wanirepo

% In this simulation we examined how reliable peak distance and pattern correlation
% by comparing two simulated data with the same ground truth patterns of signal.

% define SNR levels

snr_all = [.1 .3 .5 .7 .9 1.1];

% create ground truth pattern

pattern = [0.4 1.7 0.5 0.7 0.2

wanirepo

poscm = colormap_tor([0.96 0.41 0], [1 1 0]);  % warm
negcm = colormap_tor([0.11 0.46 1], [.23 1 1]);  % cools

cluster_surf(cl ,which('surf_BrainMesh_ICBM152Right_smoothed.mat'), 2, 'heatmap', 'colormaps', poscm, negcm)

axis vis3d;

wanirepo

cd('/Users/clinpsywoo/github/fastRPCA');
setup_fastRPCA;

% load an example data
load('/Users/clinpsywoo/github/SAS2015_PatRec/data.mat');

X = dat.dat;
SS = svd(X, 'econ');  % can decompose x or x', but faster when rows >> cols
                      % 3 solvers (5 variants)
                      %   1) constrained

wanirepo

function [bestL, bestP, info] = KL_heuristic_k2(A, varargin)

% usage: [bestL, bestP, info] = KL_heuristic_k2(A, varargin)
%
% feature: use the Kernighan-Lin (KL) heuristic to optimize any partition 
%          score function, e.g., modularity Q or stochastic block model's
%          likelihood function. This works only for 2 partitioning problem.
%
% input:   A        adjacency matrix
%

wanirepo

function L = SBM_likelihood(A, z, varargin)

% usage: L = SBM_likelihood(A, z)
%
% feature: log-likelihood estimation for simple Stochastic Block Model (SBM)
%          (undirected, unweighted) based on Maximum Likelihood estimation. 
%
% input:   A      adjacency matrix (simple graph)
%          z      group membership
%

wanirepo

% Data info: 
%   Each of the school .mat files has an A matrix (sparse) and a
%   "local_info" variable, one row per node: a student/faculty status
%   flag, gender, major, second major/minor (if applicable), dorm/house,
%   year, and high school. Missing data is coded 0.

% datdir = '/Users/clinpsywoo/Documents/2011-2016yr/2014_2015_4th_GS/Network_modeling/Problem_sets/facebook100';
datdir = '/Volumes/engram/Users/wani/Documents/Network_modeling/Problem_sets/facebook100';
fnames = filenames(fullfile(datdir, '*mat'));

wanirepo

function nmi = norm_mutual_info(za, zb)

% function nmi = norm_mutual_info(za, zb)
%
% feature: This function calculates the normalized mutual information,
%          which tells us how much information we learn about Community 
%          structure A (or B) if we know B (or A). If A and B are 
%          identical, we learn everything about A from B (or B from A). 
%          In this case, nmi returns 1. If they are entirely uncorrelated, 
%          we learn nothing. In this case, nmi returns 0. 

wanirepo

function [max_z, max_q, outinfo] = community_modularity(A, varargin)

% function [z, q, outinfo] = community_modularity(A, optional_inputs)
%
% feature: This function conduct the greedy agglomerative algorithm to find
%          community structure that maximizes the network's modularity (Q). 
%
% input:   A      adjacency matrix
%
% output:  max_z    a vector of community membership that maximize Q

wanirepo

function q = modularity_wani(A,z,varargin)

% function q = modularity_wani(A,z, [optional 'scalar' or 'degree'])
%
% feature: This function calculates the modularity (same with 
%          assortativity), q. It works for categorical and continuous
%          (needs optional input, 'scalar') attributes. 
% 
% input:   z   attributes or category membership
%          A   adjacency matrix

wanirepo

function A = build_adjacency_from_list(ij)

% function A = build_adjacency_from_list(ij)
%
% ij: row, column

A = zeros(max(max(ij)),max(max(ij)));

for i = 1:length(ij)
    A(ij(i,1), ij(i,2)) = 1;