Machine learning in trading: theory, models, practice and algo-trading - page 1922

 
Maxim Dmitrievsky:

Altai... But I didn't go at the last moment, I didn't want to.)

by the way, you know about the pros?

I can share my code for parsing Catbust models for continuous variables only. It reads C++ code, converts into MQL arrays and executes. I can't say it will work with all possible parameters, I was making it for a specific format.
 
Aliaksandr Hryshyn:
I can share code for parsing Catbust models, only for continuous variables. Reading C++ code, converting it to MQL arrays and executing it. I can't say that with all possible parameters it will work, I did it for a specific format.

What's the parsing on? I use python for everything.

It spits out in this format. Binary Classifier

#include <string>
#include <vector>

/* Model data */
static const struct CatboostModel {
    unsigned int FloatFeatureCount = 24;
    unsigned int BinaryFeatureCount = 149;
    unsigned int TreeCount = 38;
    unsigned int TreeDepth[38] = {4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4};
    unsigned int TreeSplits[152] = {111, 141, 18, 122, 100, 119, 14, 81, 123, 46, 70, 33, 137, 63, 95, 12, 136, 61, 56, 27, 135, 98, 78, 44, 138, 80, 147, 36, 142, 125, 65, 92, 94, 55, 77, 112, 113, 120, 58, 17, 133, 35, 16, 71, 130, 117, 76, 68, 103, 99, 54, 29, 110, 64, 41, 3, 116, 140, 106, 88, 127, 87, 118, 69, 128, 105, 8, 45, 148, 79, 121, 109, 102, 124, 62, 131, 146, 66, 5, 104, 86, 139, 93, 11, 20, 67, 4, 89, 59, 143, 51, 32, 30, 144, 42, 53, 2, 40, 19, 25, 90, 115, 50, 75, 7, 129, 82, 73, 79, 24, 49, 0, 114, 38, 97, 31, 37, 72, 126, 107, 47, 96, 43, 23, 22, 34, 26, 15, 86, 10, 28, 84, 39, 74, 9, 57, 145, 83, 132, 134, 52, 101, 108, 21, 126, 91, 1, 48, 13, 60, 85, 6};
    unsigned int BorderCounts[24] = {0, 2, 7, 5, 5, 2, 5, 6, 3, 4, 6, 2, 9, 8, 6, 9, 7, 5, 7, 6, 5, 8, 8, 24};
    float Borders[149] = {-0.000455000001 f, -0.000224999996 f, -0.00365500012 f, 0.000404999999 f, 0.000615000026 f, 0.000675000018 f, 0.00104500004 f, 0.00156 f, 0.00159500004 f, -0.00115499995 f, -0.000969999994 f, -0.000215000007 f, -1.49999996 e-05 f, 0.000854999991 f, -0.00139999995 f, -6.50000002 e-05 f, 0.000375000003 f, 0.000615000026 f, 0.000905000023 f, 0.000555000035 f, 0.000864999951 f, -0.000505000004 f, -0.000364999985 f, 0.000264999981 f, 0.000385000021 f, 0.001085 f, -0.00156500004 f, -0.000914999982 f, -0.000415000017 f, -7.50000036 e-05 f, 0.000705000013 f, 0.000864999951 f, -4.99999987 e-06 f, 0.000224999996 f, 0.000274999999 f, -0.00166499999 f, -0.00149499997 f, -0.000364999985 f, 0.0014500001 f, -0.00346500007 f, -0.00191999995 f, -0.00103499996 f, 0.000224999996 f, 0.00164999999 f, 0.00318 f, -0.00142500002 f, -0.00111499999 f, -0.00681000017 f, -0.00107500004 f, 0.000104999999 f, 0.000185000012 f, 0.000505000004 f, 0.000564999995 f, 0.00059499999 f, 0.00116500002 f, 0.00246499991 f, -0.00215499988 f, -0.0020349999 f, 0.000155000002 f, 0.00059499999 f, 0.000725000049 f, 0.00143499998 f, 0.00159500004 f, 0.00461499998 f, -0.00113500003 f, -5.49999968 e-05 f, 6.50000002 e-05 f, 7.50000036 e-05 f, 0.000735000009 f, 0.00431500003 f, -0.000439999974 f, -0.000224999996 f, -0.000155000002 f, -0.000135000009 f, 0.000325000001 f, 0.000534999999 f, 0.000714999973 f, 0.001605 f, 0.0020349999 f, -0.00679500028 f, -0.00156500004 f, -0.00130999996 f, -0.000815000036 f, -0.000484999997 f, 0.000274999999 f, 0.00126500009 f, -0.00630000001 f, -0.000965000014 f, -0.000914999982 f, 0.000944999978 f, 0.001085 f, -0.00104500004 f, -0.000570000033 f, -0.000135000009 f, 0.000415000017 f, 0.000774999964 f, 0.00129000004 f, 0.00136499992 f, -0.00214500003 f, -0.00078500004 f, 0.000564999995 f, 0.000969999994 f, 0.00129500008 f, 0.00171500002 f, -0.00109499996 f, -0.000665 f, -0.000505000004 f, -0.000455000001 f, 0.00092000002 f, -0.00078500004 f, -0.00033000001 f, 0.000375000003 f, 0.000754999986 f, 0.000944999978 f, 0.000974999974 f, 0.00135000004 f, 0.00179500005 f, -0.000735000009 f, -0.000195000001 f, -0.000140000004 f, -4.50000007 e-05 f, 2.49999994 e-05 f, 0.000549999997 f, 0.000729999971 f, 0.00175000005 f, -0.000645000022 f, -0.000404999999 f, -0.000390000001 f, -0.00033000001 f, -0.000315000012 f, -0.000204999989 f, -0.000195000001 f, 4.99999987 e-05 f, 6.50000002 e-05 f, 0.000109999994 f, 0.000230000005 f, 0.000245000003 f, 0.000354999996 f, 0.00046499999 f, 0.000484999997 f, 0.000495000044 f, 0.00059499999 f, 0.000684999977 f, 0.000705000013 f, 0.000725000049 f, 0.00109999999 f, 0.00122500001 f, 0.00124499993 f, 0.00194999995 f, };

    /* Aggregated array of leaf values for trees. Each tree is represented by a separate line: */
    double LeafValues[608] = {
        0.2730029119914884, 0.03364653273046463, -0.2371262400839919, 0.1081843550866285, 0.1343627920272425, -0.1126874256586927, -0.1126874256586927, -0.1126874256586927, -0.06059264820464742, 0.06930028482667829, 0, -0.249182516740322, 0, -0.04043442721784622, 0.1126874256586928, -0.246778769760217,
        0.3055616697384914, 0, 0, 0, 0.3295134099067072, 0, -0.001400906528597944, 0.1109887188810945, 0.3268369286843394, 0.09915101998784448, 0.1058842186334935, -0.2170923208654514, 0.2805477815282972, 0.1585452078030638, 0.04581636331023499, -0.1482988821054673,
        0.2661001303798985, 0, 0.2465781759237509, -0.1025474154359036, 0.1236081969018748, -0.1513185903680103, 0.09970504556623555, -0.1329324554655258, 0.1311330854183022, 0, 0.1102178581205619, -0.09318782033023576, 0, 0, 0.0984009666714989, -0.2078721521946149,
        0.2318376125278687, -0.1062335532728426, 0, 0, 0.08412564157842428, -0.1469343266107289, 0, -0.08357104102221358, 0.1653044215102119, -0.03314292702875558, 0, 0, 0.003358906412990077, -0.1912230767439488, 0, -0.2522267340231065,
        0.1973025375909275, 0, 0, 0, 0.4228820616711522, -0.07638314839084562, 0, 0, 0.2694211287720111, 0, 0, 0, 0.1652145942168661, -0.08206648374492893, -0.1450852254716266, -0.1363614260665522,
        0.2270555010525044, 0, 0.1627207525378816, -0.06377453863892701, 0, 0, -0.1357966649842286, -0.2427437659214983, 0, 0, 0, 0, 0, 0, 0, -0.1803912820573122,
        0.1804444671623995, -0.1017902080898772, 0.2133898509109472, 0.2517605145878034, 0, 0, 0, 0.0667661734515297, 0.2610915548565391, 0, 0.1052820435018607, -0.04560350655907942, 0, 0, 0, -0.3270645727235584,
        0.3575664582748267, 0, -0.0134804607394401, -0.04992725827315483, 0.2020647226798946, 0, -0.03385866654059267, 0, 0.2644495544004545, 0, 0.05182748809759461, -0.1768682974102572, 0.2407016500831285, 0, 0.04550057548317996, -0.119019763974849,
        0.08658245310355768, -0.02639731363946828, 0, 0, -0.07937732361985407, 0.2547371055272361, 0, 0, 0.02587599274452583, -0.05393875649408716, 0, 0, 0, -0.1657068825017175, 0, -0.2049254584747038,
        0.1440498437609123, 0.1101736004819604, 0.005464554800258488, -0.03812379875242829, 0.1819257725985174, 0, 0.02309394186822163, -0.08799582858720537, 0.08924300136100559, 0, -0.1587820248277704, 0, 0.07685524153284377, 0, 0.03664203213434057, -0.1531993322169632,
        0.09806057100343098, -0.09888524364037948, 0.2135150121698442, -0.09009400810853242, 0.07220208574561482, 0, 0.06638832682433267, -0.08176789304081045, 0.0580997781754348, 0.2757911650361233, 0.2520388352390843, -0.03558969703545899, 0, 0, 0.05616828900715019, -0.05996334853624528,
        0.3034312237500126, -0.3295604473826144, 0.1887070939415764, -0.01674053821735176, 0.04203126063490011, 0, 0.06936231294655706, -0.04128791044025015, 0, 0, 0.1230751670630003, -0.02722926856756647, 0.03326065080614352, 0, 0.06968005579997801, -0.05689069395020619,
        0.1144715475069234, 0, 0.01532939962304299, -0.09842006335636103, 0, 0, 0.3532831730583329, -0.1424529047285753, 0.1130693244873004, 0, -0.001413815681729, -0.1730902495689088, 0, 0, -0.003744815582707896, -0.2340067817777089,
        0.0582716295838749, 0.05887691806098397, 0.1830039055150205, 0.1275695040047543, 0.2265370556123239, 0.05865002066522316, 0.1412030624760486, -0.04465374880604451, 0.1016168407643287, -0.1696982846816441, 0.0168802138361802, -0.09464076746916356, 0.118358865381315, 0.07766416051208853, -0.004086300252646373, 0.01145464025038506,
        0.09893204118662431, 0, 0, 0, -0.1771744077440305, 0, -0.08956662944160931, 0, 0.06459969382272165, 0, -0.09920331948638744, 0, 0.06208790080353844, -0.06391545778445595, -0.03815083591344838, -0.193220691727352,
        0.2084212418556134, -0.2711170554066691, 0.3287662064308552, 0.04618819791309881, 0.02295062367871115, 0.06903818051790414, 0.06785880462261525, -0.01900550327916934, 0, 0, 0, 0, 0, 0, 0, -0.1379757023193675,
        0.1277198477469503, -0.1045845285066445, 0.06646719763990752, -0.006328728989568992, 0, 0, 0, 0, 0.2991650315125301, -0.1609657699217688, 0.1807990380964121, -0.02247201152624968, 0.06039630602452812, 0, 0.07323877669092338, 0.1041619957787472,
        -0.1701607137827854, 0, 0.08119342965694411, 0, 0, 0, 0, 0, 0, 0, 0.02263621203523299, 0, 0, 0, 0.001461819609651068, -0.3310861822552173,
        0.1708582471998724, 0, 0, 0, 0, -0.08085455495800464, 0, 0, -0.02242709602120458, -0.01626809043535743, -0.08378843901194441, -0.1314392215326333, 0.1670789581203374, -0.03477863896354667, -0.02057073074698931, -0.132977812589716,
        0.01576995464742881, 0, 0.05788166290521737, 0, 0.1155558453551253, 0, 0, 0, 0.009175549226526487, -0.09285703148627725, 0.0170554478209398, -0.1704207949809702, -0.1872038714907393, 0, 0.1259508080010625, -0.1193817874448983,
        -0.1624959866223847, 0.03397677382231543, 0, -0.01337295631517065, 0, 0.1165918182388884, 0, -0.04635935471889165, 0, 0.012563032729967, 0, -0.1185940873147897, 0, 0.02522877097419614, 0, -0.02570582073728468,
        0.002633980002093404, 0.0725570801392979, 0.03442625637449047, 0.001037481484499863, -0.04931529849937184, -0.2105671840353762, 0.1489911821071239, 0.2202194677045035, 0.1810528663002426, 0, -0.08188791865647969, -0.124584203103273, 0, 0.03156045615123341, 0.05563213612263092, -0.04578705044003427,
        0.01165640797726642, -0.1810863968750629, -0.1089920493861719, 0.05654669419619869, 0.05301303138076533, 0.1259240607012236, -0.1400660470693698, 0.06632028296608294, 0.02792682995145789, -0.1631488652519533, -0.1472788242094764, 0.02141183442530574, 0.284237301261878, -0.001197458738763785, 0.05972702215452129, -0.0586075718789894,
        0.02490937469062505, 0.01810224834922746, -0.1092925911367815, -0.1197570696964759, 0.008067995573721135, -0.1023547665228953, -0.09294834637942173, 0.231300348695698, 0.2206397515352709, 0, -0.03762173512827768, 0, 0.102636146583814, -0.04563726647379882, -0.0298583349638738, -0.03244852061992397,
        -0.1794615195377556, 0.01921769229013687, 0, 0.01044638539736725, 0, 0.02781136690266, 0, 0.001867775508010755, 0, 0.1067785434424472, 0, -0.2932442639776253, 0, 0, 0, -0.03241018659571911,
        -0.006510415667175931, 0.07059931629954573, -0.05002576775584883, 0, 0.02889911804947202, 0.1366522086842556, 0.1459606096328157, -0.07315994927835844, -0.1602705507235337, 0.1878187897030766, -0.04626610184165392, -0.09837710067806367, 0.05397003977271773, -0.04858868406475466, 0.0649201842045576, -0.06524393947925287,
        0.1459267556026626, 0.01372089516811126, -0.1001303921089584, 0, 0.2092093674681419, 0.01930448166419142, -0.04972139914274094, 0, 0.03545870984455322, 0, -0.07554900451460518, 0, 0.2137989937258072, 0.0008411572827327659, -0.00117214692641536, 0.09422976943966678,
        -0.1641700048226127, 0.07641634809302257, 0.01054185317373139, 0.1341178828759175, 0, -0.04019050552180111, 0, 0.1596324334341981, 0, 0.006806725110812047, 0, -0.1081606151666887, 0, 0.01822843651581126, 0, -0.01720619226968497,
        0.009025394520361704, -0.00389494343189025, 0.2311406287627894, -0.083367208305538, 0.1730715229027212, -0.1114791940489316, 0, -0.1028046654549743, -0.07334162028427468, 0.04581415665697729, 0.09898474179992452, 0.1365328178250054, -0.04325183693301483, -0.002210798573244916, -0.1387629807152628, -0.08980091117790198,
        0.1201356461649662, 0.1758279743860605, 0.04350349009977216, 0.1134402521456353, -0.06435518652676646, -0.2395731049930946, 0.08878547365332778, -0.03259992777530323, 0.04016967881155449, 0.05586731905591313, 0.02231616278420573, 0.06715298880059364, -0.02931637068858008, -0.02727342673220743, 0.07981966823218006, -0.00736687454594985,
        -0.1523999096887992, 0.01066390065885025, 0, -0.007937651487390564, 0, 0.05838570541522675, 0, -0.01764599778668323, 0.00926922900423862, -0.01462296480325223, 0, -0.1231100245909153, 0, 0.2071885095206176, 0, -0.07553876970469377,
        -0.007509531863847287, -0.03821554347886918, 0, 0, 0.04539951031452136, -0.03237816844587264, 0.1489237277306394, -0.06858743023508017, 0, 0, 0, 0, -0.02197724937765806, -0.009927643925657297, 0.1075288047240592, 0.007583049665065472,
        -0.1438530341047301, 0.08211619188336085, 0.009520674504357616, -0.035052444268162, 0, -0.2209655809626173, 0, 0.02928893608785839, 0, 0.2307562221331639, 0, 0.004914926553117083, 0, -0.04531825623377965, 0, -0.01478427605905595,
        -0.07585048830556372, 0.06213280806503956, 0, 0, -0.2460691271464409, 0.1587981422466466, 0, 0, 0, -0.01873021929806146, 0, 0.1355384701582952, -0.06505176113152071, 0.006237844209643408, 0, -0.01139845636090814,
        0.03344525515709466, 0, 0.05456132700219524, 0, -0.3220774353233821, 0, 0.09756717225728033, 0, 0, 0, 0, 0, -0.05013487401906989, -0.1004156738161951, 0.01006705311047576, -0.06297947180380781,
        0.03125880796992506, 0.1620757216856216, 0.02218793960373364, 0, -0.05510500531128774, 0, -0.1305668615108228, 0.09175301826776584, -0.02241534935432258, 0.06091737602659867, 0.1959961615001555, -0.08945488952436154, -0.1297656911182584, -0.0327910998454452, 0.04823531757180094, -0.0451880914096086,
        -0.03549878434185903, -0.05751707772342768, 0.03023724321196803, -0.03668922584353116, 0.1446378062221211, -0.1558238670878492, 0.0440168187902071, -0.07335968350547692, 0.05992982442842611, 0, 0.1297678384005503, 0.001564747370113251, 0.1215230794033289, -0.237198658134785, 0.1200964187472702, -0.003075362232407817,
        0.009596007555535021, -0.02731003882847802, -0.03313751244478664, 0.2002494267502239, -0.00142054347110939, 0, -0.07476518666658544, 0.06964401248797676, -0.1775794863889658, -0.02635446781295587, -0.04719524974954924, 0.1681250432344917, 0, 0, 0.08871226782186471, -0.01856541295695367
    };
    double Scale = 1;
    double Bias = 0;
} CatboostModelStatic;

/* Model applicator */
double ApplyCatboostModel(
    const std::vector<float>& features
) {
    const struct CatboostModel& model = CatboostModelStatic;

    /* Binarise features */
    std::vector<unsigned char> binaryFeatures(model.BinaryFeatureCount);
    unsigned int binFeatureIndex = 0;
    for (unsigned int i = 0; i < model.FloatFeatureCount; ++i) {
        for(unsigned int j = 0; j < model.BorderCounts[i]; ++j) {
            binaryFeatures[binFeatureIndex] = (unsigned char)(features[i] > model.Borders[binFeatureIndex]);
            ++binFeatureIndex;
        }
    }

    /* Extract and sum values from trees */
    double result = 0.0;
    const unsigned int* treeSplitsPtr = model.TreeSplits;
    const double* leafValuesForCurrentTreePtr = model.LeafValues;
    for (unsigned int treeId = 0; treeId < model.TreeCount; ++treeId) {
        const unsigned int currentTreeDepth = model.TreeDepth[treeId];
        unsigned int index = 0;
        for (unsigned int depth = 0; depth < currentTreeDepth; ++depth) {
            index |= (binaryFeatures[treeSplitsPtr[depth]] << depth);
        }
        result += leafValuesForCurrentTreePtr[index];
        treeSplitsPtr += currentTreeDepth;
        leafValuesForCurrentTreePtr += (1 << currentTreeDepth);
    }
    return model.Scale * result + model.Bias;
}

double ApplyCatboostModel(
    const std::vector<float>& floatFeatures,
    const std::vector<std::string>&
) {
    return ApplyCatboostModel(floatFeatures);
}
 
MQL
Gets mql arrays
 
Aliaksandr Hryshyn:
MQL

Share if you don't mind

Maybe I'll get something useful out of it

 
Maxim Dmitrievsky:

share, if you don't mind

Maybe I'll get something useful out of it

Only later, when I get home
 
Aleksey Vyazmikin:

I realized that this type of clustering does not create rules,

I don't know the clustering algorithm that creates the rules.

So the question remains - how to save in csv belonging string to each class?

write.csv(myfile, file = "C:\\Users\\......\\myfile.csv", sep = ";",row.names = F,col.names = T)

Although here's strange, why not just continue clustering with existing data and define a new string in one of the classes, or can?

Of course you can, but not in µl!!!

Aleksey Vyazmikin:
But I found a book on R.

I read it, it's cool.

Aleksey Vyazmikin:

And I don't understand, how can I roll up the results into a specific column?

I don't understand what you want.)

Aleksey Vyazmikin:

This picture has the same predictors as before, but the sample size is different, and most importantly new predictors have been added.

And that's how to interpret this - the propensity to overtrain?

I already told you, interpret according to the direct purpose of the tool, and you're aiming to nail with a flower

https://ru.wikipedia.org/wiki/%D0%A1%D0%BD%D0%B8%D0%B6%D0%B5%D0%BD%D0%B8%D0%B5_%D1%80%D0%B0%D0%B7%D0%BC%D0%B5%D1%80%D0%BD%D0%BE%D1%81%D1%82%D0%B8#:~:text=%D0%B5%D0%B4%D0%B8%D0%BD%D1%81%D1%82%D0%B2%D0%B5%D0%BD%D0%BD%D0%BE%20%D0%B2%D0%BE%D0%B7%D0%BC%D0%BE%D0%B6%D0%BD%D1%8B%D0%BC%20%D0%B2%D0%B0%D1%80%D0%B8%D0%B0%D0%BD%D1%82%D0%BE%D0%BC.-,%D0%9F%D1%80%D0%B5%D0%B8%D0%BC%D1%83%D1%89%D0%B5%D1%81%D1%82%D0%B2%D0%B0%20%D1%81%D0%BD%D0%B8%D0%B6%D0%B5%D0%BD%D0%B8%D1%8F%20%D1%80%D0%B0%D0%B7%D0%BC%D0%B5%D1%80%D0%BD%D0%BE%D1%81%D1%82%D0%B8,%D1%82%D0%B0%D0%BA%D0%B8%D0%BC%20%D0%BA%D0%B0%D0%BA%202D%20%D0%B8%D0%BB%D0%B8%203D.


Feature selection[edit|edit code]

Main article:Feature selection

Thefeature selection method tries to find a subset of the original variables (which are called features or attributes). There are three strategies - a filter strategy(e.g.,feature accumulation [en]), awrapping strategy(e.g., search according to accuracy), and anembedding strategy(selecting attributes to add or remove as the model builds based on prediction errors). See alsocombinatorial optimization problems.

In some cases,data analysis, such asregression orclassification, can be performed in the reduced space more accurately than in the original space [3].

Feature projection[edit|edit code]

Feature projection converts data fromhigh dimensional space to low dimensional space. The data transformation can be linear, as inthe Principal Components Method(PCM), but there are a large number ofnonlinear downsizing techniques [en] [4] [5]. For multidimensional data,a tensor representation can be used to reduce dimensionality throughpolylinear training of subspaces [en] [6].


What we did yesterday.

Dimensionality reduction[edit|edit code]

For high dimensional datasets (i.e. with more than 10 dimensions), dimensionality reduction is usually done before applyingthe k-nearest neighborsalgorithm( k-NN), in order to avoid the effectof the curse of dimensionality [16].


Advantages of dimensionality reduction[edit|edit code]

  1. It reduces the time and memory required.
  2. Removing multicollinearity improves the speed of the machine learning model.
  3. It is easier to represent data visually when reduced to very low dimensions, such as 2D or 3D.


 

Decided to look at meaningful market reversals. Significant U-turns as a target. Thought it would be chaos, but no.

green reversal up.

red reversal down.

Gray is not a reversal.

It's a lot clearer in 2D.


I have added more data, anyway I have 4 clusters for buy and 4 for sell. Now I should probably choose the necessary clusters and try to separate the reversal from the reverse one in each of them using some classifier


Just imagine how much garbage is in the data, it all should be separated from the needed information


You can't do that with ordinary clustering.


You need to try something more serious, like DBscan, or maybe manually select, somewhere heard about this technology

 
mytarmailS:

Decided to look at meaningful market reversals. Significant U-turns as a target. Thought it would be chaos, but no.

green reversal up.

red reversal down.

Gray is not a reversal.

It's a lot clearer in 2D.


I have added more data, anyway I have 4 clusters for buy and 4 for sell. Now I should probably choose the necessary clusters and try to separate U-turn and no-turn in each of them with the help of some qualifier


Imagine how much garbage is in the data, it all should be separated from the needed information


You can't do that with ordinary clustering.


You need to try something more serious, DBscan, for example, or maybe manually select, somewhere I heard about such a technology

Is there any way to look for attributes within a particular cluster?

 
Rorschach:

Is there any way to see the attributes within a particular cluster?

What do you mean? Clusters do not have attributes, they combine parts of attributes by similarity, if I may say so

 
mytarmailS:

What do you mean? Clusters do not have features, they combine parts of features by similarity, so to speak.

The values of the features in the cluster are interesting.