summaryrefslogtreecommitdiff
path: root/gi/pf
diff options
context:
space:
mode:
Diffstat (limited to 'gi/pf')
-rw-r--r--gi/pf/base_distributions.cc22
-rw-r--r--gi/pf/base_distributions.h21
-rw-r--r--gi/pf/conditional_pseg.h3
-rw-r--r--gi/pf/pfdist.cc6
-rw-r--r--gi/pf/pfnaive.cc4
5 files changed, 20 insertions, 36 deletions
diff --git a/gi/pf/base_distributions.cc b/gi/pf/base_distributions.cc
index d362fd76..d9761005 100644
--- a/gi/pf/base_distributions.cc
+++ b/gi/pf/base_distributions.cc
@@ -59,7 +59,7 @@ prob_t PhraseConditionalUninformativeUnigramBase::p0(const vector<WordID>& vsrc,
const int flen = vsrc.size() - start_src;
const int elen = vtrg.size() - start_trg;
prob_t p;
- p.logeq(log_poisson(elen, flen + 0.01)); // elen | flen ~Pois(flen + 0.01)
+ p.logeq(Md::log_poisson(elen, flen + 0.01)); // elen | flen ~Pois(flen + 0.01)
//p.logeq(log_poisson(elen, 1)); // elen | flen ~Pois(flen + 0.01)
for (int i = 0; i < elen; ++i)
p *= u(vtrg[i + start_trg]); // draw e_i ~Uniform
@@ -73,7 +73,7 @@ prob_t PhraseConditionalUninformativeBase::p0(const vector<WordID>& vsrc,
const int elen = vtrg.size() - start_trg;
prob_t p;
//p.logeq(log_poisson(elen, flen + 0.01)); // elen | flen ~Pois(flen + 0.01)
- p.logeq(log_poisson(elen, 1)); // elen | flen ~Pois(flen + 0.01)
+ p.logeq(Md::log_poisson(elen, 1)); // elen | flen ~Pois(flen + 0.01)
for (int i = 0; i < elen; ++i)
p *= kUNIFORM_TARGET; // draw e_i ~Uniform
return p;
@@ -113,7 +113,7 @@ prob_t PhraseConditionalBase::p0(const vector<WordID>& vsrc,
const int elen = vtrg.size() - start_trg;
prob_t uniform_src_alignment; uniform_src_alignment.logeq(-log(flen + 1));
prob_t p;
- p.logeq(log_poisson(elen, flen + 0.01)); // elen | flen ~Pois(flen + 0.01)
+ p.logeq(Md::log_poisson(elen, flen + 0.01)); // elen | flen ~Pois(flen + 0.01)
for (int i = 0; i < elen; ++i) { // for each position i in e-RHS
const WordID trg = vtrg[i + start_trg];
prob_t tp = prob_t::Zero();
@@ -139,9 +139,9 @@ prob_t PhraseJointBase::p0(const vector<WordID>& vsrc,
const int elen = vtrg.size() - start_trg;
prob_t uniform_src_alignment; uniform_src_alignment.logeq(-log(flen + 1));
prob_t p;
- p.logeq(log_poisson(flen, 1.0)); // flen ~Pois(1)
+ p.logeq(Md::log_poisson(flen, 1.0)); // flen ~Pois(1)
// elen | flen ~Pois(flen + 0.01)
- prob_t ptrglen; ptrglen.logeq(log_poisson(elen, flen + 0.01));
+ prob_t ptrglen; ptrglen.logeq(Md::log_poisson(elen, flen + 0.01));
p *= ptrglen;
p *= kUNIFORM_SOURCE.pow(flen); // each f in F ~Uniform
for (int i = 0; i < elen; ++i) { // for each position i in E
@@ -171,9 +171,9 @@ prob_t PhraseJointBase_BiDir::p0(const vector<WordID>& vsrc,
prob_t uniform_trg_alignment; uniform_trg_alignment.logeq(-log(elen + 1));
prob_t p1;
- p1.logeq(log_poisson(flen, 1.0)); // flen ~Pois(1)
+ p1.logeq(Md::log_poisson(flen, 1.0)); // flen ~Pois(1)
// elen | flen ~Pois(flen + 0.01)
- prob_t ptrglen; ptrglen.logeq(log_poisson(elen, flen + 0.01));
+ prob_t ptrglen; ptrglen.logeq(Md::log_poisson(elen, flen + 0.01));
p1 *= ptrglen;
p1 *= kUNIFORM_SOURCE.pow(flen); // each f in F ~Uniform
for (int i = 0; i < elen; ++i) { // for each position i in E
@@ -193,9 +193,9 @@ prob_t PhraseJointBase_BiDir::p0(const vector<WordID>& vsrc,
}
prob_t p2;
- p2.logeq(log_poisson(elen, 1.0)); // elen ~Pois(1)
+ p2.logeq(Md::log_poisson(elen, 1.0)); // elen ~Pois(1)
// flen | elen ~Pois(flen + 0.01)
- prob_t psrclen; psrclen.logeq(log_poisson(flen, elen + 0.01));
+ prob_t psrclen; psrclen.logeq(Md::log_poisson(flen, elen + 0.01));
p2 *= psrclen;
p2 *= kUNIFORM_TARGET.pow(elen); // each f in F ~Uniform
for (int i = 0; i < flen; ++i) { // for each position i in E
@@ -227,9 +227,9 @@ JumpBase::JumpBase() : p(200) {
for (int j = min_jump; j <= max_jump; ++j) {
prob_t& cp = cpd[j];
if (j < 0)
- cp.logeq(log_poisson(1.5-j, 1));
+ cp.logeq(Md::log_poisson(1.5-j, 1));
else if (j > 0)
- cp.logeq(log_poisson(j, 1));
+ cp.logeq(Md::log_poisson(j, 1));
cp.poweq(0.2);
z += cp;
}
diff --git a/gi/pf/base_distributions.h b/gi/pf/base_distributions.h
index a23ac32b..0d597c5c 100644
--- a/gi/pf/base_distributions.h
+++ b/gi/pf/base_distributions.h
@@ -13,24 +13,7 @@
#include "prob.h"
#include "tdict.h"
#include "sampler.h"
-
-inline double log_poisson(unsigned x, const double& lambda) {
- assert(lambda > 0.0);
- return log(lambda) * x - lgamma(x + 1) - lambda;
-}
-
-inline double log_binom_coeff(unsigned n, unsigned k) {
- assert(n >= k);
- if (n == k) return 0.0;
- return lgamma(n + 1) - lgamma(k + 1) - lgamma(n - k + 1);
-}
-
-// http://en.wikipedia.org/wiki/Negative_binomial_distribution
-inline double log_negative_binom(unsigned x, unsigned r, double p) {
- assert(p > 0.0);
- assert(p < 1.0);
- return log_binom_coeff(x + r - 1, x) + r * log(1 - p) + x * log(p);
-}
+#include "m.h"
inline std::ostream& operator<<(std::ostream& os, const std::vector<WordID>& p) {
os << '[';
@@ -68,7 +51,7 @@ struct Model1 {
struct PoissonUniformUninformativeBase {
explicit PoissonUniformUninformativeBase(const unsigned ves) : kUNIFORM(1.0 / ves) {}
prob_t operator()(const TRule& r) const {
- prob_t p; p.logeq(log_poisson(r.e_.size(), 1.0));
+ prob_t p; p.logeq(Md::log_poisson(r.e_.size(), 1.0));
prob_t q = kUNIFORM; q.poweq(r.e_.size());
p *= q;
return p;
diff --git a/gi/pf/conditional_pseg.h b/gi/pf/conditional_pseg.h
index 0aa5e8e0..2e9e38fc 100644
--- a/gi/pf/conditional_pseg.h
+++ b/gi/pf/conditional_pseg.h
@@ -6,6 +6,7 @@
#include <boost/functional/hash.hpp>
#include <iostream>
+#include "m.h"
#include "prob.h"
#include "ccrp_nt.h"
#include "mfcr.h"
@@ -210,7 +211,7 @@ struct ConditionalParallelSegementationModel {
prob_t AlignProbability(unsigned span) const {
prob_t p;
- p.logeq(aligns.logprob(span, log_poisson(span, 1.0)));
+ p.logeq(aligns.logprob(span, Md::log_poisson(span, 1.0)));
return p;
}
diff --git a/gi/pf/pfdist.cc b/gi/pf/pfdist.cc
index ef08a165..3d578db2 100644
--- a/gi/pf/pfdist.cc
+++ b/gi/pf/pfdist.cc
@@ -315,7 +315,7 @@ struct BackwardEstimate {
for (int i = 0; i < src_cov.size(); ++i)
if (!src_cov[i]) r.push_back(src_[i]);
const prob_t uniform_alignment(1.0 / r.size());
- e.logeq(log_poisson(trg_.size() - trg_cov, r.size() - 1)); // p(trg len remaining | src len remaining)
+ e.logeq(Md::log_poisson(trg_.size() - trg_cov, r.size() - 1)); // p(trg len remaining | src len remaining)
for (unsigned j = trg_cov; j < trg_.size(); ++j) {
prob_t p;
for (unsigned i = 0; i < r.size(); ++i)
@@ -352,7 +352,7 @@ struct BackwardEstimateSym {
if (!src_cov[i]) r.push_back(src_[i]);
r.push_back(0); // NULL word
const prob_t uniform_alignment(1.0 / r.size());
- e.logeq(log_poisson(trg_.size() - trg_cov, r.size() - 1)); // p(trg len remaining | src len remaining)
+ e.logeq(Md::log_poisson(trg_.size() - trg_cov, r.size() - 1)); // p(trg len remaining | src len remaining)
for (unsigned j = trg_cov; j < trg_.size(); ++j) {
prob_t p;
for (unsigned i = 0; i < r.size(); ++i)
@@ -367,7 +367,7 @@ struct BackwardEstimateSym {
r.pop_back();
const prob_t inv_uniform(1.0 / (trg_.size() - trg_cov + 1.0));
prob_t inv;
- inv.logeq(log_poisson(r.size(), trg_.size() - trg_cov));
+ inv.logeq(Md::log_poisson(r.size(), trg_.size() - trg_cov));
for (unsigned i = 0; i < r.size(); ++i) {
prob_t p;
for (unsigned j = trg_cov - 1; j < trg_.size(); ++j)
diff --git a/gi/pf/pfnaive.cc b/gi/pf/pfnaive.cc
index acba9d22..e1a53f5c 100644
--- a/gi/pf/pfnaive.cc
+++ b/gi/pf/pfnaive.cc
@@ -77,7 +77,7 @@ struct BackwardEstimateSym {
r.push_back(src_[i]);
r.push_back(0); // NULL word
const prob_t uniform_alignment(1.0 / r.size());
- e.logeq(log_poisson(trg_.size() - trg_cov, r.size() - 1)); // p(trg len remaining | src len remaining)
+ e.logeq(Md::log_poisson(trg_.size() - trg_cov, r.size() - 1)); // p(trg len remaining | src len remaining)
for (unsigned j = trg_cov; j < trg_.size(); ++j) {
prob_t p;
for (unsigned i = 0; i < r.size(); ++i)
@@ -92,7 +92,7 @@ struct BackwardEstimateSym {
r.pop_back();
const prob_t inv_uniform(1.0 / (trg_.size() - trg_cov + 1.0));
prob_t inv;
- inv.logeq(log_poisson(r.size(), trg_.size() - trg_cov));
+ inv.logeq(Md::log_poisson(r.size(), trg_.size() - trg_cov));
for (unsigned i = 0; i < r.size(); ++i) {
prob_t p;
for (unsigned j = trg_cov - 1; j < trg_.size(); ++j)