forked from pandas-dev/pandas
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
DOC: update query/eval figures on performance comparison (pandas-dev#…
…48368) Co-authored-by: Joris Van den Bossche <jorisvandenbossche@gmail.com>
- Loading branch information
Showing
7 changed files
with
132 additions
and
24 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,108 @@ | ||
from timeit import repeat as timeit | ||
|
||
import numpy as np | ||
import seaborn as sns | ||
|
||
from pandas import DataFrame | ||
|
||
setup_common = """from pandas import DataFrame | ||
from numpy.random import randn | ||
df = DataFrame(randn(%d, 3), columns=list('abc')) | ||
%s""" | ||
|
||
setup_with = "s = 'a + b * (c ** 2 + b ** 2 - a) / (a * c) ** 3'" | ||
|
||
|
||
def bench_with(n, times=10, repeat=3, engine="numexpr"): | ||
return ( | ||
np.array( | ||
timeit( | ||
"df.eval(s, engine=%r)" % engine, | ||
setup=setup_common % (n, setup_with), | ||
repeat=repeat, | ||
number=times, | ||
) | ||
) | ||
/ times | ||
) | ||
|
||
|
||
setup_subset = "s = 'a <= b <= c ** 2 + b ** 2 - a and b > c'" | ||
|
||
|
||
def bench_subset(n, times=20, repeat=3, engine="numexpr"): | ||
return ( | ||
np.array( | ||
timeit( | ||
"df.query(s, engine=%r)" % engine, | ||
setup=setup_common % (n, setup_subset), | ||
repeat=repeat, | ||
number=times, | ||
) | ||
) | ||
/ times | ||
) | ||
|
||
|
||
def bench(mn=3, mx=7, num=100, engines=("python", "numexpr"), verbose=False): | ||
r = np.logspace(mn, mx, num=num).round().astype(int) | ||
|
||
ev = DataFrame(np.empty((num, len(engines))), columns=engines) | ||
qu = ev.copy(deep=True) | ||
|
||
ev["size"] = qu["size"] = r | ||
|
||
for engine in engines: | ||
for i, n in enumerate(r): | ||
if verbose & (i % 10 == 0): | ||
print("engine: %r, i == %d" % (engine, i)) | ||
ev_times = bench_with(n, times=1, repeat=1, engine=engine) | ||
ev.loc[i, engine] = np.mean(ev_times) | ||
qu_times = bench_subset(n, times=1, repeat=1, engine=engine) | ||
qu.loc[i, engine] = np.mean(qu_times) | ||
|
||
return ev, qu | ||
|
||
|
||
def plot_perf(df, engines, title, filename=None): | ||
from matplotlib.pyplot import figure | ||
|
||
sns.set() | ||
sns.set_palette("Set2") | ||
|
||
fig = figure(figsize=(4, 3), dpi=120) | ||
ax = fig.add_subplot(111) | ||
|
||
for engine in engines: | ||
ax.loglog(df["size"], df[engine], label=engine, lw=2) | ||
|
||
ax.set_xlabel("Number of Rows") | ||
ax.set_ylabel("Time (s)") | ||
ax.set_title(title) | ||
ax.legend(loc="best") | ||
ax.tick_params(top=False, right=False) | ||
|
||
fig.tight_layout() | ||
|
||
if filename is not None: | ||
fig.savefig(filename) | ||
|
||
|
||
if __name__ == "__main__": | ||
import os | ||
|
||
pandas_dir = os.path.dirname( | ||
os.path.dirname(os.path.abspath(os.path.dirname(__file__))) | ||
) | ||
static_path = os.path.join(pandas_dir, "doc", "source", "_static") | ||
|
||
join = lambda p: os.path.join(static_path, p) | ||
|
||
fn = join("eval-query-perf-data.h5") | ||
|
||
engines = "python", "numexpr" | ||
|
||
ev, qu = bench(verbose=True) # only this one | ||
|
||
plot_perf(ev, engines, "DataFrame.eval()", filename=join("eval-perf.png")) | ||
plot_perf(qu, engines, "DataFrame.query()", filename=join("query-perf.png")) |
Binary file not shown.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file not shown.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters