This repository has been archived by the owner. It is now read-only.
Switch branches/tags
Nothing to show
Find file Copy path
Fetching contributors…
Cannot retrieve contributors at this time
99 lines (85 sloc) 3.43 KB
Averaged perceptron classifier. Implementation geared for simplicity rather than
from collections import defaultdict
import pickle
import random
class AveragedPerceptron(object):
'''An averaged perceptron, as implemented by Matthew Honnibal.
See more implementation details here:
def __init__(self):
# Each feature gets its own weight vector, so weights is a dict-of-dicts
self.weights = {}
self.classes = set()
# The accumulated values, for the averaging. These will be keyed by
# feature/clas tuples
self._totals = defaultdict(int)
# The last time the feature was changed, for the averaging. Also
# keyed by feature/clas tuples
# (tstamps is short for timestamps)
self._tstamps = defaultdict(int)
# Number of instances seen
self.i = 0
def predict(self, features):
'''Dot-product the features and current weights and return the best label.'''
scores = defaultdict(float)
for feat, value in features.items():
if feat not in self.weights or value == 0:
weights = self.weights[feat]
for label, weight in weights.items():
scores[label] += value * weight
# Do a secondary alphabetic sort, for stability
return max(self.classes, key=lambda label: (scores[label], label))
def update(self, truth, guess, features):
'''Update the feature weights.'''
def upd_feat(c, f, w, v):
param = (f, c)
self._totals[param] += (self.i - self._tstamps[param]) * w
self._tstamps[param] = self.i
self.weights[f][c] = w + v
self.i += 1
if truth == guess:
return None
for f in features:
weights = self.weights.setdefault(f, {})
upd_feat(truth, f, weights.get(truth, 0.0), 1.0)
upd_feat(guess, f, weights.get(guess, 0.0), -1.0)
return None
def average_weights(self):
'''Average weights from all iterations.'''
for feat, weights in self.weights.items():
new_feat_weights = {}
for clas, weight in weights.items():
param = (feat, clas)
total = self._totals[param]
total += (self.i - self._tstamps[param]) * weight
averaged = round(total / float(self.i), 3)
if averaged:
new_feat_weights[clas] = averaged
self.weights[feat] = new_feat_weights
return None
def save(self, path):
'''Save the pickled model weights.'''
return pickle.dump(dict(self.weights), open(path, 'w'))
def load(self, path):
'''Load the pickled model weights.'''
self.weights = pickle.load(open(path))
return None
def train(nr_iter, examples):
'''Return an averaged perceptron model trained on ``examples`` for
``nr_iter`` iterations.
model = AveragedPerceptron()
for i in range(nr_iter):
for features, class_ in examples:
scores = model.predict(features)
guess, score = max(scores.items(), key=lambda i: i[1])
if guess != class_:
model.update(class_, guess, features)
return model