RandomBaseline does not return an array of shape [n,2] when running evaluate_performance with use_default_protocol=True.
Actual Behavior
RandomBaseline returns a 1-d array of length n when running evaluate_performance with use_default_protocol=True.
Expected Behavior
RandomBaseline should, like other models, return a 2-d array of shape [n,2] when running evaluate_performance with use_default_protocol=True.
Steps to Reproduce
import numpy as np
from ampligraph.datasets import load_wn18rr
from ampligraph.latent_features import RandomBaseline, DistMult
from ampligraph.evaluation import evaluate_performance
X = load_wn18rr()
model = RandomBaseline()
model.fit(X['train'])
print(evaluate_performance(X['test'][:5], model).shape) # Returns (5,)
model = DistMult(epochs=0)
model.fit(X['train'])
print(evaluate_performance(X['test'][:5], model).shape) # Returns (5, 2)
Source
The get_ranks function of RandomBaseline is different from that of the other models, it returns one rank for each test triple regardless of evaluation protocol.
tabacof
commented
5 years ago
Description
RandomBaseline does not return an array of shape [n,2] when running
evaluate_performancewithuse_default_protocol=True.Actual Behavior
RandomBaseline returns a 1-d array of length n when running
evaluate_performancewithuse_default_protocol=True.Expected Behavior
RandomBaseline should, like other models, return a 2-d array of shape [n,2] when running
evaluate_performancewithuse_default_protocol=True.Steps to Reproduce
Source
The
get_ranksfunction of RandomBaseline is different from that of the other models, it returns one rank for each test triple regardless of evaluation protocol.