def __init__(self, dictionary, correlation, verbose=False):
self._correlation = correlation
self._dictionary = dictionary
self._verbose = verbose
if self._verbose:
print self.__doc__
self.mc = SimpleMarkovClassifier(dtype="unicode")
self.trainSimpleMarkovClassifier()
if self._verbose:
self.print_transition_probabilities()
def testSimpleMarkovClassifier():
mc = SimpleMarkovClassifier(dtype="c")
text = "after the letter e follows either space or the letters r t or i"
for word in text.split():
word = word.lower()
features = list(zip(" " + word))
labels = list(word + " ")
mc.train(mdp.numx.array(features), labels)
assert mc.input_dim == 1
num_transitions = 0
features = mc.features
for feature, count in list(features.items()):
if count:
prob = mc.prob(mdp.numx.array([feature]))
prob_sum = 0
for p in prob:
for k, v in list(p.items()):
prob_sum += v
if v:
num_transitions += 1
assert abs(prob_sum - 1.0) < 1e-5
# calculate the number of transitions (the negative set deletes the artefact of two spaces)
trans = len(set((list(zip(" ".join(text.split()) + " ", \
" " + " ".join(text.split()))))) - set([(' ', ' ')]))
assert num_transitions == trans
letters_following_e = [' ', 'r', 't', 'i']
letters_prob = mc.prob(mdp.numx.array([['e']]))[0]
prob_sum = 0
for letter, prob in list(letters_prob.items()):
prob_sum += prob
if prob > 1e-5:
assert letter in letters_following_e
assert abs(prob_sum - 1.0) < 1e-5
