Thread: C - Reading and iterating through data from file to calculate statistics

I'm trying to implement a program that reads in data from a file called grad.dat. Each record (i.e. each line) in the data file gives statistics for a given country, year, degree, and gender, etc. The records are formatted as follows: <countryCode countryName gender degree year numGrads>


Note: there are only 3 different types of degrees - L6, L7, and L8


Part of grad.dat:

Code:

	AUS Australia F L6 2010 1276
	AUS Australia M L6 2010 5779
	AUS Australia F L6 2011 1255
	AUS Australia M L6 2011 5739
	BEL Belgium F L6 2017 157
	BEL Belgium M L6 2017 1665
	BEL Belgium F L7 2010 61
	BEL Belgium F L8 2016 0
	BEL Belgium F L8 2017 1
	BEL Belgium M L8 2017 13
	BRA Brazil F L6 2010 7187
	BRA Brazil M L6 2010 32173
	BRA Brazil F L6 2011 6240
	BRA Brazil M L6 2011 30527
	BRA Brazil M L6 2014 30156
	BRA Brazil M L6 2016 32443
	CAN Canada F L6 2010 561
	CAN Canada F L6 2012 599
	CAN Canada M L6 2012 3018

I'm trying to use this data to generate a series of reports. I'm stuck on the first report where I have to include:


The graduate percentage for each country, by degree, for all years and all genders


a. each country will be a row, and there will be a column for each type of degree, plus one column for
all degrees combined


b. each cell will show the proportion of graduates in that specific country, for that specific degree,
compared to the total graduates in all countries combined, for that degree


So generally, I want the first report to be printed like:

Code:

	Country          L6         L7        L8       Total
	----------------------------------------------------
	Country#1         %        %       %       %


	Country#2         .....                         


	Country#3

I'm required to store the graduate data in a linked list which I think I did correctly, but I'm having trouble with figuring out how to find the total number of graduates for all degrees in a specific country, as well as the total graduates in all countries combined, for that degree. My attempt at this is in report.c and I think I have the right idea of declaring variables for each degree (L6, L7, L8) and then adding the number of grads to the variable if the record's degree in the file matches the variable. I also think I have the right idea of finding the total number of graduates in a specific country by doing totalAllDegreesForCountry = L6+L7+L8.


However, I'm having trouble figuring out how to keep track of the degree percentages for EACH specific country (right now I don't even access country variable and I don't know where I would use it), and then also iterating through every country and finding the total number of graduates for all degrees and countries.


I would really appreciate some help with this or a push in the right direction.


defs.h

Code:

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


	#define MAX_STR 32


	typedef struct {
	  char code[MAX_STR];
	  char country[MAX_STR];
	  char gender[MAX_STR];
	  char degree[MAX_STR];
	  int year;
	  int numberOfGrads;
	} DataType;


	typedef struct Node {
	  DataType *data;
	  struct Node *next;
	} NodeType;


	typedef struct {
		int size;
		NodeType *head;
		NodeType *tail;
	} ListType;
	void initData(DataType**, char*, char*, char*, char*, int, int);
	void printData(const DataType*);
	void addDataToList(NodeType**, DataType*);
	void addDataToList(NodeType**, DataType*);
	void reportOne(ListType*);

main.c

Code:

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


	#include "defs.h"	
	int main()
	{
	  FILE *infile;  
	  DataType *data;
	  ListType *list ;
	  char code[MAX_STR];
	  char country[MAX_STR];
	  char gender[MAX_STR];
	  char degree[MAX_STR];
	  int year;
	  int numberOfGrads;
	  char input[MAX_STR];


	  list->size = 0;
	  list->head = NULL;
	  list->tail = NULL;


	  infile = fopen("grad.dat", "r");
	  if (!infile) {
		printf("Error: could not open file\n");
		exit(1);
	  }
	  
	  while (1) {
		fscanf(infile, "%s %s %s %s %d %d ", code, country, gender, degree, &year,  &numberOfGrads);
		initData(&data, code, country, gender, degree, year, numberOfGrads);
		addDataToList(list, data);
		if (feof(infile))
		  break;
	  }
	  fclose(infile);


	  while (1){
		 printf(" 0. Quit \n");
		 printf(" 1 = Top 5 and bottom 5 countries of female graduates \n");


		printf("Enter a selection: ");
		scanf("%s", input);  


		if(strcmp(input, "1")==0){
			reportOne(list);
		}else if(strcmp(input, "0")==0){
		  break;
		}
	  }
	}


	void initData(DataType **r, char *co, char *c, char *g, char *d, int y, int n){
		*r = malloc(sizeof(DataType));
		strcpy((*r)->code, co);
		strcpy((*r)->country, c);
		strcpy((*r)->gender, g);
		strcpy((*r)->degree, d);
		(*r)->year = y;
		(*r)->numberOfGrads = n;
	}


	void printData(const DataType *data){
		printf("%s %s %s %s %d %d\n", data->code, data->country, data->gender, data->degree, data->year, data->numberOfGrads);
	}


	void addDataToList(NodeType **listHead, DataType *data){
	  NodeType *currNode;
	  NodeType *prevNode;
	  NodeType *newNode;
	  
	  currNode = *listHead;
	  prevNode = NULL;


	  while (currNode != NULL) {
		prevNode = currNode;
		currNode = currNode->next;
	  }


	  newNode = malloc(sizeof(NodeType));
	  newNode->data = data;
	  newNode->next = NULL;


	  if (prevNode == NULL) 
		*listHead = newNode;
	  else
		prevNode->next = newNode;
	  newNode->next = currNode;
	}


	void printList(NodeType *listHead){
	  NodeType *currNode = listHead;
	  while (currNode != NULL) {
		printData(currNode->data);
		currNode = currNode->next;
	  }
	}

reports.c

Code:

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


	#include "defs.h"
	void reportOne(ListType* list){
	  NodeType *currNode = list->head;
	 
	  float L6 = 0;
	  float L7 = 0;
	  float L8 = 0;


	  float totalSpecificDegree;
	  float totalAllDegreesForCountry;
	  float totalAllDegreesAllCountries;


	  printf("%20s %15s %15s %15s %15s \n", "Country", "L6","L7","L8", "Total");


	  while (currNode != NULL) {
		if(strcmp(currNode->data->degree, "L6")==0){ 
			L6 += (currNode->data->numberOfGrads);
		}else if(strcmp(currNode->data->degree,"L7")==0){
			L7 += currNode->data->numberOfGrads;
		}else if(strcmp(currNode->data->degree,"L8")==0){
			L8 += currNode->data->numberOfGrads;
		}
		currNode = currNode->next;
		totalAllDegreesForCountry = L6+L7+L8;
	  }
	  
	  printf("%-15s %6.2f %6.2f %6.2f %7.2f \n", currNode->data->country, L6/totalSpecificDegree, L7/totalSpecificDegree, L8/totalSpecificDegree, totalAllDegreesForCountry/totalAllDegreesAllCountries;);
	}