Merge pull request #155 from githubnext/autoloop/perf-comparison-36d7559a

[Autoloop] [Autoloop: perf-comparison]

Author: mrjf

benchmarks/pandas/bench_advance_date_fn.py

@@ -0,0 +1,46 @@
+"""
+Benchmark: pandas DateOffset arithmetic — date frequency parsing and advancement.
+Mirrors tsb advanceDate / parseFreq.
+Outputs JSON: {"function": "advance_date_fn", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+"""
+import json
+import time
+import pandas as pd
+
+WARMUP = 5
+ITERATIONS = 1000
+
+d = pd.Timestamp("2023-06-15")
+offsets = [
+    pd.DateOffset(days=1),
+    pd.DateOffset(days=3),
+    pd.offsets.BDay(1),
+    pd.offsets.Week(1),
+    pd.offsets.MonthBegin(1),
+    pd.offsets.MonthEnd(1),
+    pd.DateOffset(hours=1),
+    pd.DateOffset(hours=2),
+    pd.DateOffset(minutes=1),
+    pd.offsets.YearBegin(1),
+]
+
+for _ in range(WARMUP):
+    for off in offsets:
+        d + off
+    pd.Timestamp("2023-01-01")
+    pd.Timestamp(1672531200000, unit="ms")
+
+t0 = time.perf_counter()
+for _ in range(ITERATIONS):
+    for off in offsets:
+        d + off
+    pd.Timestamp("2023-01-01")
+    pd.Timestamp(1672531200000, unit="ms")
+total = (time.perf_counter() - t0) * 1000
+
+print(json.dumps({
+    "function": "advance_date_fn",
+    "mean_ms": round(total / ITERATIONS, 3),
+    "iterations": ITERATIONS,
+    "total_ms": round(total, 3),
+}))

benchmarks/pandas/bench_any_all_reduce_na.py

@@ -0,0 +1,42 @@
+"""
+Benchmark: Series.any() / all() / DataFrame.any() / all() — boolean reductions.
+Outputs JSON: {"function": "any_all_reduce_na", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+"""
+import json
+import time
+import numpy as np
+import pandas as pd
+
+SIZE = 100_000
+ROWS = 10_000
+WARMUP = 5
+ITERATIONS = 100
+
+bool_data = np.arange(SIZE) % 3 != 0
+s = pd.Series(bool_data)
+df = pd.DataFrame({
+    "a": np.arange(ROWS) % 2 == 0,
+    "b": np.arange(ROWS) > ROWS // 2,
+    "c": np.ones(ROWS, 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_reduce_na",
+    "mean_ms": total / ITERATIONS,
+    "iterations": ITERATIONS,
+    "total_ms": total,
+}))

benchmarks/pandas/bench_dataframe_diff_shift_fn.py

@@ -0,0 +1,39 @@
+"""
+Benchmark: pandas DataFrame.diff() / DataFrame.shift() — discrete difference and shift.
+Outputs JSON: {"function": "dataframe_diff_shift_fn", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+"""
+import json
+import time
+import pandas as pd
+import numpy as np
+
+SIZE = 100_000
+WARMUP = 5
+ITERATIONS = 20
+
+df = pd.DataFrame({
+    "a": np.arange(SIZE, dtype=float),
+    "b": np.sin(np.arange(SIZE) * 0.01) * 100,
+    "c": np.arange(SIZE) * 2.5,
+})
+
+for _ in range(WARMUP):
+    df.diff()
+    df.diff(periods=3)
+    df.shift(1)
+    df.shift(-2)
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    df.diff()
+    df.diff(periods=3)
+    df.shift(1)
+    df.shift(-2)
+total = (time.perf_counter() - start) * 1000
+
+print(json.dumps({
+    "function": "dataframe_diff_shift_fn",
+    "mean_ms": round(total / ITERATIONS, 3),
+    "iterations": ITERATIONS,
+    "total_ms": round(total, 3),
+}))

benchmarks/pandas/bench_dataframe_ffill_bfill_fn.py

@@ -0,0 +1,37 @@
+"""
+Benchmark: pandas DataFrame.ffill() / DataFrame.bfill() — forward/backward fill.
+Outputs JSON: {"function": "dataframe_ffill_bfill_fn", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+"""
+import json
+import time
+import pandas as pd
+import numpy as np
+
+SIZE = 100_000
+WARMUP = 5
+ITERATIONS = 20
+
+df = pd.DataFrame({
+    "a": [float("nan") if i % 5 == 0 else i * 0.1 for i in range(SIZE)],
+    "b": [float("nan") if i % 7 == 0 else i * 2.0 for i in range(SIZE)],
+    "c": [float("nan") if i % 3 == 0 else i * 0.5 for i in range(SIZE)],
+})
+
+for _ in range(WARMUP):
+    df.ffill()
+    df.bfill()
+    df.ffill(limit=3)
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    df.ffill()
+    df.bfill()
+    df.ffill(limit=3)
+total = (time.perf_counter() - start) * 1000
+
+print(json.dumps({
+    "function": "dataframe_ffill_bfill_fn",
+    "mean_ms": round(total / ITERATIONS, 3),
+    "iterations": ITERATIONS,
+    "total_ms": round(total, 3),
+}))

benchmarks/pandas/bench_date_range_fn.py

@@ -0,0 +1,32 @@
+"""
+Benchmark: pandas.date_range() — generate a fixed-frequency date sequence.
+Outputs JSON: {"function": "date_range_fn", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+"""
+import json
+import time
+import pandas as pd
+
+WARMUP = 5
+ITERATIONS = 100
+
+start = "2020-01-01"
+end = "2022-12-31"
+
+for _ in range(WARMUP):
+    pd.date_range(start=start, end=end, freq="D")
+    pd.date_range(start=start, periods=365, freq="D")
+    pd.date_range(start=start, periods=24, freq="h")
+
+t0 = time.perf_counter()
+for _ in range(ITERATIONS):
+    pd.date_range(start=start, end=end, freq="D")
+    pd.date_range(start=start, periods=365, freq="D")
+    pd.date_range(start=start, periods=24, freq="h")
+total = (time.perf_counter() - t0) * 1000
+
+print(json.dumps({
+    "function": "date_range_fn",
+    "mean_ms": round(total / ITERATIONS, 3),
+    "iterations": ITERATIONS,
+    "total_ms": round(total, 3),
+}))

benchmarks/pandas/bench_date_range_stats_na.py

@@ -0,0 +1,30 @@
+"""
+Benchmark: pd.date_range — generate date arrays with various frequencies.
+Outputs JSON: {"function": "date_range_stats_na", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+"""
+import json
+import time
+import pandas as pd
+
+WARMUP = 5
+ITERATIONS = 100
+
+start_ = "2020-01-01"
+end_ = "2022-12-31"
+
+for _ in range(WARMUP):
+    pd.date_range(start=start_, end=end_, freq="D")
+    pd.date_range(start=start_, periods=365, freq="D")
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    pd.date_range(start=start_, end=end_, freq="D")
+    pd.date_range(start=start_, periods=365, freq="D")
+total = (time.perf_counter() - start) * 1000
+
+print(json.dumps({
+    "function": "date_range_stats_na",
+    "mean_ms": total / ITERATIONS,
+    "iterations": ITERATIONS,
+    "total_ms": total,
+}))

benchmarks/pandas/bench_date_utils_na.py

@@ -0,0 +1,40 @@
+"""
+Benchmark: date parsing utilities — equivalent to advanceDate / parseFreq / toDateInput.
+Outputs JSON: {"function": "date_utils_na", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+"""
+import json
+import time
+import pandas as pd
+from datetime import datetime
+
+WARMUP = 5
+ITERATIONS = 200
+
+d = pd.Timestamp("2023-06-15")
+
+for _ in range(WARMUP):
+    pd.tseries.frequencies.to_offset("D")
+    pd.tseries.frequencies.to_offset("MS")
+    d + pd.tseries.frequencies.to_offset("D")
+    d + pd.tseries.frequencies.to_offset("MS")
+    d + pd.tseries.frequencies.to_offset("QS")
+    pd.Timestamp("2023-06-15")
+    pd.Timestamp(1686787200000, unit="ms")
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    pd.tseries.frequencies.to_offset("D")
+    pd.tseries.frequencies.to_offset("MS")
+    d + pd.tseries.frequencies.to_offset("D")
+    d + pd.tseries.frequencies.to_offset("MS")
+    d + pd.tseries.frequencies.to_offset("QS")
+    pd.Timestamp("2023-06-15")
+    pd.Timestamp(1686787200000, unit="ms")
+total = (time.perf_counter() - start) * 1000
+
+print(json.dumps({
+    "function": "date_utils_na",
+    "mean_ms": total / ITERATIONS,
+    "iterations": ITERATIONS,
+    "total_ms": total,
+}))

benchmarks/pandas/bench_diff_shift_df_na.py

@@ -0,0 +1,35 @@
+"""
+Benchmark: DataFrame.diff() / shift() — diff and shift on 10k-row DataFrame.
+Outputs JSON: {"function": "diff_shift_df_na", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+"""
+import json
+import time
+import numpy as np
+import pandas as pd
+
+ROWS = 10_000
+WARMUP = 5
+ITERATIONS = 50
+
+df = pd.DataFrame({
+    "a": np.arange(ROWS) * 2.0,
+    "b": np.arange(ROWS) * 3.0,
+    "c": np.arange(ROWS) * 0.5,
+})
+
+for _ in range(WARMUP):
+    df.diff(periods=1)
+    df.shift(periods=2)
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    df.diff(periods=1)
+    df.shift(periods=2)
+total = (time.perf_counter() - start) * 1000
+
+print(json.dumps({
+    "function": "diff_shift_df_na",
+    "mean_ms": total / ITERATIONS,
+    "iterations": ITERATIONS,
+    "total_ms": total,
+}))

benchmarks/pandas/bench_ffill_bfill_df_na.py

@@ -0,0 +1,36 @@
+"""
+Benchmark: DataFrame.ffill() / bfill() — forward/backward fill on 10k-row DataFrame.
+Outputs JSON: {"function": "ffill_bfill_df_na", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+"""
+import json
+import time
+import numpy as np
+import pandas as pd
+
+ROWS = 10_000
+WARMUP = 5
+ITERATIONS = 50
+
+data = {}
+for col, offset in zip("abcde", range(5)):
+    arr = np.arange(ROWS, dtype=float) + offset
+    arr[::10] = np.nan
+    data[col] = arr
+df = pd.DataFrame(data)
+
+for _ in range(WARMUP):
+    df.ffill()
+    df.bfill()
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    df.ffill()
+    df.bfill()
+total = (time.perf_counter() - start) * 1000
+
+print(json.dumps({
+    "function": "ffill_bfill_df_na",
+    "mean_ms": total / ITERATIONS,
+    "iterations": ITERATIONS,
+    "total_ms": total,
+}))

benchmarks/pandas/bench_ffill_bfill_series_na.py

@@ -0,0 +1,33 @@
+"""
+Benchmark: Series.ffill() / bfill() — forward/backward fill on 100k-element Series.
+Outputs JSON: {"function": "ffill_bfill_series_na", "mean_ms": ..., "iterations": ..., "total_ms": ...}
+"""
+import json
+import time
+import numpy as np
+import pandas as pd
+
+SIZE = 100_000
+WARMUP = 5
+ITERATIONS = 50
+
+data = np.arange(SIZE, dtype=float) * 1.5
+data[::10] = np.nan
+s = pd.Series(data)
+
+for _ in range(WARMUP):
+    s.ffill()
+    s.bfill()
+
+start = time.perf_counter()
+for _ in range(ITERATIONS):
+    s.ffill()
+    s.bfill()
+total = (time.perf_counter() - start) * 1000
+
+print(json.dumps({
+    "function": "ffill_bfill_series_na",
+    "mean_ms": total / ITERATIONS,
+    "iterations": ITERATIONS,
+    "total_ms": total,
+}))