CSC352 Lecture 7
Lecture notes for Lecture 7
(Tonje)
The Idea
Python
sw = {sw1, sw,2...} #Global
cat = [c1, c2 ...] #local
allWords = [w1,w2....] #local
wordFreq = {[f1,w1],[f2,w2] ...}
Sort, Reverse
mostFreq = wordFreq[0:5]
mostFreqWords = [w for f,w in mostFreq]
dict = {}
dict = {cat1:{w1:count1, w2:count2}...} #This time count is associated with cat1
for c in cat:
if c in dict.keys():
wdict = dict[c] #get data associated with c
for w in mostFreqWords:
if w is in wdict.keys():
wdict[w] +=1
else
wdict[w] = 1
else:
dict[c] = {}
for w in mostFreqWords:
dict[c][w] = 1
