from zincbase import KB
from zincbase.utils.data_science import calc_auc_roc
kb = KB()
Xs = []
Ys = []
csvfile = csv.reader(open('./assets/countries_s3_test.csv', 'r'),
delimiter='\t')
for row in csvfile:
Xs.append([row[0], row[1]])
Ys.append(row[2])
kb.from_csv('./assets/countries_s3_train.csv', delimiter='\t')
kb.build_kg_model(cuda=True, embedding_size=1000, gamma=0.1)
kb.train_kg_model(steps=40000, batch_size=512, lr=0.000002, neg_to_pos=64)
y_true = []
sample = []
for ((head, relation), tail) in zip(Xs, Ys):
for candidate_region in [
'oceania', 'asia', 'europe', 'africa', 'americas'
]:
y_true.append(1 if candidate_region == tail else 0)
sample.append((kb._entity2id[head], kb._relation2id[relation],
kb._entity2id[candidate_region]))
sample = torch.LongTensor(sample).cuda()
with torch.no_grad():
y_score, _ = kb._kg_model(sample)
y_score = y_score.squeeze(1).cpu().numpy()
"""Test the combination of edge attributes and negative examples."""
import context
from zincbase import KB
kb = KB()
kb.seed(555)
kb.from_csv('./assets/countries_s1_train.csv', delimiter='\t')
# specifying both a ~ and a truthiness < 0 is probably unnecessary.
kb.store('~locatedin(canada, africa)', {'truthiness': -1.})
kb.build_kg_model(cuda=False,
embedding_size=100,
pred_attributes=['truthiness'])
kb.train_kg_model(steps=1000, batch_size=4, neg_ratio=0.01)
canada_in_africa = kb.estimate_triple_prob('canada', 'locatedin', 'africa')
canada_in_asia = kb.estimate_triple_prob('canada', 'locatedin', 'asia')
canada_in_america = kb.estimate_triple_prob('canada', 'locatedin',
'northern_america')
assert 2 * canada_in_africa < canada_in_asia
assert canada_in_america > 2 * canada_in_asia
clafrica_truthiness = kb.estimate_triple_prob_with_attrs(
'canada', 'locatedin', 'africa', 'truthiness')
clasia_truthiness = kb.estimate_triple_prob_with_attrs('canada', 'locatedin',
'asia', 'truthiness')
from zincbase import KB
kb = KB()
kb.seed(555)
kb.from_csv('./assets/countries_s1_train.csv', delimiter='\t')
rule_num = kb.store('~locatedin(canada, africa)')
b = list(kb.query('locatedin(canada, X)'))
assert len(b) == 1
assert b[0]['X'] == 'northern_america'
assert kb.delete_rule(rule_num)
kb.build_kg_model(cuda=False, embedding_size=100)
kb.train_kg_model(steps=500, batch_size=512, neg_ratio=0.01)
canada_in_africa_naive = kb.estimate_triple_prob('canada', 'locatedin',
'africa')
canada_in_asia_naive = kb.estimate_triple_prob('canada', 'locatedin', 'asia')
austria_neighbors_spain_naive = kb.estimate_triple_prob(
'austria', 'neighbor', 'spain')
austria_neighbors_france_naive = kb.estimate_triple_prob(
'austria', 'neighbor', 'france')
kb = KB()
kb.seed(555)
kb.from_csv('./assets/countries_s1_train.csv', delimiter='\t')
"""
from zincbase import KB
kb = KB()
kb.from_csv('./assets/countries_s1_train.csv', delimiter='\t')
print(list(kb.query('locatedin(X, northern_europe)')))
# prints [{'X': 'norway'}, {'X': 'iceland'}, {'X': 'faroe_islands'}, ...]
print(list(kb.query('neighbor(austria, X)')))
# prints [{'X': 'italy'}, {'X': 'czechia'}, {'X': 'slovenia'}, ...]
kb.build_kg_model(cuda=True, embedding_size=100)
kb.train_kg_model(steps=1000, batch_size=512) # takes < 1 minute
print(kb.estimate_triple_prob('mali', 'locatedin', 'africa'))
# prints a number close to 1
print(kb.get_most_likely('singapore', 'locatedin', '?', k=2))
# prints [{'prob': 0.9672, 'triple': ('singapore', 'locatedin', 'south_eastern_asia')}, ...]
print(kb.get_most_likely('austria', 'neighbor', '?', k=8))
# prints [{'prob': 0.9749, 'triple': ('austria', 'neighbor', 'liechtenstein')} ...]
kb.fit_knn()
print(kb.get_nearest_neighbors('uganda', k=4))
# # # # # # # # # # # # # # # # # # # # # # # #
kb.attr('tom', {'owns_a_raincoat': 0.0, 'doesnt_own_raincoat': 1.0})
kb.attr('todd', {'owns_a_raincoat': 0.0, 'doesnt_own_raincoat': 1.0})
kb.attr('oleg', {'owns_a_raincoat': 0.0, 'doesnt_own_raincoat': 1.0})
kb.attr('john', {'owns_a_raincoat': 0.0, 'doesnt_own_raincoat': 1.0})
kb.attr('akshay', {'owns_a_raincoat': 0.0, 'doesnt_own_raincoat': 1.0})
kb.attr('vedant', {'owns_a_raincoat': 0.0, 'doesnt_own_raincoat': 1.0})
kb.attr('other1', {'owns_a_raincoat': 1.0, 'doesnt_own_raincoat': 0.0})
kb.attr('other2', {'owns_a_raincoat': 1.0, 'doesnt_own_raincoat': 0.0})
kb.attr('other3', {'owns_a_raincoat': 1.0, 'doesnt_own_raincoat': 0.0})
kb.attr('other4', {'owns_a_raincoat': 1.0, 'doesnt_own_raincoat': 0.0})
kb.attr('other5', {'owns_a_raincoat': 1.0, 'doesnt_own_raincoat': 0.0})
kb.attr('other6', {'owns_a_raincoat': 1.0, 'doesnt_own_raincoat': 0.0})
kb.build_kg_model(cuda=False,
embedding_size=30,
node_attributes=['owns_a_raincoat', 'doesnt_own_raincoat'],
attr_loss_to_graph_loss=0.9)
# Ideally use bs=1 to overfit on this small dataset
# bs=2 at least checks that it works with > 1 bs
kb.train_kg_model(steps=12001, batch_size=2, neg_to_pos=4)
# # # # # # # # # # # # # # # # # # # # # # # #
# People from Seattle should be more likely to
# own an umbrella (attribute prediction test)
# # # # # # # # # # # # # # # # # # # # # # # #
x = kb._kg_model.run_embedding(kb.get_embedding('other1'), 'owns_a_raincoat')
y = kb._kg_model.run_embedding(kb.get_embedding('other1'),
'doesnt_own_raincoat')
assert round(x) == 1
assert round(y) == 0
x = kb._kg_model.run_embedding(kb.get_embedding('other2'), 'owns_a_raincoat')