Skip to content

ENH Improve performance for expected mutual information #24794

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 2 commits into from
Closed

ENH Improve performance for expected mutual information #24794

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
827044c
optimize calculating start values
Kshitij68 Nov 7, 2022
39dd0bf
Add benchmarks
Kshitij68 Nov 7, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
53 changes: 53 additions & 0 deletions benchmarks/bench_adjusted_mutual_info_score.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,53 @@
from collections import defaultdict
from itertools import product
from time import time

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

from sklearn.metrics import adjusted_mutual_info_score

repeat = 10
n_samples = [1_000, 10_000, 100_000, 1_000_000]
n_labels = [10, 100, 1_000]

rng = np.random.default_rng(0)

result = defaultdict(list)
for ns, nl in product(n_samples, n_labels):
local_result = []
for i in range(repeat):
print(f"Repetition {i+1} for n_samples={ns} and n_labels={nl}")
x = rng.integers(low=0, high=nl, size=ns)
y = rng.integers(low=0, high=nl, size=ns)

start = time()
adjusted_mutual_info_score(x, y)
end = time()
local_result.append(end - start)

result["n_samples"].append(ns)
result["n_labels"].append(nl)
result["mean_time"].append(np.mean(local_result))

result = pd.DataFrame(result)
plt.figure("Adjusted Mutual Info Score Benchmarks against number of Labels")
for n_sample in n_samples:
samples = result[result["n_samples"] == n_sample]
plt.plot(
samples["n_labels"], samples["mean_time"], label=f"{str(n_sample)} samples"
)
plt.xlabel("n_labels")
plt.ylabel("Time (s)")
plt.legend()

plt.figure("Adjusted Mutual Info Score Benchmarks against number of Samples")
for n_label in n_labels:
labels = result[result["n_labels"] == n_label]
plt.plot(labels["n_samples"], labels["mean_time"], label=f"{str(n_label)} labels")
plt.xlabel("n_samples")
plt.ylabel("Time (s)")
plt.legend()

plt.show()
3 changes: 2 additions & 1 deletion sklearn/metrics/cluster/_expected_mutual_info_fast.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,7 +50,8 @@ def expected_mutual_information(contingency, int n_samples):
gln_N = gammaln(N + 1)
gln_nij = gammaln(nijs + 1)
# start and end values for nij terms for each summation.
start = np.array([[v - N + w for w in b] for v in a], dtype='int')
start = np.array(np.meshgrid(a, b), dtype='int').T
start = np.array([start[i].sum(axis=1) - N for i in range(len(start))])
start = np.maximum(start, 1)
end = np.minimum(np.resize(a, (C, R)).T, np.resize(b, (R, C))) + 1
# emi itself is a summation over the various values.
Expand Down