Path: ...!news-out.netnews.com!postmaster.netnews.com!us14.netnews.com!not-for-mail
X-Trace: DXC=XDO2S7nchUY2BFZQ=P]QnYHWonT5<]0T]Q;nb^V>PUfV=AnO\FUBY[PnF54O@^\1?TKTo[:hc[gi]Wk5\ZZ8Yg0Pnk9`jfQW@>]dDioXmM8L1QOXeKkS2`?jY
X-Complaints-To: support@blocknews.net
Date: Wed, 12 Jun 2024 18:29:27 -0400
MIME-Version: 1.0
User-Agent: Betterbird (Windows)
Subject: Re: "undefined behavior"?
Newsgroups: comp.lang.c
References: <666a095a$0$952$882e4bbb@reader.netnews.com>
 <v4d4h5$1rc9e$1@dont-email.me>
Content-Language: en-US
From: DFS <nospam@dfs.com>
In-Reply-To: <v4d4h5$1rc9e$1@dont-email.me>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit
Lines: 383
Message-ID: <666a2146$0$950$882e4bbb@reader.netnews.com>
NNTP-Posting-Host: 127.0.0.1
X-Trace: 1718231366 reader.netnews.com 950 127.0.0.1:59703
Bytes: 13460

On 6/12/2024 5:38 PM, David Brown wrote:
> On 12/06/2024 22:47, DFS wrote:
>> Wrote a C program to mimic the stats shown on:
>>
>> https://www.calculatorsoup.com/calculators/statistics/descriptivestatistics.php
>>
>> My code compiles and works fine - every stat matches - except for one 
>> anomaly: when using a dataset of consecutive numbers 1 to N, all 
>> values  > 40 are flagged as outliers.  Up to 40, no problem.  Random 
>> numbers dataset of any size: no problem.
>>
>> And values 41+ definitely don't meet the conditions for outliers 
>> (using the IQR * 1.5 rule).
>>
>> Very strange.
>>
>> Edit: I just noticed I didn't initialize a char:
>> before: char outliers[100];
>> after : char outliers[100] = "";
>>
>> And the problem went away.  Reset it to before and problem came back.
>>
>> Makes no sense.  What could cause the program to go FUBAR at data 
>> point 41+ only when the dataset is consecutive numbers?
>>
>> Also, why doesn't gcc just do you a solid and initialize to "" for you?
>>
> 
> It is /really/ difficult to know exactly what your problem is without 
> seeing your C code!  There may be other problems that you haven't seen yet.

The outlier section starts on line 169
=====================================================================================

//this code is hereby released to the public domain

#include <stdlib.h>
#include <stdio.h>
#include <math.h>
#include <string.h>
#include <time.h>

/*
  this program computes the descriptive statistics of a randomly 
generated set of N integers

  1.0 release Dec 2020
  2.0 release Jun 2024

  used the population skewness and Kurtosis formulas from:
 
https://www.calculatorsoup.com/calculators/statistics/descriptivestatistics.php
  also test the results of this code against that site

  compile: gcc -Wall prog.c -o prog -lm
  usage  : ./prog N -option (where N is 2 or higher, and option is -r or 
-c or -o)
            -r generates N random numbers
		   -c generates consecutive numbers 1 to N
		   -o generates random numbers with outliers
*/


//random ints
int randNbr(int low, int high) {
	return (low + rand() / (RAND_MAX / (high - low + 1) + 1));
}

//comparator function used with qsort
int compareint (const void * a, const void * b)
{
   if (*(int*)a > *(int*)b) return 1;
   else if (*(int*)a < *(int*)b) return -1;
   else return 0;
}


int main(int argc, char *argv[])
{
	if(argc < 3) {
		printf("Missing argument:\n");
		printf(" * enter a number greater than 2\n");
		printf(" * enter an option -r -c or -o\n");
		exit(0);
	}	
	
	
	//vars
	int i=0, lastmode=0;
	int N = atoi(argv[1]);
	int nums[N];
	
	double sumN=0.0, median=0.0, Q1=0.0, Q2=0.0, Q3=0.0, IQR=0.0;
	double stddev = 0.0, kurtosis = 0.0;
	double sqrdiffmean = 0.0, cubediffmean = 0.0, quaddiffmean = 0.0;
	double meanabsdev = 0.0, rootmeansqr = 0.0;
	char mode[100], tmp[12];
	
	//generate random dataset
	if(strcmp(argv[2],"-r") == 0) {
		srand(time(NULL));
		for(i=0;i<N;i++) { nums[i] = randNbr(1,N*3); }
		
		printf("%d Randoms:\n", N);
		printf("No commas  : ");   for(i=0;i<N;i++) { printf("%d ", nums[i]); }
		printf("\nWith commas: "); for(i=0;i<N;i++) { printf("%d,", nums[i]); }
		qsort(nums,N,sizeof(int),compareint);
		printf("\nSorted     : "); for(i=0;i<N;i++) { printf("%d ", nums[i]); }
		printf("\nSorted     : "); for(i=0;i<N;i++) { printf("%d,", nums[i]); }
	}	
	
	//generate random dataset with outliers
	if(strcmp(argv[2],"-o") == 0) {
		srand(time(NULL));
		nums[0] = 1; nums[1] = 3;
		for(i=2;i<N-2;i++) { nums[i] = randNbr(100,N*30); }	
		nums[N-2] = 1000; nums[N-1] = 2000;
		
		printf("%d Randoms with outliers:\n", N);
		printf("No commas  : ");   for(i=0;i<N;i++) { printf("%d ", nums[i]); }
		printf("\nWith commas: "); for(i=0;i<N;i++) { printf("%d,", nums[i]); }
		qsort(nums,N,sizeof(int),compareint);
		printf("\nSorted     : "); for(i=0;i<N;i++) { printf("%d ", nums[i]); }
		printf("\nSorted     : "); for(i=0;i<N;i++) { printf("%d,", nums[i]); }
	}	
	
	
	//generate consecutive numbers 1 to N
	if(strcmp(argv[2],"-c") == 0) {
		for(i=0;i<N;i++) { nums[i] = i + 1; }
		
		printf("%d Consecutive:\n", N);
		printf("No commas     : ");   for(i=0;i<N;i++) { printf("%d ", nums[i]); }
		printf("\nWith commas   : "); for(i=0;i<N;i++) { printf("%d,", nums[i]); }
	}
	
	//various
	for(i=0;i<N;i++) {sumN += nums[i];}
	double min = nums[0], max = nums[N-1];

	
	//calc descriptive stats
	double mean = sumN / (double)N;
	int ucnt = 1, umaxcnt=1;
	for(i = 0; i < N; i++)
	{
		sqrdiffmean  += pow(nums[i] - mean, 2);  // for variance and sum squares
		cubediffmean += pow(nums[i] - mean, 3);  // for skewness
		quaddiffmean += pow(nums[i] - mean, 4);  // for Kurtosis
		meanabsdev   += fabs((nums[i] - mean));  // for mean absolute deviation
		rootmeansqr  += nums[i] * nums[i];       // for root mean square
		
		//mode	
		if(ucnt == umaxcnt && lastmode != nums[i])
		{			
			sprintf(tmp,"%d ",nums[i]);	
			strcat(mode,tmp);
		}
		
		if(nums[i]-nums[i+1]!=0) {ucnt=1;} else {ucnt++;}
		
		if(ucnt>umaxcnt)
		{
			umaxcnt=ucnt;
			memset(mode, '\0', sizeof(mode));
			sprintf(tmp, "%d ", nums[i]);			
			strcat(mode, tmp);
			lastmode = nums[i];
		}
	}
	
	
	// median and quartiles
	// quartiles divide sorted dataset into four sections
	// Q1 = median of values less than Q2
	// Q2 = median of the data set
	// Q3 = median of values greater than Q2
	if(N % 2 == 0) {
		Q2 = median = (nums[(N/2)-1] + nums[N/2]) / 2.0;
========== REMAINDER OF ARTICLE TRUNCATED ==========