def get(self, symbols):
"""
Estimates the perplexity of a vector of symbols.
@return float value
"""
exr = symbols_to_items(symbols, self.ngram)
entropy = 0
for symbol, occurrences in exr.items():
realsymbol = " ".join(symbol).strip()
probability = self.model.get(realsymbol, self.epsilon)
self_information = log2(1.0 / probability)
entropy += (probability * self_information) * occurrences
return pow(2, entropy)
def get(self):
"""
Estimates the Shannon entropy of a vector of symbols.
Shannon's entropy measures the information contained in a message as
opposed to the portion of the message that is determined
(or predictable).
@return float value
"""
exr = symbols_to_items(self.symbols, self.ngram)
total = len(self.symbols) - self.ngram + 1
entropy = 0
for symbol,occurrences in exr.items():
probability = 1.0 * occurrences / total
self_information = log2( 1.0 / probability )
entropy += (probability * self_information)
return entropy