Iteration 169: Add 10 benchmark pairs (549 total, +5 vs best 544)

Added 10 new benchmark pairs covering specific options/variants:
- read_json_all_orients: readJson with records/split/columns/values/index orients
- pivot_table_fill_value: pivotTable with fill_value=0 option
- dataframe_cov_options: dataFrameCov/dataFrameCorr with ddof and minPeriods
- dataframe_rolling_apply_fn: standalone dataFrameRollingApply function
- pct_change_fill_method: pctChangeSeries/pctChangeDataFrame with fillMethod options
- reindex_fill_methods: reindexSeries/reindexDataFrame with ffill/bfill/nearest
- json_normalize_meta: jsonNormalize with recordPath, meta fields, metaPrefix
- interpolate_zero_nearest: interpolateSeries with zero/nearest/linear with limit
- dropna_thresh_subset: dropnaDataFrame with thresh and subset options
- wide_to_long_sep_suffix: wideToLong with sep and suffix regex options

Run: https://github.com/githubnext/tsessebe/actions/runs/24590758458

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

Author: github-actions[bot]

benchmarks/pandas/bench_dataframe_cov_options.py

@@ -0,0 +1,33 @@
+"""Benchmark: DataFrame.cov / DataFrame.corr with options (ddof, min_periods)."""
+import json, time
+import numpy as np
+import pandas as pd
+
+SIZE = 20_000
+WARMUP = 3
+ITERATIONS = 20
+
+rng = np.random.default_rng(42)
+a = np.arange(SIZE) * 0.5 + np.sin(np.arange(SIZE) * 0.01)
+b = np.arange(SIZE) * 0.3 - np.cos(np.arange(SIZE) * 0.02)
+c = (np.arange(SIZE) % 100) * 1.5
+df = pd.DataFrame({"a": a, "b": b, "c": c})
+
+for _ in range(WARMUP):
+    df.cov(ddof=0)
+    df.cov(ddof=1, min_periods=100)
+    df.corr(min_periods=50)
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    df.cov(ddof=0)
+    df.cov(ddof=1, min_periods=100)
+    df.corr(min_periods=50)
+total = (time.perf_counter() - start) * 1000
+
+print(json.dumps({
+    "function": "dataframe_cov_options",
+    "mean_ms": total / ITERATIONS,
+    "iterations": ITERATIONS,
+    "total_ms": total,
+}))

benchmarks/pandas/bench_dataframe_rolling_apply_fn.py

@@ -0,0 +1,31 @@
+"""Benchmark: DataFrame rolling apply with a custom range function per column."""
+import json, time
+import numpy as np
+import pandas as pd
+
+ROWS = 5_000
+WINDOW = 10
+WARMUP = 3
+ITERATIONS = 10
+
+a = np.sin(np.arange(ROWS) * 0.01)
+b = np.cos(np.arange(ROWS) * 0.02)
+c = (np.arange(ROWS) % 100) * 0.5
+df = pd.DataFrame({"a": a, "b": b, "c": c})
+
+range_fn = lambda w: np.max(w) - np.min(w)
+
+for _ in range(WARMUP):
+    df.rolling(WINDOW).apply(range_fn, raw=True)
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    df.rolling(WINDOW).apply(range_fn, raw=True)
+total = (time.perf_counter() - start) * 1000
+
+print(json.dumps({
+    "function": "dataframe_rolling_apply_fn",
+    "mean_ms": total / ITERATIONS,
+    "iterations": ITERATIONS,
+    "total_ms": total,
+}))

benchmarks/pandas/bench_dropna_thresh_subset.py

@@ -0,0 +1,35 @@
+"""Benchmark: DataFrame.dropna with thresh and subset options."""
+import json, time
+import numpy as np
+import pandas as pd
+
+SIZE = 100_000
+WARMUP = 5
+ITERATIONS = 30
+
+a = [None if i % 5 == 0 else float(i) for i in range(SIZE)]
+b = [None if i % 7 == 0 else float(i * 2) for i in range(SIZE)]
+c = [None if i % 11 == 0 else float(i * 3) for i in range(SIZE)]
+d = [None if i % 3 == 0 else f"label_{i % 20}" for i in range(SIZE)]
+df = pd.DataFrame({"a": a, "b": b, "c": c, "d": d})
+
+for _ in range(WARMUP):
+    df.dropna(how="any")
+    df.dropna(how="all")
+    df.dropna(thresh=3)
+    df.dropna(subset=["a", "b"])
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    df.dropna(how="any")
+    df.dropna(how="all")
+    df.dropna(thresh=3)
+    df.dropna(subset=["a", "b"])
+total = (time.perf_counter() - start) * 1000
+
+print(json.dumps({
+    "function": "dropna_thresh_subset",
+    "mean_ms": total / ITERATIONS,
+    "iterations": ITERATIONS,
+    "total_ms": total,
+}))

benchmarks/pandas/bench_interpolate_zero_nearest.py

@@ -0,0 +1,32 @@
+"""Benchmark: Series.interpolate with zero and nearest methods."""
+import json, time
+import numpy as np
+import pandas as pd
+
+SIZE = 50_000
+WARMUP = 5
+ITERATIONS = 30
+
+data = [None if i % 7 in (0, 1, 2) else np.sin(i * 0.01) * 100 for i in range(SIZE)]
+s = pd.Series(data, dtype="float64")
+
+for _ in range(WARMUP):
+    s.interpolate(method="zero")
+    s.interpolate(method="nearest")
+    s.interpolate(method="linear", limit=2)
+    s.interpolate(method="pad", limit=5)
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    s.interpolate(method="zero")
+    s.interpolate(method="nearest")
+    s.interpolate(method="linear", limit=2)
+    s.interpolate(method="pad", limit=5)
+total = (time.perf_counter() - start) * 1000
+
+print(json.dumps({
+    "function": "interpolate_zero_nearest",
+    "mean_ms": total / ITERATIONS,
+    "iterations": ITERATIONS,
+    "total_ms": total,
+}))

benchmarks/pandas/bench_json_normalize_meta.py

@@ -0,0 +1,45 @@
+"""Benchmark: pd.json_normalize with record_path, meta fields, and nested data."""
+import json, time
+import pandas as pd
+
+SIZE = 2_000
+WARMUP = 3
+ITERATIONS = 20
+
+records = [
+    {
+        "id": i,
+        "dept": f"dept_{i % 10}",
+        "location": {"city": f"city_{i % 20}", "country": "US"},
+        "employees": [
+            {"name": f"emp_{i}_{j}", "salary": (i * 3 + j) * 1000, "active": j % 2 == 0}
+            for j in range(3)
+        ],
+    }
+    for i in range(SIZE)
+]
+
+for _ in range(WARMUP):
+    pd.json_normalize(
+        records,
+        record_path="employees",
+        meta=["id", "dept"],
+        meta_prefix="company_",
+    )
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    pd.json_normalize(
+        records,
+        record_path="employees",
+        meta=["id", "dept"],
+        meta_prefix="company_",
+    )
+total = (time.perf_counter() - start) * 1000
+
+print(json.dumps({
+    "function": "json_normalize_meta",
+    "mean_ms": total / ITERATIONS,
+    "iterations": ITERATIONS,
+    "total_ms": total,
+}))

benchmarks/pandas/bench_pct_change_fill_method.py

@@ -0,0 +1,37 @@
+"""Benchmark: Series.pct_change / DataFrame.pct_change with fill_method options."""
+import json, time
+import numpy as np
+import pandas as pd
+
+SIZE = 50_000
+WARMUP = 5
+ITERATIONS = 30
+
+data = [None if i % 20 == 0 else np.sin(i * 0.01) * 100 + 100 for i in range(SIZE)]
+s = pd.Series(data, dtype="float64")
+
+df = pd.DataFrame({
+    "a": data,
+    "b": [None if i % 15 == 0 else np.cos(i * 0.02) * 50 + 50 for i in range(SIZE)],
+})
+
+for _ in range(WARMUP):
+    s.pct_change(fill_method="pad")
+    s.pct_change(fill_method="bfill")
+    s.pct_change(fill_method=None)
+    df.pct_change(fill_method="pad", periods=2)
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    s.pct_change(fill_method="pad")
+    s.pct_change(fill_method="bfill")
+    s.pct_change(fill_method=None)
+    df.pct_change(fill_method="pad", periods=2)
+total = (time.perf_counter() - start) * 1000
+
+print(json.dumps({
+    "function": "pct_change_fill_method",
+    "mean_ms": total / ITERATIONS,
+    "iterations": ITERATIONS,
+    "total_ms": total,
+}))

benchmarks/pandas/bench_pivot_table_fill_value.py

@@ -0,0 +1,28 @@
+"""Benchmark: pivot_table with fill_value=0 — fills missing cells with 0."""
+import json, time
+import numpy as np
+import pandas as pd
+
+ROWS = 50_000
+WARMUP = 3
+ITERATIONS = 10
+
+rows = [f"row_{i % 50}" for i in range(ROWS)]
+cols = [f"col_{i % 30}" for i in range(ROWS)]
+vals = np.arange(ROWS, dtype=np.float64) * 0.1
+df = pd.DataFrame({"row": rows, "col": cols, "value": vals})
+
+for _ in range(WARMUP):
+    df.pivot_table(values="value", index="row", columns="col", aggfunc="sum", fill_value=0)
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    df.pivot_table(values="value", index="row", columns="col", aggfunc="sum", fill_value=0)
+total = (time.perf_counter() - start) * 1000
+
+print(json.dumps({
+    "function": "pivot_table_fill_value",
+    "mean_ms": total / ITERATIONS,
+    "iterations": ITERATIONS,
+    "total_ms": total,
+}))

benchmarks/pandas/bench_read_json_all_orients.py

@@ -0,0 +1,42 @@
+"""Benchmark: pd.read_json with all orient options (records, split, columns, index, values)."""
+import json, time
+import numpy as np
+import pandas as pd
+
+SIZE = 5_000
+WARMUP = 3
+ITERATIONS = 20
+
+ids = list(range(SIZE))
+values = [i * 1.1 for i in range(SIZE)]
+labels = [f"cat_{i % 10}" for i in range(SIZE)]
+df = pd.DataFrame({"id": ids, "value": values, "label": labels})
+
+records_json = df.to_json(orient="records")
+split_json = df.to_json(orient="split")
+columns_json = df.to_json(orient="columns")
+values_json = df.to_json(orient="values")
+index_json = df.to_json(orient="index")
+
+for _ in range(WARMUP):
+    pd.read_json(records_json, orient="records")
+    pd.read_json(split_json, orient="split")
+    pd.read_json(columns_json, orient="columns")
+    pd.read_json(values_json, orient="values")
+    pd.read_json(index_json, orient="index")
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    pd.read_json(records_json, orient="records")
+    pd.read_json(split_json, orient="split")
+    pd.read_json(columns_json, orient="columns")
+    pd.read_json(values_json, orient="values")
+    pd.read_json(index_json, orient="index")
+total = (time.perf_counter() - start) * 1000
+
+print(json.dumps({
+    "function": "read_json_all_orients",
+    "mean_ms": total / ITERATIONS,
+    "iterations": ITERATIONS,
+    "total_ms": total,
+}))

benchmarks/pandas/bench_reindex_fill_methods.py

@@ -0,0 +1,37 @@
+"""Benchmark: Series.reindex / DataFrame.reindex with fill methods (ffill, bfill, nearest)."""
+import json, time
+import numpy as np
+import pandas as pd
+
+SIZE = 20_000
+WARMUP = 3
+ITERATIONS = 20
+
+orig_labels = list(range(0, SIZE * 2, 2))  # even numbers
+data = [i * 1.5 for i in range(SIZE)]
+s = pd.Series(data, index=orig_labels)
+
+new_index = list(range(SIZE * 2))  # all numbers 0..SIZE*2-1
+
+df = pd.DataFrame({"a": data, "b": [v * 2 for v in data]}, index=orig_labels)
+
+for _ in range(WARMUP):
+    s.reindex(new_index, method="ffill")
+    s.reindex(new_index, method="bfill")
+    s.reindex(new_index, method="nearest")
+    df.reindex(new_index, method="ffill")
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    s.reindex(new_index, method="ffill")
+    s.reindex(new_index, method="bfill")
+    s.reindex(new_index, method="nearest")
+    df.reindex(new_index, method="ffill")
+total = (time.perf_counter() - start) * 1000
+
+print(json.dumps({
+    "function": "reindex_fill_methods",
+    "mean_ms": total / ITERATIONS,
+    "iterations": ITERATIONS,
+    "total_ms": total,
+}))

benchmarks/pandas/bench_wide_to_long_sep_suffix.py

@@ -0,0 +1,43 @@
+"""Benchmark: pd.wide_to_long with sep and suffix options."""
+import json, time
+import pandas as pd
+
+ROWS = 5_000
+WARMUP = 3
+ITERATIONS = 20
+
+ids = list(range(ROWS))
+df1 = pd.DataFrame({
+    "id": ids,
+    "A_1": [i * 1.0 for i in ids],
+    "A_2": [i * 1.1 for i in ids],
+    "A_3": [i * 1.2 for i in ids],
+    "B_1": [i * 2.0 for i in ids],
+    "B_2": [i * 2.1 for i in ids],
+    "B_3": [i * 2.2 for i in ids],
+})
+
+students = [f"s{i}" for i in ids]
+df2 = pd.DataFrame({
+    "student": students,
+    "score_Q1": [i + 10 for i in ids],
+    "score_Q2": [i + 20 for i in ids],
+    "score_Q3": [i + 30 for i in ids],
+})
+
+for _ in range(WARMUP):
+    pd.wide_to_long(df1, stubnames=["A", "B"], i="id", j="period", sep="_")
+    pd.wide_to_long(df2, stubnames="score", i="student", j="quarter", sep="_", suffix=r"Q\d+")
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    pd.wide_to_long(df1, stubnames=["A", "B"], i="id", j="period", sep="_")
+    pd.wide_to_long(df2, stubnames="score", i="student", j="quarter", sep="_", suffix=r"Q\d+")
+total = (time.perf_counter() - start) * 1000
+
+print(json.dumps({
+    "function": "wide_to_long_sep_suffix",
+    "mean_ms": total / ITERATIONS,
+    "iterations": ITERATIONS,
+    "total_ms": total,
+}))