from math import sqrt def getMetrics (record, commons): # define variables lc, w

Question

from math import sqrt

def getMetrics (record, commons): # define variables lc, wc, and cc and # initialize them (mostly to zero) lc = 0 # letter count

wc = 0

cc = 0

__________ = len (record) # word count

__________ = __________ # common-word count

# loop through every word in the record:

for word in __________: # count if the word is in commons

if word in __________:

cc = cc + __________ # accumulate the characters

lc = __________ + len (word) # return the two measurements

return [float (cc) / wc, float (lc) / wc]

def getMetricsList (paragraphs, commons):

metricsList = []

for record in paragraphs:

metricsList.append (__________ (record, commons))

return metricsList

def findCentroid (metricsList):

# we assume there is at least one record here

# n is the number of elements in a record

# and nn is the number of records

n = __________ (metricsList [0])

nn = len (__________) # create and initialize the accumulator

result = [0] * n

for record in metricsList:

for i in range (n):

result [i] = result [i] + record [i]

for i in range (n):

result [i] = result [i] / float (nn)

return result

def findDistance (rec1, rec2): # we assume the two records have the same length

dist = 0.0

n = len (rec1)

for i in range (n):

dist = dist + (rec1 [i] - rec2 [i]) ** 2

return sqrt (__________)

def findDistanceList (paragraphs, commons):

metricsList = __________ (paragraphs, commons)

centroid = __________ (metricsList)

distanceList = []

for metrics in metricsList:

distanceList.append (__________ (metrics, centroid))

return distanceList

def findOutLinerIndices (paragraphs, commons, howMany):

distanceList = findDistanceList (paragraphs, commons)

work = distanceList [:] # make a clone

work.__________ () # sort the list

work.__________ () # reverse the list

criterion = work [howMany-1]

result = []

for i in range (len (paragraphs)):

if distanceList [i] >= criterion:

result.append (i)

return result

def test (paragraphs, commons):

indices = findOutLinerIndices (paragraphs, commons, 5)

for i in indices:

score='%4.2f, %4.2f'%tuple(getMetrics(paragraphs[i],commons))

print (str (i) + ': ' + score + ' --- ' + str(paragraphs[i]))

def test1 ():

from pg1 import paragraphs, commons

test (paragraphs, commons) def main ():

test1 ()

def test2 ():

from pg1260 import paragraphs, commons

test (paragraphs, commons)def main ():

test2 ()

def main ():

print ('***********************************')

print ('Results for pg1.py:')

test1 ()

print ('***********************************')

print ('Results for pg1260.py:')

test2 ()

print ('***********************************')

main ()

Explanation / Answer

# define variables lc, wc, and cc and # initialize them (mostly to zero) lc = 0 # letter count

wc = 0

cc = 0

__________ = len (record) # word count

__________ = __________ # common-word count

# loop through every word in the record:

for word in __________: # count if the word is in commons

if word in __________:

cc = cc + __________ # accumulate the characters

lc = __________ + len (word) # return the two measurements

return [float (cc) / wc, float (lc) / wc]

def getMetricsList (paragraphs, commons):

metricsList = []

for record in paragraphs:

metricsList.append (__________ (record, commons))

return metricsList

def findCentroid (metricsList):

# we assume there is at least one record here

# n is the number of elements in a record

# and nn is the number of records

n = __________ (metricsList [0])

nn = len (__________) # create and initialize the accumulator

result = [0] * n

for record in metricsList:

for i in range (n):

result [i] = result [i] + record [i]

for i in range (n):

result [i] = result [i] / float (nn)

return result

def findDistance (rec1, rec2): # we assume the two records have the same length

dist = 0.0

n = len (rec1)

for i in range (n):

dist = dist + (rec1 [i] - rec2 [i]) ** 2

return sqrt (__________)

def findDistanceList (paragraphs, commons):

metricsList = __________ (paragraphs, commons)

centroid = __________ (metricsList)

distanceList = []

for metrics in metricsList:

distanceList.append (__________ (metrics, centroid))

return distanceList

def findOutLinerIndices (paragraphs, commons, howMany):

distanceList = findDistanceList (paragraphs, commons)

work = distanceList [:] # make a clone

work.__________ () # sort the list

work.__________ () # reverse the list

criterion = work [howMany-1]

result = []

for i in range (len (paragraphs)):

if distanceList [i] >= criterion:

result.append (i)

return result

def test (paragraphs, commons):

indices = findOutLinerIndices (paragraphs, commons, 5)

for i in indices:

score='%4.2f, %4.2f'%tuple(getMetrics(paragraphs[i],commons))

print (str (i) + ': ' + score + ' --- ' + str(paragraphs[i]))

def test1 ():

from pg1 import paragraphs, commons

test (paragraphs, commons) def main ():

test1 ()

def test2 ():

from pg1260 import paragraphs, commons

test (paragraphs, commons)def main ():

test2 ()

def main ():

print ('***********************************')

print ('Results for pg1.py:')

test1 ()

print ('***********************************')

print ('Results for pg1260.py:')

test2 ()

print ('***********************************')

main ()

Related Questions

Navigate

• Browse (All)
• Browse F
• Subjects

---

---

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.