ran some experiments with ml3, still no good results

1 files changed, 8 insertions, 14 deletions

diff --git a/experiments/ml3.pyx b/experiments/ml3.pyx
index 1f46ef5..5cbe3ba 100644
--- a/experiments/ml3.pyx
+++ b/experiments/ml3.pyx
@@ -10,17 +10,16 @@ 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 = dist * log(delta)
+    structural = delta ** dist
     # structural = plogis(w1,delta) * plogis(w2,delta) * plogis(w3,delta)
     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 = structural + temporal
+    result = log(structural) + temporal
     # print 'st', structural, temporal
     return result
 
-
 cdef DTYPE_t weight_failure(int dist, int dt, DTYPE_t alpha, DTYPE_t delta,
                             DTYPE_t w1, DTYPE_t w2, DTYPE_t w3):
     """weight for failed infection, exponential time model"""
@@ -29,7 +28,7 @@ cdef DTYPE_t weight_failure(int dist, int dt, DTYPE_t alpha, DTYPE_t delta,
     # structural = plogis(w1,delta) * plogis(w2,delta) * plogis(w3,delta)
     temporal = exp(-alpha * dt)
     # temporal = 1.  - 1. / (1. + dt/alpha)**0.01
-    result = log(1. - structural)
+    result = log(1. - structural + structural*temporal)
     # print 'stnv', structural, temporal
     return result
 
@@ -53,7 +52,7 @@ def ml3(dict root_victims, dict victims, dict non_victims, DTYPE_t age,
         # likely parent infects it
         failures = [weight_failure(dist, dt, alpha, delta, w1, w2, w3)
                     for (dist, dt, w1, w2, w3) in parents]
-        # probs_fail[i] = sum(failures)
+        probs_fail[i] = sum(failures)
         successes = [weight_success(dist, dt, alpha, delta, w1, w2, w3)
                      for (dist, dt, w1, w2, w3) in parents]
         dists = [dist for (dist, dt, w1, w2, w3) in parents]
@@ -67,20 +66,15 @@ def ml3(dict root_victims, dict victims, dict non_victims, DTYPE_t age,
                 probs[i] = prob
                 parent_dists[i] = dists[l]
                 parent_dts[i] = dts[l]
-                probs_fail[i] = failures[l]
-
-    # print successes
-    # print failures
-    # print probs
+                # probs_fail[i] = failures[l]
 
     # calculate log likelihood
-    ll =  probs_fail.sum() # add probability that all edges to victims fail
-    # ll += probs_nv.sum() # add probability that all edges to non_victims fail
+    ll =  probs_fail.sum() # add probability that all edges to all victims fail
 
     # print 'probs', probs
     max_beta_add = float('-inf')
     # iterate over all victim nodes to find the optimal threshold
-    for beta in np.arange(0.1, 1., .1):
+    for beta in np.arange(0.2, 1., 1.):
         thresh = log(beta/(3012.*(1.-beta)))
         # print 'beta:', beta, 'thresh:', thresh, 'infected:', len(probs[probs>=thresh])
         roots = n_roots + len(probs[probs<thresh])
@@ -89,7 +83,7 @@ def ml3(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) + len(probs[probs>=thresh]) * log(1. - beta)
+        beta_add += roots * log(beta/3012.) + len(probs[probs>=thresh]) * log(1. - beta)
 
         if beta_add > max_beta_add:
             max_beta = beta