUP = 5;
+const ITERATIONS = 50;
+
+const s = new Series({ data: Array.from({ length: SIZE }, (_, i) => i % 2 === 0) });
+const df = DataFrame.fromColumns({
+  a: Array.from({ length: SIZE }, (_, i) => i % 3 !== 0),
+  b: Array.from({ length: SIZE }, (_, i) => i > 0),
+  c: Array.from({ length: SIZE }, () => true),
+});
+
+for (let i = 0; i < WARMUP; i++) {
+  anySeries(s);
+  allSeries(s);
+  anyDataFrame(df);
+  allDataFrame(df);
+}
+
+const start = performance.now();
+for (let i = 0; i < ITERATIONS; i++) {
+  anySeries(s);
+  allSeries(s);
+  anyDataFrame(df);
+  allDataFrame(df);
+}
+const total = performance.now() - start;
+
+console.log(
+  JSON.stringify({
+    function: "any_all",
+    mean_ms: total / ITERATIONS,
+    iterations: ITERATIONS,
+    total_ms: total,
+  }),
+);

benchmarks/tsb/bench_dataframe_reflected_arith.ts

@@ -0,0 +1,40 @@
+/**
+ * Benchmark: dataframe_reflected_arith — dataFrameRadd / dataFrameRsub / dataFrameRmul / dataFrameRdiv.
+ * Outputs JSON: {"function": "dataframe_reflected_arith", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+ */
+import { DataFrame, dataFrameRadd, dataFrameRsub, dataFrameRmul, dataFrameRdiv } from "../../src/index.ts";
+
+const SIZE = 50_000;
+const WARMUP = 5;
+const ITERATIONS = 30;
+
+const df = DataFrame.fromColumns({
+  a: Array.from({ length: SIZE }, (_, i) => i * 1.5),
+  b: Array.from({ length: SIZE }, (_, i) => (i % 100) + 1),
+  c: Array.from({ length: SIZE }, (_, i) => i * 0.25),
+});
+
+for (let i = 0; i < WARMUP; i++) {
+  dataFrameRadd(df, 10);
+  dataFrameRsub(df, 1000);
+  dataFrameRmul(df, 3);
+  dataFrameRdiv(df, 100);
+}
+
+const start = performance.now();
+for (let i = 0; i < ITERATIONS; i++) {
+  dataFrameRadd(df, 10);
+  dataFrameRsub(df, 1000);
+  dataFrameRmul(df, 3);
+  dataFrameRdiv(df, 100);
+}
+const total = performance.now() - start;
+
+console.log(
+  JSON.stringify({
+    function: "dataframe_reflected_arith",
+    mean_ms: total / ITERATIONS,
+    iterations: ITERATIONS,
+    total_ms: total,
+  }),
+);

benchmarks/tsb/bench_dt_strftime.ts

@@ -0,0 +1,34 @@
+/**
+ * Benchmark: dt_strftime — dt.strftime formatting on 100k datetime values.
+ * Outputs JSON: {"function": "dt_strftime", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+ */
+import { Series } from "../../src/index.ts";
+
+const ROWS = 100_000;
+const WARMUP = 3;
+const ITERATIONS = 10;
+
+const now = Date.now();
+const data = Array.from({ length: ROWS }, (_, i) => new Date(now + i * 60_000));
+const s = new Series({ data });
+
+for (let i = 0; i < WARMUP; i++) {
+  s.dt.strftime("%Y-%m-%d");
+  s.dt.strftime("%H:%M:%S");
+}
+
+const start = performance.now();
+for (let i = 0; i < ITERATIONS; i++) {
+  s.dt.strftime("%Y-%m-%d");
+  s.dt.strftime("%H:%M:%S");
+}
+const total = performance.now() - start;
+
+console.log(
+  JSON.stringify({
+    function: "dt_strftime",
+    mean_ms: total / ITERATIONS,
+    iterations: ITERATIONS,
+    total_ms: total,
+  }),
+);

benchmarks/tsb/bench_series_reflected_arith.ts

@@ -0,0 +1,37 @@
+/**
+ * Benchmark: series_reflected_arith — seriesRadd / seriesRsub / seriesRmul / seriesRdiv.
+ * Outputs JSON: {"function": "series_reflected_arith", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+ */
+import { Series, seriesRadd, seriesRsub, seriesRmul, seriesRdiv } from "../../src/index.ts";
+
+const SIZE = 100_000;
+const WARMUP = 5;
+const ITERATIONS = 50;
+
+const a = new Series({ data: Array.from({ length: SIZE }, (_, i) => i * 1.5) });
+const b = new Series({ data: Array.from({ length: SIZE }, (_, i) => (i % 1000) + 1) });
+
+for (let i = 0; i < WARMUP; i++) {
+  seriesRadd(a, 10);
+  seriesRsub(a, 1000);
+  seriesRmul(a, 3);
+  seriesRdiv(b, 100);
+}
+
+const start = performance.now();
+for (let i = 0; i < ITERATIONS; i++) {
+  seriesRadd(a, 10);
+  seriesRsub(a, 1000);
+  seriesRmul(a, 3);
+  seriesRdiv(b, 100);
+}
+const total = performance.now() - start;
+
+console.log(
+  JSON.stringify({
+    function: "series_reflected_arith",
+    mean_ms: total / ITERATIONS,
+    iterations: ITERATIONS,
+    total_ms: total,
+  }),
+);

benchmarks/tsb/bench_str_swapcase_capitalize.ts

@@ -0,0 +1,33 @@
+/**
+ * Benchmark: str_swapcase_capitalize — str.swapcase and str.capitalize on 100k strings.
+ * Outputs JSON: {"function": "str_swapcase_capitalize", "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) => `Hello World ${i % 500} EXAMPLE`);
+const s = new Series({ data });
+
+for (let i = 0; i < WARMUP; i++) {
+  s.str.swapcase();
+  s.str.capitalize();
+}
+
+const start = performance.now();
+for (let i = 0; i < ITERATIONS; i++) {
+  s.str.swapcase();
+  s.str.capitalize();
+}
+const total = performance.now() - start;
+
+console.log(
+  JSON.stringify({
+    function: "str_swapcase_capitalize",
+    mean_ms: total / ITERATIONS,
+    iterations: ITERATIONS,
+    total_ms: total,
+  }),
+);