Lab Five Solution | Python Fiddle

import segment

# dictValueTotal: {any -> number} -> number
# compute the sum total of all values in a dictionary
# with numerical values
def dictValueTotal(theDict):
   total = 0

for key in theDict:
      total = total + theDict[key]

return total

# fileToDict: string -> {string -> int}
# open a file with the given filename and parse its contents
# into a dictionary. The keys are strings and the values are ints.
def fileToDict(filename):
   myDict = {}

with open(filename, 'r') as inputFile:
      for line in inputFile:
         key, value = line.strip().split()
         myDict[key] = int(value)

return myDict

# createProbabilityFunction: {string: int} -> (string -> float)
# Output a function which accepts as input a word and produces as output a
# float representing the probability that this word occurs at random.
def createProbabilityFunction(wordFreqDict):
   n = dictValueTotal(wordFreqDict) # make sure to do this outside the inner function

def probFunction(word):
      if word not in wordFreqDict:
         return 1.0 / (n * 10**(len(word) - 2))

return float(wordFreqDict[word]) / n

return probFunction

# segmentLines: string, string -> [string]
# use the segment function in the segment library to segment 
# each line of a given file
def segmentLines(wordFreqFilename, wordSegmentFilename):
   freqDict = fileToDict(wordFreqFilename)
   p = createProbabilityFunction(freqDict)

segmentedLines = []
   with open(wordSegmentFilename, 'r') as inputFile:
      for line in inputFile:
         segmentedLine = segment.segment(line.strip(), p)
         segmentedLines.append(' '.join(segmentedLine))

return segmentedLines

if __name__ == "__main__":
   from unittest import test

# test fileToDict
   with open('test.txt', 'w') as temp:
      temp.write("example\t15\n")

testDict = fileToDict('test.txt')

test({'example': 15}, testDict)
   test(100, dictValueTotal({'a': 50, 'b': 25, 'c':25}))
   test(0, dictValueTotal({})) # test on an empty dictionary
   test(1.0, createProbabilityFunction({'example':15})('example'))

D = {'example':15, 'other':85}
   test(0.15, createProbabilityFunction(D)('example'))
   test(0.85, createProbabilityFunction(D)('other'))
   test(1.0 / (100 * 10**3), createProbabilityFunction(D)('crap!'))

with open('counts-test.txt', 'w') as temp:
      temp.write("hello\t10\nthere\t10\n")

with open('strings-test.txt', 'w') as temp:
      temp.write("hellothere\n")

test(['hello there'], segmentLines('counts-test.txt', 'strings-test.txt'))

# cleanup (the os module! very handy for file operations)
   import os
   os.remove('counts-test.txt')
   os.remove('strings-test.txt')

Python Fiddle

Python Cloud IDE