I currently have a problem of reading data from a CSV file.
I think the code works almost fine. However, the printed output shows some weird characters as below (output 9-11).
Do you have any idea on what is happening here? I just want to get rid of these weird characters so that I can process the imported data accordingly.
Alternatively, if you have any feedback on my coding style, please share with me if you don't mind.
Output:
Obsns size is 150 and feat size is 4.
1. 5.100000, 3.500000, 1.400000, 0.200000, Iris-setosa
2. 4.900000, 3.000000, 1.400000, 0.200000, Iris-setosa
3. 4.700000, 3.200000, 1.300000, 0.200000, Iris-setosa
4. 4.600000, 3.100000, 1.500000, 0.200000, Iris-setosa
5. 5.000000, 3.600000, 1.400000, 0.200000, Iris-setosa
6. 5.400000, 3.900000, 1.700000, 0.400000, Iris-setosa
7. 4.600000, 3.400000, 1.400000, 0.300000, Iris-setosa
8. 5.000000, 3.400000, 1.500000, 0.200000, Iris-setosa
9. 4.400000, 2.900000, 1.400000, 0.200000, ��L>-setosa
10. 4.900000, 3.100000, 1.500000, 0.100000, Iris���=osa
11. 5.400000, 3.700000, 1.500000, 0.200000, Iris-set��L>
12. 4.800000, 3.400000, 1.600000, 0.200000, Iris-setosa
13. 4.800000, 3.000000, 1.400000, 0.100000, Iris-setosa
14. 4.300000, 3.000000, 1.100000, 0.100000, Iris-setosa
Code:
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
int checkObsnsSize(char *dataFileName);
void readIris();
int main() {
readIris();
return 0;
}
void readIris() {
int featSize = 4;
char *dataFileName = "iris.data";
int obsnsSize = checkObsnsSize(dataFileName);
float feat[featSize][obsnsSize];
int label[obsnsSize];
memset(feat, 0, featSize * obsnsSize * sizeof(float));
memset(label, 0, obsnsSize * sizeof(int));
printf("Obsns size is %d and feat size is %d.\n", obsnsSize, featSize);
FILE *fpDataFile = fopen(dataFileName, "r");
if (!fpDataFile) {
printf("Missing input file: %s\n", dataFileName);
exit(1);
}
int index = 0;
while (!feof(fpDataFile)) {
char line[1024];
char flowerType[20];
fgets(line, 1024, fpDataFile);
sscanf(line, "%f,%f,%f,%f,%[^\n]",
&feat[1][index], &feat[2][index],
&feat[3][index], &feat[4][index], flowerType);
printf("%d. %f, %f, %f, %f, %s\n", ((int)index + 1),
feat[1][index], feat[2][index],
feat[3][index], feat[4][index], flowerType);
index++;
}
fclose(fpDataFile);
}
int checkObsnsSize(char *dataFileName) {
int obsnsSize = 0;
char line[1024];
FILE *fpDataFile = fopen(dataFileName, "r");
if (!fpDataFile) {
printf("Missing input file: %s\n", dataFileName);
exit(1);
}
while (!feof(fpDataFile)) {
fgets(line, 1024, fpDataFile);
obsnsSize++;
}
fclose(fpDataFile);
return obsnsSize;
}
sscanf(line, "%f,%f,%f,%f,%[^\n]", &feat[1][index], &feat[2][index],
&feat[3][index], &feat[4][index], flowerType);
printf("%d. %f, %f, %f, %f, %s\n", ((int) index+1), feat[1][index], feat[2][index],
feat[3][index], feat[4][index], flowerType);
In these two line you access index out of bounds here &feat[4][index]
. This causes undefined behaviour .
As declaration of array is
float feat[featSize][obsnsSize]; //where featSize is 4
So you can access index from 0
to 3
not 4
( array indexing start from 0
).
A couple of things:
Don't check on feof
, check the return value fgets()
instead.
while (!feof(fpDataFile)) {
Always check the return value of sscanf()
.
Your index should start at 0 instead of 1 (index 4 is out of bounds):
sscanf(line, "%f,%f,%f,%f,%[^\\n]", &feat[0][index], &feat[1][index], &feat[2][index], &feat[3][index], flowerType); printf("%d. %f, %f, %f, %f, %s\\n", ((int)index + 1), feat[0][index], feat[1][index], feat[2][index], feat[3][index], flowerType);
As @chqrlie stated: use %19[^\\n]
to avoid overflow as flowerType
size is only 20
:
sscanf(line, "%f,%f,%f,%f,%19[^\\n]", &feat[0][index], &feat[1][index], &feat[2][index], &feat[3][index], flowerType);
So to put it all together, the correct code looks like this:
1- Use fgets() return value to determine when the file is completely read.
2- Read into arrays starting at index 0
3- Check return value of sscanf().
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
int checkObsnsSize(char * dataFileName);
void readIris ();
int main () {
readIris();
return 0;
}
void readIris() {
int featSize = 4;
char *dataFileName = "iris.data";
int obsnsSize = checkObsnsSize(dataFileName);
float feat[featSize][obsnsSize];
int label[obsnsSize];
memset(feat, 0, featSize*obsnsSize*sizeof(float));
memset(label, 0, obsnsSize*sizeof(int));
printf("Obsns size is %d and feat size is %d.\n", obsnsSize, featSize);
FILE *fpDataFile = fopen(dataFileName,"r");
if (!fpDataFile) {
printf("Missing input file: %s\n", dataFileName);
exit(1);
}
int index = 0;
char line[1024]; char flowerType[20];
while (fgets(line, 1024, fpDataFile))
{
if( 5 == sscanf(line, "%f,%f,%f,%f,%19[^\n]", &feat[0][index], &feat[1][index], &feat[2][index], &feat[3][index], flowerType))
{
printf("%d. %f, %f, %f, %f, %s\n", ((int) index+1), feat[0][index], feat[1][index], feat[2][index], feat[3][index], flowerType);
index++;
}
}
fclose(fpDataFile);
}
int checkObsnsSize(char * dataFileName) {
int obsnsSize = 0;
char line[1024];
FILE *fpDataFile = fopen(dataFileName,"r");
if (!fpDataFile) {
printf("Missing input file: %s\n", dataFileName);
exit(1);
}
while (!feof(fpDataFile)) {
fgets(line, 1024, fpDataFile);
obsnsSize++;
}
fclose(fpDataFile);
return obsnsSize;
}
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.