How to do a reduction over one dimension of 2D data in Thrust

Question

I'm new to CUDA and the thrust library. I'm learning and trying to implement a function that will have a for loop doing a thrust function. Is there a way to convert this loop into another thrust function? Or should I use a CUDA kernel to achieve this?

I have come up with code like this

// thrust functor
struct GreaterthanX
{
    const float _x;
    GreaterthanX(float x) : _x(x) {}

    __host__ __device__ bool operator()(const float &a) const
    {
        return a > _x;
    }
};

int main(void)
{
    // fill a device_vector with
    // 3 2 4 5
    // 0 -2 3 1
    // 9 8 7 6
    int row = 3;
    int col = 4;
    thrust::device_vector<int> vec(row * col);
    thrust::device_vector<int> count(row);
    vec[0] = 3;
    vec[1] = 2;
    vec[2] = 4;
    vec[3] = 5;
    vec[4] = 0;
    vec[5] = -2;
    vec[6] = 3;
    vec[7] = 1;
    vec[8] = 9;
    vec[9] = 8;
    vec[10] = 7;
    vec[11] = 6;

    // Goal: For each row, count the number of elements greater than 2. 
    // And then find the row with the max count

    // count the element greater than 2 in vec
    for (int i = 0; i < row; i++)
    {
        count[i] = thrust::count_if(vec.begin(), vec.begin() + i * col, GreaterthanX(2));
    }

    thrust::device_vector<int>::iterator result = thrust::max_element(count.begin(), count.end());
    int max_val = *result;
    unsigned int position = result - count.begin();

    printf("result = %d at position %d\r\n", max_val, position);
    // result = 4 at position 2

    return 0;
}

My goal is to find the row that has the most elements greater than 2. I'm struggling at how to do this without a loop. Any suggestions would be very appreciated. Thanks.