1.Two-Sum Problem
The goal of this problem is to implement a variant of the 2-SUM algorithm (covered in the Week 5 lecture on hash table applications)
The file contains 500,000 positive integers (there might be some repetitions!).This is your array of integers, with the ith row
of the file specifying the ithentry
of the array.
Your task is to compute the number of target values t in
the interval [2500,4000] (inclusive) such that there are distinct numbers x,y in
the input file that satisfy x+y=t.
(NOTE: ensuring distinctness requires a one-line addition to the algorithm from lecture.)
Write your numeric answer (an integer between 0 and 1501) in the space provided.
#include<stdio.h>
#include<stdlib.h>
#include<ctype.h>
const char INFILE[] = "HashInt.txt";
#define MAX 10000000
void fetch_hash(long *hash) {
FILE *fp = fopen(INFILE,"r");
char line[10];
long i;
for (i=0; i<MAX; i++)
hash[i] = 0;
while (fgets(line,10,fp))
hash[atoi(line)] ++;
}
short two_sum(long *hash, long t) {
long x;
for (x = 1; x < (t-1)/2; x++)
if ((hash[x])&&(hash[t-x]))
return 1;
return 0;
}
void main()
{
long *hash = calloc(MAX,sizeof(long));
fetch_hash(hash);
short i,count = 0;
for (i = 2500; i <= 4000; i++)
if (two_sum(hash,i))
count++;
printf("count = %d\n",count);
}
2.Median Problem
The goal of this problem is to implement the "Median Maintenance" algorithm (covered in the Week 5 lecture on heap
applications). The text file contains a list of the integers from 1 to 10000 in unsorted order; you should treat this as a stream of numbers, arriving one by one. Letting xi denote
the ith
number of the file, the kth
median mk is
defined as the median of the numbers x1,…,xk.
(So, if k is
odd, then mk is ((k+1)/2)th
smallest number among x1,…,xk;
if k is
even, then mk is
the (k/2)th
smallest number among x1,…,xk.)
In the box below you should type the sum of these 10000 medians, modulo 10000 (i.e., only the last 4 digits). That
is, you should compute (m1+m2+m3+⋯+m10000)mod10000.
#include<stdio.h>
#include<stdlib.h>
#include<ctype.h>
#include"heap.h"
const char INFILE[] = "Median.txt";
#define MAX 10000
short RETURN_MEDIAN(short *A1,short *A2,short x) {
if (x<A2[1])
MAX_HEAP_INSERT(A1,x);
else
MIN_HEAP_INSERT(A2,x);
if (A1[0]-A2[0]>1)
MIN_HEAP_INSERT(A2,EXTRACT_MAX(A1));
if (A2[0]>A1[0])
MAX_HEAP_INSERT(A1,EXTRACT_MIN(A2));
return A1[1];
}
void print(short *A) {
short i;
for (i=1; i<=A[0]; i++)
printf("%d ",A[i]);
}
void main() {
short *A1,*A2,m=0;
A1 = calloc(1+MAX,sizeof(short));
A2 = calloc(1+MAX,sizeof(short));
A1[0] = 1; A1[1] = 0;
A2[0] = 1; A2[1] = 20000;
char line[10];
FILE *fp = fopen(INFILE,"r");
while (fgets(line,10,fp))
m = (m + RETURN_MEDIAN(A1,A2,atoi(line))) % 10000;
printf("%d\n",m);
}
where "heap.h" contains many heap functions.
#ifndef _HEAP_H_
#define _HEAP_H_
// MAX_HEAP
void MAX_HEAPIFY(short *A,short i) {
short left=2*i,right=2*i+1,larger,tmp;
if ((left<=A[0])&&(A[left]>A[i]))
larger = left;
else
larger = i;
if ((right<=A[0])&&(A[right]>A[larger]))
larger = right;
if (larger != i) {
tmp = A[larger]; A[larger] = A[i]; A[i] = tmp;
MAX_HEAPIFY(A,larger);
}
}
short EXTRACT_MAX(short *A) {
short max = A[1];
A[1] = A[A[0]--];
MAX_HEAPIFY(A,1);
return max;
}
void HEAP_INCREASE_KEY(short *A,short i,short key) {
short tmp;
A[i] = key;
while ((i>1)&&(A[i/2]<A[i])) {
tmp = A[i]; A[i] = A[i/2]; A[i/2] = tmp;
i = i/2;
}
}
void MAX_HEAP_INSERT(short *A,short key) {
A[0]++;
HEAP_INCREASE_KEY(A,A[0],key);
}
// MIN_HEAP
void MIN_HEAPIFY(short *A,short i) {
short left=2*i,right=2*i+1,smaller,tmp;
if ((left<=A[0])&&(A[left]<A[i]))
smaller = left;
else
smaller = i;
if ((right<=A[0])&&(A[right]<A[smaller]))
smaller = right;
if (smaller != i) {
tmp = A[smaller]; A[smaller] = A[i]; A[i] = tmp;
MIN_HEAPIFY(A,smaller);
}
}
short EXTRACT_MIN(short *A) {
short min = A[1];
A[1] = A[A[0]--];
MIN_HEAPIFY(A,1);
return min;
}
void HEAP_DECREASE_KEY(short *A,short i,short key) {
short tmp;
A[i] = key;
while ((i>1)&&(A[i/2]>A[i])) {
tmp = A[i]; A[i] = A[i/2]; A[i/2] = tmp;
i = i/2;
}
}
void MIN_HEAP_INSERT(short *A,short key) {
A[0]++;
HEAP_DECREASE_KEY(A,A[0],key);
}
#endif