tried generating cascades and recovering parameters, still got the same

result where optimization minimizes alpha, delta as much as possible

1 files changed, 15 insertions, 11 deletions

diff --git a/experiments/ml.pyx b/experiments/ml.pyx
index 67b561c..e1ce4cf 100644
--- a/experiments/ml.pyx
+++ b/experiments/ml.pyx
@@ -15,8 +15,8 @@ cdef DTYPE_t weight_success(int dist, int dt, DTYPE_t alpha, DTYPE_t delta,
     cdef DTYPE_t structural, temporal, result
     structural = delta ** dist
     # structural = plogis(w1,delta) * plogis(w2,delta) * plogis(w3,delta)
-    # temporal = exp(-alpha*dt) * (exp(alpha)-1)
-    temporal = 1 - exp(-alpha*dt)
+    temporal = exp(-alpha*dt) * (exp(alpha)-1.)
+    # 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)
@@ -42,7 +42,7 @@ def ml(dict root_victims, dict victims, dict non_victims, DTYPE_t age,
         DTYPE_t beta, ll
         list parents, failures, successes
     n_roots, n_victims = len(root_victims), len(victims)
-    n_nodes = 11270
+    n_nodes = 100
     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 +62,16 @@ 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
@@ -79,7 +83,7 @@ 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):
+    for beta in [0.13]:#np.arange(0.001, .2, .002):
         thresh = log(beta/(1.-beta))
         # print 'beta:', beta, 'thresh:', thresh, 'infected:', len(probs[probs>=thresh])
         roots = n_roots + len(probs[probs<thresh])
@@ -87,7 +91,7 @@ def ml(dict root_victims, dict victims, dict non_victims, DTYPE_t age,
         # add probability for realized edges and subtract probability these edges fail
         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) + (n_nodes-roots) * log(1. - beta)
 
         if beta_add > max_beta_add:
             max_beta = beta