def log_likelihood(self, tau, kappa):
estimates = self.precompute_likelihood_estimates(tau, kappa)
if var(estimates) > 0:
logging.info("Performing exponential Russian Roulette on %d precomputed samples" %
len(estimates))
rr_ified = self.rr_instance.exponential(estimates)
return rr_ified
else:
logging.warn("Russian Roulette on one estimate not possible. Returning the estimate")
return mean(estimates)
def ciRegenerative(N):
sim = simulateLindleyEfficient(lam, mu, N)
# Now we're going to split the simulation results vector every time we encounter
# an ampty system (i.e. a waiting time of zero)
idx = where(sim == 0)[0] # the positions of the zeros
sa = split(sim, idx) # split the list into sub-lists
Yi = [sum(x) for x in sa] # the sum of the waiting times in each sub-list
Ni = [len(x) for x in sa] # the number of waiting times in each sub-list
M = len(Yi) # the number of sub-lists
Yavg = mean(Yi) # The average of the sums of the waiting times
Navg = mean(Ni) # the mean number of waiting times of the sub-lists
Wavg = Yavg / Navg # The overall mean waiting time
cv = cov(
Yi, Ni
)[0,
1] # sample covariance is element at (0, 1) or (1, 0) of the covariance matrix
sV2 = var(Yi) + Wavg**2 * var(Ni) - 2 * Wavg * cv
print(sV2)
ci = Wavg - 1.96 * sqrt(sV2 / M) / Navg, Wavg + 1.96 * sqrt(sV2 / M) / Navg
return (ci)
def ciBatchMeans(M, N, k):
sim = simulateLindleyEfficient(lam, mu, M * N + k)
# throw away the first k observations, and divide the rest into
# subruns of length N each
run = sim[k:(M * N + k)]
p = reshape(run, (M, N))
sample = mean(p, axis=0) # take row means
meanW = mean(sample)
varW = var(sample)
ci = meanW - 1.96 * sqrt(varW / M), meanW + 1.96 * sqrt(varW / M)
return ci
print(test_1)
#--------------------↑前六列测试数据----------------------
p_0_pre = diff_0 * test_1
print("前六列为'否'各概率:")
print(p_0_pre)
print("前六列为'是'各概率:")
p_1_pre = diff_1 * test_1
print(p_1_pre)
#--------------------↑前六列概率计算----------------------
print("val0： （存放'否'类中后两列密度和含糖率的数据）")
print(val0)
print("val1： （存放'是'类中后两列密度和含糖率的数据）")
print(val1)
mean0 = np.array([mean(val0[0]), mean(val0[1])]) #两个数 分别为0(否)类 密度和含糖率的均值
mean1 = np.array([mean(val1[0]), mean(val1[1])]) #两个数 分别为1(是)类 密度和含糖率的均值
var0 = np.array([var(val0[0]), var(val0[1])]) #两个数 分别为0(否)类 密度和含糖率的方差
var1 = np.array([var(val1[0]), var(val1[1])]) #两个数 分别为1(是)类 密度和含糖率的方差
#--------------------↑后两列均值方差计算----------------------
def gaussian(mean, var, x):
res = 1 / sqrt(2 * 3.14 * var) * np.exp(-(mean - x)**2 / 2 * var)
return res
p_0_pro = gaussian(mean0[0], var0[0], 0.697) + gaussian(
mean0[1], var0[1], 0.460)
print(p_0_pro)
p_1_pro = gaussian(mean1[0], var1[0], 0.697) + gaussian(
mean1[1], var1[1], 0.460)
print(p_1_pro)
def detect_insertions( h0_mean, h1_mean, h2_mean, heads_per_base, inputf, reads_per_base, tails_per_base):
fp_scores, tp_scores = [], []
not_found_insertions = json.load(open(data_d('subject_genome.fa.alu_positions.json')))
if not not_found_insertions:
return
pers_alu_info = copy.deepcopy(not_found_insertions)
total_alus = count_alus(not_found_insertions)
false_positives = []
skip_until = -1
window = []
for col in inputf.pileup():
if col.pos < skip_until:
continue
if len(window) == WIN_LENGTH:
window = window[1:WIN_LENGTH]
window.append(site(col))
# if col.pos < 36265890:
# continue
if boundary(window) and enough_coverage(window, reads_per_base):
reason = potential_ALU_insert(window, heads_per_base, tails_per_base)
if reason:
spanning = window_stats(window)
if spanning >= h0_mean:
continue
# hyp, _ = min((None, h0_mean), ('heterozygous', h1_mean), ('homozygous', h2_mean),
# key = lambda (hyp, mean): abs(spanning - mean))
hyp, _ = min(('heterozygous', h1_mean), ('homozygous', h2_mean),
key = lambda (hyp, mean): abs(spanning - mean))
if hyp:
chrom = inputf.getrname(col.tid)
window = []
skip_until = col.pos + RLEN
fp = True
for hap_no, haplotype_positions in enumerate(pers_alu_info[chrom]):
for inserted in haplotype_positions:
if abs(inserted['ref_pos'] - col.pos) < 300:
if inserted in not_found_insertions[chrom][hap_no]: not_found_insertions[chrom][
hap_no].remove(inserted)
fp = False
if fp:
false_positives.append([hyp, spanning, chrom, col.pos, reason])
fp_scores.append(spanning)
else:
tp_scores.append(spanning)
logm('\t'.join(map(str, [hyp, not fp, spanning, chrom, col.pos, reason])))
print 'False positives:\n', pformat(sorted(false_positives, key=lambda fp: (fp[-1], fp[-2])))
print 'False negatives:\n', pformat(not_found_insertions)
print
#print bgr_spanning, reads_per_base
print 'True positives: %d (%.2lf%%)\t' % (len(tp_scores), float(100 * len(tp_scores)) / (len(tp_scores) + len(fp_scores))), mean(tp_scores), var(tp_scores)
if fp_scores:
print 'False positives: %d (%.2lf%%)\t' % (
len(fp_scores), float(100 * len(fp_scores)) / (len(tp_scores) + len(fp_scores))), mean(fp_scores), var(fp_scores)
print 'False negatives: %d(%.2f%%)\n' % (count_alus(not_found_insertions), float(100 * count_alus(not_found_insertions)) / total_alus)
