Iteration 116: Add 5 benchmark pairs (345 total, +5 vs best 340)

Run: https://github.com/githubnext/tsessebe/actions/runs/24484182038

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

Author: github-actions[bot]

benchmarks/pandas/bench_cat_from_codes.py

@@ -0,0 +1,18 @@
+"""Benchmark: pd.Categorical.from_codes on 100k-element code array"""
+import json, time
+import pandas as pd
+
+ROWS = 100_000
+WARMUP = 3
+ITERATIONS = 10
+categories = ["alpha", "beta", "gamma", "delta"]
+codes = [i % 4 for i in range(ROWS)]
+
+for _ in range(WARMUP):
+    pd.Categorical.from_codes(codes, categories=categories)
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    pd.Categorical.from_codes(codes, categories=categories)
+total = (time.perf_counter() - start) * 1000
+print(json.dumps({"function": "cat_from_codes", "mean_ms": total / ITERATIONS, "iterations": ITERATIONS, "total_ms": total}))

benchmarks/pandas/bench_multi_index_isin.py

@@ -0,0 +1,21 @@
+"""Benchmark: MultiIndex.isin() on 100k-pair MultiIndex"""
+import json, time
+import pandas as pd
+
+ROWS = 100_000
+WARMUP = 3
+ITERATIONS = 10
+a = [f"a{i % 100}" for i in range(ROWS)]
+b = [i % 1000 for i in range(ROWS)]
+tuples = list(zip(a, b))
+mi = pd.MultiIndex.from_tuples(tuples)
+lookup_tuples = [(f"a{i % 100}", i % 1000) for i in range(1000)]
+
+for _ in range(WARMUP):
+    mi.isin(lookup_tuples)
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    mi.isin(lookup_tuples)
+total = (time.perf_counter() - start) * 1000
+print(json.dumps({"function": "multi_index_isin", "mean_ms": total / ITERATIONS, "iterations": ITERATIONS, "total_ms": total}))

benchmarks/pandas/bench_multi_index_reorder_levels.py

@@ -0,0 +1,21 @@
+"""Benchmark: MultiIndex.reorder_levels() on 100k-pair MultiIndex"""
+import json, time
+import pandas as pd
+
+ROWS = 100_000
+WARMUP = 3
+ITERATIONS = 10
+a = [f"a{i % 100}" for i in range(ROWS)]
+b = [i % 1000 for i in range(ROWS)]
+c = [i % 50 for i in range(ROWS)]
+tuples = list(zip(a, b, c))
+mi = pd.MultiIndex.from_tuples(tuples)
+
+for _ in range(WARMUP):
+    mi.reorder_levels([2, 0, 1])
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    mi.reorder_levels([2, 0, 1])
+total = (time.perf_counter() - start) * 1000
+print(json.dumps({"function": "multi_index_reorder_levels", "mean_ms": total / ITERATIONS, "iterations": ITERATIONS, "total_ms": total}))

benchmarks/pandas/bench_multi_index_set_names.py

@@ -0,0 +1,20 @@
+"""Benchmark: MultiIndex.set_names() on 100k-pair MultiIndex"""
+import json, time
+import pandas as pd
+
+ROWS = 100_000
+WARMUP = 3
+ITERATIONS = 10
+a = [f"a{i % 100}" for i in range(ROWS)]
+b = [i % 1000 for i in range(ROWS)]
+tuples = list(zip(a, b))
+mi = pd.MultiIndex.from_tuples(tuples)
+
+for _ in range(WARMUP):
+    mi.set_names(["level0", "level1"])
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    mi.set_names(["level0", "level1"])
+total = (time.perf_counter() - start) * 1000
+print(json.dumps({"function": "multi_index_set_names", "mean_ms": total / ITERATIONS, "iterations": ITERATIONS, "total_ms": total}))

benchmarks/pandas/bench_multi_index_to_array.py

@@ -0,0 +1,20 @@
+"""Benchmark: MultiIndex.to_flat_index() (equivalent of toArray()) on 100k-pair MultiIndex"""
+import json, time
+import pandas as pd
+
+ROWS = 100_000
+WARMUP = 3
+ITERATIONS = 10
+a = [f"a{i % 100}" for i in range(ROWS)]
+b = [i % 1000 for i in range(ROWS)]
+tuples = list(zip(a, b))
+mi = pd.MultiIndex.from_tuples(tuples)
+
+for _ in range(WARMUP):
+    mi.to_flat_index()
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    mi.to_flat_index()
+total = (time.perf_counter() - start) * 1000
+print(json.dumps({"function": "multi_index_to_array", "mean_ms": total / ITERATIONS, "iterations": ITERATIONS, "total_ms": total}))

benchmarks/tsb/bench_cat_from_codes.ts

@@ -0,0 +1,23 @@
+/**
+ * Benchmark: catFromCodes on 100k-element code array
+ */
+import { catFromCodes } from "../../src/index.js";
+
+const ROWS = 100_000;
+const WARMUP = 3;
+const ITERATIONS = 10;
+const categories = ["alpha", "beta", "gamma", "delta"];
+const codes = Array.from({ length: ROWS }, (_, i) => i % 4);
+
+for (let i = 0; i < WARMUP; i++) catFromCodes(codes, categories);
+const start = performance.now();
+for (let i = 0; i < ITERATIONS; i++) catFromCodes(codes, categories);
+const total = performance.now() - start;
+console.log(
+  JSON.stringify({
+    function: "cat_from_codes",
+    mean_ms: total / ITERATIONS,
+    iterations: ITERATIONS,
+    total_ms: total,
+  }),
+);

benchmarks/tsb/bench_multi_index_isin.ts

@@ -0,0 +1,30 @@
+/**
+ * Benchmark: MultiIndex.isin() on 100k-pair MultiIndex
+ */
+import { MultiIndex } from "../../src/index.js";
+
+const ROWS = 100_000;
+const WARMUP = 3;
+const ITERATIONS = 10;
+const a = Array.from({ length: ROWS }, (_, i) => `a${i % 100}`);
+const b = Array.from({ length: ROWS }, (_, i) => i % 1000);
+const tuples: [string, number][] = a.map((v, i) => [v, b[i] as number]);
+const mi = new MultiIndex({ tuples });
+// 1000 tuples to look up
+const lookupTuples: [string, number][] = Array.from({ length: 1000 }, (_, i) => [
+  `a${i % 100}`,
+  i % 1000,
+]);
+
+for (let i = 0; i < WARMUP; i++) mi.isin(lookupTuples);
+const start = performance.now();
+for (let i = 0; i < ITERATIONS; i++) mi.isin(lookupTuples);
+const total = performance.now() - start;
+console.log(
+  JSON.stringify({
+    function: "multi_index_isin",
+    mean_ms: total / ITERATIONS,
+    iterations: ITERATIONS,
+    total_ms: total,
+  }),
+);

benchmarks/tsb/bench_multi_index_reorder_levels.ts

@@ -0,0 +1,26 @@
+/**
+ * Benchmark: MultiIndex.reorderLevels() on 100k-pair MultiIndex
+ */
+import { MultiIndex } from "../../src/index.js";
+
+const ROWS = 100_000;
+const WARMUP = 3;
+const ITERATIONS = 10;
+const a = Array.from({ length: ROWS }, (_, i) => `a${i % 100}`);
+const b = Array.from({ length: ROWS }, (_, i) => i % 1000);
+const c = Array.from({ length: ROWS }, (_, i) => i % 50);
+const tuples: [string, number, number][] = a.map((v, i) => [v, b[i] as number, c[i] as number]);
+const mi = new MultiIndex({ tuples });
+
+for (let i = 0; i < WARMUP; i++) mi.reorderLevels([2, 0, 1]);
+const start = performance.now();
+for (let i = 0; i < ITERATIONS; i++) mi.reorderLevels([2, 0, 1]);
+const total = performance.now() - start;
+console.log(
+  JSON.stringify({
+    function: "multi_index_reorder_levels",
+    mean_ms: total / ITERATIONS,
+    iterations: ITERATIONS,
+    total_ms: total,
+  }),
+);

benchmarks/tsb/bench_multi_index_set_names.ts

@@ -0,0 +1,25 @@
+/**
+ * Benchmark: MultiIndex.setNames() on 100k-pair MultiIndex
+ */
+import { MultiIndex } from "../../src/index.js";
+
+const ROWS = 100_000;
+const WARMUP = 3;
+const ITERATIONS = 10;
+const a = Array.from({ length: ROWS }, (_, i) => `a${i % 100}`);
+const b = Array.from({ length: ROWS }, (_, i) => i % 1000);
+const tuples: [string, number][] = a.map((v, i) => [v, b[i] as number]);
+const mi = new MultiIndex({ tuples });
+
+for (let i = 0; i < WARMUP; i++) mi.setNames(["level0", "level1"]);
+const start = performance.now();
+for (let i = 0; i < ITERATIONS; i++) mi.setNames(["level0", "level1"]);
+const total = performance.now() - start;
+console.log(
+  JSON.stringify({
+    function: "multi_index_set_names",
+    mean_ms: total / ITERATIONS,
+    iterations: ITERATIONS,
+    total_ms: total,
+  }),
+);

benchmarks/tsb/bench_multi_index_to_array.ts

@@ -0,0 +1,25 @@
+/**
+ * Benchmark: MultiIndex.toArray() on 100k-pair MultiIndex
+ */
+import { MultiIndex } from "../../src/index.js";
+
+const ROWS = 100_000;
+const WARMUP = 3;
+const ITERATIONS = 10;
+const a = Array.from({ length: ROWS }, (_, i) => `a${i % 100}`);
+const b = Array.from({ length: ROWS }, (_, i) => i % 1000);
+const tuples: [string, number][] = a.map((v, i) => [v, b[i] as number]);
+const mi = new MultiIndex({ tuples });
+
+for (let i = 0; i < WARMUP; i++) mi.toArray();
+const start = performance.now();
+for (let i = 0; i < ITERATIONS; i++) mi.toArray();
+const total = performance.now() - start;
+console.log(
+  JSON.stringify({
+    function: "multi_index_to_array",
+    mean_ms: total / ITERATIONS,
+    iterations: ITERATIONS,
+    total_ms: total,
+  }),
+);