8000 ENH Improve `plot_semi_supervised_newsgroups.py` example by patel-zeel · Pull Request #21673 · scikit-learn/scikit-learn · GitHub
[go: up one dir, main page]
Skip to content

ENH Improve plot_semi_supervised_newsgroups.py example #21673

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 3 commits into from
Nov 23, 2021
Merged

ENH Improve plot_semi_supervised_newsgroups.py example #21673

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
38ec089
accelerate example
patel-zeel Nov 15, 2021
88811f3
Enable LabelSpreading
patel-zeel Nov 15, 2021
c22a379
fix linting, remove `import os`
patel-zeel Nov 15, 2021
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
19 changes: 13 additions & 6 deletions examples/semi_supervised/plot_semi_supervised_newsgroups.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,6 @@

"""

import os

import numpy as np

Expand All @@ -26,7 +25,17 @@
from sklearn.semi_supervised import LabelSpreading
from sklearn.metrics import f1_score

data = fetch_20newsgroups(subset="train", categories=None)
# Loading dataset containing first five categories
data = fetch_20newsgroups(
subset="train",
categories=[
"alt.atheism",
"comp.graphics",
"comp.os.ms-windows.misc",
"comp.sys.ibm.pc.hardware",
"comp.sys.mac.hardware",
],
)
print("%d documents" % len(data.filenames))
print("%d categories" % len(data.target_names))
print()
Expand Down Expand Up @@ -98,7 +107,5 @@ def eval_and_print_metrics(clf, X_train, y_train, X_test, y_test):
print("SelfTrainingClassifier on 20% of the training data (rest is unlabeled):")
eval_and_print_metrics(st_pipeline, X_train, y_train, X_test, y_test)

if "CI" not in os.environ:
# LabelSpreading takes too long to run in the online documentation
print("LabelSpreading on 20% of the data (rest is unlabeled):")
eval_and_print_metrics(ls_pipeline, X_train, y_train, X_test, y_test)
print("LabelSpreading on 20% of the data (rest is unlabeled):")
eval_and_print_metrics(ls_pipeline, X_train, y_train, X_test, y_test)
0