def predictDaysProbDens(kdeDict, maxDay):
daysProbDens = {}
daysList = [i for i in range(0, maxDay + 1)]
for key in kdeDict.keys():
probDens = prediction(kdeDict[key], daysList)
daysProbDens[key] = probDens
return daysProbDens
def dtfWeightingT(queriesEpoch, tweetsEpoch, kdeQwordDict, qid, qword, docId, wordsIndex, docsLength, avgDocsLength, k1, b):
kde = kdeQwordDict[qid + '_' + qword]
queryEpoch = queriesEpoch[qid]
tweetEpoch = tweetsEpoch[docId]
if queryEpoch >= tweetEpoch:
timeSpan = getTimeSpan(queryEpoch, tweetEpoch )
probDens = prediction(kde, [timeSpan])
probDen = probDens[0]
count = wordsIndex[qword][docId]
docLength = docsLength[docId]
numerator = (k1 + 1) * count * probDen
denominator = k1 * (1 - b + b * docLength / avgDocsLength) + count * probDen
dtf = 1.0 * numerator / denominator
else:
dtf = 0
return dtf
maxDay = 16 # 2011,2012: 16 ; 2013, 2014: 58
daysList = [i for i in range(0, maxDay + 1)]
queryTimeFile = 'E:\\eclipse\\QueryExpansion\\data\\QueryTime\\' + year + '.MBid_query_time.txt'
tweetsEpochFile = 'E:\\eclipse\\TemporalRetrieval\\data\\pickle_data\\tweetsEpoch\\tweetsEpoch_'+ year + '.pkl'
qrelFile = 'E:\\eclipse\\QueryExpansion\\data\\qrels\\' + 'qrels.microblog' + year + '_new.txt'
kdePrfTimeFile ='E:\\eclipse\\TemporalRetrieval\\data\\pickle_data\\KDE\\' + year + '\\kde_prf' + str(topN) +'_' + year + '.pkl'
kdeDict = getPickleData(kdePrfTimeFile)
queriesEpoch = getQueriesEpoch(queryTimeFile, year)
tweetsEpoch = getPickleData(tweetsEpochFile)
relevantResults = relevantGet(qrelFile)
relevantTimeSpan = getResultsTimeSpan(relevantResults, tweetsEpoch, queriesEpoch)
x1 = np.array(daysList, dtype=np.float)
for qid in kdeDict.keys():
probDens = prediction(kdeDict[qid], x1)
y1 = probDens
drawHistLine(relevantTimeSpan[qid], x1, y1, maxDay, qid)
figPath = 'E:\eclipse\TemporalRetrieval\data\img\\' + qid + '.png'
plt.savefig(figPath)
plt.close()
print 'draw for ' + qid
