fix: cats set learn_returns_prediction correctly (#4071)

test/pred-sets/ref/cats.predict

@@ -1,57 +1,57 @@
-17540.90625,0.00016
-15536.194336,0.00016
-17381.867188,0.00016
-12421.001953,0.00016
-13341.68457,0.00016
-15988.089844,0.00016
-13866.5,0.00016
-17106.007812,0.00016
-15123.611328,0.00016
-15783.711914,0.00016
-22992.765625,0.000002
-7194.499512,0.000002
-15160.824219,0.00016
-17345.21875,0.00016
-14788.841797,0.00016
-14527.181641,0.00016
-16322.044922,0.00016
-12985.182617,0.00016
-13590.578125,0.00016
-14753.837891,0.00016
-17058.365234,0.00016
-13427.973633,0.00016
-16906.275391,0.00016
-14033.335938,0.00016
-12143.845703,0.00016
-14244.833008,0.00016
-16280.450195,0.00016
-16732.472656,0.00016
-14155.6875,0.00016
-15759.546875,0.00016
-14163.108398,0.00016
-14782.350586,0.00016
-12062.177734,0.00016
-22556.402344,0.000002
-16126.390625,0.00016
-17084.583984,0.00016
-17965.972656,0.00016
-12816.858398,0.00016
-14803.016602,0.00016
-16711.628906,0.00016
-14877.601562,0.00016
-15326.173828,0.00016
-13539.920898,0.00016
-15957.607422,0.00016
-15291.404297,0.00016
-13974.890625,0.00016
-17413.5625,0.00016
-13018.841797,0.00016
-17922.017578,0.00016
-17293.945312,0.00016
-15109.65625,0.00016
-16252.369141,0.00016
-14785.5625,0.00016
-17082.445312,0.00016
-15951.467773,0.00016
-12971.433594,0.00016
-12969.782227,0.00016
+17118.012,0.00016043648
+15724.644,0.00016043648
+15331.798,0.00016043648
+15138.831,0.00016043648
+13393.029,0.00016043648
+12710.978,0.00016043648
+14503.708,0.00016043648
+15936.4,0.00016043648
+17257.076,0.00016043648
+17208.654,0.00016043648
+14921.187,0.00016043648
+16660.594,0.00016043648
+13486.455,0.00016043648
+6641.8545,2.1031378e-06
+14801.345,0.00016043648
+17399.625,0.00016043648
+16820.953,0.00016043648
+13160.789,0.00016043648
+15094.871,0.00016043648
+13487.722,0.00016043648
+17514.398,0.00016043648
+12287.391,0.00016043648
+17394.318,0.00016043648
+12249.621,0.00016043648
+12830.798,0.00016043648
+14759.012,0.00016043648
+17850.668,0.00016043648
+15202.806,0.00016043648
+16561.379,0.00016043648
+12855.774,0.00016043648
+13520.215,0.00016043648
+14063.967,0.00016043648
+16150.232,0.00016043648
+12360.427,0.00016043648
+13487.657,0.00016043648
+17476.367,0.00016043648
+15890.128,0.00016043648
+14077.783,0.00016043648
+17775.543,0.00016043648
+15440.219,0.00016043648
+16326.922,0.00016043648
+13204.399,0.00016043648
+17127.232,0.00016043648
+17641.572,0.00016043648
+13169.023,0.00016043648
+16228.357,0.00016043648
+14428.307,0.00016043648
+16230.57,0.00016043648
+12099.055,0.00016043648
+17408.406,0.00016043648
+17183.14,0.00016043648
+13980.631,0.00016043648
+16711.67,0.00016043648
+1768.2766,2.1031378e-06
+12294.268,0.00016043648
+15582.021,0.00016043648
+17690.637,0.00016043648

test/pred-sets/ref/cats_load.predict

@@ -1,10 +1,10 @@
-25.2719,0.00625
-2.12902,0.40625
-4.47363,0.00625
-18.2057,0.00625
-2.40591,0.40625
-9.58582,0.00625
-0.939304,0.40625
-1.78012,0.40625
-2.09265,0.40625
-0.803812,0.40625
+2.3137953,0.40625
+1.8475317,0.40625
+2.1299162,0.40625
+1.7430687,0.40625
+14.327164,0.00625
+1.7164373,0.40625
+1.748255,0.40625
+30.00431,0.00625
+0.51225615,0.40625
+2.3816023,0.40625

test/pred-sets/ref/cats_room_temp.predict

@@ -1,100 +1,100 @@
-53.204613,0.088333
-9.196535,0.005
-17.174236,0.088333
-77.290878,0.005
-15.437802,0.088333
-93.60582,0.005
-73.45269,0.005
-19.235268,0.088333
-40.031319,0.005
-18.646629,0.088333
-66.666214,0.005
-53.193462,0.088333
-34.754963,0.005
-34.701981,0.005
-57.403484,0.005
-67.807449,0.005
-86.918579,0.005
-52.78149,0.088333
-43.365547,0.005
-55.016094,0.088333
-8.145193,0.005
-57.613731,0.088333
-50.82185,0.088333
-48.282825,0.005
-81.51001,0.005
-26.397629,0.005
-23.397736,0.005
-50.563953,0.088333
-53.253433,0.088333
-53.1661,0.088333
-50.818462,0.088333
-72.269608,0.005
-73.63446,0.005
-70.715919,0.005
-23.831461,0.005
-51.322205,0.088333
-26.745371,0.005
-54.481422,0.088333
-52.270885,0.088333
-48.716354,0.088333
-9.419978,0.005
-2.715931,0.005
-51.904087,0.088333
-51.104538,0.088333
-0.305278,0.005
-76.843658,0.005
-20.968102,0.005
-58.275642,0.005
-6.868239,0.005
-40.830856,0.005
-54.123058,0.088333
-51.637661,0.088333
-95.593292,0.005
-48.718655,0.088333
-53.290802,0.088333
-80.526413,0.005
-50.78907,0.088333
-12.805883,0.005
-89.139755,0.005
-76.673355,0.005
-55.554798,0.005
-11.593977,0.005
-51.988331,0.088333
-30.242346,0.005
-66.171425,0.005
-51.027653,0.088333
-53.797455,0.088333
-91.316422,0.005
-75.985733,0.005
-51.833698,0.088333
-95.297424,0.005
-54.301224,0.088333
-49.036102,0.088333
-31.043774,0.005
-56.56052,0.005
-48.777672,0.088333
-53.007671,0.088333
-49.76527,0.088333
-28.06632,0.005
-53.554474,0.088333
-54.249149,0.088333
-15.149416,0.005
-48.76757,0.088333
-48.71854,0.088333
-52.769234,0.088333
-79.306122,0.005
-2.746499,0.005
-53.082054,0.088333
-58.803741,0.005
-49.790363,0.088333
-56.004501,0.005
-88.905861,0.005
-52.904503,0.088333
-52.2649,0.088333
-11.048922,0.005
-53.875389,0.088333
-49.905197,0.088333
-42.230206,0.005
-42.714077,0.005
-68.103302,0.005
+84.607056,0.005
+3.9181187,0.08833334
+39.260834,0.005
+17.99776,0.08833334
+39.331844,0.005
+6.7627044,0.005
+77.12543,0.005
+69.8972,0.005
+17.184662,0.08833334
+54.76903,0.005
+0.66596967,0.005
+13.026539,0.005
+52.522453,0.08833334
+86.18144,0.005
+49.648746,0.08833334
+53.096367,0.08833334
+41.92059,0.005
+88.03693,0.005
+50.15336,0.08833334
+1.6463974,0.005
+57.090523,0.08833334
+25.416866,0.005
+94.471146,0.005
+43.387676,0.005
+59.151047,0.08833334
+38.3481,0.005
+51.486103,0.08833334
+50.88297,0.08833334
+85.89383,0.005
+55.38167,0.005
+51.260296,0.08833334
+85.17497,0.005
+50.680935,0.08833334
+49.601463,0.08833334
+59.61712,0.005
+76.559,0.005
+51.651062,0.08833334
+62.96363,0.005
+7.8253226,0.005
+32.741436,0.005
+21.816528,0.005
+53.33639,0.08833334
+33.895855,0.005
+48.782,0.08833334
+48.93803,0.08833334
+48.645847,0.08833334
+53.199036,0.08833334
+77.73645,0.005
+62.783302,0.005
+18.494978,0.005
+66.79538,0.005
+53.29303,0.08833334
+53.5938,0.08833334
+47.533524,0.005
+8.389192,0.005
+28.030102,0.005
+52.605915,0.08833334
+53.525967,0.08833334
+50.158722,0.08833334
+47.26561,0.005
+72.41367,0.005
+1.1448574,0.005
+53.4234,0.08833334
+88.777985,0.005
+95.276276,0.005
+49.196915,0.08833334
+48.705658,0.08833334
+51.38816,0.08833334
+9.958978,0.005
+95.176796,0.005
+56.863132,0.005
+48.599724,0.08833334
+42.992935,0.005
+49.75944,0.08833334
+21.298155,0.005
+21.954062,0.005
+54.1602,0.08833334
+53.210964,0.08833334
+52.06177,0.08833334
+55.077793,0.005
+50.11463,0.08833334
+55.921093,0.005
+67.825,0.005
+74.41847,0.005
+79.864365,0.005
+24.734612,0.005
+53.9586,0.08833334
+94.53804,0.005
+48.65285,0.08833334
+67.55201,0.005
+48.724384,0.08833334
+50.91952,0.08833334
+40.403355,0.005
+46.697994,0.005
+49.63687,0.08833334
+50.199287,0.08833334
+52.23696,0.08833334
+48.77658,0.08833334
+52.563095,0.08833334
+14.676942,0.005

test/pred-sets/ref/cats_save.predict

@@ -1,10 +1,10 @@
-0.001202,0.00625
-0.611352,0.40625
-0.582045,0.40625
-2.234319,0.40625
-20.461426,0.00625
-1.228605,0.40625
-10.350056,0.00625
+0.6113522,0.40625
+2.2343192,0.40625
+1.2286053,0.40625
 22.592487,0.00625
-2.287724,0.40625
-1.316346,0.40625
+1.3163464,0.40625
+2.1290207,0.40625
+18.205719,0.00625
+9.585819,0.00625
+1.7801242,0.40625
+0.8038121,0.40625

test/train-sets/ref/cats-pdf-train.stderr

@@ -15,17 +15,17 @@ Input label = continuous
 Output pred = pdf
 average  since         example        example        current        current  current
 loss     last          counter         weight          label        predict features
-0.657567 0.657567            1            1.0 {185.12,0.6...                      10
-0.557941 0.458316            2            2.0 {772.59,0.4...                      10
-0.363443 0.168945            4            4.0 {14122,0.02,0}                      10
-0.299771 0.236098            8            8.0 {12715.1,0....                      10
-0.307594 0.315418           16           16.0 {669.12,0.4...                      10
-0.290863 0.274131           32           32.0 {10786.7,0....                      10
+0.657567 0.657567            1            1.0 {185.12,0.6... 185-1156.75...       10
+0.557941 0.458316            2            2.0 {772.59,0.4... 185-7100.25...       10
+0.363443 0.168945            4            4.0 {14122,0.02,0} 185-7100.25...       10
+0.299771 0.236098            8            8.0 {12715.1,0.... 185-7100.25...       10
+0.307594 0.315418           16           16.0 {669.12,0.4... 185-18987.2...       10
+0.290863 0.274131           32           32.0 {10786.7,0.... 185-18987.2...       10
 
 finished run
 number of examples = 57
 weighted example sum = 57.000000
 weighted label sum = 57.000000
 average loss = 0.267669
 total feature number = 570
-Learn() count per node: id=0, #l=21; id=1, #l=37; id=2, #l=20;
+Learn() count per node: id=0, #l=21; id=1, #l=37; id=2, #l=20;