Skip to content

DOC Change print format of Approximate nearest neighbors in TSNE example #25569

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

Merged
merged 15 commits into from
Feb 9, 2023
Merged

DOC Change print format of Approximate nearest neighbors in TSNE example #25569

Changes from all commits
Commits
Show all changes
15 commits
Select commit Hold shift + click to select a range
40f551d
DOC Add pynndescent to Approximate nearest neighbors in TSNE example
Jan 24, 2023
5e83ad4
Add ImportError message if pynndescent is missing
Jan 24, 2023
4488c33
Remove AnnoyTransformer from benchmark
Jan 24, 2023
62c0932
Remove test to assert almost exact results
Jan 25, 2023
7397aed
Implement joblib logic and use as many threads as CPUs by default
Jan 25, 2023
ca420a6
Implement notebook style and tutorialization
Jan 25, 2023
2a3bfc2
Update examples/neighbors/approximate_nearest_neighbors.py
ArturoAmorQ Jan 26, 2023
19c6a5e
Fix format
Jan 26, 2023
f82a752
Update examples/neighbors/approximate_nearest_neighbors.py
ArturoAmorQ Jan 27, 2023
16236d7
Change double run of KNeighbors and NMSlib transformers to single run
Jan 27, 2023
afe8249
Fix wording
Jan 27, 2023
cb0049f
Fix logical progression
Jan 27, 2023
fdec3ec
Merge branch 'main' into pynndescent
ogrisel Feb 8, 2023
f66a2b5
DOC Change print format of Approximate nearest neighbors in TSNE example
Feb 8, 2023
cd79076
Fix conflicts
Feb 8, 2023
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
65 changes: 30 additions & 35 deletions examples/neighbors/approximate_nearest_neighbors.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,54 +156,50 @@ def load_mnist(n_samples):

for dataset_name, (X, y) in datasets:

msg = "Benchmarking on %s:" % dataset_name
print("\n%s\n%s" % (msg, "-" * len(msg)))
msg = f"Benchmarking on {dataset_name}:"
print(f"\n{msg}\n" + str("-" * len(msg)))

for transformer_name, transformer in transformers:
longest = np.max([len(name) for name, model in transformers])
whitespaces = " " * (longest - len(transformer_name))
start = time.time()
transformer.fit(X)
fit_duration = time.time() - start
print("%s: %s%.3f sec (fit)" % (transformer_name, whitespaces, fit_duration))
print(f"{transformer_name:<{longest}} {fit_duration:.3f} sec (fit)")
start = time.time()
Xt = transformer.transform(X)
transform_duration = time.time() - start
print(
"%s: %s%.3f sec (transform)"
% (transformer_name, whitespaces, transform_duration)
)
print(f"{transformer_name:<{longest}} {transform_duration:.3f} sec (transform)")
if transformer_name == "PyNNDescentTransformer":
start = time.time()
Xt = transformer.transform(X)
transform_duration = time.time() - start
print(
"%s: %s%.3f sec (transform)"
% (transformer_name, whitespaces, transform_duration)
f"{transformer_name:<{longest}} {transform_duration:.3f} sec"
" (transform)"
)

# %%
# Sample output::
#
# Benchmarking on MNIST_10000:
# ----------------------------
# KNeighborsTransformer: 0.007 sec (fit)
# KNeighborsTransformer: 1.139 sec (transform)
# NMSlibTransformer: 0.208 sec (fit)
# NMSlibTransformer: 0.315 sec (transform)
# PyNNDescentTransformer: 4.823 sec (fit)
# PyNNDescentTransformer: 4.884 sec (transform)
# PyNNDescentTransformer: 0.744 sec (transform)
# KNeighborsTransformer 0.007 sec (fit)
# KNeighborsTransformer 1.139 sec (transform)
# NMSlibTransformer 0.208 sec (fit)
# NMSlibTransformer 0.315 sec (transform)
# PyNNDescentTransformer 4.823 sec (fit)
# PyNNDescentTransformer 4.884 sec (transform)
# PyNNDescentTransformer 0.744 sec (transform)
#
# Benchmarking on MNIST_20000:
# ----------------------------
# KNeighborsTransformer: 0.011 sec (fit)
# KNeighborsTransformer: 5.769 sec (transform)
# NMSlibTransformer: 0.733 sec (fit)
# NMSlibTransformer: 1.077 sec (transform)
# PyNNDescentTransformer: 14.448 sec (fit)
# PyNNDescentTransformer: 7.103 sec (transform)
# PyNNDescentTransformer: 1.759 sec (transform)
# KNeighborsTransformer 0.011 sec (fit)
# KNeighborsTransformer 5.769 sec (transform)
# NMSlibTransformer 0.733 sec (fit)
# NMSlibTransformer 1.077 sec (transform)
# PyNNDescentTransformer 14.448 sec (fit)
# PyNNDescentTransformer 7.103 sec (transform)
# PyNNDescentTransformer 1.759 sec (transform)
#
# Notice that the `PyNNDescentTransformer` takes more time during the first
# `fit` and the first `transform` due to the overhead of the numba just in time
Expand Down Expand Up @@ -248,18 +244,17 @@ def load_mnist(n_samples):

for dataset_name, (X, y) in datasets:

msg = "Benchmarking on %s:" % dataset_name
print("\n%s\n%s" % (msg, "-" * len(msg)))
msg = f"Benchmarking on {dataset_name}:"
print(f"\n{msg}\n" + str("-" * len(msg)))

for transformer_name, transformer in transformers:
longest = np.max([len(name) for name, model in transformers])
whitespaces = " " * (longest - len(transformer_name))
start = time.time()
Xt = transformer.fit_transform(X)
transform_duration = time.time() - start
print(
"%s: %s%.3f sec (fit_transform)"
% (transformer_name, whitespaces, transform_duration)
f"{transformer_name:<{longest}} {transform_duration:.3f} sec"
" (fit_transform)"
)

# plot TSNE embedding which should be very similar across methods
Expand All @@ -284,15 +279,15 @@ def load_mnist(n_samples):
#
# Benchmarking on MNIST_10000:
# ----------------------------
# TSNE with internal NearestNeighbors: 24.828 sec (fit_transform)
# TSNE with KNeighborsTransformer: 20.111 sec (fit_transform)
# TSNE with NMSlibTransformer: 21.757 sec (fit_transform)
# TSNE with internal NearestNeighbors 24.828 sec (fit_transform)
# TSNE with KNeighborsTransformer 20.111 sec (fit_transform)
# TSNE with NMSlibTransformer 21.757 sec (fit_transform)
#
# Benchmarking on MNIST_20000:
# ----------------------------
# TSNE with internal NearestNeighbors: 51.955 sec (fit_transform)
# TSNE with KNeighborsTransformer: 50.994 sec (fit_transform)
# TSNE with NMSlibTransformer: 43.536 sec (fit_transform)
# TSNE with internal NearestNeighbors 51.955 sec (fit_transform)
# TSNE with KNeighborsTransformer 50.994 sec (fit_transform)
# TSNE with NMSlibTransformer 43.536 sec (fit_transform)
#
# We can observe that the default :class:`~sklearn.manifold.TSNE` estimator with
# its internal :class:`~sklearn.neighbors.NearestNeighbors` implementation is
Expand Down