Refefer
commented
6 years ago That the log likelihood. It's sorted in descending order of prediction, so the first label is the best.
On Thu, Aug 30, 2018, 2:53 AM mailong25 notifications@github.com wrote:
I tired to use python API: X = [Sparse or numpy arrays] y = [[1, 3]] # Currently requires list[list[int]]
trainer = Trainer(n_trees=32, n_jobs=-1)
trainer.fit(X, y)
trainer.save(path)
clf = Inferencer(path)
clf.predict(X, fmt='dict')
And the prediction result of an example look like this: [(5866, -0.40310976), (437, -0.67100734), (995, -0.8778681), (2642, -1.1181042), (5217, -1.1278155), (5967, -1.1540765), (7558, -1.3282802), (4391, -1.5430373), (4017, -1.624005), (5781, -1.9639409), (1347, -2.012597), (4063, -2.0736518)
What -0.40310976, -0.67100734, ..... mean ? And how can I select the most appropriate labels from this result?
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/Refefer/fastxml/issues/15, or mute the thread https://github.com/notifications/unsubscribe-auth/ABdKFa5BMADissJT5oiWvcGI4hAeti51ks5uV7YOgaJpZM4WTJlu .
I tired to use python API: X = [Sparse or numpy arrays] y = [[1, 3]] # Currently requires list[list[int]]
trainer = Trainer(n_trees=32, n_jobs=-1)
trainer.fit(X, y)
trainer.save(path)
clf = Inferencer(path)
clf.predict(X, fmt='dict')
And the prediction result of an example look like this: [(5866, -0.40310976), (437, -0.67100734), (995, -0.8778681), (2642, -1.1181042), (5217, -1.1278155), (5967, -1.1540765), (7558, -1.3282802), (4391, -1.5430373), (4017, -1.624005), (5781, -1.9639409), (1347, -2.012597), (4063, -2.0736518)
What -0.40310976, -0.67100734, ..... mean ? And how can I select the most appropriate labels from this result?