Changeset 1241 for cpp/frams/genetics
- Timestamp:
- 05/18/23 03:43:42 (20 months ago)
- Location:
- cpp/frams/genetics
- Files:
-
- 4 edited
Legend:
- Unmodified
- Added
- Removed
-
cpp/frams/genetics/f4/f4_general.cpp
r1240 r1241 1363 1363 // in the future this could be generalized to all neuron properties, for example N:|:power:0.6:range:1.4, or can even use '=' or ',' instead of ':' if no ambiguity 1364 1364 char prop_dir, prop_symbol, prop_end[2]; // prop_end is only to ensure that neuron parameter definition is completed 1365 if (sscanf(genot + pos_inout, ":%c%c%1[:]", &prop_dir, &prop_symbol, &prop_end) != 3)1365 if (sscanf(genot + pos_inout, ":%c%c%1[:]", &prop_dir, &prop_symbol, prop_end) != 3) 1366 1366 // error: incorrect format 1367 1367 return pos_inout + 1 + 1; … … 1402 1402 #ifdef F4_SIMPLIFY_MODIFIERS 1403 1403 char *ptr = (char*)(genot + pos_inout); 1404 1405 #ifdef __BORLANDC__ // "[bcc32c Error] cannot compile this non-trivial TLS destruction yet" (C++B 10.4u2) 1406 static 1407 #else 1408 thread_local 1409 #endif 1410 vector<int> modifs_counts(strlen(all_modifiers_no_comma)); ///<an array with a known constant size storing counters of each modifier symbol from all_modifiers_no_comma, created once to avoid reallocation every time when modifier genes are simplified during parsing. Initialization of required size; it will never be resized. 1411 std::fill(modifs_counts.begin(), modifs_counts.end(), 0); //zeroing only needed if we encountered a char from all_modifiers_no_comma and enter the 'while' loop below 1412 1413 while (char *m = GenoOperators::strchrn0(all_modifiers_no_comma, *ptr)) //only processes a section of chars known in all_modifiers_no_comma, other characters will exit the loop 1414 { 1415 modifs_counts[m - all_modifiers_no_comma]++; 1404 string original = ""; 1405 while (GenoOperators::strchrn0(all_modifiers_no_comma, *ptr)) //only processes a section of chars known in all_modifiers_no_comma, other characters will exit the loop 1406 { 1407 original += *ptr; 1416 1408 GenoOperators::skipWS(++ptr); //advance and ignore whitespace 1417 1409 } … … 1419 1411 if (advanced > 0) //found modifiers 1420 1412 { 1421 string simplified = GenoOperators::simplifiedModifiers( all_modifiers_no_comma, modifs_counts);1413 string simplified = GenoOperators::simplifiedModifiers(original); 1422 1414 // add a node for each char in "simplified" 1423 1415 for (size_t i = 0; i < simplified.length(); i++) -
cpp/frams/genetics/f4/f4_oper.cpp
r1238 r1241 18 18 // TODO add support for properties of (any class of) neurons - not just sigmoid/force/intertia (':' syntax) for N 19 19 // TODO add mapping genotype character ranges for neural [connections] 20 // TODO for some genotypes, #defining/undefining F4_SIMPLIFY_MODIFIERS produces significantly different phenotypes (e.g. length of some Joint changes from 1.25 to 1.499, coordinates of Parts change, friction of some part changes from 1.28 to 0.32). Comparing f4_Node trees, the simplification works as intended, there are no huge changes apart from removing contradicting modifiers like 'R' and 'r' or 'L' and 'l', and dispersing the modifiers (changed order). There is no reason for such a significant influence of this. A hypothesis is that something may be wrong with calculating the influence of individual modifiers, e.g. some strong nonlinearity is introduced where it should not be, or some compensation between modifiers that should not influence each other (like L and R), or some modifier f4_Nodes are skipped/ignored when applying? Investigate. Example genotype that displays this issue: /*4*/,i<qlM,C<X>N:*#1>>,r<MRF<Xcm>N:Gpart>#5#1#2MLL#1>#1>>>>#5ML#2L#1>>>Lf,r<#1>rM<CqmLlCfqiFLqXFfl><F,<<XI>iN:|[-1:4.346]><XF><<XrRQ>N:G#3>>QiXFMR>fXM#2MfcR>R#3>>X21 20 // TODO The f0 genotypes for /*4*/<<RX>X>X> and RX(X,X) are identical, but if you replace R with Q or C, there are small differences - check why and perhaps unify? 21 // TODO F4_SIMPLIFY_MODIFIERS in f4_general.cpp: currently it works while parsing (which is a bit "cheating": we get a phenotype that is a processed version of the genotype, thus some changes in modifiers in the genotype have no effect on its phenotype). Another (likely better) option, instead of simplifying while parsing, would be during mutations (like it is done in f1): when mutations add/modify/remove a modifier node, they could "clean" the tree by simplifying modifiers on the same subpath just as GenoOperators::simplifiedModifiers() does. This way, simplifying would be only performed when we actually modify a part of a genotype, not each time we interpret it, and there would be no hidden mechanism: all visible genes would have an expected effect on the phenotype. 22 22 23 23 -
cpp/frams/genetics/genooperators.cpp
r1233 r1241 473 473 474 474 //#include <cassert> 475 string GenoOperators::simplifiedModifiers (const char *str_of_char_pairs, vector<int> &char_counts)475 string GenoOperators::simplifiedModifiersFixedOrder(const char *str_of_char_pairs, vector<int> &char_counts) 476 476 { 477 477 // assert(strlen(str_of_char_pairs) == char_counts.size()); 478 478 // assert(char_counts.size() % 2 == 0); 479 const int MAX_NUMBER_SAME_TYPE = 8; // max. number of modifiers of each type = 8 (mainly for Rr)479 const int MAX_NUMBER_SAME_TYPE = 8; // max. number of modifiers of each type (case-sensitive) - mainly for rR, even though for rR, 4 would be sufficient if we assume lower or upper can be chosen as required for minimal length, e.g. rrrrr==RRR, RRRRRR==rr 480 480 string simplified; 481 //#define CLUMP_IDENTICAL_MODIFIERS //not good because properties are calculated incrementally, non-linearly, and their values are updated after each modifier character, so these values may for example saturate after a large number of identical modifier symbols. The order of modifiers is in generalrelevant and extreme values of properties increase this relevance, so better keep the modifiers dispersed.481 //#define CLUMP_IDENTICAL_MODIFIERS //not good because with the exception of rR properties are calculated incrementally, non-linearly, and their values are updated after each modifier character, so these values may for example saturate after a large number of identical modifier symbols. The order of modifiers is (with the exception of rR) relevant and extreme values of properties increase this relevance, so better keep the modifiers dispersed. 482 482 #ifdef CLUMP_IDENTICAL_MODIFIERS 483 483 for (size_t i = 0; i < strlen(str_of_char_pairs); i++) … … 507 507 return simplified; 508 508 } 509 510 string GenoOperators::simplifiedModifiers(const string & original) 511 { 512 const int MAX_NUMBER_SAME_TYPE = 6; // max. number of modifiers of each type (case-insensitive). rR could be treated separately in simplification because their influence follows different (i.e., simple additive) logic - so the simplifiedModifiersFixedOrder() logic with cancelling out is appropriate for rR. However in this function, making no exception to rR does not cause any harm to these modifiers either - the only consequence is that we will not remove antagonistic letters and will not simplify sequences of rR longer than 4, while they could be simplified (e.g. rrrrr==RRR, RRRRRR==rr). 513 int counter[256] = {}; //initialize with zeros; 256 is unnecessarily too big and redundant, but enables very fast access (indexed directly by the ascii code) 514 string simplified = ""; 515 for (int i = original.size() - 1; i >= 0; i--) //iterate from end to begin - easier to remove "oldest" = first modifiers 516 { 517 unsigned char c = original[i]; 518 if (!std::isalpha(c)) 519 continue; 520 unsigned char lower = std::tolower(c); 521 counter[lower]++; 522 if (counter[lower] <= MAX_NUMBER_SAME_TYPE) //get rid of modifiers that are too numerous, but get rid of the first ones in the string (="oldest", the last ones looking from the end), because their influence on the parameter value is the smallest 523 simplified += c; 524 } 525 std::reverse(simplified.begin(), simplified.end()); //"simplified" was built in reverse order, so need to restore the order that corresponds to "original" 526 return simplified; 527 } -
cpp/frams/genetics/genooperators.h
r1233 r1241 215 215 static void skipWS(char *&s); ///<advances pointer \a s skipping whitespaces. 216 216 static bool areAlike(char*, char*); ///<compares two text strings skipping whitespaces. Returns 1 when equal, 0 when different. 217 static char* strchrn0(const char *str, char ch); ///<like strchr, but does not find zerochar in \a str.217 static char* strchrn0(const char *str, char ch); ///<like strchr, but does not find ascii=0 char in \a str. 218 218 219 219 static int getRandomChar(const char *choices, const char *excluded); ///<returns index of a random character from \a choices excluding \a excluded, or -1 when everything is excluded or \a choices is empty. 220 static string simplifiedModifiers (const char *str_of_char_pairs, vector<int> &char_counts); ///<returns a sequence of chars from \a str_of_char_pairs based on how many times each char occurred in \a char_counts. Assume that an even-index char and the following odd-index char have the opposite influence, so they cancel out.220 static string simplifiedModifiersFixedOrder(const char *str_of_char_pairs, vector<int> &char_counts); ///<returns a sequence of chars from \a str_of_char_pairs based on how many times each char occurred in \a char_counts. Assume that an even-index char and the following odd-index char have the opposite influence, so they cancel out. We don't use this function, because a fixed order imposed by this function means that the number of different parameter values produced by a sequence of modifiers is lowered (N same-letter upper- and lower-case chars yield only 2*N different values). Due to how modifiers work, the effect of aaA, aAa, Aaa etc. is different (N same-letter upper- and lower-case chars yield 2^N different values), so simplifying modifiers should not impose any order and should not interfere with their original order - see \a simplifiedModifiers(). 221 221 //@} 222 static string simplifiedModifiers(const string &original); ///<from the \a original sequence removes modifiers that are too numerous (exceeding a defined threshold number), starting the removal from the leftmost (="oldest" when interpreting the sequence from left to right) ones. 222 223 }; 223 224
Note: See TracChangeset
for help on using the changeset viewer.