function dataMat = readSeparatedDataColumns( location, ...
  desiredColumns)
%readNewerDataFromCsv -  Read newer data provided by Lars.
% Reads the newer data from Lars. It assumes the script
% separateNewerDataColumns() has already been run. This script
% eliminates the data points for which self_match = 1.
%
% USAGE: dataMat =readSeparatedDataColumns(location, desiredColumns)
% location - string with the directory where the results of
% separateNewerDataColumns() are stored.
% desiredColumns - cell array of strings, each indicating the name
% of the column (feature) to be read.
% dataMat - matrix, each column corresponding to one of the columnNames.
%
% EXAMPLE: 
% dataMat = readSeparatedDataColumns('data_dir', {'ratio', zscore'});
% returns a N-by-2 matrix, with column 1 containing the ratio feature
% and column 2 containing the zscore feature.

%Written by Luca Cazzanti
%Copyright 2005
%$Id$

%location = 'newer_csv_data';

%desiredColumns = {'ratio', 'zscore', ...
%  'experiment_contact_order', 'prediction_contact_order', ...
% 'experiment_percent_alpha', 'prediction_percent_alpha', ...
%  'experiment_percent_beta', 'prediction_percent_beta', ...
%  'correct_superfamily'};


nColumns = length(desiredColumns);

% First find the self-matches: must take them out of each feature
fname = fullfile(location, 'self_match.txt');
if exist(fname, 'file')
  self_match = textread(fname, '%n', 'headerlines', 1);
  idx = find(self_match == 1);
  dataMat = zeros(length(self_match) - length(idx), nColumns);
  clear self_match;
  disp('Self-matches were found and removed');
  
  % Find rest of features
  for iCol = 1:nColumns
    fname = fullfile(location, [desiredColumns{iCol} '.txt']);
    tmp = textread(fname, '%n', 'headerlines', 1);
    tmp(idx) = [];
    dataMat(:,iCol) = tmp;
  end
else 
  
  % Find rest of features
  for iCol = 1:nColumns
    fname = fullfile(location, [desiredColumns{iCol} '.txt']);
    tmp = textread(fname, '%n', 'headerlines', 1);
    dataMat(:,iCol) = tmp;
  end
end %if exist(fname)