lakshith-403

/*
Solution for full marks uses binary search
*/

#include <bits/stdc++.h>

#define ll long long
#define pb push_back
#define f first
#define s second

lakshith-403

#include <bits/stdc++.h>

#define ll long long
#define pb push_back
#define f first
#define s second
#define what_is(a) cout << #a << " is " << a << "\n";
#define shit cout << "shit" << "\n";
#define pi pair<int,int>

lakshith-403

#include <bits/stdc++.h>

using namespace std;

struct subset{int parent,rank;};

struct edge{int u,v,w;};

bool comp(edge a,edge b){
    return a.w < b.w;

lakshith-403

#include <bits/stdc++.h>

using namespace std;

#define int long long 
#define what_is(a) cout << #a << " is " << a << "\n"
#define checker(a) cout << "checker reached " << a << "\n"

inline void io(){
    ios_base::sync_with_stdio(false);

lakshith-403

#include <bits/stdc++.h>

using namespace std;

#define int long long 
#define what_is(a) cout << #a << " is " << a << "\n"
#define checker(a) cout << "checker reached " << a << "\n"

inline void io(){
    ios_base::sync_with_stdio(false);

lakshith-403

#include <bits/stdc++.h>

using namespace std;

#define int long long
#define what_is(a) cout << #a << " is " << a << "\n"
#define checker(a) cout << "checker reached " << a << "\n"

inline void io(){
    ios_base::sync_with_stdio(false);

lakshith-403

#include <bits/stdc++.h>

using namespace std;
#define int long long

struct Flight
{
    int start, finish, profit;
};

lakshith-403

/**
 * @author Lakshith Nishshanke
 * @brief 
 * @version 0.1
 * @date 2021-10-23
 * 
 * @copyright Copyright (c) 2021
 * 
 * Used a greedy approach. Sorted time frames first by their starting time,second by their endind time.
 * And then greedily checked if it is possible to reserve dates in the sorted order.

lakshith-403

#include <bits/stdc++.h>


using namespace std;

int C,P;

struct projectStruct{
    string name;
    int days;

lakshith-403

import torch
import torchvision
from torch import nn
from torch import optim
import pandas as pd
import numpy as np
from torch.utils.data import Dataset
from sklearn.preprocessing import maxabs_scale

from torch.utils.tensorboard import SummaryWriter