def corpus():
rel_ext_data_home = os.path.join('data', 'rel_ext_data')
src_filename = os.path.join(
os.path.dirname(os.path.realpath(__file__)),
'..',
rel_ext_data_home, 'corpus.tsv.gz')
return rel_ext.Corpus(src_filename)
import numpy as np
import os
import rel_ext
from sklearn.linear_model import LogisticRegression
import utils
# As usual, we unite our corpus and KB into a dataset, and create some splits for experimentation:
# In[3]:
rel_ext_data_home = os.path.join('data', 'rel_ext_data')
# In[4]:
corpus = rel_ext.Corpus(os.path.join(rel_ext_data_home, 'corpus.tsv.gz'))
# In[5]:
kb = rel_ext.KB(os.path.join(rel_ext_data_home, 'kb.tsv.gz'))
# In[6]:
dataset = rel_ext.Dataset(corpus, kb)
# You are not wedded to this set-up for splits. The bake-off will be conducted on a previously unseen test-set, so all of the data in `dataset` is fair game:
# In[7]:
splits = dataset.build_splits(split_names=['tiny', 'train', 'dev'],
split_fracs=[0.01, 0.79, 0.20],