def nbest(relation):
best1 = 0
best5 = 0
best10 = 0
for r in relation:
wordlist = r.split(' ')
w1 = word_to_vec_dict[wordlist[0]]
w2 = word_to_vec_dict[wordlist[1]]
w4 = word_to_vec_dict[wordlist[3]]
ret = distsim.show_nearest(
word_to_vec_dict, w1 - w2 + w4,
set([wordlist[0], wordlist[1], wordlist[3]]), distsim.cossim_dense)
print ret
if wordlist[2] == ret[0][0]:
best1 += 1
for r in range(5):
if wordlist[2] == ret[r][0]:
best5 += 1
for r in range(10):
if wordlist[2] == ret[r][0]:
best10 += 1
totalword = len(relation)
accbest1 = round(float(best1) / totalword, 2)
accbest5 = round(float(best5) / totalword, 2)
accbest10 = round(float(best10) / totalword, 2)
return accbest1, accbest5, accbest10
def table(lines):
data = []
for line in lines:
data.append(line.split(' '))
data = [data]
t = PrettyTable(['Class', '1-best', '5-best', '10-best'])
title = ['adversarial1', 'adversarial2']
p = [1, 5, 10]
for num in range(len(data)):
total = len(data[num])
count = [0, 0, 0]
for row in data[num]:
word_to_vec_dict = distsim.load_word2vec("nyt_word2vec.4k")
w1 = word_to_vec_dict[row[0]]
w2 = word_to_vec_dict[row[1]]
w4 = word_to_vec_dict[row[3]]
ret = distsim.show_nearest(word_to_vec_dict, w1 - w2 + w4,
set([row[0], row[1], row[3]]),
distsim.cossim_dense)
true = row[2]
for i in range(len(p)):
l = [j[0] for j in ret[:p[i]]]
if true in l:
count[i] += 1
t.add_row([
title[num], count[0] / float(total), count[1] / float(total),
count[2] / float(total)
])
print t
def calculateAccuracies(solutions):
word_to_vec_dict = distsim.load_word2vec("nyt_word2vec.4k")
accuracies = {}
errors = {}
for k, v in solutions.iteritems():
#print 'group: ' + str(k)
accuracies[k] = (float(0.0), float(0.0), float(0.0))
errors[k] = ''
size = len(v)
hasShownError = False
for i in v:
w1 = word_to_vec_dict[i[0]]
w2 = word_to_vec_dict[i[1]]
w4 = word_to_vec_dict[i[3]]
ret = distsim.show_nearest(word_to_vec_dict, w1 - w2 + w4,
set([str(i[0]),
str(i[1]),
str(i[3])]), distsim.cossim_dense)
isInTenBest = False
for n in range(len(ret)):
(p, q) = ret[n]
if p == i[2]:
isInTenBest = True
if n == 0:
(x, y, z) = accuracies[k]
x += 1.0
y += 1.0
z += 1.0
accuracies[k] = (x, y, z)
elif n < 5:
(x, y, z) = accuracies[k]
y += 1.0
z += 1.0
accuracies[k] = (x, y, z)
else:
(x, y, z) = accuracies[k]
z += 1.0
accuracies[k] = (x, y, z)
if not isInTenBest and not hasShownError:
errors[k] = (i[0], i[1], i[2], i[3], ret[0][0])
hasShownError = True
(a, b, c) = accuracies[k]
a /= size
b /= size
c /= size
accuracies[k] = (a, b, c)
#print accuracies[k]
#print errors
return (accuracies, errors)
def n_best_accuracy(n, strings):
total = len(strings)
count = 0
for line in strings:
items = line.strip().split(" ")
w1 = word_to_vec_dict[items[0].strip()]
w2 = word_to_vec_dict[items[1].strip()]
w3 = items[2].strip()
w4 = word_to_vec_dict[items[3].strip()]
ret = distsim.show_nearest(
word_to_vec_dict, w1 - w2 + w4,
set([items[0].strip(), items[1].strip(), items[3].strip()]),
distsim.cossim_dense)
for i in range(n):
if w3 == ret[i][0]:
count += 1
break
return count * 100.0 / total
def sim_compare(word_to_vec_dict,w1,w2,w3,w4):
ans = [0,0,0]
rank = {}
ww1 = word_to_vec_dict[w1]
ww2 = word_to_vec_dict[w2]
ww4 = word_to_vec_dict[w4]
ret = distsim.show_nearest(word_to_vec_dict,
ww1-w2+ww4,
set([w1,w2,w4]),
distsim.cossim_dense)
rank = print_result(ret,ret[0][0],rank)
if w3 in rank and rank[w3] == 1:
ans[0] += 1
ans[1] += 1
ans[2] += 1
elif w3 in rank and rank[w3] <= 5 and rank[w3] > 1:
ans[1] += 1
ans[2] += 1
elif w3 in rank and rank[w3] <= 10 and rank[w3] > 5:
ans[2] += 1
rinfo = w1+" : "+w2+" :: {} : "+w4
print rinfo.format(ret[0][0]),'--- Compare:',ret[0][0],w3
return ans
#print g
#print groups
best1 = 0
best5 = 0
best10 = 0
N = len(groups[g])
print g
for line in groups[g]:
words = line.split()
#print words[0]+":"+words[1]+"::"+words[2]+":"+words[3]
expected = words[2]
w1 = word_to_vec_dict[words[0]]
w2 = word_to_vec_dict[words[1]]
w4 = word_to_vec_dict[words[3]]
ret = distsim.show_nearest(word_to_vec_dict, w1 - w2 + w4,
set([words[0], words[1], words[3]]),
distsim.cossim_dense)
print(" {} : {} :: {} : {}".format(words[0], words[1], ret[0][0],
words[3]))
#print "-------"
for i in range(0, 10):
try:
#print ret[i][0]
if (ret[i][0] == expected):
#print ret[i][0]+" @ position "+str(i)
if (i == 0):
best1 += 1
best5 += 1
best10 += 1
if (i > 0 and i < 5):
best5 += 1
match_position = defaultdict(list)
catorder = []
for line in file:
line = line.strip().split()
if line[0] == '//':
continue
if line[0] == ':':
cat = line[1]
catorder.append(cat)
else:
word0 = word_to_vec_dict[line[0]]
word1 = word_to_vec_dict[line[1]]
word3 = word_to_vec_dict[line[3]]
ret = distsim.show_nearest(word_to_vec_dict, word0 - word1 + word3,
set([line[0], line[1], line[3]]),
distsim.cossim_dense)
count = 0
while (count < len(ret)):
if ret[count][0] == line[2]:
break
else:
count += 1
if count != len(ret):
match_position[cat].append([count + 1])
else:
match_position[cat].append([-1])
print cat + " " + str(line) + "\n"
print str(ret)
for key in catorder:
#!/usr/bin/env python
import distsim
word_to_ccdict = distsim.load_contexts("nytcounts.4k")
### provide your answer below
###Answer examples; replace with your choices
print 'jack'
for i, (word, score) in enumerate(distsim.show_nearest(word_to_ccdict,
word_to_ccdict['jack'],
set(['jack']),
distsim.cossim_sparse),
start=1):
print("{}: {} ({})".format(i, word, score))
print '\n'
print 'man'
for i, (word, score) in enumerate(distsim.show_nearest(word_to_ccdict,
word_to_ccdict['man'],
set(['man']),
distsim.cossim_sparse),
start=1):
print("{}: {} ({})".format(i, word, score))
print '\n'
print 'nice'
for i, (word, score) in enumerate(distsim.show_nearest(word_to_ccdict,
word_to_ccdict['nice'],
set(['nice']),
#!/usr/bin/env python
import distsim
word_to_vec_dict = distsim.load_word2vec("nyt_word2vec.4k")
###Provide your answer below
###Answer examples; replace with your choices
print("Word 1 is::::america")
for i, (word, score) in enumerate(
distsim.show_nearest(word_to_vec_dict, word_to_vec_dict['america'],
set(['america']), distsim.cossim_dense)):
print("{}: {} ({})".format(i, word, score))
print("--------------------")
print("Word 2 is::::years")
for i, (word, score) in enumerate(
distsim.show_nearest(word_to_vec_dict, word_to_vec_dict['years'],
set(['years']), distsim.cossim_dense)):
print("{}: {} ({})".format(i, word, score))
print("--------------------")
print("Word 3 is::::great")
for i, (word, score) in enumerate(
distsim.show_nearest(word_to_vec_dict, word_to_vec_dict['great'],
set(['great']), distsim.cossim_dense)):
print("{}: {} ({})".format(i, word, score))
print("--------------------")
print("Word 4 is::::run")
for i, (word, score) in enumerate(
distsim.show_nearest(word_to_vec_dict, word_to_vec_dict['run'],
#!/usr/bin/env python
import distsim
word_to_vec_dict = distsim.load_word2vec("nyt_word2vec.4k")
###Provide your answer below
print(distsim.show_nearest(word_to_vec_dict, word_to_vec_dict['california'],set(['california']),distsim.cossim_dense))
print(distsim.show_nearest(word_to_vec_dict, word_to_vec_dict['doctors'],set(['doctors']),distsim.cossim_dense))
print(distsim.show_nearest(word_to_vec_dict, word_to_vec_dict['small'],set(['small']),distsim.cossim_dense))
print(distsim.show_nearest(word_to_vec_dict, word_to_vec_dict['draw'],set(['draw']),distsim.cossim_dense))
print(distsim.show_nearest(word_to_vec_dict, word_to_vec_dict['month'],set(['month']),distsim.cossim_dense))
print(distsim.show_nearest(word_to_vec_dict, word_to_vec_dict['france'],set(['france']),distsim.cossim_dense))
###Answer examples
print(distsim.show_nearest(word_to_vec_dict, word_to_vec_dict['jack'],set(['jack']),distsim.cossim_dense))
#!/usr/bin/env python
import distsim
# you may have to replace this line if it is too slow
word_to_ccdict = distsim.load_contexts("nytcounts.4k")
### provide your answer below
ans = list()
###Answer examples
ans.append(
distsim.show_nearest(word_to_ccdict, word_to_ccdict['miami'],
set(['miami']), distsim.cossim_sparse))
ans.append(
distsim.show_nearest(word_to_ccdict, word_to_ccdict['doctor'],
set(['doctor']), distsim.cossim_sparse))
ans.append(
distsim.show_nearest(word_to_ccdict, word_to_ccdict['giant'],
set(['giant']), distsim.cossim_sparse))
ans.append(
distsim.show_nearest(word_to_ccdict, word_to_ccdict['agree'],
set(['agree']), distsim.cossim_sparse))
ans.append(
distsim.show_nearest(word_to_ccdict, word_to_ccdict['terrorist'],
set(['terrorist']), distsim.cossim_sparse))
ans.append(
distsim.show_nearest(word_to_ccdict, word_to_ccdict['hotel'],
set(['hotel']), distsim.cossim_sparse))
ans.append(
distsim.show_nearest(word_to_ccdict, word_to_ccdict['hospital'],
set(['hospital']), distsim.cossim_sparse))
ans.append(
#!/usr/bin/env python
import distsim
word_to_vec_dict = distsim.load_word2vec("nyt_word2vec.4k")
###Provide your answer below
###Answer examples
distsim.show_nearest(word_to_vec_dict, word_to_vec_dict['jack'], set(['jack']),
distsim.cossim_dense)
#!/usr/bin/env python
import distsim
word_to_vec_dict = distsim.load_word2vec("../nyt_word2vec.4k")
for i, (word,
score) in enumerate(distsim.show_nearest(word_to_vec_dict,
word_to_vec_dict['company'],
set(['company']),
distsim.cossim_dense),
start=1):
print("{}: {} ({})".format(i, word, score))
#!/usr/bin/env python
import distsim
# you may have to replace this line if it is too slow
word_to_ccdict = distsim.load_contexts("nytcounts.4k")
### provide your answer below
###Answer examples
#distsim.show_nearest(word_to_ccdict, word_to_ccdict['jack'],set(['jack']),distsim.cossim_sparse)
# people
rihanna = distsim.show_nearest(word_to_ccdict, word_to_ccdict['rihanna'],
set(['rihanna']), distsim.cossim_sparse)
obama = distsim.show_nearest(word_to_ccdict, word_to_ccdict['obama'],
set(['obama']), distsim.cossim_sparse)
# companies
nba = distsim.show_nearest(word_to_ccdict, word_to_ccdict['nba'], set(['nba']),
distsim.cossim_sparse)
netflix = distsim.show_nearest(word_to_ccdict, word_to_ccdict['netflix'],
set(['netflix']), distsim.cossim_sparse)
# country
iran = distsim.show_nearest(word_to_ccdict, word_to_ccdict['iran'],
set(['iran']), distsim.cossim_sparse)
# common nouns
terrorism = distsim.show_nearest(word_to_ccdict, word_to_ccdict['terrorism'],
set(['terrorism']), distsim.cossim_sparse)
economy = distsim.show_nearest(word_to_ccdict, word_to_ccdict['economy'],
set(['economy']), distsim.cossim_sparse)
data = distsim.show_nearest(word_to_ccdict, word_to_ccdict['data'],
set(['data']), distsim.cossim_sparse)
sex = distsim.show_nearest(word_to_ccdict, word_to_ccdict['sex'], set(['sex']),
#!/usr/bin/env python
import distsim
"""
word_to_vec_dict = distsim.load_word2vec("nyt_word2vec.4k")
king = word_to_vec_dict['king']
man = word_to_vec_dict['man']
woman = word_to_vec_dict['woman']
ret = distsim.show_nearest(word_to_vec_dict,
king-man+woman,
set(['king','man','woman']),
distsim.cossim_dense)
"""
word_to_ccdict = distsim.load_contexts("nytcounts.4k")
king = word_to_ccdict['king']
man = word_to_ccdict['man']
woman = word_to_ccdict['woman']
d = {}
for key1 in king:
if key1 in man and key1 in woman:
d[key1] = king.get(key1) - man.get(key1) + woman.get(key1)
ret = distsim.show_nearest(word_to_ccdict, d, set(['king', 'man', 'woman']),
distsim.cossim_sparse)
print("king : man :: {} : woman".format(ret[0][0]))
category_list = []
category_num_dict = defaultdict(list)
for line in f:
line = line.strip('\n')
if line[0] == '//':
continue
elif line[0] == ':':
category = line.split(' ')[1]
category_list.append(category)
word = line.strip().split(' ')
if len(word) == 4:
word1_dict = word_to_vec_dict[word[0]]
word2_dict = word_to_vec_dict[word[1]]
word4_dict = word_to_vec_dict[word[3]]
ret = distsim.show_nearest(word_to_vec_dict,
word1_dict - word2_dict + word4_dict,
set([word[0], word[1],
word[3]]), distsim.cossim_dense)
count = 0
find = False
while (count < len(ret)):
if ret[count][0] == word[2]:
count += 1
find = True
break
else:
count += 1
if find == False:
count = None
print word
print ret
for g in range(1, 9):
analogy = []
for i in range(0, len(L)):
if L[i][0] == g and len(L[i][1].split()) == 4:
analogy.append(L[i][1].split())
best1 = best5 = best10 = 0
for a in range(0, len(analogy)):
first = word_to_vec_dict[analogy[a][0]]
second = word_to_vec_dict[analogy[a][1]]
fourth = word_to_vec_dict[analogy[a][3]]
ret = distsim.show_nearest(
word_to_vec_dict, first - second + fourth,
set([analogy[a][0], analogy[a][1], analogy[a][3]]),
distsim.cossim_dense)
#ret = distsim.show_nearest(word_to_ccdict,z,set([ analogy[a][0], analogy[a][1], analogy[a][3] ]),distsim.cossim_sparse)
if analogy[a][2] == ret[0][0]:
best1 += 1
if analogy[a][2] in [w[0] for w in ret[0:5]]:
best5 += 1
if analogy[a][2] in [w[0] for w in ret[0:10]]:
best10 += 1
"""
print("---------------------------------------------------------------------------------------")
for i in range(0,len(ret)):
print(analogy[a][0]+" : "+analogy[a][1]+" :: "+ret[i][0]+" : "+analogy[a][3])
print("---------------------------------------------------------------------------------------")
"""
correct1 = 0
correct5 = 0
correct10 = 0
total = 0
if length - 4 == 0:
total += 1
flag = True
word1 = w[0].strip('\t')
word2 = w[1].strip('\t')
word3 = w[2].strip('\t')
word4 = w[3].strip('\t')
words1 = word_to_vec_dict[word1]
words2 = word_to_vec_dict[word2]
words4 = word_to_vec_dict[word4]
ret = distsim.show_nearest(word_to_vec_dict,
words1 - words2 + words4,
set([word1, word2,
word4]), distsim.cossim_dense)
sim = []
for i in ret:
sim.append(i[0])
pos = -1
if word3 in sim:
pos = sim.index(word3)
if pos != -1 and pos < 10:
correct10 += 1
if pos != -1 and pos < 5:
correct5 += 1
if pos != -1 and pos < 1:
correct1 += 1
elif line[0] == ':':
s = line.split(' ')
#!/usr/bin/env python
import distsim
word_to_vec_dict = distsim.load_word2vec("nyt_word2vec.4k")
###Provide your answer below
###Answer examples; replace with your choices
print 'china'
for i, (word,
score) in enumerate(distsim.show_nearest(word_to_vec_dict,
word_to_vec_dict['china'],
set(['china']),
distsim.cossim_dense),
start=1):
print("{}: {} ({})".format(i, word, score))
print 'human'
for i, (word,
score) in enumerate(distsim.show_nearest(word_to_vec_dict,
word_to_vec_dict['human'],
set(['human']),
distsim.cossim_dense),
start=1):
print("{}: {} ({})".format(i, word, score))
print 'handsome'
for i, (word,
score) in enumerate(distsim.show_nearest(word_to_vec_dict,
word_to_vec_dict['handsome'],
set(['handsome']),
distsim.cossim_dense),
start=1):
print("{}: {} ({})".format(i, word, score))
print 'fight'
num_snt = 0 #counting number of sentences
for i in temp:
num_snt += 1
#print "i",i
words = i.split(" ")
word1 = word_to_vec_dict[words[0].strip()]
word2 = word_to_vec_dict[words[1].strip()]
word3 = words[2].strip()
word4 = word_to_vec_dict[words[3].strip()]
new_word = word1 - word2 + word4
# print "words[0]",words[0]
# print "words[0]",words[1]
# print "words[0]",words[3]
#for i, (word, score) in enumerate(distsim.show_nearest(word_to_vec_dict,new_word,set([words[0].strip(),words[1].strip(),words[3].strip()]),distsim.cossim_dense), start=1):
ret = distsim.show_nearest(
word_to_vec_dict, new_word,
set([words[0].strip(), words[1].strip(), words[3].strip()]),
distsim.cossim_dense)
counter = 0
#print ret[counter][0]
while counter <= 9:
if counter == 0 and ret[counter][0] == word3:
#print "ji",ret[counter][0]
best_1 += 1
best_5 += 1
best_10 += 1
break
elif counter > 0 and counter <= 4 and ret[counter][0] == word3:
best_5 += 1
best_10 += 1
break
elif counter > 4 and counter <= 9 and ret[counter][0] == word3:
#!/usr/bin/env python
import distsim
word_to_vec_dict = distsim.load_word2vec("nyt_word2vec.4k")
#===============================================================================
# king = word_to_vec_dict['king']
# man = word_to_vec_dict['man']
# woman = word_to_vec_dict['woman']
# ret = distsim.show_nearest(word_to_vec_dict,
# king-man+woman, # <------------------------------- THE CORE OF RESASONING
# set(['king','man','woman']),
# distsim.cossim_dense)
# print("king : man :: {} : woman".format(ret[0][0]))
#===============================================================================
king = word_to_vec_dict['great']
man = word_to_vec_dict['greatest']
woman = word_to_vec_dict['biggest']
ret = distsim.show_nearest(
word_to_vec_dict,
king - man +
woman, # <------------------------------- THE CORE OF RESASONING
set(['great', 'greatest', 'biggest']),
distsim.cossim_dense)
print("king : man :: {} : woman".format(ret[0][0]))
#!/usr/bin/env python
import distsim
word_to_vec_dict = distsim.load_word2vec("nyt_word2vec.4k")
king = word_to_vec_dict['king']
man = word_to_vec_dict['man']
woman = word_to_vec_dict['woman']
ret = distsim.show_nearest(word_to_vec_dict, king - man + woman,
set(['king', 'man', 'woman']), distsim.cossim_dense)
print("king : man :: {} : woman".format(ret[0][0]))
#!/usr/bin/env python
import distsim
word_to_vec_dict = distsim.load_word2vec("nyt_word2vec.4k")
###Provide your answer below
###Answer examples; replace with your choices
print 'jack'
for i, (word, score) in enumerate(distsim.show_nearest(word_to_vec_dict, word_to_vec_dict['jack'],set(['jack']),distsim.cossim_dense)):
print("{}: {} ({})".format(i, word, score))
print '\n'
print 'man'
for i, (word, score) in enumerate(distsim.show_nearest(word_to_vec_dict, word_to_vec_dict['man'],set(['man']),distsim.cossim_dense)):
print("{}: {} ({})".format(i, word, score))
print '\n'
print 'nice'
for i, (word, score) in enumerate(distsim.show_nearest(word_to_vec_dict, word_to_vec_dict['nice'],set(['nice']),distsim.cossim_dense)):
print("{}: {} ({})".format(i, word, score))
print '\n'
print 'move'
for i, (word, score) in enumerate(distsim.show_nearest(word_to_vec_dict, word_to_vec_dict['move'],set(['move']),distsim.cossim_dense)):
print("{}: {} ({})".format(i, word, score))
print '\n'
print 'father'
for i, (word, score) in enumerate(distsim.show_nearest(word_to_vec_dict, word_to_vec_dict['father'],set(['father']),distsim.cossim_dense)):
print("{}: {} ({})".format(i, word, score))
#!/usr/bin/env python
import distsim
# you may have to replace this line if it is too slow
word_to_vec_dict = distsim.load_word2vec("nyt_word2vec.4k")
### provide your answer below
experiment_list = ['edward', 'school', 'red', 'saved', 'eyebrows', 'church']
###Answer examples
for e_word in experiment_list:
print 'Experiment =', e_word
if e_word not in word_to_vec_dict:
print e_word, ' does not exist in lookup dictionary'
continue
for i, (word,
score) in enumerate(distsim.show_nearest(word_to_vec_dict,
word_to_vec_dict[e_word],
set([e_word]),
distsim.cossim_dense),
start=1):
print("{}: {} ({})".format(i, word, score))
print '\n---------------------------------------------\n'
task_accuracies = defaultdict(list)
file = open("word-test.v3.txt", "r")
for line in file:
line = line.strip('\n')
if line.startswith('//'):
continue
if line.startswith(":"):
category = line[2:]
else:
words = line.split()
w1_dict = word_to_vec_dict[words[0]]
w2_dict = word_to_vec_dict[words[1]]
w4_dict = word_to_vec_dict[words[3]]
result = distsim.show_nearest(word_to_vec_dict, w1_dict - w2_dict + w4_dict, set([words[0],words[1],words[3]]), distsim.cossim_dense)
i = 0
match = False
for vec in result:
i+=1
if vec[0] == words[2]:
match = True
break
if not match:
i = 0
task_accuracies[category].append(i)
for key, value in task_accuracies.items():
top1 = 0
top5 = 0
top10 = 0
#!/usr/bin/env python
import distsim
word_to_ccdict = distsim.load_contexts("nytcounts.4k")
#word_to_ccdict = distsim.load_contexts("nytcounts.4k")
for i, (word, score) in enumerate(distsim.show_nearest(word_to_ccdict,
word_to_ccdict['dog'],
set(['dog']),
distsim.cossim_sparse),
start=1):
print("{}: {} ({})".format(i, word, score))
#!/usr/bin/env python
import distsim
word_to_ccdict = distsim.load_contexts("nytcounts.4k")
### provide your answer below
###Answer examples; replace with your choices
for i, (word, score) in enumerate(distsim.show_nearest(word_to_ccdict, word_to_ccdict['florida'],set(['florida']),distsim.cossim_sparse), start=1):
print("{}: {} ({})".format(i, word, score))
for i, (word, score) in enumerate(distsim.show_nearest(word_to_ccdict, word_to_ccdict['teachers'],set(['teachers']),distsim.cossim_sparse), start=1):
print("{}: {} ({})".format(i, word, score))
for i, (word, score) in enumerate(distsim.show_nearest(word_to_ccdict, word_to_ccdict['single'],set(['single']),distsim.cossim_sparse), start=1):
print("{}: {} ({})".format(i, word, score))
for i, (word, score) in enumerate(distsim.show_nearest(word_to_ccdict, word_to_ccdict['buy'],set(['buy']),distsim.cossim_sparse), start=1):
print("{}: {} ({})".format(i, word, score))
for i, (word, score) in enumerate(distsim.show_nearest(word_to_ccdict, word_to_ccdict['week'],set(['week']),distsim.cossim_sparse), start=1):
print("{}: {} ({})".format(i, word, score))
for i, (word, score) in enumerate(distsim.show_nearest(word_to_ccdict, word_to_ccdict['china'],set(['china']),distsim.cossim_sparse), start=1):
print("{}: {} ({})".format(i, word, score))
#!/usr/bin/env python
import distsim
word_to_ccdict = distsim.load_contexts("nytcounts.4k")
### provide your answer below
# proper-noun america
# common-noun years
# adjective great
# verb run
# word 5 between
# word 6 wife
print("Word 1 is::::america")
for i, (word, score) in enumerate(distsim.show_nearest(word_to_ccdict, word_to_ccdict['america'],set(['america']),distsim.cossim_sparse), start=1):
print("{}: {} ({})".format(i, word, score))
print("--------------------")
print("Word 2 is::::years")
for i, (word, score) in enumerate(distsim.show_nearest(word_to_ccdict, word_to_ccdict['years'],set(['years']),distsim.cossim_sparse), start=1):
print("{}: {} ({})".format(i, word, score))
print("--------------------")
print("Word 3 is::::great")
for i, (word, score) in enumerate(distsim.show_nearest(word_to_ccdict, word_to_ccdict['great'],set(['great']),distsim.cossim_sparse), start=1):
print("{}: {} ({})".format(i, word, score))
print("--------------------")
print("Word 4 is::::run")
for i, (word, score) in enumerate(distsim.show_nearest(word_to_ccdict, word_to_ccdict['run'],set(['run']),distsim.cossim_sparse), start=1):
print("{}: {} ({})".format(i, word, score))
#!/usr/bin/env python
import distsim
word_to_vec_dict = distsim.load_word2vec("nyt_word2vec.4k")
###Provide your answer below
###Answer examples
print "jack", distsim.show_nearest(word_to_vec_dict, word_to_vec_dict['jack'],
set(['jack']), distsim.cossim_dense)
print "london", distsim.show_nearest(word_to_vec_dict,
word_to_vec_dict['london'],
set(['london']), distsim.cossim_dense)
print "month", distsim.show_nearest(word_to_vec_dict,
word_to_vec_dict['month'], set(['month']),
distsim.cossim_dense)
print "attack", distsim.show_nearest(word_to_vec_dict,
word_to_vec_dict['attack'],
set(['attack']), distsim.cossim_dense)
print "happy", distsim.show_nearest(word_to_vec_dict,
word_to_vec_dict['happy'], set(['happy']),
distsim.cossim_dense)
print "jail", distsim.show_nearest(word_to_vec_dict, word_to_vec_dict['jail'],
set(['jail']), distsim.cossim_dense)
print "fantastic", distsim.show_nearest(word_to_vec_dict,
word_to_vec_dict['fantastic'],
set(['fantastic']),
distsim.cossim_dense)
#!/usr/bin/env python
import distsim
word_to_vec_dict = distsim.load_word2vec("nyt_word2vec.4k")
king = word_to_vec_dict['usa']
man = word_to_vec_dict['dollar']
woman = word_to_vec_dict['won']
ret = distsim.show_nearest(word_to_vec_dict, king - man + woman,
set(['usa', 'dollar', 'won']), distsim.cossim_dense)
print("usa : dollar :: {} : won".format(ret[0][0]))
