# In[7]:
wordentail_data['edge_disjoint']['dev'][:5]
# Let's test to make sure no edges are shared between `train` and `dev`:
# In[8]:
nli.get_edge_overlap_size(wordentail_data, 'edge_disjoint')
# As we expect, a *lot* of vocabulary items are shared between `train` and `dev`:
# In[9]:
nli.get_vocab_overlap_size(wordentail_data, 'edge_disjoint')
# This is a large percentage of the entire vocab:
# In[10]:
len(wordentail_data['vocab'])
# Here's the distribution of labels in the `train` set. It's highly imbalanced, which will pose a challenge for learning. (I'll go ahead and reveal that the `dev` set is similarly distributed.)
# In[11]:
def label_distribution(split):
return pd.DataFrame(wordentail_data[split]['train'])[1].value_counts()
def test_vocab_overlap_size(wordentail_data, split, count):
result = nli.get_vocab_overlap_size(wordentail_data, split)
assert result == count
def test_vocab_overlap_size(wordentail_data):
result = nli.get_vocab_overlap_size(wordentail_data)
assert result == 0
