def test_svm():
trainingset = [ngrams(1, "foo foo bar baz"), ngrams(1, "foo foo bar bar baz baz"), ngrams(1,"foo foo bar baz")]
labels = [1, -1, -1]
lsc = LinearSVMClassifier()
for vec in zip(trainingset, labels):
lsc.addFeatureVector(vec[0], vec[1])
print lsc.classify(ngrams(1, "foo foo bar bar baz baz"))
print lsc.classify(ngrams(1, "foo foo foo bar baz"))
def test_svm():
trainingset = [
ngrams(1, "foo foo bar baz"),
ngrams(1, "foo foo bar bar baz baz"),
ngrams(1, "foo foo bar baz")
]
labels = [1, -1, -1]
lsc = LinearSVMClassifier()
for vec in zip(trainingset, labels):
lsc.addFeatureVector(vec[0], vec[1])
print lsc.classify(ngrams(1, "foo foo bar bar baz baz"))
print lsc.classify(ngrams(1, "foo foo foo bar baz"))
from cuckoovec import CuckooVector import numpy as np import string from ngrams import * vocab = [c for c in string.ascii_uppercase + string.ascii_lowercase] # letters n = 5 t = 2 # form random sparse vectors from <= t random words and weights def randsparse(t): return dict(zip(np.random.choice(vocab, t), np.random.randn(t))) s1 = [randsparse(t) for i in range(n)] s2 = [randsparse(t) for i in range(n)] t1 = ngrams(s1) print(t1) t2 = ngrams(s2) v1 = CuckooVector(t1) v2 = CuckooVector(t2) # these should be close to orthogonal. print(v1.dot(v2))
def hashindex(elements: List, hashsize: int, gramsize: int):
return [hash(tp) % hashsize for tp in ngrams(elements, gramsize, True)]
def _wordchar_to_idx(self, words: List, hashsize: int, gramsize: int):
chars = []
for w in words:
chars += [for tp in ngrams(list(w), gramsize, True)]
return [hash(tp) % hashsize for tp in chars]
import ngrams
sentence = 'this is a foo bar sentences and i want to ngramize it'
n = 6
sixgrams = ngrams(sentence.split(), n)
for grams in sixgrams:
print(grams)
