def it_should_find_related_test(self):
vector_space = VectorSpace(self.documents)
eq_(vector_space.related(0), [1.0000000000000002, 0.9999999999999998, 0.0])
def anotate(inpt, skipsize):
k = 2
queueSize = skipsize * 2 + 1
queueMid = skipsize + 1
queueIsReady = lambda x : len(x) == queueSize
def push(element, queue):
queue.append(element)
if len(queue) > queueSize:
queue.pop(0)
vocabulary = get_document_vocabulary(inpt)
vocSize = len(vocabulary) + 1
print "Starting on determining word co-occurences."
cocs = defaultdict(list)
queue = []
for word in inpt:
push(word, queue)
if queueIsReady(queue):
mid = queue[queueMid]
if mid in vocabulary:
coc = []
for i in xrange(skipsize):
if queue[i] in vocabulary:
word1 = queue[i]
else:
word1 = "_UNKNOWN_"
if queue[i+1+skipsize] in vocabulary:
word2 = queue[i+1+skipsize]
else:
word2 = "_UNKNOWN_"
coc.append(word1)
coc.append(word2)
#print "final co-occurences"
#print coc
cocs[mid].append(coc)
#print "Coc[mid]"
#print cocs[mid]
print "Determining LSA relatedness scores between documents..."
clustered = dict()
for key in cocs.keys():
#print "KEY:" + key
#print "\ncocs[" + key + "]:"
#print "len cocs key"
#print len(cocs[key])
#print cocs[key][0]
#print cocs[key][1]
#print " ".join(cocs[key][0])
a = [" ".join(cocs[key][i]) for i in range(len(cocs[key]))]
#a = a[:6]
#print "len a"
#print len(a)
"""
print a[0]
print a[1]
print a[2]
print a[3]
print a[4]
print a[5]
"""
vector_space = VectorSpace(a)
scores = vector_space.related(0)
LSIscores = []
for i in range(len(a)):
ss = {"docText" : a[i], "similarity" : scores[i]}
LSIscores.append(ss)
LSIscores = sorted(LSIscores, key=lambda k: k['similarity'], reverse=True)
"""print "scores"
print LSIscores"""
LSIscores = LSIscores[:len(LSIscores)/2]
"""
text = ""
for item in LSIscores:
text += item["docText"] + " "
print "text is: " + text
d = defaultdict(int)
for word in text.split():
d[word] += 1
"""
itemsToCluster = []
for item in LSIscores:
text = item["docText"]
d = defaultdict(int)
for word in text.split():
d[word] += 1
d = normalize_coc(d)
itemsToCluster.append(d)
"""
print "printing d follows"
print d
#normalize
d = normalize_coc(d)
print "after normalization"
print d
d = list(d)
print d
"""
clustered[key] = kmeans_process(itemsToCluster)
#print "half scores"
#print LSIscores
#print cocs[key]
#clustered[key] = kmeans_process(LSIScores)
print "Starting anotating corpus."
anotated = []
queue = []
for word in inpt:
push(word, queue)
if queueIsReady(queue):
word = queue[queueMid]
if word in clustered and len(clustered[word]) > 1:
coc = defaultdict(int)
for i in xrange(skipsize):
if queue[i] in vocabulary:
word1 = queue[i]
else:
word1 = "_UNKNOWN_"
if queue[i+1+skipsize] in vocabulary:
word2 = queue[i+1+skipsize]
else:
word2 = "_UNKNOWN_"
coc[word1] += 1
coc[word2] += 1
coc = normalize_coc(coc)
# Now get the best cluster
bestValue = 1
bestIndex = -1
for i in xrange(k):
distance = clustered[word][i].distance(coc)
if distance < bestValue:
bestValue = distance
bestIndex = i
word = word + "_" + str(bestIndex) + " "
anotated.append(word)
return (clustered, anotated)
def it_should_find_return_similarity_rating_test(self):
vectorSpace = VectorSpace(self.documents)
eq_(vectorSpace.related(0), [1.0, 0.9922455760198575, 0.08122814162371816, 0.0762173599906487])
offset = 0
rows = c.execute('select * from articles limit {0} offset {1}'.format(limit, offset))
for row in rows:
#print row
texts.append(row[1] + " " + row[11])
ids.append(row[0])
#vector_space = VectorSpace(["The cat in the hat disabled", "A cat is a fine pet ponies.", "Dogs and cats make good pets.","I haven't got a hat."])
vector_space = VectorSpace(texts)
#Search for cat
#print vector_space.search(["cat"])
#Show score for relatedness against document 0
group = dict()
for id in range(len(ids)):
prob = vector_space.related(id)
for i in range(len(ids)):
if prob[i] > 0.2 and prob[i] < 0.9 and id != i:
if group.has_key(offset + id + 1) == False:
group[offset + id + 1] = []
group[offset + id + 1].append(offset + i + 1)
print(offset + id + 1, offset + i + 1, prob[i])
print(group)
#id = 139
#prob = vector_space.related(id)
#for i in range(len(ids)):
# if prob[i] > 0.2 and id != i:
# print(offset + id + 1, offset + i + 1, prob[i])
