def run_svm_model_factory():
##### YOUR CODE HERE
return rel_ext.experiment(splits,
model_factory=lambda: SVC(kernel='linear'),
train_split='train',
test_split='dev',
featurizers=featurizers)
def test_experiment(featurizer, vectorize, corpus, kb):
dataset = rel_ext.Dataset(corpus, kb)
splits = dataset.build_splits(
split_names=['tiny_train', 'tiny_dev', 'rest'],
split_fracs=[0.05, 0.05, 0.90],
seed=1)
results = rel_ext.experiment(splits,
train_split='tiny_train',
test_split='tiny_dev',
featurizers=[featurizer],
vectorize=vectorize,
verbose=False)
def run_svm_model_factory():
from sklearn.svm import SVC
##### YOUR CODE HERE
model_factory = lambda: SVC(kernel='linear')
svc_results = rel_ext.experiment(splits,
train_split='train',
test_split='dev',
featurizers=featurizers,
model_factory=model_factory,
verbose=True)
return svc_results
def run_svm_model_factory():
##### YOUR CODE HERE
from sklearn.svm import SVC
glove_results = rel_ext.experiment(
splits,
train_split='train',
test_split='dev',
model_factory=(lambda: SVC(kernel='linear', max_iter=2)),
featurizers=[glove_middle_featurizer],
vectorize=False, # Crucial for this featurizer!
verbose=True)
return glove_results
# In[10]:
featurizers = [simple_bag_of_words_featurizer]
# In[11]:
model_factory = lambda: LogisticRegression(fit_intercept=True,
solver='liblinear')
# In[12]:
baseline_results = rel_ext.experiment(splits,
train_split='train',
test_split='dev',
featurizers=featurizers,
model_factory=model_factory,
verbose=True)
# Studying model weights might yield insights:
# In[13]:
rel_ext.examine_model_weights(baseline_results)
# ### Distributed representations
#
# This simple baseline sums the GloVe vector representations for all of the words in the "middle" span and feeds those representations into the standard `LogisticRegression`-based `model_factory`. The crucial parameter that enables this is `vectorize=False`. This essentially says to `rel_ext.experiment` that your featurizer or your model will do the work of turning examples into vectors; in that case, `rel_ext.experiment` just organizes these representations by relation type.
# In[14]:
# In[11]:
featurizers = [simple_bag_of_words_featurizer]
# In[12]:
model_factory = lambda: LogisticRegression(fit_intercept=True,
solver='liblinear')
# In[13]:
baseline_results = rel_ext.experiment(splits,
train_split='train',
test_split='dev',
featurizers=featurizers,
model_factory=model_factory,
verbose=True)
# Studying model weights might yield insights:
# In[14]:
rel_ext.examine_model_weights(baseline_results)
# ### Distributed representations
#
# This simple baseline sums the GloVe vector representations for all of the words in the "middle" span and feeds those representations into the standard `LogisticRegression`-based `model_factory`. The crucial parameter that enables this is `vectorize=False`. This essentially says to `rel_ext.experiment` that your featurizer or your model will do the work of turning examples into vectors; in that case, `rel_ext.experiment` just organizes these representations by relation type.
# In[15]: