def xQuAD(basepath, topicID, filename, cutoff=50, method="mine"):
"""
return a ranking list using the framework of xQuAD.
"""
document_selected = []
out_file = open(basepath + "rank/" + topicID + "/" + filename, "w")
runlist_file = open(basepath + "rank/" + topicID + "/runlist", "w")
print >> runlist_file, "xquad_mine_less"
print >> runlist_file, "xquad_mine_all"
print >> runlist_file, "xquad_standard_less"
print >> runlist_file, "xquad_standard_all"
runlist_file.close()
documents, subtopicID_word, query_prob, document_term_frequency, average_document_len, word2id_weight, topic_words = data_preprocessing_xquad(
basepath, topicID, method)
subtopic_word = {}
keys = subtopicID_word.keys()
keys.sort()
for key in keys:
if filename == "xquad_mine_less" or filename == "xquad_standard_less":
if key == keys[-1]: continue
if key == keys[-2]: continue
# if key == 3:continue
if not subtopic_word.has_key(key):
subtopic_word[key] = subtopicID_word[key]
# print len(subtopicID_word.keys()),len(subtopic_word.keys())
if filename == "xquad_mine_less" or filename == "xquad_standard_less":
prob_sum = 0.0
for key in query_prob.keys():
if key == keys[-1]:
query_prob[key] = 0
elif key == keys[-2] and len(query_prob.keys()) > 3:
query_prob[key] = 0
else:
prob_sum += query_prob[key]
for key in query_prob.keys():
# print key,query_prob[key]
query_prob[key] /= prob_sum
document_subtopic_rel, rel_subtopic_ave = document_subtopic_relevance(
subtopic_word, documents, average_document_len, topic_words,
document_term_frequency)
filem = open("middle/" + topicID + "div", "w")
#iteratively selected the best document to build ranking list
for i in range(cutoff):
print topicID, "%2d-th best document." % (i + 1)
best_document = select_best_document(document_subtopic_rel,
rel_subtopic_ave, query_prob,
subtopic_word, document_selected,
filem)
document_selected.append(best_document)
if len(document_selected) == len(documents) - 1:
# all document in ranking list
break
# print the ranking result to the evaluation files
for index, document in enumerate(document_selected):
documentID = document.get_id()
document_rank = index + 1
document_score = document.get_ranking_score()
print >> out_file, topicID + " Q0 " + documentID + " " + str(
document_rank) + " " + str(document_score) + " TESTRUN"
out_file.close()
def xQuAD(basepath,topicID,cutoff= 50):
"""
return a ranking list using the framework of xQuAD.
"""
document_selected =[] #docs ranking list
out_file = open(basepath+"rank/"+topicID+"/xquad_result","w")
runlist_file = open(basepath+"rank/"+topicID+"/runlist","w")
print >>runlist_file,"xquad_result"
runlist_file.close()
documents,subtopicID_word,query,document_term_frequency,average_document_len,word2id_weight = data_preprocessing_xquad(basepath,topicID)
sid_doc_related_probility = similarity_computing(documents,subtopicID_word,average_document_len,query,document_term_frequency)
#iteratively selected the best document to build ranking list
for i in range(cutoff):
print "%s-th best document."%i
best_document = best_document_select(documents,subtopicID_word,query,document_term_frequency,average_document_len,word2id_weight,document_selected,sid_doc_related_probility)
document_selected.append(best_document)
if len(document_selected) == len(documents):
# all document in ranking list
break
# print the ranking result to the evaluation files
for index,document in enumerate(document_selected):
documentID = document.get_id()
document_rank = index+1
document_score = document.get_ranking_score()
print >>out_file,topicID +" Q0 "+documentID+" "+str(document_rank) +" "+str(document_score)+ " TESTRUN"
out_file.close()
# call the evaluation function to evaluate the run result
r = call_eval_for_result(basepath,topicID,10)
def xQuAD(basepath,topicID,filename,cutoff= 50,method="mine"):
"""
return a ranking list using the framework of xQuAD.
"""
document_selected =[]
out_file = open(basepath+"rank/"+topicID+"/"+filename,"w")
runlist_file = open(basepath+"rank/"+topicID+"/runlist","w")
print >>runlist_file,"xquad_mine_less"
print >>runlist_file,"xquad_mine_all"
print >>runlist_file,"xquad_standard_less"
print >>runlist_file,"xquad_standard_all"
runlist_file.close()
documents,subtopicID_word,query_prob,document_term_frequency,average_document_len,word2id_weight,topic_words = data_preprocessing_xquad(basepath,topicID,method)
subtopic_word={}
keys = subtopicID_word.keys()
keys.sort()
for key in keys:
if filename == "xquad_mine_less" or filename =="xquad_standard_less":
if key==keys[-1]:continue
if key==keys[-2]:continue
# if key == 3:continue
if not subtopic_word.has_key(key):
subtopic_word[key] = subtopicID_word[key]
# print len(subtopicID_word.keys()),len(subtopic_word.keys())
if filename == "xquad_mine_less" or filename =="xquad_standard_less":
prob_sum = 0.0
for key in query_prob.keys():
if key == keys[-1]:
query_prob[key]=0
elif key == keys[-2] and len(query_prob.keys())>3:
query_prob[key]=0
else:
prob_sum+=query_prob[key]
for key in query_prob.keys():
# print key,query_prob[key]
query_prob[key] /= prob_sum
document_subtopic_rel,rel_subtopic_ave = document_subtopic_relevance(subtopic_word,documents,average_document_len,topic_words,document_term_frequency)
filem= open("middle/"+topicID+"div","w")
#iteratively selected the best document to build ranking list
for i in range(cutoff):
print topicID,"%2d-th best document."%(i+1)
best_document = select_best_document(document_subtopic_rel,rel_subtopic_ave,query_prob,subtopic_word,document_selected,filem)
document_selected.append(best_document)
if len(document_selected) == len(documents)-1:
# all document in ranking list
break
# print the ranking result to the evaluation files
for index,document in enumerate(document_selected):
documentID = document.get_id()
document_rank = index+1
document_score = document.get_ranking_score()
print >>out_file,topicID +" Q0 "+documentID+" "+str(document_rank) +" "+str(document_score)+ " TESTRUN"
out_file.close()
def xQuAD(basepath, topicID, cutoff=50):
"""
return a ranking list using the framework of xQuAD.
"""
document_selected = [] #docs ranking list
out_file = open(basepath + "rank/" + topicID + "/xquad_result", "w")
runlist_file = open(basepath + "rank/" + topicID + "/runlist", "w")
print >> runlist_file, "xquad_result"
runlist_file.close()
documents, subtopicID_word, query, document_term_frequency, average_document_len, word2id_weight = data_preprocessing_xquad(
basepath, topicID)
sid_doc_related_probility = similarity_computing(documents,
subtopicID_word,
average_document_len,
query,
document_term_frequency)
#iteratively selected the best document to build ranking list
for i in range(cutoff):
print "%s-th best document." % i
best_document = best_document_select(documents, subtopicID_word, query,
document_term_frequency,
average_document_len,
word2id_weight, document_selected,
sid_doc_related_probility)
document_selected.append(best_document)
if len(document_selected) == len(documents):
# all document in ranking list
break
# print the ranking result to the evaluation files
for index, document in enumerate(document_selected):
documentID = document.get_id()
document_rank = index + 1
document_score = document.get_ranking_score()
print >> out_file, topicID + " Q0 " + documentID + " " + str(
document_rank) + " " + str(document_score) + " TESTRUN"
out_file.close()
# call the evaluation function to evaluate the run result
r = call_eval_for_result(basepath, topicID, 10)