def test_d3_3a_nb():
global x_tr_pruned, y_tr
theta_nb = naive_bayes.estimate_nb(x_tr_pruned, y_tr, 0.1)
y_hat, scores = clf_base.predict(x_tr_pruned[55], theta_nb, labels)
assert_almost_equals(scores['2000s'], -1840.5064690929203, places=3)
eq_(y_hat, '1980s')
y_hat, scores = clf_base.predict(x_tr_pruned[155], theta_nb, labels)
assert_almost_equals(scores['1980s'], -2153.0199277981355, places=3)
eq_(y_hat, '2000s')
def perceptron_update(x, y, weights, labels):
'''
compute the perceptron update for a single instance
:param x: instance, a counter of base features and weights
:param y: label, a string
:param weights: a weight vector, represented as a dict
:param labels: set of possible labels
:returns: updates to weights, which should be added to weights
:rtype: defaultdict
'''
weights_update = defaultdict(float)
pred, _ = predict(x, weights, labels)
predf = make_feature_vector(x, pred)
true_pred = make_feature_vector(x, y)
if pred != y:
weights_update.update(true_pred)
for features, value in predf.items():
predf[features] = -value
weights_update.update(predf)
return weights_update
def perceptron_update(x,y,weights,labels):
'''
compute the perceptron update for a single instance
:param x: instance, a counter of base features and weights
:param y: label, a string
:param weights: a weight vector, represented as a dict
:param labels: set of possible labels
:returns: updates to weights, which should be added to weights
:rtype: defaultdict
'''
ypred, scores = predict(x, weights, labels)
orig_feature = make_feature_vector(x, y)
if(ypred ==y):
return defaultdict(float)
else:
pred_feature = make_feature_vector(x, ypred)
res = {}
for key in orig_feature.keys():
if key in pred_feature.keys():
res[key] = orig_feature[key]-pred_feature[key]
else:
res[key] = orig_feature[key]
for key in pred_feature.keys():
if key not in orig_feature.keys():
res[key] = -pred_feature[key]
output = defaultdict(float, res)
return output
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 classify(words, all_tags):
"""This nested function should return a list of tags, computed using a classifier with the weights passed as arguments to make_classifier_tagger and using basefeatures for each token (just the token and the offset)
:param words: list of words
:param all_tags: all possible tags
:returns: list of tags
:rtype: list
"""
tags = []
for word in words:
label, score = clf_base.predict({word:1},weights,list(all_tags))
tags.append(label)
return tags
def classify(words, all_tags):
"""This nested function should return a list of tags, computed using a classifier with the weights passed as arguments to make_classifier_tagger and using basefeatures for each token (just the token and the offset)
:param words: list of words
:param all_tags: all possible tags
:returns: list of tags
:rtype: list
"""
mylist = []
for word in words:
myCounter = Counter()
myCounter[word] = 1
#print(myCounter)
ypred, pred_wt = clf_base.predict(myCounter, weights, all_tags)
mylist.append(ypred)
#print(mylist)
return mylist