def saga_cv(which, alphas, l1_ratio):
if which == 'cdcp':
n_folds = 3
path = os.path.join("data", "process", "erule", "folds", "{}", "{}")
elif which == 'ukp':
n_folds = 5
path = os.path.join("data", "process", "ukp-essays", "folds", "{}",
"{}")
else:
raise ValueError
clf_link = SAGAClassifier(loss='smooth_hinge',
penalty='l1',
tol=1e-4,
max_iter=100,
random_state=0,
verbose=0)
clf_prop = clone(clf_link)
link_scores = np.zeros((n_folds, len(alphas)))
prop_scores = np.zeros_like(link_scores)
for k in range(n_folds):
X_tr_link, y_tr_link = load_csr(path.format(k, 'train.npz'),
return_y=True)
X_te_link, y_te_link = load_csr(path.format(k, 'val.npz'),
return_y=True)
X_tr_prop, y_tr_prop = load_csr(path.format(k, 'prop-train.npz'),
return_y=True)
X_te_prop, y_te_prop = load_csr(path.format(k, 'prop-val.npz'),
return_y=True)
le = LabelEncoder()
y_tr_prop_enc = le.fit_transform(y_tr_prop)
y_te_prop_enc = le.transform(y_te_prop)
link_sw = compute_sample_weight('balanced', y_tr_link)
for j, alpha in enumerate(alphas):
beta = alpha * l1_ratio
alpha *= 1 - l1_ratio
clf_link.set_params(alpha=alpha, beta=beta)
clf_prop.set_params(alpha=alpha, beta=beta)
clf_link.fit(X_tr_link, y_tr_link, sample_weight=link_sw)
y_pred_link = clf_link.predict(X_te_link)
clf_prop.fit(X_tr_prop, y_tr_prop_enc)
y_pred_prop = clf_prop.predict(X_te_prop)
with warnings.catch_warnings() as w:
warnings.simplefilter('ignore')
link_f = f1_score(y_te_link, y_pred_link, average='binary')
prop_f = f1_score(y_te_prop_enc, y_pred_prop, average='macro')
link_scores[k, j] = link_f
prop_scores[k, j] = prop_f
return link_scores, prop_scores
class BaselineStruct(BaseArgumentMixin):
def __init__(self, alpha_link, alpha_prop, l1_ratio, exact_test=False):
self.alpha_link = alpha_link
self.alpha_prop = alpha_prop
self.l1_ratio = l1_ratio
self.compat_features = False
self.exact_test = exact_test
def initialize_labels(self, y_props_flat, y_links_flat):
self.prop_encoder_ = LabelEncoder().fit(y_props_flat)
self.link_encoder_ = LabelEncoder().fit(y_links_flat)
self.n_prop_states = len(self.prop_encoder_.classes_)
self.n_link_states = len(self.link_encoder_.classes_)
def fit(self, X_link, y_link, X_prop, y_prop):
self.initialize_labels(y_prop, y_link)
y_link = self.link_encoder_.transform(y_link)
y_prop = self.prop_encoder_.transform(y_prop)
self.link_clf_ = SAGAClassifier(loss='smooth_hinge',
penalty='l1',
tol=1e-4,
max_iter=500,
random_state=0,
verbose=0)
self.prop_clf_ = clone(self.link_clf_)
alpha_link = self.alpha_link * (1 - self.l1_ratio)
beta_link = self.alpha_link * self.l1_ratio
sw = compute_sample_weight('balanced', y_link)
self.link_clf_.set_params(alpha=alpha_link, beta=beta_link)
self.link_clf_.fit(X_link, y_link, sample_weight=sw)
alpha_prop = self.alpha_prop * (1 - self.l1_ratio)
beta_prop = self.alpha_prop * self.l1_ratio
self.prop_clf_.set_params(alpha=alpha_prop, beta=beta_prop)
self.prop_clf_.fit(X_prop, y_prop)
return self
def decision_function(self, X_link, X_prop, docs):
link_offsets = np.cumsum([len(doc.features) for doc in docs])
y_link_flat = self.link_clf_.decision_function(X_link)
y_link_marg = np.zeros(
(len(y_link_flat), len(self.link_encoder_.classes_)))
link_on, = self.link_encoder_.transform([True])
y_link_marg[:, link_on] = y_link_flat.ravel()
Y_link = [
y_link_marg[start:end]
for start, end in zip(np.append(0, link_offsets), link_offsets)
]
prop_offsets = np.cumsum([len(doc.prop_features) for doc in docs])
y_prop_marg = self.prop_clf_.decision_function(X_prop)
Y_prop = [
y_prop_marg[start:end]
for start, end in zip(np.append(0, prop_offsets), prop_offsets)
]
Y_pred = []
for y_link, y_prop in zip(Y_link, Y_prop):
Y_pred.append(DocLabel(y_prop, y_link))
assert len(Y_pred) == len(docs)
return Y_pred
def fast_decode(self, Y_marg, docs, constraints):
if constraints:
Y_pred = []
zero_compat = np.zeros(
(self.n_prop_states, self.n_prop_states, self.n_link_states))
for doc, y in zip(docs, Y_marg):
potentials = (y.nodes, y.links, zero_compat, [], [], [])
y_decoded, _ = self._inference(doc,
potentials,
relaxed=False,
exact=self.exact_test,
constraints=constraints)
Y_pred.append(y_decoded)
else:
Y_pred = [
self._round(y.nodes, y.links, inverse_transform=True)
for y in Y_marg
]
return Y_pred
def predict(self, X_link, X_prop, docs, constraints=""):
Y_marg = self.decision_function(X_link, X_prop, docs)
return self.fast_decode(Y_marg, docs, constraints)
class BaselineStruct(BaseArgumentMixin):
def __init__(self, alpha_link, alpha_prop, l1_ratio):
self.alpha_link = alpha_link
self.alpha_prop = alpha_prop
self.l1_ratio = l1_ratio
self.compat_features = False
def initialize_labels(self, y_props_flat, y_links_flat):
self.prop_encoder_ = LabelEncoder().fit(y_props_flat)
self.link_encoder_ = LabelEncoder().fit(y_links_flat)
self.n_prop_states = len(self.prop_encoder_.classes_)
self.n_link_states = len(self.link_encoder_.classes_)
def fit(self, X_link, y_link, X_prop, y_prop):
self.initialize_labels(y_prop, y_link)
y_link = self.link_encoder_.transform(y_link)
y_prop = self.prop_encoder_.transform(y_prop)
self.link_clf_ = SAGAClassifier(loss='smooth_hinge',
penalty='l1',
tol=1e-4,
max_iter=500,
random_state=0,
verbose=0)
self.prop_clf_ = clone(self.link_clf_)
alpha_link = self.alpha_link * (1 - self.l1_ratio)
beta_link = self.alpha_link * self.l1_ratio
sw = compute_sample_weight('balanced', y_link)
self.link_clf_.set_params(alpha=alpha_link, beta=beta_link)
self.link_clf_.fit(X_link, y_link, sample_weight=sw)
alpha_prop = self.alpha_prop * (1 - self.l1_ratio)
beta_prop = self.alpha_prop * self.l1_ratio
self.prop_clf_.set_params(alpha=alpha_prop, beta=beta_prop)
self.prop_clf_.fit(X_prop, y_prop)
return self
def decision_function(self, X_link, X_prop, docs):
link_offsets = np.cumsum([len(doc.features) for doc in docs])
y_link_flat = self.link_clf_.decision_function(X_link)
y_link_marg = np.zeros(
(len(y_link_flat), len(self.link_encoder_.classes_)))
link_on, = self.link_encoder_.transform([True])
y_link_marg[:, link_on] = y_link_flat.ravel()
Y_link = [
y_link_marg[start:end]
for start, end in zip(np.append(0, link_offsets), link_offsets)
]
prop_offsets = np.cumsum([len(doc.prop_features) for doc in docs])
y_prop_marg = self.prop_clf_.decision_function(X_prop)
Y_prop = [
y_prop_marg[start:end]
for start, end in zip(np.append(0, prop_offsets), prop_offsets)
]
Y_pred = []
for y_link, y_prop in zip(Y_link, Y_prop):
Y_pred.append(DocLabel(y_prop, y_link))
assert len(Y_pred) == len(docs)
return Y_pred