public Model inference(string[] strs)
{
//System.out.println("inference");
Model newModel = new Model();
//System.out.println("read dataset");
LDADataset dataset = LDADataset.ReadDataset(strs, globalDict);
return(inference(dataset));
}
/**
* Init parameters for inference
* reading new dataset from file
*/
public bool initNewModel(LDACommandLineOptions option, Model trnModel)
{
if (!init(option))
{
return(false);
}
LDADataset dataset = LDADataset.ReadDataset(dir + "\\" + dfile, trnModel.data.LocalDictionary);
if (dataset == null)
{
Console.WriteLine("Fail to read dataset!\n");
return(false);
}
return(initNewModel(option, dataset, trnModel));
}
/**
* Init parameters for estimation
*/
public bool initNewModel(LDACommandLineOptions option)
{
//if (!init(option))
//return false;
var rnd = new Random();
int m, n, w, k;
p = new double[K];
data = LDADataset.ReadDataset(dir + "\\" + dfile);
if (data == null)
{
Console.WriteLine("Fail to read training data!\n");
return(false);
}
//+ allocate memory and assign values for variables
M = data.M;
V = data.V;
dir = option.dir;
savestep = option.savestep;
// K: from command line or default value
// alpha, beta: from command line or default values
// niters, savestep: from command line or default values
nw = new int[V][];
for (w = 0; w < V; w++)
{
nw[w] = new int[K];
for (k = 0; k < K; k++)
{
nw[w][k] = 0;
}
}
nd = new int[M][];
for (m = 0; m < M; m++)
{
nd[m] = new int[K];
for (k = 0; k < K; k++)
{
nd[m][k] = 0;
}
}
nwsum = new int[K];
for (k = 0; k < K; k++)
{
nwsum[k] = 0;
}
ndsum = new int[M];
for (m = 0; m < M; m++)
{
ndsum[m] = 0;
}
z = new List <int> [M];
for (m = 0; m < data.M; m++)
{
int N = data.Docs[m].Length;
z[m] = new List <int>();
//initilize for z
for (n = 0; n < N; n++)
{
int topic = (int)Math.Floor(rnd.NextDouble() * K);
z[m].Add(topic);
// number of instances of word assigned to topic j
nw[data.Docs[m].Words[n]][topic] += 1;
// number of words in document i assigned to topic j
nd[m][topic] += 1;
// total number of words assigned to topic j
nwsum[topic] += 1;
}
// total number of words in document i
ndsum[m] = N;
}
theta = new double[M][];
for (m = 0; m < M; m++)
{
theta[m] = new double[K];
}
phi = new double[K][];
for (k = 0; k < K; k++)
{
phi[k] = new double[V];
}
return(true);
}