def find_best_smoother(x_tr, y_tr, x_dv, y_dv, smoothers):
'''
find the smoothing value that gives the best accuracy on the dev data
:param x_tr: training instances
:param y_tr: training labels
:param x_dv: dev instances
:param y_dv: dev labels
:param smoothers: list of smoothing values
:returns: best smoothing value
:rtype: float
'''
labels = list(set(y_tr))
scores = {}
best = 0
best_sm = 0
for i in smoothers:
weights = estimate_nb(x_tr, y_tr, i)
y_hat = clf_base.predict_all(x_dv, weights, labels)
acc = evaluation.acc(y_hat, y_dv)
scores[i] = acc
if acc > best:
best = acc
best_sm = i
return best_sm, scores
def test_d2_2_predict():
global x_tr_pruned, x_dv_pruned, y_dv
y_hat, scores = clf_base.predict(x_tr_pruned[0], hand_weights.theta_hand,
labels)
eq_(scores['pre-1980'], 0.1)
assert_almost_equals(scores['2000s'], 1.3, places=5)
eq_(y_hat, '2000s')
eq_(scores['1980s'], 0.0)
y_hat = clf_base.predict_all(x_dv_pruned, hand_weights.theta_hand, labels)
assert_almost_equals(evaluation.acc(y_hat, y_dv), .3422222, places=5)
def find_best_smoother(x_tr,y_tr,x_dv,y_dv,smoothers):
'''
find the smoothing value that gives the best accuracy on the dev data
:param x_tr: training instances
:param y_tr: training labels
:param x_dv: dev instances
:param y_dv: dev labels
:param smoothers: list of smoothing values
:returns: best smoothing value
:rtype: float
'''
my_acc_dict = {}
max_score = 0.0;
for i in range(len(smoothers)):
weights = estimate_nb(x_tr, y_tr, smoothers[i])
y_hat = clf_base.predict_all(x_dv,weights,y_dv)
acc = evaluation.acc(y_hat,y_dv)
if( acc > max_score):
max_score = acc
my_acc_dict[smoothers[i]] = acc
return max_score, my_acc_dict