def fit_shallow_neural_classifier_with_crossvalidation(X, y):
basemod = TorchShallowNeuralClassifier(max_iter=50)
cv = 3
param_grid = {'hidden_dim': [25, 50, 100]}
best_mod = utils.fit_classifier_with_crossvalidation(
X, y, basemod, cv, param_grid)
return best_mod
def fit_softmax_with_crossvalidation(X, y):
"""A MaxEnt model of dataset with hyperparameter cross-validation.
Parameters
----------
X : 2d np.array
The matrix of features, one example per row.
y : list
The list of labels for rows in `X`.
Returns
-------
sklearn.linear_model.LogisticRegression
A trained model instance, the best model found.
"""
basemod = LogisticRegression(fit_intercept=True,
solver='liblinear',
multi_class='auto')
cv = 3
param_grid = {'C': [0.4, 0.6, 0.8, 1.0], 'penalty': ['l1', 'l2']}
best_mod = utils.fit_classifier_with_crossvalidation(
X, y, basemod, cv, param_grid)
return best_mod
def fit_basic_sgd_classifier_with_crossvalidation(X, y):
basemod = BasicSGDClassifier()
cv = 5
param_grid = {'eta': [0.01, 0.1, 1.0], 'max_iter': [10]}
best_mod = utils.fit_classifier_with_crossvalidation(
X, y, basemod, cv, param_grid)
return best_mod
def test_color_describer_cross_validation(color_describer_dataset):
color_seqs, word_seqs, vocab = color_describer_dataset
mod = torch_color_describer.ContextualColorDescriber(vocab,
embed_dim=10,
hidden_dim=10,
max_iter=100,
embedding=None)
best_mod = utils.fit_classifier_with_crossvalidation(
color_seqs,
word_seqs,
mod,
cv=2,
scoring=None,
param_grid={'hidden_dim': [10, 20]})
def fit_softmax_with_crossvalidation(X, y):
"""A MaxEnt model of dataset with hyperparameter
cross-validation. Some notes:
* 'fit_intercept': whether to include the class bias feature.
* 'C': weight for the regularization term (smaller is more regularized).
* 'penalty': type of regularization -- roughly, 'l1' ecourages small
sparse models, and 'l2' encourages the weights to conform to a
gaussian prior distribution.
Other arguments can be cross-validated; see
http://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html
Parameters
----------
X : 2d np.array
The matrix of features, one example per row.
y : list
The list of labels for rows in `X`.
Returns
-------
sklearn.linear_model.LogisticRegression
A trained model instance, the best model found.
"""
basemod = LogisticRegression(fit_intercept=True,
solver='liblinear',
multi_class='auto')
cv = 5
param_grid = {
'fit_intercept': [True, False],
'C': [0.4, 0.6, 0.8, 1.0, 2.0, 3.0],
'penalty': ['l1', 'l2']
}
best_mod = utils.fit_classifier_with_crossvalidation(
X, y, basemod, cv, param_grid)
return best_mod
def test_rnn_classifier_cross_validation(model_class, X_sequence):
train, test, vocab = X_sequence
mod = model_class(vocab, max_iter=2)
X, y = zip(*train)
best_mod = utils.fit_classifier_with_crossvalidation(
X, y, mod, cv=2, param_grid={'hidden_dim': [10, 20]})
# In[40]:
for timestep in toy_proba[0]:
print(dict(zip(toy_vocab, timestep)))
# ### Cross-validation
# You can use `utils.fit_classifier_with_crossvalidation` to cross-validate these models. Just be sure to set `scoring=None` so that the sklearn model selection methods use the `score` method of `ContextualColorDescriber`, which is an alias for `listener_accuracy`:
# In[41]:
best_mod = utils.fit_classifier_with_crossvalidation(
toy_color_seqs_train,
toy_word_seqs_train,
toy_mod,
cv=2,
scoring=None,
param_grid={'hidden_dim': [10, 20]})
# ## Baseline SCC model
# Just to show how all the pieces come together, here's a very basic SCC experiment using the core code and very simplistic assumptions (which you will revisit in the assignment) about how to represent the examples:
# To facilitate quick development, we'll restrict attention to the two-word examples:
# In[42]:
dev_corpus = ColorsCorpusReader(COLORS_SRC_FILENAME, word_count=2)
# In[43]: