Iteration 163: 6 new benchmark pairs (514 total, +1 vs best 513)

Added: series_to_array, dataframe_has_col_get, series_var_method,
series_min_max_method, dataframe_var_method, dataframe_median_method.

Run: https://github.com/githubnext/tsessebe/actions/runs/24583783780

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

Author: github-actions[bot]

benchmarks/pandas/bench_dataframe_has_col_get.py

@@ -0,0 +1,25 @@
+"""Benchmark: DataFrame column presence and access (.keys(), [], __getitem__) on 100k-row DataFrame."""
+import json, time
+import pandas as pd
+
+SIZE = 100_000
+WARMUP = 10
+ITERATIONS = 100
+
+df = pd.DataFrame({"a": list(range(SIZE)), "b": [i * 2.0 for i in range(SIZE)], "c": [str(i) for i in range(SIZE)]})
+
+for _ in range(WARMUP):
+    "a" in df.columns
+    df["b"]
+    df.get("c")
+
+times = []
+for _ in range(ITERATIONS):
+    t0 = time.perf_counter()
+    "a" in df.columns
+    df["b"]
+    df.get("c")
+    times.append((time.perf_counter() - t0) * 1000)
+
+total = sum(times)
+print(json.dumps({"function": "dataframe_has_col_get", "mean_ms": round(total / ITERATIONS, 3), "iterations": ITERATIONS, "total_ms": round(total, 3)}))

benchmarks/pandas/bench_dataframe_median_method.py

@@ -0,0 +1,20 @@
+"""Benchmark: DataFrame.median() — column-wise median on 100k-row DataFrame."""
+import json, time
+import pandas as pd
+
+SIZE = 100_000
+WARMUP = 5
+ITERATIONS = 50
+
+df = pd.DataFrame({"a": [i * 1.1 for i in range(SIZE)], "b": [i * 2.2 for i in range(SIZE)], "c": [i * 3.3 for i in range(SIZE)]})
+
+for _ in range(WARMUP): df.median()
+
+times = []
+for _ in range(ITERATIONS):
+    t0 = time.perf_counter()
+    df.median()
+    times.append((time.perf_counter() - t0) * 1000)
+
+total = sum(times)
+print(json.dumps({"function": "dataframe_median_method", "mean_ms": round(total / ITERATIONS, 3), "iterations": ITERATIONS, "total_ms": round(total, 3)}))

benchmarks/pandas/bench_dataframe_var_method.py

@@ -0,0 +1,20 @@
+"""Benchmark: DataFrame.var() — column-wise variance on 100k-row DataFrame."""
+import json, time
+import pandas as pd
+
+SIZE = 100_000
+WARMUP = 10
+ITERATIONS = 100
+
+df = pd.DataFrame({"a": [i * 1.1 for i in range(SIZE)], "b": [i * 2.2 for i in range(SIZE)], "c": [i * 3.3 for i in range(SIZE)]})
+
+for _ in range(WARMUP): df.var()
+
+times = []
+for _ in range(ITERATIONS):
+    t0 = time.perf_counter()
+    df.var()
+    times.append((time.perf_counter() - t0) * 1000)
+
+total = sum(times)
+print(json.dumps({"function": "dataframe_var_method", "mean_ms": round(total / ITERATIONS, 3), "iterations": ITERATIONS, "total_ms": round(total, 3)}))

benchmarks/pandas/bench_series_min_max_method.py

@@ -0,0 +1,24 @@
+"""Benchmark: Series.min() and .max() — min/max on 100k numeric Series."""
+import json, time
+import math
+import pandas as pd
+
+SIZE = 100_000
+WARMUP = 10
+ITERATIONS = 100
+
+s = pd.Series([math.sin(i) * 1000 for i in range(SIZE)])
+
+for _ in range(WARMUP):
+    s.min()
+    s.max()
+
+times = []
+for _ in range(ITERATIONS):
+    t0 = time.perf_counter()
+    s.min()
+    s.max()
+    times.append((time.perf_counter() - t0) * 1000)
+
+total = sum(times)
+print(json.dumps({"function": "series_min_max_method", "mean_ms": round(total / ITERATIONS, 3), "iterations": ITERATIONS, "total_ms": round(total, 3)}))

benchmarks/pandas/bench_series_to_array.py

@@ -0,0 +1,24 @@
+"""Benchmark: Series.to_numpy() and .tolist() — convert 100k-element Series to plain arrays."""
+import json, time
+import pandas as pd
+import numpy as np
+
+SIZE = 100_000
+WARMUP = 10
+ITERATIONS = 100
+
+s = pd.Series([i * 2.5 for i in range(SIZE)])
+
+for _ in range(WARMUP):
+    s.to_numpy()
+    s.tolist()
+
+times = []
+for _ in range(ITERATIONS):
+    t0 = time.perf_counter()
+    s.to_numpy()
+    s.tolist()
+    times.append((time.perf_counter() - t0) * 1000)
+
+total = sum(times)
+print(json.dumps({"function": "series_to_array", "mean_ms": round(total / ITERATIONS, 3), "iterations": ITERATIONS, "total_ms": round(total, 3)}))

benchmarks/pandas/bench_series_var_method.py

@@ -0,0 +1,20 @@
+"""Benchmark: Series.var() — variance on 100k numeric Series."""
+import json, time
+import pandas as pd
+
+SIZE = 100_000
+WARMUP = 10
+ITERATIONS = 100
+
+s = pd.Series([i * 0.5 for i in range(SIZE)])
+
+for _ in range(WARMUP): s.var()
+
+times = []
+for _ in range(ITERATIONS):
+    t0 = time.perf_counter()
+    s.var()
+    times.append((time.perf_counter() - t0) * 1000)
+
+total = sum(times)
+print(json.dumps({"function": "series_var_method", "mean_ms": round(total / ITERATIONS, 3), "iterations": ITERATIONS, "total_ms": round(total, 3)}))

benchmarks/tsb/bench_dataframe_has_col_get.ts

@@ -0,0 +1,40 @@
+/**
+ * Benchmark: DataFrame.has(), .col(), .get() — column presence and access on 100k-row DataFrame.
+ * Outputs JSON: {"function": "dataframe_has_col_get", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+ */
+import { DataFrame } from "../../src/index.ts";
+
+const SIZE = 100_000;
+const WARMUP = 10;
+const ITERATIONS = 100;
+
+const df = new DataFrame({
+  a: Array.from({ length: SIZE }, (_, i) => i),
+  b: Array.from({ length: SIZE }, (_, i) => i * 2.0),
+  c: Array.from({ length: SIZE }, (_, i) => String(i)),
+});
+
+for (let i = 0; i < WARMUP; i++) {
+  df.has("a");
+  df.col("b");
+  df.get("c");
+}
+
+const times: number[] = [];
+for (let i = 0; i < ITERATIONS; i++) {
+  const t0 = performance.now();
+  df.has("a");
+  df.col("b");
+  df.get("c");
+  times.push(performance.now() - t0);
+}
+
+const total = times.reduce((a, b) => a + b, 0);
+console.log(
+  JSON.stringify({
+    function: "dataframe_has_col_get",
+    mean_ms: Math.round((total / ITERATIONS) * 1000) / 1000,
+    iterations: ITERATIONS,
+    total_ms: Math.round(total * 1000) / 1000,
+  }),
+);

benchmarks/tsb/bench_dataframe_median_method.ts

@@ -0,0 +1,34 @@
+/**
+ * Benchmark: DataFrame.median() — column-wise median on 100k-row DataFrame.
+ * Outputs JSON: {"function": "dataframe_median_method", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+ */
+import { DataFrame } from "../../src/index.ts";
+
+const SIZE = 100_000;
+const WARMUP = 5;
+const ITERATIONS = 50;
+
+const df = new DataFrame({
+  a: Array.from({ length: SIZE }, (_, i) => i * 1.1),
+  b: Array.from({ length: SIZE }, (_, i) => i * 2.2),
+  c: Array.from({ length: SIZE }, (_, i) => i * 3.3),
+});
+
+for (let i = 0; i < WARMUP; i++) df.median();
+
+const times: number[] = [];
+for (let i = 0; i < ITERATIONS; i++) {
+  const t0 = performance.now();
+  df.median();
+  times.push(performance.now() - t0);
+}
+
+const total = times.reduce((a, b) => a + b, 0);
+console.log(
+  JSON.stringify({
+    function: "dataframe_median_method",
+    mean_ms: Math.round((total / ITERATIONS) * 1000) / 1000,
+    iterations: ITERATIONS,
+    total_ms: Math.round(total * 1000) / 1000,
+  }),
+);

benchmarks/tsb/bench_dataframe_var_method.ts

@@ -0,0 +1,34 @@
+/**
+ * Benchmark: DataFrame.var() — column-wise variance on 100k-row DataFrame.
+ * Outputs JSON: {"function": "dataframe_var_method", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+ */
+import { DataFrame } from "../../src/index.ts";
+
+const SIZE = 100_000;
+const WARMUP = 10;
+const ITERATIONS = 100;
+
+const df = new DataFrame({
+  a: Array.from({ length: SIZE }, (_, i) => i * 1.1),
+  b: Array.from({ length: SIZE }, (_, i) => i * 2.2),
+  c: Array.from({ length: SIZE }, (_, i) => i * 3.3),
+});
+
+for (let i = 0; i < WARMUP; i++) df.var();
+
+const times: number[] = [];
+for (let i = 0; i < ITERATIONS; i++) {
+  const t0 = performance.now();
+  df.var();
+  times.push(performance.now() - t0);
+}
+
+const total = times.reduce((a, b) => a + b, 0);
+console.log(
+  JSON.stringify({
+    function: "dataframe_var_method",
+    mean_ms: Math.round((total / ITERATIONS) * 1000) / 1000,
+    iterations: ITERATIONS,
+    total_ms: Math.round(total * 1000) / 1000,
+  }),
+);

benchmarks/tsb/bench_series_min_max_method.ts

@@ -0,0 +1,34 @@
+/**
+ * Benchmark: Series.min() and .max() — min/max on 100k numeric Series.
+ * Outputs JSON: {"function": "series_min_max_method", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+ */
+import { Series } from "../../src/index.ts";
+
+const SIZE = 100_000;
+const WARMUP = 10;
+const ITERATIONS = 100;
+
+const s = new Series({ data: Array.from({ length: SIZE }, (_, i) => Math.sin(i) * 1000) });
+
+for (let i = 0; i < WARMUP; i++) {
+  s.min();
+  s.max();
+}
+
+const times: number[] = [];
+for (let i = 0; i < ITERATIONS; i++) {
+  const t0 = performance.now();
+  s.min();
+  s.max();
+  times.push(performance.now() - t0);
+}
+
+const total = times.reduce((a, b) => a + b, 0);
+console.log(
+  JSON.stringify({
+    function: "series_min_max_method",
+    mean_ms: Math.round((total / ITERATIONS) * 1000) / 1000,
+    iterations: ITERATIONS,
+    total_ms: Math.round(total * 1000) / 1000,
+  }),
+);