def search_grid(self, X, y, param_grid, verbose):
if '__algorithm' in param_grid.keys():
algorithm = param_grid['__algorithm']
else:
algorithm = self.best_algorithm
if '__best_parameter' in param_grid.keys(
) and param_grid['__best_parameter']:
self.param_base = self.best_param.copy()
param_grid = ParameterGrid({
p[0]: p[1]
for p in param_grid.items() if not p[0].startswith('__')
})
for param in param_grid:
trainer = crf.Trainer(verbose=verbose)
param_train = self.param_base.copy()
param_train.update(param)
trainer.select(algorithm, self.graphical_model)
trainer.set_params(param_train)
if isinstance(self.cv, int):
cv = KFold(n=len(X),
n_folds=self.cv,
shuffle=True,
random_state=None)
print('Parameter: (%s) %s' % (algorithm, param_train))
cv_score = []
for j, indices in enumerate(cv):
X_train, y_train = X[indices[0]], y[indices[0]]
X_test, y_test = X[indices[1]], y[indices[1]]
for xseq, yseq in zip(X_train, y_train):
trainer.append(xseq, yseq)
start = time.time()
trainer.train('model')
fit_elapsed_in_sec = time.time() - start
trainer.clear()
tagger = crf.Tagger()
tagger.open('model')
start = time.time()
y_pred = [tagger.tag(xseq) for xseq in X_test]
predict_elapsed_in_sec = time.time() - start
tagger.close()
score = self.scorer(y_pred, y_test)
print(
' cv(%i): score %.4f, train size %i, test size %i, train elapsed %.4f sec, test elapsed %.4f sec'
% (j, score, X_train.shape[0], X_test.shape[0],
fit_elapsed_in_sec, predict_elapsed_in_sec))
cv_score.append(score)
score = np.mean(cv_score)
if self.best_score < score:
self.best_score = score
self.best_param = param_train
self.best_algorithm = algorithm
del cv_score[:]
