def estimate_failures(samples, #samples from noisy labelers
n_samples=10000, #number of samples to run MCMC for
burn=None, #burn-in. Defaults to n_samples/2
thin=10, #thinning rate. Sample every k samples from markov chain
alpha_p=1, beta_p=1, #beta parameters for true positive rate
alpha_e=1, beta_e=10 #beta parameters for noise rates
):
if burn is None:
burn = n_samples / 2
S,N = samples.shape
p = Beta('p', alpha=alpha_p, beta=beta_p) #prior on true label
l = Bernoulli('l', p=p, size=S)
e_pos = Beta('e_pos', alpha_e, beta_e, size=N) # error rate if label = 1
e_neg = Beta('e_neg', alpha_e, beta_e, size=N) # error rate if label = 0
@deterministic(plot=False)
def noise_rate(l=l, e_pos=e_pos, e_neg=e_neg):
#probability that a noisy labeler puts a label 1
return np.outer(l, 1-e_pos) + np.outer(1-l, e_neg)
noisy_label = Bernoulli('noisy_label', p=noise_rate, size=samples.shape, value=samples, observed=True)
variables = [l, e_pos, e_neg, p, noisy_label, noise_rate]
model = MCMC(variables, verbose=3)
model.sample(iter=n_samples, burn=burn, thin=thin)
model.write_csv('out.csv', ['p', 'e_pos', 'e_neg'])
p = np.median(model.trace('p')[:])
e_pos = np.median(model.trace('e_pos')[:],0)
e_neg = np.median(model.trace('e_neg')[:],0)
return p, e_pos, e_neg
def estimate_failures_from_counts(counts, #samples from noisy labelers
n_samples=10000, #number of samples to run MCMC for
burn=None, #burn-in. Defaults to n_samples/2
thin=10, #thinning rate. Sample every k samples from markov chain
alpha_p=1, beta_p=1, #beta parameters for true positive rate
alpha_e=1, beta_e=10 #beta parameters for noise rates
):
if burn is None:
burn = n_samples / 2
S = counts.sum()
N = len(counts.shape)
p_label = Beta('p_label', alpha=alpha_p, beta=beta_p) #prior on true label
e_pos = Beta('e_pos', alpha_e, beta_e, size=N) # error rate if label = 1
e_neg = Beta('e_neg', alpha_e, beta_e, size=N) # error rate if label = 0
print counts
@deterministic(plot=False)
def patterns(p_label=p_label, e_pos=e_pos, e_neg=e_neg):
#probability that the noisy labelers output pattern p
P = np.zeros((2,)*N)
for pat in itertools.product([0,1], repeat=N):
P[pat] = p_label*np.product([1-e_pos[i] if pat[i]==1 else e_pos[i] for i in xrange(N)])
P[pat] += (1-p_label)*np.product([e_neg[i] if pat[i]==1 else 1-e_neg[i] for i in xrange(N)])
assert np.abs(P.sum() - 1) < 1e-6
return P.ravel()
pattern_counts = Multinomial('pattern_counts',n=S, p=patterns, value=counts.ravel(), observed=True)
variables = [p_label, e_pos, e_neg, patterns]
model = MCMC(variables, verbose=3)
model.sample(iter=n_samples, burn=burn, thin=thin)
model.write_csv('out.csv', ['p_label', 'e_pos', 'e_neg'])
p = np.median(model.trace('p_label')[:])
e_pos = np.median(model.trace('e_pos')[:],0)
e_neg = np.median(model.trace('e_neg')[:],0)
return p, e_pos, e_neg
import pmodel
import pymc
import networkx as nx
import matplotlib.pyplot as plt
from pymc import MCMC
from pymc.Matplot import plot
M = MCMC(pmodel)
M.sample(iter=300000, burn=250, thin=10)
#plot(M, path='./plots')
M.write_csv('out.csv')
#pathways = model.pathways
#traces = {}
#for p in pathways:
# traces[p] = M.trace(p)[:]
#plt.hist(traces[pathways[0]], bins='auto')
#plt.show()
#t = M.trace(pathways[0])[:]
#g = pymc.graph.graph(pymc.Model(model), path='.')
#g.write('model.dot')
#G = nx.drawing.nx_agraph.read_dot('model.dot')
#nx.draw(G)
#plt.draw()
#hist(M.trace('late_mean')[:])
#show()
# PyMC implementation of Panel 6.4 from Royle & Dorazio (2008) pp. 217
# MA MacNeil - 04.03.14
import Mbht
import sys
import os
import pdb
from pymc import MCMC, BinaryMetropolis, Metropolis, AdaptiveMetropolis
from pymc import Matplot as mp
import pdb
M = MCMC(Mbht)
#M = MCMC(models,db='sqlite',dbname='xx_dbase')
xex = 6
M.isample(10**xex, 10**xex-10**(xex-1), thin=10**(xex-4), verbose=2)
#M.isample(100000, 80000, thin=10, verbose=2)
try:
os.mkdir('Outputs')
except OSError:
pass
os.chdir('Outputs')
M.write_csv("zz_results.csv")
mp.plot(M)
import model
import pymc
from pymc import MCMC
M = MCMC(model)
M.sample(iter=250, burn=50, thin=10)
#plot(M, path='./plots')
M.write_csv('quick.csv')
#pathways = model.pathways
#traces = {}
#for p in pathways:
# traces[p] = M.trace(p)[:]
#plt.hist(traces[pathways[0]], bins='auto')
#plt.show()
#t = M.trace(pathways[0])[:]
#g = pymc.graph.graph(pymc.Model(model), path='.')
#g.write('model.dot')
#G = nx.drawing.nx_agraph.read_dot('model.dot')
#nx.draw(G)
#plt.draw()
#hist(M.trace('late_mean')[:])
#show()
# Run model
#
# PyMC implementation of Smith et al. (2012) Ecology: http://www.esajournals.org/doi/abs/10.1890/12-0460.1
#
# Created by M. Aaron MacNeil on 20/07/12.
#
import snapper
from pymc import MCMC, BinaryMetropolis, Metropolis, AdaptiveMetropolis
from pymc import Matplot as mp
M = MCMC(snapper)
xex = 5
M.isample(10**xex, 10**xex-10**(xex-1), thin=100, verbose=2)
M.write_csv("results.csv")
mp.plot(M)
M = MCMC(model3)
#MAP = pymc.MAP(model3)
#MAP.fit()
def get_coeffs(map_):
return [{
str(v): v.value
} for v in map_.variables if str(v).startswith('p')
or str(v).startswith('b') or str(v).startswith('e')]
#print get_coeffs(MAP)
M.sample(iter=10000, burn=250, thin=10)
#plot(M, path='./plots')
M.write_csv('shortout.csv')
#pathways = model.pathways
#traces = {}
#for p in pathways:
# traces[p] = M.trace(p)[:]
#plt.hist(traces[pathways[0]], bins='auto')
#plt.show()
#t = M.trace(pathways[0])[:]
#import networkx as nx
g = pymc.graph.graph(pymc.Model(model3), path='.')
g.write_png('model.png')
#G = nx.drawing.nx_agraph.read_dot('model.dot')
#nx.draw(G)
#plt.show()
import model
import pymc
from pymc import MCMC
M = MCMC(model)
for i in range(5):
M.sample(iter=250, burn=50, thin=10)
M.write_csv('quick/' + str(i) + '.csv')
