def ns_qtspr():
# get the query-based pagerank result
qtspr_mtx = qts_pagerank.online_tspr()
# get the indri file names
indri_names = file_scanner()
# write the ranking result into txt file
f = open('rank/ns_qtspr_rank.txt', 'w')
query_count = -1
for cur_num in sorted(indri_names):
query_count += 1
query_id = indri_names[cur_num][0]
file_name = indri_names[cur_num][1]
# doc id in the current indri file
doc_id = doc_extracter(file_name)
# sort by descending order
qtspr_score = np.argsort(qtspr_mtx[query_count][doc_id])[::-1].tolist()
doc_id_arr = np.array(doc_id)
qtspr_rank = doc_id_arr[qtspr_score]
rank_num = 0
for idx in qtspr_rank:
rank_num += 1
f.write("{} Q0 {} {} {} run-1\n".format(
query_id, idx + 1, rank_num, qtspr_mtx[query_count][idx]))
f.close()
print "No-search QTSPR ranking finished." + '\n'
def ws_qtspr():
# get the query-based pagerank result
qtspr_mtx = qts_pagerank.online_tspr()
# get the indri file names
indri_names = file_scanner()
# write the ranking result into txt file
f = open('rank/ws_qtspr_rank.txt', 'w')
query_count = -1
for cur_num in sorted(indri_names):
query_count += 1
query_id = indri_names[cur_num][0]
file_name = indri_names[cur_num][1]
# doc id in the current indri file
doc_id = doc_extracter(file_name)
# normalize intri score for each doc
indri_score = score_extracter(file_name)
indri_score_pos = np.power(math.e, indri_score)
# transform to all positive value
indri_norm = [float(i)/sum(indri_score_pos) for i in indri_score_pos]
# normalize pagerank value
qtspr_value = qtspr_mtx[query_count][doc_id]
qtspr_norm = [float(i)/sum(qtspr_value) for i in qtspr_value]
# combine indri and pagerank score
ws_score = map(add, np.multiply(indri_norm, 0.95), np.multiply(qtspr_norm, 0.05))
# sort by descending order
qtspr_score = np.argsort(ws_score)[::-1].tolist()
doc_id_arr = np.array(doc_id)
qtspr_rank = doc_id_arr[qtspr_score]
rank_num = 0
for idx in qtspr_rank:
rank_num += 1
f.write("{} Q0 {} {} {} run-1\n".format(query_id, idx + 1, rank_num, ws_score[doc_id.index(idx)]))
f.close()
print "Weighted Sum Query-based TSPR ranking finished." + '\n'
def cm_qtspr():
# get the query-based pagerank result
qtspr_mtx = qts_pagerank.online_tspr()
# get the indri file names
indri_names = file_scanner()
# write the ranking result into txt file
f = open('rank/cm_qtspr_rank.txt', 'w')
query_count = -1
for cur_num in sorted(indri_names):
query_count += 1
query_id = indri_names[cur_num][0]
file_name = indri_names[cur_num][1]
# doc id in the current indri file
doc_id = doc_extracter(file_name)
doc_num = len(doc_id)
# normalize intri score for each doc
indri_score = score_extracter(file_name)
indri_score_pos = np.power(math.e, indri_score)
# transform to all positive value
indri_norm = [float(i)/sum(indri_score_pos) for i in indri_score_pos]
# normalize pagerank value
qtspr_value = qtspr_mtx[query_count][doc_id]
qtspr_norm = [float(i)/sum(qtspr_value) for i in qtspr_value]
# use custom method to combine
mu_list = np.arange(0.86, 0.96, 0.1 / doc_num)[::-1]
decay_list = np.arange(0.65, 1.0, 0.35 / doc_num)
mu2_list = cosine_inter(mu_list)
mu3_list = np.multiply(np.subtract(1.0, mu2_list), decay_list)
# TODO: change the pagerank score to be penalty
# ws_score = map(add, np.multiply(indri_norm, mu2_list), np.multiply(qtspr_norm, np.subtract(1.0, mu2_list)))
ws_score = np.subtract(np.multiply(indri_norm, mu2_list), np.multiply(qtspr_norm, mu3_list))
# sort by descending order
qtspr_score = np.argsort(ws_score)[::-1].tolist()
doc_id_arr = np.array(doc_id)
qtspr_rank = doc_id_arr[qtspr_score]
rank_num = 0
for idx in qtspr_rank:
rank_num += 1
f.write("{} Q0 {} {} {} run-1\n".format(query_id, idx + 1, rank_num, ws_score[doc_id.index(idx)]))
f.close()
print "Custom method query-based TSPR ranking finished." + '\n'
def ns_qtspr():
# get the query-based pagerank result
qtspr_mtx = qts_pagerank.online_tspr()
# get the indri file names
indri_names = file_scanner()
# write the ranking result into txt file
f = open('rank/ns_qtspr_rank.txt', 'w')
query_count = -1
for cur_num in sorted(indri_names):
query_count += 1
query_id = indri_names[cur_num][0]
file_name = indri_names[cur_num][1]
# doc id in the current indri file
doc_id = doc_extracter(file_name)
# sort by descending order
qtspr_score = np.argsort(qtspr_mtx[query_count][doc_id])[::-1].tolist()
doc_id_arr = np.array(doc_id)
qtspr_rank = doc_id_arr[qtspr_score]
rank_num = 0
for idx in qtspr_rank:
rank_num += 1
f.write("{} Q0 {} {} {} run-1\n".format(query_id, idx + 1, rank_num, qtspr_mtx[query_count][idx]))
f.close()
print "No-search QTSPR ranking finished." + '\n'