Iteration 155: DataFrameExpanding std/var/sum/count/median/apply + TZDatetimeIndex extra + TimedeltaIndex toStrings

Run: https://github.com/githubnext/tsessebe/actions/runs/24567781388

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

Author: github-actions[bot]

benchmarks/pandas/bench_dataframe_expanding_median_apply.py

@@ -0,0 +1,32 @@
+"""Benchmark: DataFrame.expanding().median() and .apply(fn) on 10k-row DataFrame."""
+import pandas as pd
+import numpy as np
+import json
+import time
+
+ROWS = 10_000
+WARMUP = 2
+ITERATIONS = 5
+
+a = np.sin(np.arange(ROWS) * 0.05) * 100
+b = np.cos(np.arange(ROWS) * 0.05) * 80
+df = pd.DataFrame({"a": a, "b": b})
+
+sum_fn = lambda x: x.sum()
+
+for _ in range(WARMUP):
+    df.expanding().median()
+    df.expanding().apply(sum_fn, raw=True)
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    df.expanding().median()
+    df.expanding().apply(sum_fn, raw=True)
+total = time.perf_counter() - start
+
+print(json.dumps({
+    "function": "dataframe_expanding_median_apply",
+    "mean_ms": total / ITERATIONS * 1000,
+    "iterations": ITERATIONS,
+    "total_ms": total * 1000,
+}))

benchmarks/pandas/bench_dataframe_expanding_std_var.py

@@ -0,0 +1,30 @@
+"""Benchmark: DataFrame.expanding().std() and .var() on 10k-row DataFrame."""
+import pandas as pd
+import numpy as np
+import json
+import time
+
+ROWS = 10_000
+WARMUP = 3
+ITERATIONS = 10
+
+a = np.sin(np.arange(ROWS) * 0.01) * 100
+b = np.cos(np.arange(ROWS) * 0.01) * 50
+df = pd.DataFrame({"a": a, "b": b})
+
+for _ in range(WARMUP):
+    df.expanding().std()
+    df.expanding().var()
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    df.expanding().std()
+    df.expanding().var()
+total = time.perf_counter() - start
+
+print(json.dumps({
+    "function": "dataframe_expanding_std_var",
+    "mean_ms": total / ITERATIONS * 1000,
+    "iterations": ITERATIONS,
+    "total_ms": total * 1000,
+}))

benchmarks/pandas/bench_dataframe_expanding_sum_count.py

@@ -0,0 +1,30 @@
+"""Benchmark: DataFrame.expanding().sum() and .count() on 10k-row DataFrame."""
+import pandas as pd
+import numpy as np
+import json
+import time
+
+ROWS = 10_000
+WARMUP = 3
+ITERATIONS = 10
+
+a = (np.arange(ROWS) % 100) * 1.5
+b = (np.arange(ROWS) % 50) * 2.0
+df = pd.DataFrame({"a": a, "b": b})
+
+for _ in range(WARMUP):
+    df.expanding().sum()
+    df.expanding().count()
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    df.expanding().sum()
+    df.expanding().count()
+total = time.perf_counter() - start
+
+print(json.dumps({
+    "function": "dataframe_expanding_sum_count",
+    "mean_ms": total / ITERATIONS * 1000,
+    "iterations": ITERATIONS,
+    "total_ms": total * 1000,
+}))

benchmarks/pandas/bench_timedelta_index_tostrings.py

@@ -0,0 +1,39 @@
+"""Benchmark: TimedeltaIndex.astype(str), .to_numpy(), element access, rename
+on 10k-element TimedeltaIndex."""
+import pandas as pd
+import numpy as np
+import json
+import time
+
+SIZE = 10_000
+WARMUP = 5
+ITERATIONS = 50
+
+deltas = pd.to_timedelta(
+    [(i % 365) * 24 * 3600 + (i % 24) * 3600 + (i % 60) * 60 for i in range(SIZE)],
+    unit="s",
+)
+idx = pd.TimedeltaIndex(deltas, name="duration")
+
+for _ in range(WARMUP):
+    idx.astype(str)
+    idx.to_numpy()
+    idx[0]
+    idx[-1]
+    idx.rename("elapsed")
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    idx.astype(str)
+    idx.to_numpy()
+    idx[0]
+    idx[-1]
+    idx.rename("elapsed")
+total = time.perf_counter() - start
+
+print(json.dumps({
+    "function": "timedelta_index_tostrings",
+    "mean_ms": total / ITERATIONS * 1000,
+    "iterations": ITERATIONS,
+    "total_ms": total * 1000,
+}))

benchmarks/pandas/bench_tz_datetime_index_extra.py

@@ -0,0 +1,45 @@
+"""Benchmark: tz-aware DatetimeIndex — slice, concat, min/max, tz_convert,
+tz_localize(None), and array conversions on 10k-element index."""
+import pandas as pd
+import numpy as np
+import json
+import time
+
+SIZE = 10_000
+WARMUP = 3
+ITERATIONS = 20
+
+naive = pd.date_range("2024-01-01", periods=SIZE, freq="h")
+tz_idx = naive.tz_localize("America/New_York")
+half = SIZE // 2
+
+for _ in range(WARMUP):
+    tz_idx[:half]
+    tz_idx[:half].append(tz_idx[half:])
+    tz_idx[0]
+    tz_idx.to_list()
+    tz_idx.asi8
+    tz_idx.min()
+    tz_idx.max()
+    tz_idx.tz_convert("UTC")
+    tz_idx.tz_localize(None)
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    tz_idx[:half]
+    tz_idx[:half].append(tz_idx[half:])
+    tz_idx[0]
+    tz_idx.to_list()
+    tz_idx.asi8
+    tz_idx.min()
+    tz_idx.max()
+    tz_idx.tz_convert("UTC")
+    tz_idx.tz_localize(None)
+total = time.perf_counter() - start
+
+print(json.dumps({
+    "function": "tz_datetime_index_extra",
+    "mean_ms": total / ITERATIONS * 1000,
+    "iterations": ITERATIONS,
+    "total_ms": total * 1000,
+}))

benchmarks/tsb/bench_dataframe_expanding_median_apply.ts

@@ -0,0 +1,36 @@
+/**
+ * Benchmark: DataFrameExpanding.median() and .apply(fn) on 10k-row DataFrame.
+ * Outputs JSON: {"function": "dataframe_expanding_median_apply", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+ */
+import { DataFrame } from "../../src/index.js";
+
+const ROWS = 10_000;
+const WARMUP = 2;
+const ITERATIONS = 5;
+
+const a = Array.from({ length: ROWS }, (_, i) => Math.sin(i * 0.05) * 100);
+const b = Array.from({ length: ROWS }, (_, i) => Math.cos(i * 0.05) * 80);
+const df = DataFrame.fromColumns({ a, b });
+
+const sumFn = (vals: readonly number[]) => vals.reduce((acc, v) => acc + v, 0);
+
+for (let i = 0; i < WARMUP; i++) {
+  df.expanding().median();
+  df.expanding().apply(sumFn);
+}
+
+const start = performance.now();
+for (let i = 0; i < ITERATIONS; i++) {
+  df.expanding().median();
+  df.expanding().apply(sumFn);
+}
+const total = performance.now() - start;
+
+console.log(
+  JSON.stringify({
+    function: "dataframe_expanding_median_apply",
+    mean_ms: total / ITERATIONS,
+    iterations: ITERATIONS,
+    total_ms: total,
+  }),
+);

benchmarks/tsb/bench_dataframe_expanding_std_var.ts

@@ -0,0 +1,34 @@
+/**
+ * Benchmark: DataFrameExpanding.std() and .var() on 10k-row DataFrame.
+ * Outputs JSON: {"function": "dataframe_expanding_std_var", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+ */
+import { DataFrame } from "../../src/index.js";
+
+const ROWS = 10_000;
+const WARMUP = 3;
+const ITERATIONS = 10;
+
+const a = Array.from({ length: ROWS }, (_, i) => Math.sin(i * 0.01) * 100);
+const b = Array.from({ length: ROWS }, (_, i) => Math.cos(i * 0.01) * 50);
+const df = DataFrame.fromColumns({ a, b });
+
+for (let i = 0; i < WARMUP; i++) {
+  df.expanding().std();
+  df.expanding().var();
+}
+
+const start = performance.now();
+for (let i = 0; i < ITERATIONS; i++) {
+  df.expanding().std();
+  df.expanding().var();
+}
+const total = performance.now() - start;
+
+console.log(
+  JSON.stringify({
+    function: "dataframe_expanding_std_var",
+    mean_ms: total / ITERATIONS,
+    iterations: ITERATIONS,
+    total_ms: total,
+  }),
+);

benchmarks/tsb/bench_dataframe_expanding_sum_count.ts

@@ -0,0 +1,34 @@
+/**
+ * Benchmark: DataFrameExpanding.sum() and .count() on 10k-row DataFrame.
+ * Outputs JSON: {"function": "dataframe_expanding_sum_count", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+ */
+import { DataFrame } from "../../src/index.js";
+
+const ROWS = 10_000;
+const WARMUP = 3;
+const ITERATIONS = 10;
+
+const a = Array.from({ length: ROWS }, (_, i) => (i % 100) * 1.5);
+const b = Array.from({ length: ROWS }, (_, i) => (i % 50) * 2.0);
+const df = DataFrame.fromColumns({ a, b });
+
+for (let i = 0; i < WARMUP; i++) {
+  df.expanding().sum();
+  df.expanding().count();
+}
+
+const start = performance.now();
+for (let i = 0; i < ITERATIONS; i++) {
+  df.expanding().sum();
+  df.expanding().count();
+}
+const total = performance.now() - start;
+
+console.log(
+  JSON.stringify({
+    function: "dataframe_expanding_sum_count",
+    mean_ms: total / ITERATIONS,
+    iterations: ITERATIONS,
+    total_ms: total,
+  }),
+);

benchmarks/tsb/bench_timedelta_index_tostrings.ts

@@ -0,0 +1,41 @@
+/**
+ * Benchmark: TimedeltaIndex.toStrings(), .toArray(), .at(), .rename() on 10k-element index.
+ * Outputs JSON: {"function": "timedelta_index_tostrings", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+ */
+import { Timedelta, TimedeltaIndex } from "../../src/index.js";
+
+const SIZE = 10_000;
+const WARMUP = 5;
+const ITERATIONS = 50;
+
+const deltas = Array.from({ length: SIZE }, (_, i) =>
+  Timedelta.fromComponents({ days: i % 365, hours: i % 24, minutes: i % 60 }),
+);
+const idx = TimedeltaIndex.fromTimedeltas(deltas, "duration");
+
+for (let i = 0; i < WARMUP; i++) {
+  idx.toStrings();
+  idx.toArray();
+  idx.at(0);
+  idx.at(SIZE - 1);
+  idx.rename("elapsed");
+}
+
+const start = performance.now();
+for (let i = 0; i < ITERATIONS; i++) {
+  idx.toStrings();
+  idx.toArray();
+  idx.at(0);
+  idx.at(SIZE - 1);
+  idx.rename("elapsed");
+}
+const total = performance.now() - start;
+
+console.log(
+  JSON.stringify({
+    function: "timedelta_index_tostrings",
+    mean_ms: total / ITERATIONS,
+    iterations: ITERATIONS,
+    total_ms: total,
+  }),
+);

benchmarks/tsb/bench_tz_datetime_index_extra.ts

@@ -0,0 +1,53 @@
+/**
+ * Benchmark: TZDatetimeIndex — slice, concat, at, toArray, toTimestamps, min, max,
+ *            tz_convert (instance method), tz_localize_none on 10k-element TZDatetimeIndex.
+ * Outputs JSON: {"function": "tz_datetime_index_extra", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+ */
+import { date_range, tz_localize } from "../../src/index.js";
+
+const SIZE = 10_000;
+const WARMUP = 3;
+const ITERATIONS = 20;
+
+const naive = date_range({ start: "2024-01-01", periods: SIZE, freq: "h" });
+const tzIdx = tz_localize(naive, "America/New_York");
+const halfSize = Math.floor(SIZE / 2);
+
+for (let i = 0; i < WARMUP; i++) {
+  tzIdx.slice(0, halfSize);
+  const half1 = tzIdx.slice(0, halfSize);
+  const half2 = tzIdx.slice(halfSize);
+  half1.concat(half2);
+  tzIdx.at(0);
+  tzIdx.toArray();
+  tzIdx.toTimestamps();
+  tzIdx.min();
+  tzIdx.max();
+  tzIdx.tz_convert("UTC");
+  tzIdx.tz_localize_none();
+}
+
+const start = performance.now();
+for (let i = 0; i < ITERATIONS; i++) {
+  tzIdx.slice(0, halfSize);
+  const half1 = tzIdx.slice(0, halfSize);
+  const half2 = tzIdx.slice(halfSize);
+  half1.concat(half2);
+  tzIdx.at(0);
+  tzIdx.toArray();
+  tzIdx.toTimestamps();
+  tzIdx.min();
+  tzIdx.max();
+  tzIdx.tz_convert("UTC");
+  tzIdx.tz_localize_none();
+}
+const total = performance.now() - start;
+
+console.log(
+  JSON.stringify({
+    function: "tz_datetime_index_extra",
+    mean_ms: total / ITERATIONS,
+    iterations: ITERATIONS,
+    total_ms: total,
+  }),
+);