Linear make prediction #256
Conversation
Gordon119
requested review from
cjlin1,
sian-chen,
Eleven1Liu,
henryyang42 and
JamesLYC88
as code owners
libmultilabel/linear/linear.py
Outdated
| top_k_ind = np.argpartition(x, -top_k)[:, -top_k:] | ||
| pred_result = np.zeros(x.shape) | ||
| np.put_along_axis(pred_result, top_k_ind, 1, -1) | ||
| pred_result[pred_result != 1] = 0 |
There was a problem hiding this comment.
why line 588 as pred_result is initialized as the zero matrix?
There was a problem hiding this comment.
inverse_transform has to take predictions in binary labels, so I first set pred_result to zero matrix and set the top k labels to 1. I realized that line 558 is redundant and removed it.
libmultilabel/linear/linear.py
Outdated
| top_k_ind = np.argpartition(preds, -top_k)[:, -top_k:] | ||
| pred_result = np.zeros(preds.shape) | ||
| np.put_along_axis(pred_result, top_k_ind, 1, -1) | ||
| return preprocessor.binarizer.inverse_transform(pred_result) |
There was a problem hiding this comment.
where do we have this binarizer.inverse_transform defined??
There was a problem hiding this comment.
Since we’re using sklearn’s MultiLabelBinarizer, I used this:
https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.MultiLabelBinarizer.html
Co-authored-by: Jie-Jyun Liu <jiejyunliu@gmail.com>
Gordon119
force-pushed
the
Linear-make-prediction
branch
from
c59d9d5
to
fc74eb0
Compare
…iLabel into Linear-make-prediction
|
@Sinacam review |
libmultilabel/linear/linear.py
Outdated
| Returns: | ||
| list of lists which contain top k labels. | ||
| """ | ||
| top_k_ind = np.argpartition(preds, -top_k)[:, -top_k:] |
There was a problem hiding this comment.
top_k_ind is sorted ascending this way. top_k_ind = np.argpartition(preds, -top_k)[:, :top_k:-1] sorts descending.
|
LGTM |
What does this PR do?
as title.
Test CLI & API (
bash tests/autotest.sh)Test quickstart & API (
bash tests/docs/test_examples.sh)Check API Document