//inference new model ~ getting data from a specified dataset
public Model inference(LDADataset newData)
{
Console.WriteLine("init new model");
Model newModel = new Model();
newModel.initNewModel(option, newData, trnModel);
this.newModel = newModel;
Console.WriteLine("Sampling " + niters + " iteration for inference!");
for (newModel.liter = 1; newModel.liter <= niters; newModel.liter++)
{
//System.out.println("Iteration " + newModel.liter + " ...");
// for all newz_i
for (int m = 0; m < newModel.M; ++m)
{
for (int n = 0; n < newModel.data.Docs[m].Length; n++)
{
// (newz_i = newz[m][n]
// sample from p(z_i|z_-1,w)
int topic = infSampling(m, n);
newModel.z[m].Insert(n, topic);
}
} //end foreach new doc
} // end iterations
Console.WriteLine("Gibbs sampling for inference completed!");
computeNewTheta();
computeNewPhi();
newModel.liter--;
return(this.newModel);
}
protected bool readTAssignFile(string tassignFile)
{
try
{
int i, j;
var reader = new StreamReader(tassignFile);
string line;
z = new List <int> [M];
data = new LDADataset(M);
data.V = V;
for (i = 0; i < M; i++)
{
line = reader.ReadLine();
var parts = line.Split();
int length = parts.Length;
var words = new List <int>();
var topics = new List <int>();
for (j = 0; j < length; j++)
{
var token = parts[j];
var tokenParts = token.Split(':');
if (tokenParts.Count() != 2)
{
Console.WriteLine("Invalid word-topic assignment line\n");
return(false);
}
words.Add(Convert.ToInt32(tokenParts[0]));
topics.Add(Convert.ToInt32(tokenParts[0]));
}//end for each topic assignment
//allocate and add new document to the corpus
Document doc = new Document(words);
data.SetDoc(doc, i);
//assign values for z
z[i] = new List <int>();
for (j = 0; j < topics.Count(); j++)
{
z[i].Add(topics[j]);
}
}//end for each doc
reader.Close();
}
catch (Exception e)
{
Console.WriteLine("Error while loading model: " + e.Message);
return(false);
}
return(true);
}
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));
}
public static LDADataset ReadDataset(string[] strings, WordDictionary dictionary)
{
var dataSet = new LDADataset(strings.Length, dictionary);
for (int i = 0; i < strings.Length; i++)
{
dataSet.SetDoc(strings[i], i);
}
return(dataSet);
}
public static LDADataset ReadDataset(string[] strings)
{
var dataSet = new LDADataset(strings.Length);
for (int i = 0; i < strings.Length; i++)
{
dataSet.SetDoc(strings[i], i);
}
return(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));
}
public static LDADataset ReadDataset(string filename)
{
try
{
using (StreamReader reader = new StreamReader(filename))
{
var line = reader.ReadLine();
var m = Convert.ToInt32(line);
var dataSet = new LDADataset(m);
for (int i = 0; i < m; i++)
{
line = reader.ReadLine();
dataSet.SetDoc(line, i);
}
return(dataSet);
}
}
catch (Exception e)
{
Console.WriteLine("Failed reading dataSet :" + e.Message);
return(null);
}
}
/**
* Init parameters for inference
* @param newData DataSet for which we do inference
*/
public bool initNewModel(LDACommandLineOptions option, LDADataset newData, Model trnModel)
{
if (!init(option))
{
return(false);
}
int m, n;
var rnd = new Random();
K = trnModel.K;
alpha = trnModel.alpha;
beta = trnModel.beta;
p = new double[K];
Console.WriteLine("K:" + K);
data = newData;
//+ allocate memory and assign values for variables
M = data.M;
V = data.V;
dir = option.dir;
savestep = option.savestep;
Console.WriteLine("M:" + M);
Console.WriteLine("V:" + V);
// K: from command line or default value
// alpha, beta: from command line or default values
// niters, savestep: from command line or default values
nw = ArrayInitializers.ZerosInt(V, K);
nd = ArrayInitializers.ZerosInt(M, K);
nwsum = ArrayInitializers.ZerosInt(K);
ndsum = ArrayInitializers.ZerosInt(M);
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 = ArrayInitializers.Empty(M, K);
phi = ArrayInitializers.Empty(K, V);
return(true);
}
/**
* 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);
}
