Mercurial > hg > camir-aes2014

annotate core/magnatagatune/makro_cupaper12_get_significance.m @ 0:e9a9cd732c1e tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
first hg version after svn
author wolffd
date Tue, 10 Feb 2015 15:05:51 +0000
parents
children
rev   line source
wolffd@0 1 % makro_get_significance_cupaper
wolffd@0 2 %%
wolffd@0 3 % ------------------------------ Algorithms Compared id-sampling
wolffd@0 4 % ---
wolffd@0 5 'mlr vs euclidean, mlr all average feat, ID-sampling'
wolffd@0 6 file1 = 'runlog_0b506247a68167addf97fcb0296650eb_1a58077f1232c33b787b661039df107d_finalresults';
wolffd@0 7
wolffd@0 8 % euclidean average feat - TODO: which sampling is this ?
wolffd@0 9 file2 = 'runlog_0b506247a68167addf97fcb0296650eb_1a9788c5e14f30e23ed2a05dbf513c9f_finalresults';
wolffd@0 10 % ---
wolffd@0 11 % NOTE: all 4 test-set runs have exactly the same result
wolffd@0 12 % ---
wolffd@0 13 run1 = -1;
wolffd@0 14 run2 = -1;
wolffd@0 15 mode = 'join_datasets'; % '', 'avgbase', 'join_datasets'
wolffd@0 16 [p, med, avg] = test_generic_significance_signrank(file1,run1,file2,run1,0,mode);
wolffd@0 17 fprintf('p = %3.4f, median = %3.4f, avg = %3.4f \n\n',p,med,avg);
wolffd@0 18
wolffd@0 19
wolffd@0 20 %%
wolffd@0 21 % ---
wolffd@0 22 'SVM vs euclidean, SVM all average feat, ID-sampling'
wolffd@0 23 file1 = 'runlog_0b506247a68167addf97fcb0296650eb_1841892e9df07039bbe4c3a55d11026a_finalresults';
wolffd@0 24
wolffd@0 25 % euclidean average feat - TODO: which sampling is this ?
wolffd@0 26 file2 = 'runlog_0b506247a68167addf97fcb0296650eb_1a9788c5e14f30e23ed2a05dbf513c9f_finalresults';
wolffd@0 27
wolffd@0 28 [p, med, avg] = test_generic_significance_signrank(file1,run1,file2,run2,0,mode);
wolffd@0 29 fprintf('p = %3.4f, median = %3.4f, avg = %3.4f \n\n',p,med,avg);
wolffd@0 30
wolffd@0 31 %%
wolffd@0 32 % ------------------------------ Algorithms Compared TD-sampling
wolffd@0 33 % ---
wolffd@0 34 'mlr unclustered vs euclidean unclustered, mlr all average feat TD-sampling'
wolffd@0 35 file1 = 'runlog_0b506247a68167addf97fcb0296650eb_c364cb0803822d55f2940656c44b184d_finalresults';
wolffd@0 36
wolffd@0 37 % euclidean average feat TD-sampling
wolffd@0 38 file2 = 'runlog_0b506247a68167addf97fcb0296650eb_72303bfa642aad872665dee7a3b1e28c_finalresults';
wolffd@0 39
wolffd@0 40 [p, med, avg] = test_generic_significance_signrank(file1,run1,file2,run2,0,mode);
wolffd@0 41 fprintf('p = %3.4f, median = %3.4f, avg = %3.4f \n\n',p,med,avg);
wolffd@0 42
wolffd@0 43 %%
wolffd@0 44 % ---
wolffd@0 45 'SVM unclustered vs euclidean unclustered, SVM all average feat TD-sampling'
wolffd@0 46 file1 = 'runlog_0b506247a68167addf97fcb0296650eb_3434f0534fa910b26bbf927c65a7fb74_finalresults';
wolffd@0 47
wolffd@0 48 % euclidean average feat TD-sampling
wolffd@0 49 file2 = 'runlog_0b506247a68167addf97fcb0296650eb_72303bfa642aad872665dee7a3b1e28c_finalresults';
wolffd@0 50 % ---
wolffd@0 51
wolffd@0 52 [p, med, avg] = test_generic_significance_signrank(file1,run1,file2,run2,0,mode);
wolffd@0 53 fprintf('p = %3.4f, median = %3.4f, avg = %3.4f \n\n',p,med,avg);
wolffd@0 54
wolffd@0 55
wolffd@0 56 %%
wolffd@0 57 % ------------------------------ Features Compared
wolffd@0 58 'All 12-dim PCA Features compared'
wolffd@0 59 % ---
wolffd@0 60 namePCA12 = {'AcousticPCA12', ...
wolffd@0 61 'Slaney08PCA12', ...
wolffd@0 62 'TimbrePCA12', ...
wolffd@0 63 'ChromaPCA12', ...
wolffd@0 64 'AllPCA12', ...
wolffd@0 65 'GenrePCA12'};
wolffd@0 66 % this is the index how the feature types appear in the paper
wolffd@0 67 paperidx = [4 3 2 6 1 5];
wolffd@0 68
wolffd@0 69 filePCA12 = {'runlog_a18bd2111694ac59c9ba0a6810121796_1841892e9df07039bbe4c3a55d11026a_finalresults', ...
wolffd@0 70 'runlog_37e47c187886f73ec9a7d8dc24a84a52_1841892e9df07039bbe4c3a55d11026a_finalresults', ...
wolffd@0 71 'runlog_4c6787b403a07f5faf1ec26e891da4fa_1841892e9df07039bbe4c3a55d11026a_finalresults', ...
wolffd@0 72 'runlog_c5566f74e6a0d00b50f5eea05fdacfee_1841892e9df07039bbe4c3a55d11026a_finalresults', ...
wolffd@0 73 'runlog_e2c22696e7af9e7eea1fa1fd10a1f785_1841892e9df07039bbe4c3a55d11026a_finalresults', ...
wolffd@0 74 'runlog_efc6e5e9c56291cd1744092a1c59a293_1841892e9df07039bbe4c3a55d11026a_finalresults'};
wolffd@0 75
wolffd@0 76
wolffd@0 77 namePCA12 = namePCA12(paperidx);
wolffd@0 78 filePCA12 = filePCA12(paperidx);
wolffd@0 79
wolffd@0 80 p = zeros(numel(namePCA12),numel(namePCA12));
wolffd@0 81 med = zeros(numel(namePCA12),numel(namePCA12));
wolffd@0 82 avg = zeros(numel(namePCA12),numel(namePCA12));
wolffd@0 83 for i=1:numel(name)
wolffd@0 84 for j = 1:i-1
wolffd@0 85 [p(i,j), med(i,j), avg(i,j)] = test_generic_significance_signrank(filePCA12{i},-1,filePCA12{j},-1,0,mode);
wolffd@0 86 end
wolffd@0 87 % p(i,i) = 0.5;
wolffd@0 88 end
wolffd@0 89 % p = p + p';
wolffd@0 90 imagesc(p);
wolffd@0 91 colormap(hot)
wolffd@0 92 axis xy
wolffd@0 93 set(gca,'XTick',1:numel(namePCA12), 'XTickLabel', namePCA12);
wolffd@0 94 set(gca,'YTick',1:numel(namePCA12), 'YTickLabel', namePCA12);
wolffd@0 95 matrix2latex(p,'%1.3f')
wolffd@0 96
wolffd@0 97 %%
wolffd@0 98 'All 52-dim PCA Features compared'
wolffd@0 99 % ---
wolffd@0 100 namePCA52 = {'GenrePCA52', ...
wolffd@0 101 'AllPCA52', ...
wolffd@0 102 'TimbrePCA52', ...
wolffd@0 103 'AcousticPCA52', ...
wolffd@0 104 'ChromaPCA52' ...
wolffd@0 105 };
wolffd@0 106 % this is the index how the feature types appear in the paper
wolffd@0 107 paperidx = [5 3 1 4 2];
wolffd@0 108
wolffd@0 109 filePCA52 = {'runlog_3cbf4759cf58af0728aaab0b5f2660e3_1841892e9df07039bbe4c3a55d11026a_finalresults', ...
wolffd@0 110 'runlog_7d5fafec0dc504215acc8cb7a9202a56_1841892e9df07039bbe4c3a55d11026a_finalresults', ...
wolffd@0 111 'runlog_a3c2c0a5742a42fd54497e69b8f44e8d_1841892e9df07039bbe4c3a55d11026a_finalresults', ...
wolffd@0 112 'runlog_c7164074206998aa184538bedcfdcf2f_1841892e9df07039bbe4c3a55d11026a_finalresults', ...
wolffd@0 113 'runlog_efbf7c8e75ae154c2f192acd08fbdcbc_1841892e9df07039bbe4c3a55d11026a_finalresults' ...
wolffd@0 114 };
wolffd@0 115
wolffd@0 116
wolffd@0 117 namePCA52 = namePCA52(paperidx);
wolffd@0 118 filePCA52 = filePCA52(paperidx);
wolffd@0 119
wolffd@0 120 p = zeros(numel(namePCA52),numel(namePCA52));
wolffd@0 121 med = zeros(numel(namePCA52),numel(namePCA52));
wolffd@0 122 avg = zeros(numel(namePCA52),numel(namePCA52));
wolffd@0 123 for i=1:numel(name)
wolffd@0 124 for j = 1:i-1
wolffd@0 125 [p(i,j), med(i,j), avg(i,j)] = test_generic_significance_signrank(...
wolffd@0 126 filePCA52{i},run1,filePCA52{j},run2,0,mode);
wolffd@0 127 end
wolffd@0 128 % p(i,i) = 0.5;
wolffd@0 129 end
wolffd@0 130 % p = p + p';
wolffd@0 131 imagesc(p);
wolffd@0 132 colormap(hot)
wolffd@0 133 axis xy
wolffd@0 134 set(gca,'XTick',1:numel(namePCA52), 'XTickLabel', namePCA52);
wolffd@0 135 set(gca,'YTick',1:numel(namePCA52), 'YTickLabel', namePCA52);
wolffd@0 136 matrix2latex(p,'%1.3f')
wolffd@0 137
wolffd@0 138 %%
wolffd@0 139 'All full-dim Features compared (SVM)'
wolffd@0 140 % ---
wolffd@0 141 name = {'4Chroma', ...
wolffd@0 142 '1Chroma', ...
wolffd@0 143 '4Timbre', ...
wolffd@0 144 '1Timbre', ...
wolffd@0 145 '1Acoustic', ...
wolffd@0 146 'Genre', ...
wolffd@0 147 'Slaney08', ...
wolffd@0 148 '1All', ...
wolffd@0 149 '4All', ...
wolffd@0 150 '4Acoustic' ...
wolffd@0 151 };
wolffd@0 152
wolffd@0 153 % this is the index how the feature types appear in the paper
wolffd@0 154 % Features & Chroma(1/4) & Timbre(1/4) & Slaney08 & Genre & Comb. Audio (1/4) & Comb. All(1/4) \\
wolffd@0 155 paperidx = [2 1 4 3 7 6 5 10 8 9];
wolffd@0 156
wolffd@0 157 file = {'runlog_20a2f6a0f20f488e9386ebb8c5026fcf_85c439d9ef3d135936e7645ebc0efe36_finalresults', ...
wolffd@0 158 'runlog_20a2f6a0f20f488e9386ebb8c5026fcf_85c439d9ef3d135936e7645ebc0efe36_finalresults', ...
wolffd@0 159 'runlog_3154f36c34c18f60218c5d3f0c0b5931_85c439d9ef3d135936e7645ebc0efe36_finalresults', ...
wolffd@0 160 'runlog_3154f36c34c18f60218c5d3f0c0b5931_85c439d9ef3d135936e7645ebc0efe36_finalresults', ...
wolffd@0 161 'runlog_31981d48dd0d25564ef3c2b3ca650b3b_1841892e9df07039bbe4c3a55d11026a_finalresults', ...
wolffd@0 162 'runlog_37867d3b5bd4c74b7b548732b80fb947_85c439d9ef3d135936e7645ebc0efe36_finalresults', ...
wolffd@0 163 'runlog_f52d37439805ac4edc70b0432281abc3_85c439d9ef3d135936e7645ebc0efe36_finalresults', ...
wolffd@0 164 'runlog_0b506247a68167addf97fcb0296650eb_1841892e9df07039bbe4c3a55d11026a_finalresults', ...
wolffd@0 165 'runlog_800d97be9ef6274dc3bbe6b9be2406a6_1a58077f1232c33b787b661039df107d_finalresults', ...
wolffd@0 166 'runlog_cf5a61cca09e2a3182b794b70ee1ab91_1841892e9df07039bbe4c3a55d11026a_finalresults' ...
wolffd@0 167 };
wolffd@0 168
wolffd@0 169 sets2join = {[1:4],[5:8],[1:4],[5:8],[],[],[],[],[],[]};
wolffd@0 170
wolffd@0 171 name = name(paperidx);
wolffd@0 172 file = file(paperidx);
wolffd@0 173
wolffd@0 174 p = zeros(numel(name),numel(name));
wolffd@0 175 med = zeros(numel(name),numel(name));
wolffd@0 176 avg = zeros(numel(name),numel(name));
wolffd@0 177 for i=1:numel(name)
wolffd@0 178 for j = 1:i-1
wolffd@0 179 [p(i,j), med(i,j), avg(i,j)] = test_generic_significance_signrank(...
wolffd@0 180 file{i},sets2join{i},file{j},sets2join{j},0,mode);
wolffd@0 181 end
wolffd@0 182 % p(i,i) = 0.5;
wolffd@0 183 end
wolffd@0 184 p = flipud(p);
wolffd@0 185 % p = p + p';
wolffd@0 186 imagesc(p);
wolffd@0 187 colormap(hot)
wolffd@0 188 axis ij
wolffd@0 189 set(gca,'XTick',1:numel(name), 'XTickLabel', name);
wolffd@0 190 set(gca,'YTick',1:numel(name), 'YTickLabel', fliplr(name));
wolffd@0 191 matrix2latex(p,'%1.3f')
wolffd@0 192
wolffd@0 193 %%
wolffd@0 194 'Comparing Feature dimensions and PCA effect on combined all features'
wolffd@0 195 % ---
wolffd@0 196 % 'SVM all average feat, ID-sampling'
wolffd@0 197 allavg = 'runlog_0b506247a68167addf97fcb0296650eb_1841892e9df07039bbe4c3a55d11026a_finalresults';
wolffd@0 198
wolffd@0 199 % 'SVM 4 cluster feat, ID-sampling'
wolffd@0 200 allfourcluster = 'runlog_800d97be9ef6274dc3bbe6b9be2406a6_1a58077f1232c33b787b661039df107d_finalresults';
wolffd@0 201
wolffd@0 202 % 'SVM 12dim feat, ID-sampling'
wolffd@0 203 pca12 = 'runlog_e2c22696e7af9e7eea1fa1fd10a1f785_1841892e9df07039bbe4c3a55d11026a_finalresults';
wolffd@0 204
wolffd@0 205 % 'SVM 52dim feat, ID-sampling'
wolffd@0 206 pca52 = 'runlog_7d5fafec0dc504215acc8cb7a9202a56_1841892e9df07039bbe4c3a55d11026a_finalresults';
wolffd@0 207 % ---
wolffd@0 208 % NOTE: all 4 test-set runs have exactly the same result
wolffd@0 209 % ---
wolffd@0 210 run1 = -1;
wolffd@0 211 run2 = -1;
wolffd@0 212 mode = 'join_datasets'; % '', 'avgbase', 'join_datasets'
wolffd@0 213
wolffd@0 214 'AllAvg vs Pca12'
wolffd@0 215 [p, med, avg] = test_generic_significance_signrank(allavg,run1,pca12,run2,0,mode);
wolffd@0 216 fprintf('p = %3.4f, median = %3.4f, avg = %3.4f \n\n',p,med,avg);
wolffd@0 217
wolffd@0 218 'AllAvg vs pca52'
wolffd@0 219 [p, med, avg] = test_generic_significance_signrank(allavg,run1,pca52,run2,0,mode);
wolffd@0 220 fprintf('p = %3.4f, median = %3.4f, avg = %3.4f \n\n',p,med,avg);
wolffd@0 221
wolffd@0 222 'Pca12 vs pca52'
wolffd@0 223 [p, med, avg] = test_generic_significance_signrank(pca12,run1,pca52,run2,0,mode);
wolffd@0 224 fprintf('p = %3.4f, median = %3.4f, avg = %3.4f \n\n',p,med,avg);
wolffd@0 225
wolffd@0 226
wolffd@0 227 %%
wolffd@0 228 % ------------------------------ Algorithms Weighted Training Weighted Performance Compared
wolffd@0 229 'MLR t:w,e:w vs euclidean t:w,e:w'
wolffd@0 230 % ---
wolffd@0 231 file1 = 'runlog_0b506247a68167addf97fcb0296650eb_3cdcca7596fed97f87b0ec051cb8bba0_finalresults';
wolffd@0 232
wolffd@0 233 % euclidean baseline, file same as the unweighted above
wolffd@0 234 file2 = 'runlog_0b506247a68167addf97fcb0296650eb_1a9788c5e14f30e23ed2a05dbf513c9f_finalresults';
wolffd@0 235 % ---
wolffd@0 236 % NOTE: using the "weighted" parameter here
wolffd@0 237 % ---
wolffd@0 238 [p, med, avg] = test_generic_significance_signrank(file1,run1,file2,run2, 1 ,mode);
wolffd@0 239 fprintf('p = %3.4f, median = %3.4f, avg = %3.4f \n\n',p,med,avg);
wolffd@0 240
wolffd@0 241 %%
wolffd@0 242 'DMLR t:w,e:w vs euclidean t:w,e:w'
wolffd@0 243 % ---
wolffd@0 244 file1 = 'runlog_0b506247a68167addf97fcb0296650eb_1cc76d534804229cbdec8b20f8b75dba_finalresults';
wolffd@0 245
wolffd@0 246 % euclidean baseline, file same as the unweighted above
wolffd@0 247 file2 = 'runlog_0b506247a68167addf97fcb0296650eb_1a9788c5e14f30e23ed2a05dbf513c9f_finalresults';
wolffd@0 248 % ---
wolffd@0 249 % NOTE: using the "weighted" parameter here
wolffd@0 250 % ---
wolffd@0 251 [p, med, avg] = test_generic_significance_signrank(file1,run1,file2,run2, 1 ,mode);
wolffd@0 252 fprintf('p = %3.4f, median = %3.4f, avg = %3.4f \n\n',p,med,avg);
wolffd@0 253
wolffd@0 254 %%
wolffd@0 255 'SVM t:w,e:w vs euclidean t:w,e:w'
wolffd@0 256 % ---
wolffd@0 257 file1 = 'runlog_0b506247a68167addf97fcb0296650eb_9bd9ccddb2e4e622e2ba9826466442ba_finalresults';
wolffd@0 258
wolffd@0 259 % euclidean baseline, file same as the unweighted above
wolffd@0 260 file2 = 'runlog_0b506247a68167addf97fcb0296650eb_1a9788c5e14f30e23ed2a05dbf513c9f_finalresults';
wolffd@0 261 % ---
wolffd@0 262 % NOTE: using the "weighted" parameter here
wolffd@0 263 % ---
wolffd@0 264 [p, med, avg] = test_generic_significance_signrank(file1,run1,file2,run2, 1 ,mode);
wolffd@0 265 fprintf('p = %3.4f, median = %3.4f, avg = %3.4f \n\n',p,med,avg);
wolffd@0 266
wolffd@0 267 %%
wolffd@0 268 % ------------------------------ Algorithms Weighted Training UNWEIGHTED Performance Compared
wolffd@0 269 'MLR t:w,e:uw vs euclidean t:w,e:uw'
wolffd@0 270 % ---
wolffd@0 271 file1 = 'runlog_0b506247a68167addf97fcb0296650eb_3cdcca7596fed97f87b0ec051cb8bba0_finalresults';
wolffd@0 272
wolffd@0 273 % euclidean baseline, file same as the unweighted above
wolffd@0 274 file2 = 'runlog_0b506247a68167addf97fcb0296650eb_1a9788c5e14f30e23ed2a05dbf513c9f_finalresults';
wolffd@0 275 % ---
wolffd@0 276 % NOTE: using the "weighted" parameter here
wolffd@0 277 % ---
wolffd@0 278 [p, med, avg] = test_generic_significance_signrank(file1,run1,file2,run2, 0 ,mode);
wolffd@0 279 fprintf('p = %3.4f, median = %3.4f, avg = %3.4f \n\n',p,med,avg);
wolffd@0 280
wolffd@0 281 %%
wolffd@0 282 'DMLR t:w,e:uw vs euclidean t:w,e:uw'
wolffd@0 283 % ---
wolffd@0 284 file1 = 'runlog_0b506247a68167addf97fcb0296650eb_1cc76d534804229cbdec8b20f8b75dba_finalresults';
wolffd@0 285
wolffd@0 286 % euclidean baseline, file same as the unweighted above
wolffd@0 287 file2 = 'runlog_0b506247a68167addf97fcb0296650eb_1a9788c5e14f30e23ed2a05dbf513c9f_finalresults';
wolffd@0 288 % ---
wolffd@0 289 % NOTE: using the "weighted" parameter here
wolffd@0 290 % ---
wolffd@0 291 [p, med, avg] = test_generic_significance_signrank(file1,run1,file2,run2, 0 ,mode);
wolffd@0 292 fprintf('p = %3.4f, median = %3.4f, avg = %3.4f \n\n',p,med,avg);
wolffd@0 293
wolffd@0 294 %%
wolffd@0 295 'SVM t:w,e:uw vs euclidean t:w,e:uw'
wolffd@0 296 % ---
wolffd@0 297 file1 = 'runlog_0b506247a68167addf97fcb0296650eb_9bd9ccddb2e4e622e2ba9826466442ba_finalresults';
wolffd@0 298
wolffd@0 299 % euclidean baseline, file same as the unweighted above
wolffd@0 300 file2 = 'runlog_0b506247a68167addf97fcb0296650eb_1a9788c5e14f30e23ed2a05dbf513c9f_finalresults';
wolffd@0 301 % ---
wolffd@0 302 % NOTE: using the "weighted" parameter here
wolffd@0 303 % ---
wolffd@0 304 [p, med, avg] = test_generic_significance_signrank(file1,run1,file2,run2, 0 ,mode);
wolffd@0 305 fprintf('p = %3.4f, median = %3.4f, avg = %3.4f \n\n',p,med,avg);
wolffd@0 306
wolffd@0 307
wolffd@0 308 %%
wolffd@0 309 % ------------------------------ Algorithms w / uw Training WEIGHTED Performance Compared
wolffd@0 310 'MLR t:w,e:w vs MLR t:uw,e:w'
wolffd@0 311 % ---
wolffd@0 312 % MLR t:w,e:w
wolffd@0 313 file1 = 'runlog_0b506247a68167addf97fcb0296650eb_3cdcca7596fed97f87b0ec051cb8bba0_finalresults';
wolffd@0 314
wolffd@0 315 % MLR t:uw,e:w
wolffd@0 316 file2 = 'runlog_0b506247a68167addf97fcb0296650eb_1a58077f1232c33b787b661039df107d_finalresults';
wolffd@0 317 % ---
wolffd@0 318 % NOTE: using the "weighted" parameter here
wolffd@0 319 % ---
wolffd@0 320 [p, med, avg] = test_generic_significance_signrank(file1,run1,file2,run2, 1 ,mode);
wolffd@0 321 fprintf('p = %3.4f, median = %3.4f, avg = %3.4f \n\n',p,med,avg);
wolffd@0 322
wolffd@0 323 %%
wolffd@0 324 % ---
wolffd@0 325 'SVM t:w,e:w vs SVM t:uw,e:w'
wolffd@0 326 % ---
wolffd@0 327 % SVM t:w,e:w
wolffd@0 328 file1 = 'runlog_0b506247a68167addf97fcb0296650eb_9bd9ccddb2e4e622e2ba9826466442ba_finalresults';
wolffd@0 329
wolffd@0 330 % SVM t:uw,e:w
wolffd@0 331 file2 = 'runlog_0b506247a68167addf97fcb0296650eb_1841892e9df07039bbe4c3a55d11026a_finalresults';
wolffd@0 332 % ---
wolffd@0 333 % NOTE: using the "weighted" parameter here
wolffd@0 334 % ---
wolffd@0 335 [p, med, avg] = test_generic_significance_signrank(file1,run1,file2,run2, 1 ,mode);
wolffd@0 336 fprintf('p = %3.4f, median = %3.4f, avg = %3.4f \n\n',p,med,avg);
wolffd@0 337
wolffd@0 338 %%
wolffd@0 339 % ------------------------------ Algorithms w / uw Training WEIGHTED Performance Compared
wolffd@0 340 'DMLR t:w,e:w vs DMLR t:uw,e:w'
wolffd@0 341 % ---
wolffd@0 342 % DMLR t:w,e:w
wolffd@0 343 file1 = 'runlog_0b506247a68167addf97fcb0296650eb_1cc76d534804229cbdec8b20f8b75dba_finalresults';
wolffd@0 344
wolffd@0 345 % DMLR t:uw,e:w
wolffd@0 346 file2 = 'runlog_0b506247a68167addf97fcb0296650eb_bf08b16f453683d96ddffc31c6439730_finalresults';
wolffd@0 347 % ---
wolffd@0 348 % NOTE: using the "weighted" parameter here
wolffd@0 349 % ---
wolffd@0 350 [p, med, avg] = test_generic_significance_signrank(file1,run1,file2,run2, 1 ,mode);
wolffd@0 351 fprintf('p = %3.4f, median = %3.4f, avg = %3.4f \n\n',p,med,avg);