void test_recommend_fillmissingvalues()
{
// Make some input files
TempFileMaker tempFile1("a.arff",
"@RELATION test\n"
"@ATTRIBUTE a1 { a, b, c }\n"
"@ATTRIBUTE a2 continuous\n"
"@ATTRIBUTE a3 { d, e, f }\n"
"@ATTRIBUTE a4 { g, h, i }\n"
"@DATA\n"
"a, ?, f, i\n"
"?, 2, ?, i\n"
"b, ?, d, ?\n"
"?, 4, ?, ?\n"
"?, ?, e, g\n"
"?, ?, e, ?\n"
"a, ?, ?, h\n"
"\n"
);
// Execute the command
GPipe pipeStdOut;
if(sysExec("waffles_recommend", "fillmissingvalues a.arff baseline", &pipeStdOut) != 0)
throw Ex("exit status indicates failure");
char buf[512];
size_t len = pipeStdOut.read(buf, 512);
if(len == 512)
throw Ex("need a bigger buffer");
buf[len] = '\0';
// Check the results
GMatrix M;
M.parseArff(buf, strlen(buf));
if(M.rows() != 7 || M.cols() != 4)
throw Ex("failed");
if(M[0][0] != 0)
throw Ex("failed");
if(M[0][1] != 3)
throw Ex("failed");
if(M[1][1] != 2)
throw Ex("failed");
if(M[2][1] != 3)
throw Ex("failed");
if(M[3][3] != 2)
throw Ex("failed");
if(M[4][0] != 0)
throw Ex("failed");
if(M[5][1] != 3)
throw Ex("failed");
if(M[6][2] != 1)
throw Ex("failed");
if(M[6][3] != 1)
throw Ex("failed");
}
void test_parsearff_quoting(){
const char* inputArff=
"@relation 'squares of numbers'\n"
"\n"
"@attribute 'the number' real\n"
"\n"
"@attribute 'the square of the number' real\n"
"\n"
"@attribute exact {'is exact', inexact,is\\\\\\ exact}\n"
"\n"
"@data\n"
"1,1,'is exact'\n"
"2,4,is\\ exact\n"
"1.414,2,inexact\n"
"3,9,\"is exact\"\n"
"4,16,\"is\\ exact\"\n"
;
GMatrix M;
M.parseArff(inputArff, strlen(inputArff));
double expected_data[5][3]={{1,1,0},{2,4,0},{1.414,2,1},{3,9,0},{4,16,2}};
const GArffRelation* pRel = (const GArffRelation*)&M.relation();
const GArffRelation& R = *pRel;
TestEqual(R.size(), (std::size_t)3, "Incorrect number of attributes");
for(unsigned row = 0; row < 5; ++row){
for(unsigned col = 0; col < 3; ++col){
std::stringstream errdescr;
errdescr << "Incorrect matrix entry [" << row << "][" << col << "]";
TestEqual(M[row][col], expected_data[row][col], errdescr.str());
}
}
TestEqual(true, R.areContinuous(0,2),
"First or second attribute is not continuous");
TestEqual(true, R.areNominal(2,1), "Third attribute is not nominal");
std::stringstream val0, val1, val2;
R.printAttrValue(val0, 2, 0);
R.printAttrValue(val1, 2, 1);
R.printAttrValue(val2, 2, 2);
TestEqual("'is exact'",val0.str(),
"First value of third attribute incorrect name");
TestEqual("inexact",val1.str(),
"Second value of third attribute incorrect name");
TestEqual("is\\ exact",val2.str(),
"Third value of third attribute incorrect name");
TestEqual("'the number'",R.attrName(0),"First attribute incorrect name");
TestEqual("'the square of the number'",R.attrName(1),
"Second attribute incorrect name");
TestEqual("exact",R.attrName(2),"Third attribute incorrect name");
}
void GNaiveBayes_testMath()
{
const char* trainFile =
"@RELATION test\n"
"@ATTRIBUTE a {t,f}\n"
"@ATTRIBUTE b {r,g,b}\n"
"@ATTRIBUTE c {y,n}\n"
"@DATA\n"
"t,r,y\n"
"f,r,n\n"
"t,g,y\n"
"f,g,y\n"
"f,g,n\n"
"t,r,n\n"
"t,r,y\n"
"t,b,y\n"
"f,r,y\n"
"f,g,n\n"
"f,b,y\n"
"t,r,n\n";
GMatrix train;
train.parseArff(trainFile, strlen(trainFile));
GMatrix* pFeatures = train.cloneSub(0, 0, train.rows(), 2);
std::unique_ptr<GMatrix> hFeatures(pFeatures);
GMatrix* pLabels = train.cloneSub(0, 2, train.rows(), 1);
std::unique_ptr<GMatrix> hLabels(pLabels);
GNaiveBayes nb;
nb.setEquivalentSampleSize(0.0);
nb.train(*pFeatures, *pLabels);
GPrediction out;
GVec pat(2);
pat[0] = 0; pat[1] = 0;
nb.predictDistribution(pat, &out);
GNaiveBayes_CheckResults(7.0/12.0, 4.0/7.0*3.0/7.0, 5.0/12.0, 2.0/5.0*3.0/5.0, &out);
pat[0] = 0; pat[1] = 1;
nb.predictDistribution(pat, &out);
GNaiveBayes_CheckResults(7.0/12.0, 4.0/7.0*2.0/7.0, 5.0/12.0, 2.0/5.0*2.0/5.0, &out);
pat[0] = 0; pat[1] = 2;
nb.predictDistribution(pat, &out);
GNaiveBayes_CheckResults(7.0/12.0, 4.0/7.0*2.0/7.0, 5.0/12.0, 2.0/5.0*0.0/5.0, &out);
pat[0] = 1; pat[1] = 0;
nb.predictDistribution(pat, &out);
GNaiveBayes_CheckResults(7.0/12.0, 3.0/7.0*3.0/7.0, 5.0/12.0, 3.0/5.0*3.0/5.0, &out);
pat[0] = 1; pat[1] = 1;
nb.predictDistribution(pat, &out);
GNaiveBayes_CheckResults(7.0/12.0, 3.0/7.0*2.0/7.0, 5.0/12.0, 3.0/5.0*2.0/5.0, &out);
pat[0] = 1; pat[1] = 2;
nb.predictDistribution(pat, &out);
GNaiveBayes_CheckResults(7.0/12.0, 3.0/7.0*2.0/7.0, 5.0/12.0, 3.0/5.0*0.0/5.0, &out);
}
