Worked on synthetic data recovery so we can tell how high the actual

infector is ranked among all potential parents. Cleaned up code for the
predicting victims benchmarking test.

1 files changed, 7 insertions, 8 deletions

diff --git a/experiments/ml3.pyx b/experiments/ml3.pyx
index faeda92..da993bc 100644
--- a/experiments/ml3.pyx
+++ b/experiments/ml3.pyx
@@ -6,7 +6,7 @@ from libc.math cimport log, exp
 DTYPE = np.float64
 ctypedef np.float_t DTYPE_t
 
-cdef DTYPE_t weight_success(int dist, int dt, DTYPE_t alpha, DTYPE_t delta,
+cdef DTYPE_t weight_success(int dist, DTYPE_t 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
@@ -15,7 +15,7 @@ cdef DTYPE_t weight_success(int dist, int dt, DTYPE_t alpha, DTYPE_t delta,
     result = log(structural) + temporal
     return result
 
-cdef DTYPE_t weight_failure(int dist, int dt, DTYPE_t alpha, DTYPE_t delta,
+cdef DTYPE_t weight_failure(int dist, DTYPE_t dt, DTYPE_t alpha, DTYPE_t delta,
                             DTYPE_t w1, DTYPE_t w2, DTYPE_t w3):
     """weight for failed infection, exponential time model"""
     cdef DTYPE_t structural, temporal, result
@@ -43,21 +43,20 @@ def ml3(dict root_victims, dict victims, dict non_victims, DTYPE_t age,
         # for each victim node i, compute the probability that all its parents
         # fail to infect it, also computes the probability that its most
         # likely parent infects it
-        failures = [weight_failure(dist, dt, alpha, delta, w1, w2, w3)
+        failures = [weight_failure(dist, dt/100., alpha, delta, w1, w2, w3)
                     for (dist, dt, w1, w2, w3) in parents]
         probs_fail[i] = sum(failures)
-        successes = [weight_success(dist, dt, alpha, delta, w1, w2, w3)
+        successes = [weight_success(dist, dt/100., alpha, delta, w1, w2, w3)
                      for (dist, dt, w1, w2, w3) in parents]
         dists = [dist for (dist, dt, w1, w2, w3) in parents]
         dts = [dt for (dist, dt, w1, w2, w3) in parents]
         # find parent that maximizes log(p) - log(\tilde{p})
         # probs[i] = max(s - failures[l] for l, s in enumerate(successes)) 
-        # probs[i] = 0.
+        probs[i] = float("-inf")
         for l, s in enumerate(successes):
             prob = s - failures[l]
-            if prob > -19.523275053840013:
-                isSeed[i] = 0
-                probs[i] += prob
+            if prob > probs[i]:
+                probs[i] = prob
                 parent_dists[i] = dists[l]
                 parent_dts[i] = dts[l]
                 # probs_fail[i] = failures[l]