metatrader4 - Why is an information in my printf() function incorrect in MQL4? -

-

my print formatting giving me random answers, despite coding being correct. i'm trying display candle bar lengths of previous 2 candle bars prior trade entry. here coding i've used.

pcl1 & pcl2 relevant field entries. divided _point give integer formatting.

pcl2 = previous candle stick length, shift 2

pcl1 = previous candle stick length, shift 1

in example have focused on shift2 candlestick

short_bull_2_close   =  iclose( symbol(), 0, 2 ); short_bull_2_open    =  iopen(  symbol(), 0, 2 ); candlebody_2         =  ( short_bull_2_close - short_bull_2_open );                      // gives candlebody length in pips.

and printf() coding:

printf( "pcl1 [%d] pcl2 [%d]", candlebody_1 / point,                                candlebody_2 / point         ); // ___________________________________________________________  sell//

however, pictured & highlighted..enter image description here

1) mql4 strong typed language ( declaration precedes use of variable )
+ mql4 has historical feature of number "normalisation"

an assumption (cit.) "they divided _point give integer" does not hold.

once number has been declared double in source code as:

double upfractal = 0.0,        dnfractal = 0.0;

the mql4-compiler handles these numbers forever in ieee-754 floating point number representation , calls particular sub-version of operations on arithmetics operation such number entring into. reason simple, double has different handling ( new-mql4.56789 ) float, more int et al. numbers, represented in ieee-754, inexact by-definition, remain exact ( if happen direct power-of-2 , still in it's "virgin"-state ( have not yet been spoiled arithmetic operation, introduce un-avoidable im-precision binary-representatio ) ).

why im-precision?
why un-avoidable?
non-virgin numbers, binary-representation may yield infinitely-long description of value. on contrary, storage of value in mql4 restricted { 1 | 4 | 8 }-bytes of memory-space , infinite-representation un-avoidably cut @ distance, introducing principal im-precision , expressed by:

dbl_epsilon ~ 2.2204460492503131e-016
flt_epsilon ~ 1.192092896e-07
beyond 2 numbers, represented in ieee-754 binary-format, compiled code "equal", if not principally equal, due ieee-754 format inherent im-precision.

for indeed historical reasons, double typed values ought have been normalizedouble() converted, if 1 wants send these metatrader server-side processing and/or compare values on fair ground.

2) mql4 operations {double | int }- typed variables

if 1 had declared variable double, remains double forever.
if 1 had declared variable int, int/3 remain int, ignoring fractional products of division operation ( causes headaches not carefull mql4 coders ).

the same applied initial assumption above yields surprise, double/double -> double in cases, division satisfactorily considered ( ) integer. never assume type conversion happen values of operands.

for purpose, there 2 sorts of syntax-supports:

  • an explicit conversion function int( ... ) or double( ... )
  • an inline typecast directive ( (int) candlebody_1 / _point )

epilogue: ( ... must read custom indicator designers, cpu-performance kills )

said above, calling (int) normalizedouble(...) double-nonsense ( beyond belt + suspenders paradigm ), first, historically built-in function normalizedouble still returns double, providing zero-benefit spending cpu crunch numbers once still yields double, next division of number double value of _point expensive , inefficient, compared fact, _point related int value of digits formula of 1 / 10^digits -- fastest , cleanest way conversion, without spending avoidable cpu-cycles, multiplication ...
yes,
from computer-side of fast & efficient processing, the best is
int( make_apricedomain_value_an_int_num_of_points * candlebody_1 ),
re-using constant
int make_apricedomain_value_an_int_num_of_points = mathpow( 10, digits );


Comments

Post a Comment

Popular posts from this blog

c - zlib and gdi32 with OpenSSL? -

-
this follow question undefined reference rsa_generate_key in openssl? have openssl program generate rsa key, follows : #include <stdio.h> #include <openssl/rsa.h> #include <openssl/pem.h> int main(int argc, char* argv[]) { rsa *r = null; int ret; r = rsa_new(); bignum *bne = null; ret = rsa_generate_key_ex(r, 2048, bne, null); return 0; } when compile gcc -i../include rsatest.c -lcrypto -l. i undefined reference errors functions in libraries gdi32 , zlib. so correct this, have add -lz , -lgdi32, as gcc -i../include/ rsatest.c -lcrypto -lz -lgdi32 -l. my question is, aren't static libcrypto , libssl self sufficient? in why having add libraries make work? there option should have added while compiling library prevent this? i'm using 64 bit windows mingw compiler. made openssl library of msys , make.
Read more

java - inputmismatch exception -

-
Image
this question has answer here: scanner skipping nextline() after using next(), nextint() or other nextfoo()? 14 answers import java.util.*; public class ngg { static scanner numberentered; static scanner userinput = new scanner(system.in); static int guessednumber; static int randomnumber = (int) (math.random()* 11); static scanner reply; static string answer; public static void main(string[] args) { guesschecker(guessednumber); } public static void guesschecker(int userguess) { while (userguess != randomnumber) { intro(); userguess = intchecker(); if (userguess == randomnumber) { system.out.println("congradulations!"); system.exit(0); } else { system.out.println("that incorrect!");...
Read more

ios - Align baselines with characters in large line heights with Text Kit -

-
Image
when draw attributed string fixed line height text kit, characters aligned bottom of line fragment. while make sense on 1 line characters varying in size, breaks flow of text multiple lines. baselines appear decided largest descender each line. i've found article people behind sketch explaining exact problem in bit more detail , showing solution does, not explaining how achieved this. this want basically: when showing 2 lines large line height, result far ideal: the code i'm using: let smallfont = uifont.systemfont(ofsize: 15) let bigfont = uifont.systemfont(ofsize: 25) let paragraphstyle = nsmutableparagraphstyle() paragraphstyle.minimumlineheight = 22 paragraphstyle.maximumlineheight = 22 var attributes = [ nsfontattributename: smallfont, nsparagraphstyleattributename: paragraphstyle ] let textstorage = nstextstorage() let textcontainer = nstextcontainer(size: cgsize(width: 250, height: 500)) let layoutmanager = nslayoutmanager() textstorage.append(n...
Read more