Created
July 4, 2023 19:14
-
-
Save Micky774/9daede3d638ebbdbb34bc26f884f2748 to your computer and use it in GitHub Desktop.
Benchmarks for memview_to_ptr
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
# %% | |
results_path = 'local_artifacts/benchmarks/dist' | |
results_path += '/' if results_path[-1] != '/' else '' | |
# %% | |
from sklearn.metrics._pairwise_distances_reduction import ArgKmin | |
from scipy.sparse import csr_matrix | |
from statistics import mean, stdev | |
from time import perf_counter | |
from functools import partial | |
from itertools import product | |
from pathlib import Path | |
import numpy as np | |
import csv | |
Path(results_path).mkdir(parents=True, exist_ok=True) | |
branch = "PR" | |
METRIC = 'manhattan' | |
def _generate_PWD_data(n_samples_X, n_samples_Y, n_features, n_classes, n_outs=1, random_state=0): | |
rng = np.random.RandomState(random_state) | |
X = rng.randn(n_samples_X, n_features) | |
Y = rng.randn(n_samples_Y, n_features) | |
y_shape = (n_samples_X,) if n_outs == 1 else (n_samples_X, n_outs) | |
y = rng.randint(n_classes, size=y_shape) | |
return X, Y, y | |
N_FEATURES = 10 | |
benchmark_config = [ | |
( | |
partial(_generate_PWD_data, n_features=N_FEATURES, n_classes=2), | |
product( | |
[2_000, 10_000], | |
[2_000, 10_000], | |
["manhattan", "chebyshev", "minkowski"], | |
), | |
), | |
] | |
N_REPEATS = 10 | |
with open(f'{results_path}{branch}.csv', 'w', newline='') as csvfile: | |
writer = csv.DictWriter( | |
csvfile, | |
fieldnames=[ | |
"n_samples", | |
"n_samples_test", | |
"metric", | |
"n_repeat", | |
"duration", | |
], | |
) | |
writer.writeheader() | |
for make_data, items in benchmark_config: | |
for n_samples, n_samples_test, metric in items: | |
time_results = [] | |
for n_repeat in range(N_REPEATS): | |
X, Y, y = make_data(n_samples_X=n_samples, n_samples_Y=n_samples_test, random_state=n_repeat) | |
X = csr_matrix(X) | |
Y = csr_matrix(Y) | |
start = perf_counter() | |
ArgKmin.compute(X, Y, 100, metric=metric) | |
duration = perf_counter() - start | |
time_results.append(duration) | |
writer.writerow( | |
{ | |
"n_samples": n_samples, | |
"n_samples_test": n_samples_test, | |
"metric": metric, | |
"n_repeat": n_repeat, | |
"duration": duration, | |
} | |
) | |
results_mean, results_stdev = mean(time_results), stdev(time_results) | |
print( | |
f" {n_samples=}, {n_samples_test=}, {metric=} |" | |
f" {results_mean:.3f} +/- {results_stdev:.3f}" | |
) | |
# %% | |
import matplotlib.pyplot as plt | |
import pandas as pd | |
import seaborn as sns | |
plt.rc('font', size=12) | |
GRID_LAYOUT = (3, 4) | |
FIGURE_SIZE = (14, 12) | |
def _violen_perf(subset, ax, **kwargs): | |
sns.violinplot(data=subset, y="duration", x="branch", ax=ax) | |
def _rel_perf(subset, ax, default, **kwargs): | |
base = subset.groupby("branch")["duration"].mean()[default] | |
subset["duration"] = base / subset["duration"] | |
y_title = "speedup vs main" | |
subset = subset.rename(columns={"duration":y_title}) | |
graph = sns.barplot(subset, x="branch", y=y_title, errorbar=None, ax=ax) | |
graph.axhline(1, color="black") | |
def _abs_perf(subset, ax, **kwargs): | |
base = subset.groupby("branch")["duration"].mean().min() | |
subset = subset.rename(columns={"duration":"time (sec)"}) | |
graph = sns.barplot(subset, x="branch", y="time (sec)", errorbar=None, ax=ax) | |
graph.axhline(base, color="black") | |
def generic_chart(func, grouped, percentile_trim, branches, group_by_attrs, title, **kwargs): | |
grouped_list = list(grouped) | |
fig, axis = plt.subplots(*GRID_LAYOUT, figsize=FIGURE_SIZE, constrained_layout=True) | |
fig.patch.set_facecolor('white') | |
for (grouped_attrs, subset), ax in zip(grouped_list, axis.reshape(-1)): | |
# Optionally trim outlier data | |
if percentile_trim < 1: | |
for branch in branches: | |
_subset = subset[subset["branch"]==branch] | |
cut = _subset.duration < _subset.duration.quantile(percentile_trim) | |
subset[subset["branch"]==branch] = _subset[cut] | |
func(subset, ax, **kwargs) | |
ax.set_title("\n".join( [f"{k}={v}" for k, v in zip(group_by_attrs, grouped_attrs)])) | |
ax.set_xlabel("") | |
for ax in axis[:, 1:].ravel(): | |
ax.set_ylabel("") | |
fig.suptitle(title, fontsize=18) | |
plt.show() | |
# %% | |
_branches = ("main", "PR") | |
percentile_trim = .9 | |
branches = {br:pd.read_csv(f'{results_path}{br}.csv') for br in _branches} | |
df = pd.concat([branches[br].assign(branch=br) for br in _branches]) | |
group_by_attrs = ["metric", "n_samples_test", "n_samples"] | |
grouped = list(df.groupby(group_by_attrs)) | |
grouped_cp = list(df.groupby(group_by_attrs)) | |
default_args = dict(percentile_trim=percentile_trim, branches=_branches, group_by_attrs=group_by_attrs, default=_branches[0]) | |
# generic_chart(_violen_perf, df.groupby(group_by_attrs), **default_args) | |
rel_title = f"ArgKmin.compute(X_csr, Y_csr, 100) relative performance (higher is better)\n" | |
abs_title = f"ArgKmin.compute(X_csr, Y_csr, 100) time spent (lower is better)\n" | |
generic_chart(_rel_perf, df.groupby(group_by_attrs), title=rel_title, **default_args) | |
generic_chart(_abs_perf, df.groupby(group_by_attrs), title=abs_title, **default_args) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment