%% DCNT sample toy script to generate valid dataobj
clear all; close all; clc;

% Imagine we have a set of 3 documents with a very small number of words
doc1 = {'jump','cat','house','squid','cat','house',};
doc2 = {'cat','saddle','boat'};
doc3 = {'jump','squid','house','squid'};

% We can index these words in a vocab cell array.
vocab{1} = 'jump';
vocab{2} = 'cat';
vocab{3} = 'house';
vocab{4} = 'squid';
vocab{5} = 'saddle';
vocab{6} = 'boat';

% We then assign word indices and save them in dataobj.data.doc
dataobj.data.doc{1} = [1 2 3 4 2 3];
dataobj.data.doc{2} = [2 5 6];
% for document 3, squid corresponds to word 4 in the vocab cell array
dataobj.data.doc{3} = [1 4 3 4]; 

% Create metadata 
% Assuming we have no features, we still always need a bias matrix
F = 1; % F will always be greater than or equal to 1
D = 3; % Number of documents
dataobj.true.phiF = ones(F,D);
dataobj.true.W = length(vocab); %The number of unique words in our corpus

% If we have metadata, assume we have two features
% Let's say feature one is a binary flag that tells us a document is fiction/non-fiction 

% Let's say feature two is a normalized real value tha tells us how well
% known it is with 1 being the most well known and 0 being the least well known

F = 3; %bias feature + two features per document
phiF = zeros(F,D);
phiF(1,:) = 1; % bias feature
phiF(2,:) = [0 0 1];
phiF(3,:) = [.1 .1 1];
dataobj.true.phiF = phiF;

save('toyData.mat','dataobj'); % you can then load this to run DCNT

%NOTE: NECESSARY FOR DCNT
% dataobj.data.doc
% dataobj.true.phiF
% dataobj.true.W