rmontanana/BayesNet
rmontanana/BayesNet
1
0
Fork 0
Code Issues 2 Pull Requests Packages Projects Releases 3 Wiki Activity

Fix problem with tensors way

Browse Source
This commit is contained in:
Ricardo Montañana Gómez 2023-07-30 19:00:02 +02:00
parent 53697648e7
commit 43bb017d5d
Signed by: rmontanana
GPG Key ID: 46064262FD9A7ADE
10 changed files with 95 additions and 40 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
.vscode/launch.json vendored
View File

@ -12,10 +12,10 @@
"-m",
"TAN",
"-p",
"../../data/",
"/Users/rmontanana/Code/discretizbench/datasets/",
"--tensors"
],
"cwd": "${workspaceFolder}/build/sample/",
//"cwd": "${workspaceFolder}/build/sample/",
},
{
"type": "lldb",

12
TAN_iris.dot Normal file
View File

@ -0,0 +1,12 @@
digraph BayesNet {
label=<BayesNet >
fontsize=30
fontcolor=blue
labelloc=t
layout=circo
class [shape=circle, fontcolor=red, fillcolor=lightblue, style=filled ]
class -> sepallength class -> sepalwidth class -> petallength class -> petalwidth petallength [shape=circle]
petallength -> sepallength petalwidth [shape=circle]
sepallength [shape=circle]
sepallength -> sepalwidth sepalwidth [shape=circle]
sepalwidth -> petalwidth }

4
sample/sample.cc
View File

@ -1,7 +1,6 @@
#include <iostream>
#include <torch/torch.h>
#include <string>
#include <thread>
#include <map>
#include <argparse/argparse.hpp>
#include "ArffFiles.h"
@ -42,7 +41,7 @@ bool file_exists(const std::string& name)
}
pair<vector<vector<int>>, vector<int>> extract_indices(vector<int> indices, vector<vector<int>> X, vector<int> y)
{
vector<vector<int>> Xr;
vector<vector<int>> Xr; // nxm
vector<int> yr;
for (int col = 0; col < X.size(); ++col) {
Xr.push_back(vector<int>());
@ -199,6 +198,7 @@ int main(int argc, char** argv)
torch::Tensor Xtestt = torch::index_select(Xt, 1, ttest);
torch::Tensor ytestt = yt.index({ ttest });
clf->fit(Xtraint, ytraint, features, className, states);
auto temp = clf->predict(Xtraint);
score_train = clf->score(Xtraint, ytraint);
score_test = clf->score(Xtestt, ytestt);
} else {

1
src/BayesNet/BaseClassifier.h
View File

@ -8,6 +8,7 @@ namespace bayesnet {
public:
virtual BaseClassifier& fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states) = 0;
virtual BaseClassifier& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) = 0;
torch::Tensor virtual predict(torch::Tensor& X) = 0;
vector<int> virtual predict(vector<vector<int>>& X) = 0;
float virtual score(vector<vector<int>>& X, vector<int>& y) = 0;
float virtual score(torch::Tensor& X, torch::Tensor& y) = 0;

32
src/BayesNet/Classifier.cc
View File

@ -65,23 +65,14 @@ namespace bayesnet {
}
}
}
Tensor Classifier::predict(Tensor& X)
{
if (!fitted) {
throw logic_error("Classifier has not been fitted");
}
auto m_ = X.size(0);
auto n_ = X.size(1);
//auto Xt = torch::transpose(X, 0, 1);
vector<vector<int>> Xd(n_, vector<int>(m_, 0));
for (auto i = 0; i < n_; i++) {
auto temp = X.index({ "...", i });
Xd[i] = vector<int>(temp.data_ptr<int>(), temp.data_ptr<int>() + temp.numel());
}
auto yp = model.predict(Xd);
auto ypred = torch::tensor(yp, torch::kInt32);
return ypred;
auto Xt = torch::transpose(X, 0, 1); // Base classifiers expect samples as columns
auto y_proba = model.predict(Xt);
return y_proba.argmax(1);
}
vector<int> Classifier::predict(vector<vector<int>>& X)
{
@ -102,8 +93,7 @@ namespace bayesnet {
if (!fitted) {
throw logic_error("Classifier has not been fitted");
}
auto Xt = torch::transpose(X, 0, 1);
Tensor y_pred = predict(Xt);
Tensor y_pred = predict(X);
return (y_pred == y).sum().item<float>() / y.size(0);
}
float Classifier::score(vector<vector<int>>& X, vector<int>& y)
@ -111,13 +101,13 @@ namespace bayesnet {
if (!fitted) {
throw logic_error("Classifier has not been fitted");
}
auto m_ = X[0].size();
auto n_ = X.size();
vector<vector<int>> Xd(n_, vector<int>(m_, 0));
for (auto i = 0; i < n_; i++) {
Xd[i] = vector<int>(X[i].begin(), X[i].end());
}
return model.score(Xd, y);
// auto m_ = X[0].size();
// auto n_ = X.size();
// vector<vector<int>> Xd(n_, vector<int>(m_, 0));
// for (auto i = 0; i < n_; i++) {
// Xd[i] = vector<int>(X[i].begin(), X[i].end());
// }
return model.score(X, y);
}
vector<string> Classifier::show()
{

2
src/BayesNet/Classifier.h
View File

@ -35,7 +35,7 @@ namespace bayesnet {
int getNumberOfNodes() override;
int getNumberOfEdges() override;
int getNumberOfStates() override;
Tensor predict(Tensor& X);
Tensor predict(Tensor& X) override;
vector<int> predict(vector<vector<int>>& X) override;
float score(Tensor& X, Tensor& y) override;
float score(vector<vector<int>>& X, vector<int>& y) override;

34
src/BayesNet/Ensemble.cc
View File

@ -16,15 +16,22 @@ namespace bayesnet {
train();
// Train models
n_models = models.size();
auto Xt = torch::transpose(X, 0, 1);
for (auto i = 0; i < n_models; ++i) {
models[i]->fit(Xv, yv, features, className, states);
if (Xv == vector<vector<int>>()) {
// fit with tensors
models[i]->fit(Xt, y, features, className, states);
} else {
// fit with vectors
models[i]->fit(Xv, yv, features, className, states);
}
}
fitted = true;
return *this;
}
Ensemble& Ensemble::fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states)
{
this->X = X;
this->X = torch::transpose(X, 0, 1);
this->y = y;
Xv = vector<vector<int>>();
yv = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + y.size(0));
@ -41,17 +48,6 @@ namespace bayesnet {
yv = y;
return build(features, className, states);
}
Tensor Ensemble::predict(Tensor& X)
{
if (!fitted) {
throw logic_error("Ensemble has not been fitted");
}
Tensor y_pred = torch::zeros({ X.size(0), n_models }, kInt32);
for (auto i = 0; i < n_models; ++i) {
y_pred.index_put_({ "...", i }, models[i]->predict(X));
}
return torch::tensor(voting(y_pred));
}
vector<int> Ensemble::voting(Tensor& y_pred)
{
auto y_pred_ = y_pred.accessor<int, 2>();
@ -66,6 +62,18 @@ namespace bayesnet {
}
return y_pred_final;
}
Tensor Ensemble::predict(Tensor& X)
{
if (!fitted) {
throw logic_error("Ensemble has not been fitted");
}
Tensor y_pred = torch::zeros({ X.size(1), n_models }, kInt32);
for (auto i = 0; i < n_models; ++i) {
auto ypredict = models[i]->predict(X);
y_pred.index_put_({ "...", i }, ypredict);
}
return torch::tensor(voting(y_pred));
}
vector<int> Ensemble::predict(vector<vector<int>>& X)
{
if (!fitted) {

2
src/BayesNet/Ensemble.h
View File

@ -32,7 +32,7 @@ namespace bayesnet {
virtual ~Ensemble() = default;
Ensemble& fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
Ensemble& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
Tensor predict(Tensor& X);
Tensor predict(Tensor& X) override;
vector<int> predict(vector<vector<int>>& X) override;
float score(Tensor& X, Tensor& y) override;
float score(vector<vector<int>>& X, vector<int>& y) override;

41
src/BayesNet/Network.cc
View File

@ -170,6 +170,34 @@ namespace bayesnet {
}
fitted = true;
}
Tensor Network::predict_proba(const Tensor& samples)
{
if (!fitted) {
throw logic_error("You must call fit() before calling predict_proba()");
}
Tensor result = torch::zeros({ samples.size(0), classNumStates }, torch::kFloat64);
auto Xt = torch::transpose(samples, 0, 1);
for (int i = 0; i < samples.size(0); ++i) {
auto sample = Xt.index({ "...", i });
auto classProbabilities = predict_sample(sample);
result.index_put_({ i, "..." }, torch::tensor(classProbabilities, torch::kFloat64));
}
return result;
}
Tensor Network::predict(const Tensor& samples)
{
if (!fitted) {
throw logic_error("You must call fit() before calling predict()");
}
Tensor result = torch::zeros({ samples.size(0), classNumStates }, torch::kFloat64);
auto Xt = torch::transpose(samples, 0, 1);
for (int i = 0; i < samples.size(0); ++i) {
auto sample = Xt.index({ "...", i });
auto classProbabilities = predict_sample(sample);
result.index_put_({ i, "..." }, torch::tensor(classProbabilities, torch::kFloat64));
}
return result;
}
vector<int> Network::predict(const vector<vector<int>>& tsamples)
{
@ -231,6 +259,19 @@ namespace bayesnet {
}
return exactInference(evidence);
}
vector<double> Network::predict_sample(const Tensor& sample)
{
// Ensure the sample size is equal to the number of features
if (sample.size(0) != features.size()) {
throw invalid_argument("Sample size (" + to_string(sample.size(0)) +
") does not match the number of features (" + to_string(features.size()) + ")");
}
map<string, int> evidence;
for (int i = 0; i < sample.size(0); ++i) {
evidence[features[i]] = sample[i].item<int>();
}
return exactInference(evidence);
}
double Network::computeFactor(map<string, int>& completeEvidence)
{
double result = 1.0;

3
src/BayesNet/Network.h
View File

@ -18,6 +18,7 @@ namespace bayesnet {
torch::Tensor samples;
bool isCyclic(const std::string&, std::unordered_set<std::string>&, std::unordered_set<std::string>&);
vector<double> predict_sample(const vector<int>&);
vector<double> predict_sample(const torch::Tensor&);
vector<double> exactInference(map<string, int>&);
double computeFactor(map<string, int>&);
double mutual_info(torch::Tensor&, torch::Tensor&);
@ -43,9 +44,11 @@ namespace bayesnet {
void fit(const vector<vector<int>>&, const vector<int>&, const vector<string>&, const string&);
void fit(torch::Tensor&, torch::Tensor&, const vector<string>&, const string&);
vector<int> predict(const vector<vector<int>>&);
torch::Tensor predict(const torch::Tensor&);
//Computes the conditional edge weight of variable index u and v conditioned on class_node
torch::Tensor conditionalEdgeWeight();
vector<vector<double>> predict_proba(const vector<vector<int>>&);
torch::Tensor predict_proba(const torch::Tensor&);
double score(const vector<vector<int>>&, const vector<int>&);
vector<string> show();
vector<string> graph(const string& title); // Returns a vector of strings representing the graph in graphviz format