def analyze(self, filename=None, text=None):
# analyze a new document using the stored values
# if there is a filename given, create a new Document object
if filename != None:
doc = Document(None, filename)
words = doc.tokenize()
# otherwise, analyze the given text
elif text != None:
words = Util.tokenize(text)
# if both are None, return error
else:
print "Analyzer requires a filename or text to analyze. Please try again."
return
# store dict of log value sums
log_sums = {}
# for every heuristic...
for key in self.log_values:
# initialize a value to 0
current_sum = 0.0
# iterate over words
for word in words:
current_sum += self.log_values[key].get(word)
# store new sum
log_sums[key] = current_sum
# calculate largest log sum; this can be improved by doing this inside above loop
# for clarity, we will add an extra loop here
# track largest sum
largest = -1.0
# track largest key
largest_heuristic = ""
# iterate through all the keys
for key in log_sums:
# if the new value is larger...
if log_sums[key] > largest:
# update values
largest = log_sums[key]
largest_heuristic = key
# return best key
return largest_heuristic
