def searchDisease(M_lil, M_csc, queryString, top=20):
"""
This function is still a work in progress..
"""
sanitizer = TextCleaner.sanitizeString()
queryString = sanitizer.sub(' ', queryString)
# OPTIONAL:
# Stem the information
if _stemmer:
# Get the regex pattern that sanitizeses information and sanitize it
# Stem the information
queryString = FilterInterface.porterStemmer(queryString)
# CHOOSE HEURISTIC:
# Search-heuristic used to retrieve the list of results
if _cosineMeasure:
results = SearchInterface.sumMeasure(M_lil, M_csc, queryString)
else:
results = SearchInterface.sumMeasure(M_lil, M_csc, queryString)
# Sort the results and reverse to get the highest score first
results.sort()
results.reverse()
resultDic = {}
for item in results[:top]:
pmid = item[1]
label = _labelHash[pmid]
resultDic[label] = item[0]
resultList = sorted(resultDic.items(), key=lambda(k, v):(v, k), reverse=True)
return resultList[:20]
def search(M_lil, M_csc, queryString, top=20):
"""
This function is still a work in progress..
"""
sanitizer = TextCleaner.sanitizeString()
queryString = sanitizer.sub(' ', queryString)
# OPTIONAL:
# Stem the information
if _stemmer:
# Get the regex pattern that sanitizeses information and sanitize it
# Stem the information
queryString = FilterInterface.porterStemmer(queryString)
# CHOOSE HEURISTIC:
# Search-heuristic used to retrieve the list of results
if _cosineMeasure:
results = SearchInterface.cosineMeasure(M_lil, M_csc, queryString)
else:
results = SearchInterface.sumMeasure(M_lil, M_csc, queryString)
# Sort the results and reverse to get the highest score first
results.sort()
results.reverse()
# ###########################################################################
# ### For the term-doc matrix: ##############################################
# ###########
# # 1: Mean #
# ###########
# # Get the sum cosine score the labels
# ## (normDic counts the number of times a label has been summed)
resultDic1 = {}
normDic1 = {}
for item in results[:top]:
pmid = item[1]
# Get the labels linked to the PMID
## (Several labels can be linked to one PMID)
labels = _labelHash[pmid]
for label in labels:
try:
resultDic1[label] += item[0]
normDic1[label] += 1
except:
resultDic1[label] = item[0]
normDic1[label] = 1
# #############
# # 2: Median #
# #############
# # Get the median cosine score of the labels
# ## (normDic counts the number of times a label has been summed)
resultDicList2 = {}
normDic2 = {}
for item in results[:top]:
pmid = item[1]
# Get the labels linked to the PMID
## (Several labels can be linked to one PMID)
labels = _labelHash[pmid]
for label in labels:
try:
resultDicList2[label].append(item[0])
normDic2[label] += 1
except:
resultDicList2[label] = []
resultDicList2[label].append(item[0])
normDic2[label] = 1
resultDic2 = {}
for label in resultDicList2.keys():
labelList = resultDicList2[label]
numOfScores = len(labelList)
if numOfScores > 2:
medianIndex = numOfScores / 2
else:
medianIndex = 0
resultDic2[label] = sorted(labelList)[medianIndex]
# ##########
# # 3: Max #
# ##########
# # Get the max cosine score of labels
# ## (normDic counts the number of times a label has been summed)
resultDicList3 = {}
normDic3 = {}
for item in results[:top]:
pmid = item[1]
# Get the labels linked to the PMID
## (Several labels can be linked to one PMID)
labels = _labelHash[pmid]
for label in labels:
try:
resultDicList3[label].append(item[0])
normDic3[label] += 1
except:
resultDicList3[label] = []
resultDicList3[label].append(item[0])
normDic3[label] = 1
resultDic3 = {}
for label in resultDicList3.keys():
labelList = resultDicList3[label]
resultDic3[label] = max(labelList)
# # Normalize the summed labels
#for label in resultDic1.keys():
# resultDic1[label]/=normDic1[label]
#for label in resultDic2.keys():
# resultDic2[label]/=normDic2[label]
#for label in resultDic3.keys():
# resultDic3[label]/=normDic3[label]
###############################################################################
###################################
####### return pmid results #######
# Reverse and sort the concensus list
resultList_mean = sorted(resultDic1.items(), key=lambda(k, v):(v, k), reverse=True)
resultList_median = sorted(resultDic2.items(), key=lambda(k, v):(v, k), reverse=True)
resultList_max = sorted(resultDic3.items(), key=lambda(k, v):(v, k), reverse=True)
return [resultList_mean, resultList_median, resultList_max]
