def irbo(topics, weight=0.9, topk=10):
"""
compute the inverted rank-biased overlap
Parameters
----------
topics: a list of lists of words
weight: p (float), default 1.0: Weight of each
agreement at depth d:p**(d-1). When set
to 1.0, there is no weight, the rbo returns
to average overlap.
topk: top k words on which the topic diversity
will be computed
Returns
-------
irbo : score of the rank biased overlap over the topics
"""
if topk > len(topics[0]):
raise Exception('Words in topics are less than topk')
else:
collect = []
for list1, list2 in combinations(topics, 2):
word2index = get_word2index(list1, list2)
indexed_list1 = [word2index[word] for word in list1]
indexed_list2 = [word2index[word] for word in list2]
rbo_val = rbo(indexed_list1[:topk], indexed_list2[:topk], p=weight)[2]
collect.append(rbo_val)
return 1 - np.mean(collect)
def calc_rbo(a, b, p, count):
scores = rbo(a, b, p)
min = scores['min']
res = scores['res']
ext = scores['ext']
Z = ext / sqrt((2 * (2 * count + 5)) / (9 * count * (count - 1)))
p_value = scipy.stats.norm.sf(abs(Z)) * 2
return ext, p_value
def compute_rank_biased_overlap(ranking_A, ranking_B, rbo_parameter=0.99):
rbo_output = rbo(ranking_A, ranking_B, p=rbo_parameter)
rbo_lower_bound = rbo_output.min
rbo_residual = rbo_output.res
rbo_estimate = rbo_output.ext
reference_overlap = average_overlap(ranking_A, ranking_B)
print('Rank-biased overlap estimate: {:.4f}'.format(rbo_estimate))
print('Average overlap = {:.4f}'.format(reference_overlap))
return rbo_estimate, reference_overlap
def main():
args = parse_args()
p = args.p
lines1 = args.file1.readlines()
lines2 = args.file2.readlines()
run1 = parse_run(lines1)
run2 = parse_run(lines2)
queries = list(run1.keys() & run2.keys())
try:
queries.sort(key=int)
except ValueError:
queries.sort()
results = []
print('qno,intersection,union,p,min,res,ext')
for q in queries:
# print(run1[q])
# print(run2[q])
# return
result = rbo.rbo(run1[q], run2[q], p)
overlap = len(set(run1[q]) & set(run2[q]))
total = len(set(run1[q]) | set(run2[q]))
current = {
'qno': q,
'intersection': overlap,
'union': total,
'p': p,
'min': result['min'],
'res': result['res'],
'ext': result['ext']
}
results.append(current)
print('{},{},{},{},{:f},{:f},{:f}'.format(
q, overlap, total, p, result['min'], result['res'], result['ext']))
min_mean = np.mean([r['min'] for r in results])
res_mean = np.mean([r['res'] for r in results])
ext_mean = np.mean([r['ext'] for r in results])
overlap_mean = np.mean([r['intersection'] for r in results])
total_mean = np.mean([r['union'] for r in results])
print('{},{},{},{},{:f},{:f},{:f}'.format('mean', overlap_mean, total_mean,
p, min_mean, res_mean, ext_mean))
return results
experiment = read_list(
"/home/gentoo/src/similarity/test_strategies/ex_vs_ex_experiment/expression.csv",
count)
mean = read_list(
"/home/gentoo/src/similarity/test_strategies/ex_vs_ex_gene_mean/expression.csv",
count)
max = read_list(
"/home/gentoo/src/similarity/test_strategies/ex_vs_ex_gene_max/expression.csv",
count)
abi = read_list2("ABI-correlation-Znfx1-69524632.csv", count)
print(experiment, mean, max, abi)
print("exp", "mean")
re = rbo(experiment, mean, 0.9)
print(re)
print("exp", "max")
re = rbo(experiment, max, 0.9)
print(re)
print("mean", "max")
re = rbo(mean, max, 0.9)
print(re)
print("ABI", "exp")
re = rbo(abi, experiment, 0.9)
print(re)
print("ABI", "mean")
re = rbo(abi, mean, 0.9)
ranks.sort(reverse=True)
vector = []
if not topK or topK > len(ranks):
topK = len(ranks)
i = 0
while i < topK:
rank = ranks[i]
vector.append(set(myMap[rank]))
i += 1
return vector
if __name__ == "__main__":
topK = None
if len(sys.argv) == 4:
topK = int(sys.argv[3])
v1 = getVector(sys.argv[1], topK)
v2 = getVector(sys.argv[2], topK)
result = rbo(v1, v2, p=0.8)
print(str(result["ext"]))
# print("res " + str(result["res"]))
# print("min " + str(result["min"]))
ind = max.index(elem)
max_rank.append([mean_rank[ind][0], elem])
except ValueError:
ind = -1
max_rank.append([1, elem])
score_max = [x[0] for x in max_rank]
score_mean = [x[0] for x in mean_rank]
print(score_max)
print(score_mean)
s, p = wilcoxon(score_max, score_mean, zero_method="pratt")
spear
print("wilcoxon")
print(p)
cor, p = weightedtau(score_max, score_mean)
print("weighted tau")
print(cor)
#print(experiment,mean,max, abi)
print("mean", "max")
re = rbo(mean, max, 0.9)
print(re)
cor, p = spearmanr(mean, max)
print(cor, p)
Mef2c_667 = read_list("ABI-correlation-Mef2c-667.csv",200)
Znfx1 = read_list("ABI-correlation-Znfx1-69524632.csv",200)
#top 1 hit of Mef2c queried, should be really close to Mef2c as a way to compare
Nlk = read_list("ABI-correlation-Nlk-76085742.csv",200)
Mef2c_668 = read_list("ABI-correlation-Mef2c-668.csv",200)
Stx1a = read_list("ABI-correlation-Stx1a-2645.csv",200)
Mef2c_79567505 = read_list("ABI-correlation-Mef2c-79567505.csv",200)
print("Mef2c_667","Mef2c_667")
re = rbo(Mef2c_667,Mef2c_667,0.9)
print(re)
print("Mef2c_667","Nlk")
re = rbo(Mef2c_667,Nlk,0.9)
print(re)
print("Mef2c_667","Mef2c_668")
re = rbo(Mef2c_667,Mef2c_668,0.9)
print(re)
print("Mef2c_667","Mef2c_79567505")
re = rbo(Mef2c_667,Mef2c_79567505,0.9)
print(re)
