diff options
Diffstat (limited to 'experiments/ml.pyx')
| -rw-r--r-- | experiments/ml.pyx | 42 |
1 files changed, 22 insertions, 20 deletions
diff --git a/experiments/ml.pyx b/experiments/ml.pyx index 67b561c..c8c99cc 100644 --- a/experiments/ml.pyx +++ b/experiments/ml.pyx @@ -6,20 +6,17 @@ from libc.math cimport log, exp DTYPE = np.float64 ctypedef np.float_t DTYPE_t -cdef DTYPE_t plogis(DTYPE_t weight, DTYPE_t delta): - return 1./(1. + exp(-weight/delta)) - cdef DTYPE_t weight_success(int dist, int dt, DTYPE_t alpha, DTYPE_t delta, DTYPE_t w1, DTYPE_t w2, DTYPE_t w3): """weight for successful infection, exponential time model""" cdef DTYPE_t structural, temporal, result - structural = delta ** dist + structural = dist * log(delta) # structural = plogis(w1,delta) * plogis(w2,delta) * plogis(w3,delta) - # temporal = exp(-alpha*dt) * (exp(alpha)-1) - temporal = 1 - exp(-alpha*dt) - if exp(-alpha*dt)==0.: print 'UNDERFLOW ERROR' + temporal = log(exp(alpha)-1.) - alpha*dt + # temporal = 1 - exp(-alpha*dt) + # if exp(-alpha*dt)==0.: print 'UNDERFLOW ERROR' # temporal = 1. / (1. + (dt - 1.)/alpha)**0.01 - 1. / (1. + dt/alpha)**0.01 - result = log(structural * temporal) + result = structural + temporal # print 'st', structural, temporal return result @@ -39,10 +36,10 @@ def ml(dict root_victims, dict victims, dict non_victims, DTYPE_t age, DTYPE_t alpha, DTYPE_t delta): cdef: int n_roots, n_victims, n_nodes, roots, i, dist, dt, t, l - DTYPE_t beta, ll + DTYPE_t beta, ll, beta_add, max_beta, max_beta_add list parents, failures, successes n_roots, n_victims = len(root_victims), len(victims) - n_nodes = 11270 + n_nodes = 148152 cdef: np.ndarray[DTYPE_t] probs = np.zeros(n_victims, dtype=DTYPE) np.ndarray[DTYPE_t] probs_fail = np.zeros(n_victims, dtype=DTYPE) @@ -62,12 +59,16 @@ def ml(dict root_victims, dict victims, dict non_victims, DTYPE_t age, probs[i] = max(s - failures[l] for l, s in enumerate(successes)) # loop through non-victims - # for i, parents in enumerate(non_victims.itervalues()): - # # for each non victim node, compute the probability that all its - # # parents fail to infect it - # failures = [weight_failure(dist, dt, alpha, delta, w1, w2, w3) - # for (dist, dt, w1, w2, w3) in parents] - # probs_nv[i] = sum(failures) + for i, parents in enumerate(non_victims.itervalues()): + # for each non victim node, compute the probability that all its + # parents fail to infect it + failures = [weight_failure(dist, dt, alpha, delta, w1, w2, w3) + for (dist, dt, w1, w2, w3) in parents] + probs_nv[i] = sum(failures) + + # print successes + # print failures + # print probs # calculate log likelihood # probs.sort(); probs = probs[::-1] # sort probs in descending order @@ -79,15 +80,16 @@ def ml(dict root_victims, dict victims, dict non_victims, DTYPE_t age, # print 'probs', probs max_beta_add = float('-inf') # iterate over all victim nodes to find the optimal threshold - for beta in np.arange(0.001, .1, .001): - thresh = log(beta/(1.-beta)) + for beta in np.arange(0.001, .2, .002): + thresh = log(beta/(3012.*(1.-beta))) # print 'beta:', beta, 'thresh:', thresh, 'infected:', len(probs[probs>=thresh]) roots = n_roots + len(probs[probs<thresh]) + beta_add = 0. # add probability for realized edges and subtract probability these edges fail - beta_add = (probs[probs>=thresh]).sum() + beta_add += (probs[probs>=thresh]).sum() # add probability for the seeds and non-seeds - beta_add += roots * log(beta) + (n_nodes-roots) * log(1 - beta) + beta_add += roots * log(beta/3012.) + (n_nodes-roots) * log(1. - beta) if beta_add > max_beta_add: max_beta = beta |