def help():
print "Base Flags:"
for flag in flags.basic:
print " %s: %s" % (flag, flags.descriptions[flag])
print
print "Compound Flags:"
for flag in flags.compound:
if flag == 'All':
continue
print " %s: %s" % (flag, flags.descriptions[flag])
util.printList(flags.compoundMap[flag], indent=8)
print
def help():
print "Base Flags:"
for flag in flags.basic:
print " %s: %s" % (flag, flags.descriptions[flag])
print
print "Compound Flags:"
for flag in flags.compound:
if flag == 'All':
continue
print " %s: %s" % (flag, flags.descriptions[flag])
util.printList(flags.compoundMap[flag], indent=8)
print
length, ptr = length + 1, ptr.next
# Calculate the offset
offset, prev, ptr = k % length, None, head
if offset == 0: # Remains unchanged
return head
# Find the head of the new linked list
for i in range(length - offset):
prev, ptr = ptr, ptr.next
newHead = ptr
# Link the original tail to original head
# Update new tail
tail.next, prev.next = head, None
return newHead
# 4 -> 5 -> 1 -> 2 -> 3
printList(Solution().rotateRight(initList([1, 2, 3, 4, 5]), 2))
# 2 -> 0 -> 1
printList(Solution().rotateRight(initList([0, 1, 2]), 4))
# None
printList(Solution().rotateRight(initList([]), 0))
# 1
printList(Solution().rotateRight(initList([1]), 1))
if llst1:
tail.next = llst1
elif llst2:
tail.next = llst2
return head
def mergeSort(head):
if not head or not head.next:
return head
llst1, llst2, midPrev = head, head, None
while llst1 and llst1.next:
midPrev = midPrev.next if midPrev else llst1
llst1 = llst1.next.next
midPrev.next, llst2, llst1 = None, midPrev.next, head
llst1, llst2 = mergeSort(llst1), mergeSort(llst2)
llst = mergeList(llst1, llst2)
return llst
return mergeSort(head)
# 1 -> 2 -> 3 -> 4 -> NULL
printList(Solution().sortList(initList([4, 2, 1, 3])))
# -1 -> 0 -> 3 -> 4 -> 5 -> NULL
printList(Solution().sortList(initList([-1, 5, 3, 4, 0])))
# NULL
printList(Solution().sortList(initList([])))
from solution import Solution
from util import buildSequeneces
from util import printList
if __name__ == '__main__':
sol = Solution()
l1 = buildSequeneces([1, 2, 4])
l2 = buildSequeneces([1, 3, 4])
printList(sol.mergeTwoLists(l1, l2))
l1 = buildSequeneces([])
l2 = buildSequeneces([1, 2, 5])
printList(sol.mergeTwoLists(l1, l2))
l2 = buildSequeneces([])
printList(sol.mergeTwoLists(l1, l2))
from solution import Solution
from util import buildSequeneces
from util import printList
if __name__ == '__main__':
sol = Solution()
printList(sol.rotateRight(buildSequeneces([1, 2, 3, 4, 5]), 0))
printList(sol.rotateRight(buildSequeneces([1, 2, 3, 4, 5]), 1))
printList(sol.rotateRight(buildSequeneces([1, 2, 3, 4, 5]), 2))
printList(sol.rotateRight(buildSequeneces([1, 2, 3, 4, 5]), 3))
printList(sol.rotateRight(buildSequeneces([1, 2, 3, 4, 5]), 4))
printList(sol.rotateRight(buildSequeneces([1, 2, 3, 4, 5]), 5))
printList(sol.rotateRight(buildSequeneces([]), 5))
printList(sol.rotateRight(buildSequeneces([1]), 5))
printList(sol.rotateRight(buildSequeneces([1, 2]), 1))
printList(sol.rotateRight(buildSequeneces([1, 2]), 2))
printList(sol.rotateRight(buildSequeneces([1, 2]), 3))
while l1 and l2:
if l1.val < l2.val:
if not tail:
tail, l1 = l1, l1.next
head = tail
else:
tail.next, l1 = l1, l1.next
tail = tail.next
else:
if not tail:
tail, l2 = l2, l2.next
head = tail
else:
tail.next, l2 = l2, l2.next
tail = tail.next
if l1:
tail.next = l1
elif l2:
tail.next = l2
return head
# 1 -> 1 -> 2 -> 3 -> 4 -> 4 -> NULL
printList(Solution().mergeTwoLists(initList([1, 2, 4]), initList([1, 3, 4])))
# NULL
printList(Solution().mergeTwoLists(initList([]), initList([])))
# 0 -> NULL
printList(Solution().mergeTwoLists(initList([]), initList([0])))
# node1 = curr
# curr, length = curr.next, length + 1
# node2 = head
# for _ in range(length - k):
# node2 = node2.next
# node1.val, node2.val = node2.val, node1.val
# return head
# O(n) time & O(n) space
lst, curr, idx = [], head, 1
while curr:
lst+= [curr]
curr, idx = curr.next, idx + 1
lst[k - 1].val, lst[-k].val = lst[-k].val, lst[k - 1].val
return head
# 5 -> 2 -> 3 -> 4 -> 1 -> NULL
printList(Solution().swapNodes(initList([1, 2, 3, 4, 5]), 1))
# 1 -> 4 -> 3 -> 2 -> 5 -> NULL
printList(Solution().swapNodes(initList([1, 2, 3, 4, 5]), 2))
# 1 -> 2 -> 3 -> 4 -> 5 -> NULL
printList(Solution().swapNodes(initList([1, 2, 3, 4, 5]), 3))
# 1 -> 4 -> 3 -> 2 -> 5 -> NULL
printList(Solution().swapNodes(initList([1, 2, 3, 4, 5]), 4))
# 5 -> 2 -> 3 -> 4 -> 1 -> NULL
printList(Solution().swapNodes(initList([1, 2, 3, 4, 5]), 5))
from util import ListNode
from util import buildSequeneces
from util import printList
from solution import Solution
if __name__ == '__main__':
sol = Solution()
for i in range(0, 8):
printList(sol.reverseKGroup(buildSequeneces([1, 2, 3, 4, 5]), i))
for i in range(0, 2):
printList(sol.reverseKGroup(buildSequeneces([]), i))
k = 1
for i in range(0, k + 2):
printList(sol.reverseKGroup(buildSequeneces(list(range(1, 2))), i))
sys.path = ['.', '../', '../../'] + sys.path
from util import ListNode, initList, printList
class Solution:
def removeNthFromEnd(self, head: ListNode, n: int) -> ListNode:
prev_target, target, curr, diff = None, head, head, 1
while diff < n and curr:
curr, diff = curr.next, diff + 1
while curr and curr.next:
prev_target, target, curr = target, target.next, curr.next
if prev_target:
prev_target.next = target.next
elif target:
head = head.next
else:
head = None
return head
# 1 -> 2 -> 3 -> 5 -> NULL
printList(Solution().removeNthFromEnd(initList([1, 2, 3, 4, 5]), 2))
# NULL
printList(Solution().removeNthFromEnd(initList([1]), 1))
# 1 -> NULL
printList(Solution().removeNthFromEnd(initList([1, 2]), 1))
# 2 -> NULL
printList(Solution().removeNthFromEnd(initList([1, 2]), 2))
# self.next = next
class Solution:
def addTwoNumbers(self, l1: ListNode, l2: ListNode) -> ListNode:
carry, head, tail = 0, None, None
while l1 or l2 or carry:
d1, d2 = l1.val if l1 else 0, l2.val if l2 else 0
if not head:
head = ListNode((d1 + d2 + carry) % 10)
tail = head
else:
tail.next = ListNode((d1 + d2 + carry) % 10)
tail = tail.next
carry = (d1 + d2 + carry) // 10
l1, l2 = l1.next if l1 else l1, l2.next if l2 else l2
return head
# 0 -> 1 -> NULL
ll1, ll2 = initList([5]), initList([5])
printList(Solution().addTwoNumbers(ll1, ll2))
# 1 -> 8 -> NULL
ll1, ll2 = initList([1, 8]), initList([0])
printList(Solution().addTwoNumbers(ll1, ll2))
# 0 -> 0 -> 0 -> 1 -> NULL
ll1, ll2 = initList([9, 9, 9]), initList([1])
printList(Solution().addTwoNumbers(ll1, ll2))
sys.path = ['.', '../', '../../'] + sys.path
from util import ListNode, initList, printList
class Solution:
def deleteDuplicates(self, head: ListNode) -> ListNode:
prev, curr = None, head
while curr and curr.next:
if curr.val == curr.next.val:
val = curr.val
while curr and curr.val == val:
if prev:
prev.next = curr.next
else:
head = curr.next
curr = curr.next
else:
prev, curr = curr, curr.next
return head
# 2 -> 3 -> NULL
printList(Solution().deleteDuplicates(initList([1, 1, 1, 2, 3])))
# NULL
printList(Solution().deleteDuplicates(initList([1, 1, 1])))
# 1 -> NULL
printList(Solution().deleteDuplicates(initList([1])))
from util import buildSequeneces
from util import printList
from solution import Solution
if __name__ == '__main__':
sol = Solution()
printList(sol.swapPairs(buildSequeneces([])))
printList(sol.swapPairs(buildSequeneces([1])))
printList(sol.swapPairs(buildSequeneces([1, 2])))
printList(sol.swapPairs(buildSequeneces([1, 2, 3])))
printList(sol.swapPairs(buildSequeneces([1, 2, 3, 4])))
result = sol.swapPairs(buildSequeneces([1, 2, 3, 4, 5, 6]))
printList(result)
# # O(n) time & O(n) space
# queue, ptr = [], head
# while ptr:
# queue.append(ptr)
# ptr = ptr.next
# while queue:
# node = queue.pop(0)
# node.next, ptr = ptr, node
# return ptr
# # O(n) Recursive
# if not head or not head.next:
# return head
# tail = self.reverseList(head.next)
# head.next.next, head.next = head, None
# return tail
# 5 -> 4 -> 3 -> 2 -> 1 -> NULL
printList(Solution().reverseList(initList([1, 2, 3, 4, 5])))
# NULL
printList(Solution().reverseList(initList([])))
# 1 -> NULL
printList(Solution().reverseList(initList([1])))
# 2 -> 1 -> NULL
printList(Solution().reverseList(initList([1, 2])))
def ldaa(dic, corpus, tfidf, bContentList, newUniBContentListString, topicNum):
corpus_tfidf = tfidf[corpus]
print '------------------type(corpus_tfidf):', type(corpus_tfidf)
# for i in corpus_tfidf:
# print i
lda = models.LdaModel(corpus_tfidf, id2word=dic, num_topics=topicNum)
ldaOut = lda.print_topics(topicNum)
li = 5
vec = [(0, 1), (4, 1)]
vec = dic.doc2bow(bContentList[li])
# get similarity matrix of len(bContentList) * len(bContentList)
index = similarities.MatrixSimilarity(lda[corpus])
simMatrix = []
# get the Similarity Matrix(eg: 100 * 100) of all barrages,
for bIndex in range(len(bContentList)):
vec = bContentList[bIndex]
vec_bow = dic.doc2bow(bContentList[bIndex])
vec_lda = lda[vec_bow]
sims = index[vec_lda]
# print list(enumerate(sims))
# sorted with similarity from high to low
# sims = sorted(enumerate(sims), key=lambda item: -item[1])
# print sims, len(sims), type(sims)
simMatrix.append(list(enumerate(sims)))
# eg: simMatrix[1] = [(0, 0.91061151), (1, 0.99999994), (2, 0.99999994), (3, 0.99999994), (4, 0.73748994), (5, 0.81874228)......]
# print len(simMatrix), simMatrix[1]
# sys.exit()
# print all lda topics words
# such as:
# 0.002*"合影" + 0.002*"钱" + 0.002*"撒花" + 0.002*"没" + 0.002*"完结" + 0.002*"看" + 0.002*"啊" + 0.002*"之" + 0.002*"湫" + 0.002*"一个"
# 0.002*"买" + 0.002*"第一次" + 0.002*"支持" + 0.002*"啊" + 0.002*"没" + 0.002*"完结" + 0.002*"湫" + 0.002*"国漫" + 0.002*"撒花" + 0.002*"b"
# 0.004*"第一次" + 0.003*"湫" + 0.003*"合影" + 0.003*"在" + 0.003*"存活" + 0.003*"买" + 0.003*"确认" + 0.003*"啊" + 0.003*"椿" + 0.002*"撒花"
# 0.003*"完结" + 0.003*"撒花" + 0.003*"钱" + 0.003*"合影" + 0.002*"再见" + 0.002*"没" + 0.002*"啊" + 0.002*"湫" + 0.002*"好" + 0.001*"第一次"
# 0.003*"存活" + 0.003*"确认" + 0.002*"合影" + 0.002*"没" + 0.002*"钱" + 0.002*"秋水共长天一色" + 0.002*"第一次" + 0.001*"靠" + 0.001*"也" + 0.001*"生日"
for i in ldaOut:
r = i[1].encode('utf-8')
print r
for i in ldaOut:
r = i[1].encode('utf-8')
print 'Topic', ldaOut.index(i), ':',
util.printList(rmNum(r))
# sys.exit()
print type(ldaOut[0])
print type(ldaOut[0][0])
corpus_lda = lda[corpus_tfidf]
resList = []
iii = 0
# eg: doc [(0, 0.033333333333334041), (1, 0.033333333333659149), (2, 0.03333333333337106), (3, 0.033333333333336511), (4, 0.033333333333333631), (5, 0.033333333577374141), (6, 0.033333333333333381), (7, 0.53333330176939997), (8, 0.033333333641347308), (9, 0.033333333333333388), (10, 0.033333333333333409), (11, 0.033333358397907714), (12, 0.033333333333333381), (13, 0.033333333333333368), (14, 0.033333339280269603)]
for doc in corpus_lda:
# eg: res = (3, 0.72867093662442284), res has 72% posibility to be in type 3
res = getMax(doc)
resList.append(res)
print '---type(corpus_tfidf), type(corpus_lda)', type(corpus_tfidf), type(
corpus_lda)
print '---len(resList)', len(resList)
# len = topicNum
simMatrixTopicList = []
for topicId in range(topicNum):
simMatrixTopic = [
i for i in range(len(resList)) if resList[i][0] == topicId
]
print topicId, 'topic has:', len(simMatrixTopic), 'barrage'
simMatrixTopicList.append(simMatrixTopic)
# print len(simMatrixTopic), simMatrixTopic
# without square
# # inner distance
# # sum of all similarity of i'th row
# iRow = 0.0
# num = 0
# innDisMatrix = [0.0 for i in range(topicNum)]
# for topicId in range(topicNum):
# for i in range(len(simMatrixTopicList[topicId])-1):
# for j in range(i+1, len(simMatrixTopicList[topicId])):
# # print simMatrix[simMatrixTopicList[topicId][i]][simMatrixTopicList[topicId][j]][1]
# iRow += simMatrix[simMatrixTopicList[topicId][i]][simMatrixTopicList[topicId][j]][1]
# # print topicId, 'topic, num:', num
# lenOfIRow = len(simMatrixTopicList[topicId])
# numOfIRow = (1 + lenOfIRow - 1) * (lenOfIRow - 1) / 2
# innDisMatrix[topicId] = iRow/numOfIRow
# iRow = 0.0
# print 'inner distance:', innDisMatrix
#
# aveInnDis = sum(innDisMatrix) / len(innDisMatrix)
# print 'average inner distance:', aveInnDis
#
# # external distance
# cols = topicNum
# rows = topicNum
# extDisMatrix = [[0.0 for col in range(cols)] for row in range(rows)]
# iRow = 0.0
# for topicId in range(topicNum):
# for ti2 in range(topicId+1, topicNum):
# for i in range(len(simMatrixTopicList[topicId])):
# for j in range(len(simMatrixTopicList[ti2])):
# iRow += simMatrix[simMatrixTopicList[topicId][i]][simMatrixTopicList[ti2][j]][1]
# # iRow += iRow
# # print iRow
# lenOfIRow = len(simMatrixTopicList[topicId]) * len(simMatrixTopicList[ti2])
# extDisMatrix[topicId][ti2] = iRow / float(lenOfIRow)
# iRow = 0.0
#
# print 'external distance:', extDisMatrix
#
# totExtDis = 0
# aveExtDis = 0
# num = 0
# for i in extDisMatrix:
# for j in i:
# if j != 0:
# totExtDis += j
# num += 1
# aveExtDis = totExtDis / float(num)
#
# print 'average external distance:', aveExtDis
# print 'inner/external value:', aveInnDis/aveExtDis
# within square(**2)
# inner distance
# sum of all similarity of i'th row
iRow = 0.0
num = 0
innDisMatrix = [0.0 for i in range(topicNum)]
# innDisMatrixNum[0]: the number of similarity value every topic
innDisMatrixNum = [0.0 for i in range(topicNum)]
for topicId in range(topicNum):
for i in range(len(simMatrixTopicList[topicId]) - 1):
for j in range(i + 1, len(simMatrixTopicList[topicId])):
iRow += (simMatrix[simMatrixTopicList[topicId][i]][
simMatrixTopicList[topicId][j]][1])**2
# print topicId, 'topic, num:', num
lenOfIRow = len(simMatrixTopicList[topicId])
numOfIRow = (1 + lenOfIRow - 1) * (lenOfIRow - 1) / 2
innDisMatrix[topicId] = iRow / numOfIRow
# innDisMatrixNum[topicId] = numOfIRow
iRow = 0.0
print 'inner distance:', innDisMatrix
aveInnDis = 1 / (sum(innDisMatrix) / topicNum)
print 'average inner distance:', aveInnDis
# external distance
cols = topicNum
rows = topicNum
extDisMatrix = [[0.0 for col in range(cols)] for row in range(rows)]
# extDisMatrixNum[0]: the number of similarity value every topic
# extDisMatrixNum = [[0.0 for col in range(cols)] for row in range(rows)]
iRow = 0.0
# countt = 0
for topicId in range(topicNum):
for ti2 in range(topicId + 1, topicNum):
for i in range(len(simMatrixTopicList[topicId])):
for j in range(len(simMatrixTopicList[ti2])):
iRow += (simMatrix[simMatrixTopicList[topicId][i]][
simMatrixTopicList[ti2][j]][1])**2
# countt += 1
# print iRow
iRowNum = len(simMatrixTopicList[topicId]) * len(
simMatrixTopicList[ti2])
# print 'iRowNum:', iRowNum, 'countt:', countt
extDisMatrix[topicId][ti2] = iRow / iRowNum
iRow = 0.0
# countt = 0
print 'external distance:', extDisMatrix
totExtDis = 0
aveExtDis = 0
for i in extDisMatrix:
for j in i:
totExtDis += j
extNoneZeroNum = (1 + cols - 1) * (cols - 1) / 2
aveExtDis = 1 / (totExtDis / extNoneZeroNum)
print 'average external distance:', aveExtDis
print 'inner/external value:', aveInnDis / aveExtDis
# return aveInnDis, aveExtDis
# sys.exit()
# topic possibility distribution in user profile
topicPosi = []
for topicId in range(topicNum):
posiList = [i[1] for i in resList if i[0] == topicId]
# average accuracy rate
possi = sum(posiList) / len(posiList)
topicPosi.append(possi)
# sys.exit()
fullPath = os.getcwd()
# concatenate full path
userCodeIdListFilePath = fullPath + '/data/users/' + vCid + '/userIdList.txt'
userCodeIdList = util.getUserCodeIdList(userCodeIdListFilePath)
# for i in userCodeIdList:
# print i
favTagTlist = util.getFilesOfDir(vCid)
# concatenate full path
favTagTlist = [
fullPath + '/data/users/' + vCid + '/' + tagT for tagT in favTagTlist
]
for i in favTagTlist:
print i
tagMatrix, tagVNumMatrix, userList, catAll = clustering.scanAllTags(
favTagTlist)
catNum = len(catAll)
# eg: topicDist =
# [[125. 126. 83. 18. 121. 44. 72. 0. 108. 113. 46. 66. 114. 0. 109.],
# [ 799. 785. 558. 141. 737. 286. 425. 2. 659. 611. 376. 460. 765. 0. 657.],
# [ 308. 321. 238. 48. 272. 116. 162. 0. 259. 236. 135. 173. 284. 1. 267.],
# [ 557. 540. 378. 99. 490. 215. 315. 0. 457. 424. 232. 295. 514. 0. 449.],
# [ 537. 535. 361. 86. 477. 176. 293. 0. 463. 416. 234. 297. 509. 0. 444.]]
# 音乐 动画 番剧 广告 电影 时尚 舞蹈 公告 游戏 鬼畜 娱乐 电视剧 生活 活动 科技
topicDist = np.zeros((topicNum, catNum))
# every percentage of topic
topicPercDist = np.zeros((topicNum, catNum))
topicDistNoneNum = np.zeros(topicNum)
userIdNoneNum = 0
# topic index list: [0, 1, 2, 3, 4]
topicNumList = range(topicNum)
# a list of: all users' barrage data of a topic
aTopicNewUniBContentListString = []
topicUserNumList = []
for i in topicNumList:
aTopicNewUniBContentListString.append([])
topicUserNumList.append(0)
# used to calculate the number of topicPercDist added
topicPercDistAddNum = np.zeros(topicNum)
for i in range(len(resList)):
# print i
topicId = resList[i][0]
if topicId in topicNumList:
userId = util.getUserId(newUniBContentListString[i][0],
userCodeIdList)
# print newUniBContentListString[i][0], userId
aTopicNewUniBContentListString[topicId].append(
newUniBContentListString[i])
topicUserNumList[topicId] += 1
if userId is not None:
# print userId, favTagTlist, type(favTagTlist)
res = clustering.getTagLineOfUser(tagMatrix, tagVNumMatrix,
userList, userId)
if res is not None:
tagLineOfUI, tagVNumLineOfUI = res
# userId is not in the list
else:
continue
if tagLineOfUI is not None:
# print len(tagLineOfUI), userId, tagLineOfUI
topicDist[topicId] += tagLineOfUI
# the perc distribution of tagVideo number of a user
tagVPercLineOfUI = np.around(
tagVNumLineOfUI / float(sum(tagVNumLineOfUI)), 3)
topicPercDist[topicId] += tagVPercLineOfUI
topicPercDistAddNum[topicId] += 1
else:
topicDistNoneNum += 1
else:
userIdNoneNum += 1
topicWordBListL = []
# topicWordBListLSec = []
topicWordBListL2 = []
topicWordBListL3 = []
# print Top 10 frequent words in a topic & the barrageList of the topic, in one time
for i in topicNumList:
bContentList2 = xmlDL.divideSent(aTopicNewUniBContentListString[i], 0)
wordList2 = getMostWord(bContentList2, 20)
print '------------topic', i, ':',
for j in wordList2:
print j[0],
print
top10weightActor = []
top10weightNoActor = []
# print Top 10 frequent words in a topic & the barrageList of the topic
for i in topicNumList:
print '------------topic', i, '-------------users:', topicUserNumList
# divideSent(,0) no actors' name
bContentList = xmlDL.divideSent(aTopicNewUniBContentListString[i], 0)
wordList = getMostWord(bContentList, 20)
for j in wordList:
print j[0], j[1]
for j in aTopicNewUniBContentListString[i]:
# eg: abb5230a 417.671 灵尊：哟，火柴棍
if wordList[0][0].encode('utf-8') in j[2]:
util.printList(j)
print 'wordList[0][0]', wordList[0][0]
# the index list of all barrage in topic i which contains the 1st frequent word in topic i
topicIWord1BList = [
j[1] for j in aTopicNewUniBContentListString[i]
if wordList[0][0].encode('utf-8') in j[2]
]
topicWordBListL.append(topicIWord1BList)
# second word
# topicIWord1BListSec = [j[1] for j in aTopicNewUniBContentListString[i] if wordList[1][0].encode('utf-8') in j[2]]
# topicWordBListLSec.append(topicIWord1BListSec)
# 0.002*"合影" + 0.002*"钱" + 0.002*"撒花" + 0.002*"没" + 0.002*"完结" + 0.002*"看" + 0.002*"啊" + 0.002*"之" + 0.002*"湫" + 0.002*"一个"
# "合影" + "钱" + "撒花" + "没" + .....
wordList2 = rmNum(ldaOut[i][1].encode('utf-8'))
# get the most weight word in wordList2(after deleting actors' name)
# eg: wordList2 = '''0.440*"小凡" + 0.030*"鲸鱼" + 0.018*"上线" + 0.014*"灰" + 0.013*"套路" + 0.012*"官方" + 0.010*"小痴" + 0.009*"滴血" + 0.009*"姐姐" + 0.009*"嘴"'''
# firstWord = '上线', (default firstWord is '小凡')
firstWord = wordList2[0]
for word in wordList2:
# if '小葵' in wordList2:
# firstWord = '小葵'
# top10weightNoActor.append('小葵')
# break
if word in util.getTxtList(
'data/stopWord/jiebaNewWord_Qingyunzhi.txt'):
continue
else:
firstWord = word
top10weightNoActor.append(word)
break
top10weightActor.append(wordList2[0])
# the index list of all barrage in topic i which contains the 1st frequent word(with weight) in topic i
topicIWord1BList2 = [
j[1] for j in aTopicNewUniBContentListString[i]
if firstWord in j[2]
]
topicWordBListL2.append(topicIWord1BList2)
# weight, with actors' name
topicIWord1BList3 = [
j[1] for j in aTopicNewUniBContentListString[i]
if wordList2[0] in j[2]
]
topicWordBListL3.append(topicIWord1BList3)
print 'top 10 weight word with actor:',
for i in top10weightActor:
print i,
print
print 'top 10 weight word without actor:',
for i in top10weightNoActor:
print i,
print
plt.figure(1)
plt.subplot(211)
topicWordBListL = topicWordBListL3
for i in topicWordBListL:
y = [topicWordBListL.index(i) for indexx in range(len(i))]
plt.scatter(i, y, marker='.', color='b')
# print 'len(i), len(y):', len(i), len(y), i, y
plt.plot([], marker='.', color='b', label='Most frequent words')
plt.xlim(0, )
plt.legend()
plt.xlabel('Barrage Time(s)')
plt.ylabel('Topic ID')
plt.subplot(212)
for i in topicWordBListL2:
y = [topicWordBListL2.index(i) for indexx in range(len(i))]
plt.scatter(i, y, marker='x', color='r')
plt.plot([], marker='x', color='r', label='Most weight words')
plt.xlim(0, )
plt.legend()
plt.xlabel('Barrage Time(s)')
plt.ylabel('Topic ID')
# plt.show()
print 'the num of users of different topics:', topicUserNumList
print 'the num of users who is not in userCodeIdList:', userIdNoneNum
print '-------------------------'
# print topicDist
topicDist2 = np.sum(topicDist, axis=1)
# the percentage of tag of a user
topicDist3 = np.transpose(np.transpose(topicDist) / np.float16(topicDist2))
print topicDist3, '\n'
for i in range(len(topicPercDist)):
for j in range(len(topicPercDist[i])):
topicPercDist[i][j] = topicPercDist[i][j] / topicPercDistAddNum[i]
# topicPercDist = topicPercDist/topicPercDistAddNum
print 'topicPercDist, topicPercDist[1][1]:', topicPercDist, topicPercDist[
1][1]
np.savetxt('topicDist.txt', topicDist)
np.savetxt('topicPercDist.txt', topicPercDist)
colorList = ['b', 'c', 'g', 'k', 'm', 'r', 'y']
plt.figure(5)
for i in range(len(topicPercDist)):
plt.plot(topicPercDist[i], colorList[i])
plt.xlabel = u'用户收藏视频主题类型'
plt.ylabel = u'用户收藏视频主题占比（各主题视频数量/所有主题视频数量）'
plt.show()
print topicNum, "topics possibility average value:", topicPosi, sum(
topicPosi) / len(topicPosi)
resIndexList = [i[0] for i in resList]
resTypeList = list(set(resIndexList))
# number of type index
resTCountList = []
# barrage sequence number of type index
indexList = []
for index in resTypeList:
resTCountList.append(resIndexList.count(index))
indexList.append([i for i, v in enumerate(resIndexList) if v == index])
# print resTCountList
# print indexList[0]
# type 0
print 'all barrage comments of type 000000000000000------------'
# for i in indexList[0]:
# print uniBContentList[i][-1]
plt.xlabel("Barrage Type")
plt.ylabel("Barrage Number")
plt.plot(resTCountList, 'r-')
# plt.show()
# return 1/aveInnDis, 1/aveExtDis
return aveInnDis, aveExtDis
mid.next = reversed_tail
reversed_tail = mid
mid = nxt
# Merge the first half and the reversed second half of the list
pre, curr = None, head
while curr and reversed_tail:
nxt_front, nxt_tail = curr.next, reversed_tail.next
pre = curr.next = reversed_tail
reversed_tail.next = nxt_front
curr, reversed_tail = nxt_front, nxt_tail
if reversed_tail:
pre.next = reversed_tail
llst = initList([1, 2, 3, 4])
Solution().reorderList(llst)
printList(llst)
llst = initList([1, 2, 3, 4, 5])
Solution().reorderList(llst)
printList(llst)
llst = initList([1])
Solution().reorderList(llst)
printList(llst)
llst = initList([1, 2])
Solution().reorderList(llst)
printList(llst)
"""
from util import ListNode, initList, printList
# Definition for singly-linked list.
# class ListNode:
# def __init__(self, val = 0, next = None):
# self.val = val
# self.next = next
class Solution:
def removeElements(self, head: ListNode, val: int) -> ListNode:
prev, curr = None, head
while curr:
if curr.val == val:
if curr == head:
head = head.next
prev, curr = None, head
continue
prev.next = curr.next
curr = curr.next
continue
prev, curr = curr, curr.next
return head
printList(Solution().removeElements(initList([1, 2, 6, 3, 4, 5, 6]), 6)) # 1 -> 2 -> 3 -> 4 -> 5
printList(Solution().removeElements(initList([6, 6, 6]), 6)) # (None)
printList(Solution().removeElements(initList([1]), 1)) # (None)
printList(Solution().removeElements(initList([1, 2, 2, 1]), 2)) # 1 -> 1
import sys
sys.path = sys.path = ['.', '../', '../../'] + sys.path
from util import ListNode, initList, printList
class Solution:
def insertionSortList(self, head: ListNode) -> ListNode:
sortedList = None
while head:
ptr, head = head, head.next
prev, curr = None, sortedList
while curr and ptr.val > curr.val:
prev, curr = curr, curr.next
if prev:
ptr.next = prev.next
prev.next = ptr
elif curr:
ptr.next = sortedList
sortedList = ptr
else:
ptr.next = None
sortedList = ptr
return sortedList
# 1 -> 2 -> 3 -> 4 -> NULL
printList(Solution().insertionSortList(initList([4, 2, 1, 3])))
# -1 -> 0 -> 3 -> 4 -> 5 -> NULL
printList(Solution().insertionSortList(initList([-1, 5, 3, 4, 0])))
return head
# # O(n) time & O(n) space
# head, stack1, stack2, carry = None, [], [], 0
# while l1 or l2:
# stack1 += [l1.val] if l1 else []
# stack2 += [l2.val] if l2 else []
# l1 = l1.next if l1 else l1
# l2 = l2.next if l2 else l2
# while stack1 or stack2:
# num = carry
# num += stack1.pop() if stack1 else 0
# num += stack2.pop() if stack2 else 0
# head, carry = ListNode(num % 10, head), num // 10
# head = ListNode(carry, head) if carry else head
# return head
# 7 -> 8 -> 0 -> 7 -> NULL
printList(Solution().addTwoNumbers(initList([7, 2, 4, 3]), initList([5, 6,
4])))
# 1 -> 0 -> NULL
printList(Solution().addTwoNumbers(initList([5]), initList([5])))
# 5 -> NULL
printList(Solution().addTwoNumbers(initList([]), initList([5])))
# NULL
printList(Solution().addTwoNumbers(initList([]), initList([])))
