Terminate called after throwing an instance of 'std::invalid_argument' what(): stof - c++

Question

As I was writing the in the other post, I am trying to implement the K-means algorithm in C++. When debugging, I get no errors, but when trying to run the program, I get the error I mentioned in the title:
Terminate called after throwing an instance of 'std:invalid_argument' what():stof
I know that this error comes when the file can't convert to float. Then, what I wanted to ask is, is there something that I should change in my code, or would it be better to use another file format as input, instead of a *.csv file ? (obviosuly, I'm making the hypothesis that the program can't read something from the file. I don't know if that's the right reasoning though.)
Thank you everyone!
#include <iostream>
#include <fstream>
#include <sstream>
#include <vector>
using namespace std;
//Inizializzare il punto
struct Point {
double x, y; // Coordinate del punto
int cluster; // Cluster di default
double minDist; // Distanza minima
Point()
: x(0.0)
, y(0.0)
, cluster(-1)
, minDist(__DBL_MAX__)
{
}
Point(double x, double y)
: x(x)
, y(y)
, cluster(-1)
, minDist(__DBL_MAX__)
{
}
double distance(Point p)
{
return (p.x - x) * (p.x - x) + (p.y - y) * (p.y - y);
}
};
vector<Point> readcsv()
{
vector<Point> points;
string line;
ifstream file("Mall_Customers.csv");
while (getline(file, line)) {
stringstream lineStream(line);
string bit;
double x, y;
getline(lineStream, bit, ',');
x = stof(bit);
getline(lineStream, bit, '\n');
y = stof(bit);
points.push_back(Point(x, y));
}
return points;
}
vector<Point> points = readcsv();
void kMeansClustering(vector<Point>* points, int epochs, int k)
{
int n = points->size();
vector<Point> centroids;
srand(time(0));
for (int i = 0; i < k; ++i) {
centroids.push_back(points->at(rand() % n));
}
for (vector<Point>::iterator c = begin(centroids); c != end(centroids); ++c) {
int clusterId = c - begin(centroids);
{
for (vector<Point>::iterator it = points->begin(); it != points->end(); ++it) {
Point p = *it;
double dist = c->distance(p);
if (dist < p.minDist) {
p.minDist = dist;
p.cluster = clusterId;
}
*it = p;
}
}
}
vector<int> nPoints;
vector<double> sumX, sumY;
for (int j = 0; j < k; j++) {
nPoints.push_back(0.0);
sumX.push_back(0.0);
sumY.push_back(0.0);
}
for (vector<Point>::iterator it = points->begin(); it != points->end(); ++it) {
int clusterId = it->cluster;
nPoints[clusterId] += 1;
sumX[clusterId] += it->x;
sumY[clusterId] += it->y;
it->minDist = __DBL_MAX__; // reset distance
}
// Compute the new centroids
for (vector<Point>::iterator c = begin(centroids); c != end(centroids); ++c) {
int clusterId = c - begin(centroids);
c->x = sumX[clusterId] / nPoints[clusterId];
c->y = sumY[clusterId] / nPoints[clusterId];
}
// Write to csv
ofstream myfile;
myfile.open("output.csv");
myfile << "x,y,c" << endl;
for (vector<Point>::iterator it = points->begin(); it != points->end();
++it) {
myfile << it->x << "," << it->y << "," << it->cluster << endl;
}
myfile.close();
}
int main()
{
vector<Point> points = readcsv();
// Run k-means with 100 iterations and for 5 clusters
kMeansClustering(&points, 100, 5);
}

Answer 1

It seems to work now, thank you everyone for the help you gave me, in particular #Yksisarvinen and #molbdnilo : the problem was in the fact that I blindly imported all the csv file in the program, but I was supposed to import only two columns: one was the income, the other one was the spending column.
Although now I have to figure why it shows me the final result, not in the form of "bubbles",as one would expect from the algorithm,but in the form of points being clustered on a straight line.
When trying to open the original file, the original dataset, I get the error shown in the image below.