m1une's library

This documentation is automatically generated by online-judge-tools/verification-helper

View on GitHub

:heavy_check_mark: verify/optimization/hungarian.test.cpp

Depends on

Code

#define PROBLEM "https://judge.yosupo.jp/problem/assignment"

#include <algorithm>
#include <cassert>
#include "../../utilities/fast_io.hpp"
#include <limits>
#include <vector>

#include "../../optimization/hungarian.hpp"

long long brute_min(const std::vector<std::vector<long long>>& cost) {
    int h = int(cost.size());
    int w = h == 0 ? 0 : int(cost[0].size());
    if (h == 0 || w == 0) return 0;

    long long best = std::numeric_limits<long long>::max() / 4;
    if (h <= w) {
        std::vector<int> perm(w);
        for (int i = 0; i < w; i++) perm[i] = i;
        do {
            long long sum = 0;
            for (int i = 0; i < h; i++) sum += cost[i][perm[i]];
            best = std::min(best, sum);
        } while (std::next_permutation(perm.begin(), perm.end()));
    } else {
        std::vector<int> perm(h);
        for (int i = 0; i < h; i++) perm[i] = i;
        do {
            long long sum = 0;
            for (int j = 0; j < w; j++) sum += cost[perm[j]][j];
            best = std::min(best, sum);
        } while (std::next_permutation(perm.begin(), perm.end()));
    }
    return best;
}

long long brute_max(const std::vector<std::vector<long long>>& cost) {
    std::vector<std::vector<long long>> negated = cost;
    for (auto& row : negated) {
        for (auto& x : row) x = -x;
    }
    return -brute_min(negated);
}

void check_result(const std::vector<std::vector<long long>>& cost,
                  const m1une::opt::HungarianResult<long long>& result,
                  long long expected) {
    int h = int(cost.size());
    int w = h == 0 ? 0 : int(cost[0].size());
    assert(int(result.row_to_col.size()) == h);
    assert(int(result.col_to_row.size()) == w);
    assert(result.matching_size() == std::min(h, w));
    assert(result.cost == expected);

    std::vector<bool> used_cols(w, false);
    long long sum = 0;
    for (int i = 0; i < h; i++) {
        int j = result.row_to_col[i];
        if (j == -1) continue;
        assert(0 <= j && j < w);
        assert(!used_cols[j]);
        assert(result.col_to_row[j] == i);
        used_cols[j] = true;
        sum += cost[i][j];
    }
    for (int j = 0; j < w; j++) {
        int i = result.col_to_row[j];
        if (i == -1) continue;
        assert(0 <= i && i < h);
        assert(result.row_to_col[i] == j);
    }
    assert(sum == result.cost);

    auto pairs = result.matching();
    assert(int(pairs.size()) == result.matching_size());
    for (auto [row, col] : pairs) assert(result.row_to_col[row] == col);
}

void test_hungarian_min() {
    std::vector<std::vector<long long>> square = {
        {4, 1, 3},
        {2, 0, 5},
        {3, 2, 2},
    };
    auto sq = m1une::opt::hungarian_min(square);
    check_result(square, sq, 5);

    std::vector<std::vector<long long>> wide = {
        {7, 4, 6, 8},
        {5, 9, 3, 1},
    };
    check_result(wide, m1une::opt::hungarian(wide), brute_min(wide));

    std::vector<std::vector<long long>> tall = {
        {9, 4},
        {6, 7},
        {5, 8},
        {1, 3},
    };
    auto tall_result = m1une::opt::hungarian_min(tall);
    check_result(tall, tall_result, brute_min(tall));
    assert(tall_result.col_to_row[0] != -1);
    assert(tall_result.col_to_row[1] != -1);

    std::vector<std::vector<long long>> negative = {
        {-4, 2, 0},
        {3, -5, 1},
    };
    check_result(negative, m1une::opt::hungarian_min(negative), brute_min(negative));

    std::vector<std::vector<long long>> zero_cols(3);
    check_result(zero_cols, m1une::opt::hungarian_min(zero_cols), 0);
}

void test_hungarian_max() {
    std::vector<std::vector<long long>> cost = {
        {1, 8, 2},
        {5, 3, 4},
        {6, 7, 0},
    };
    check_result(cost, m1une::opt::hungarian_max(cost), brute_max(cost));
}

void test_against_bruteforce() {
    for (int h = 1; h <= 4; h++) {
        for (int w = 1; w <= 4; w++) {
            std::vector<std::vector<long long>> cost(h, std::vector<long long>(w));
            for (int i = 0; i < h; i++) {
                for (int j = 0; j < w; j++) {
                    cost[i][j] = ((i + 2) * (j + 3) * 5 + i * 7 - j * 11) % 17 - 8;
                }
            }
            check_result(cost, m1une::opt::hungarian_min(cost), brute_min(cost));
            check_result(cost, m1une::opt::hungarian_max(cost), brute_max(cost));
        }
    }
}

int main() {
    m1une::utilities::FastInput fast_input;
    m1une::utilities::FastOutput fast_output;

    test_hungarian_min();
    test_hungarian_max();
    test_against_bruteforce();
    int n;
    fast_input >> n;
    std::vector<std::vector<long long>> cost(n, std::vector<long long>(n));
    for (int i = 0; i < n; i++) {
        for (int j = 0; j < n; j++) {
            fast_input >> cost[i][j];
        }
    }

    auto result = m1une::opt::hungarian_min(cost);
    fast_output << result.cost << '\n';
    for (int i = 0; i < n; i++) {
        if (i) fast_output << ' ';
        fast_output << result.row_to_col[i];
    }
    fast_output << '\n';
}
#line 1 "verify/optimization/hungarian.test.cpp"
#define PROBLEM "https://judge.yosupo.jp/problem/assignment"

#include <algorithm>
#include <cassert>
#line 1 "utilities/fast_io.hpp"



#line 5 "utilities/fast_io.hpp"
#include <array>
#include <cerrno>
#include <charconv>
#include <cstddef>
#include <cstdio>
#include <cstdlib>
#include <cstdint>
#include <cstring>
#include <iterator>
#include <string>
#include <sys/stat.h>
#include <type_traits>
#include <utility>
#include <unistd.h>
#include <vector>

namespace m1une {
namespace utilities {

struct FastOutput;

namespace internal {

// Shared with the convenience helpers in template.hpp.
inline FastOutput* standard_output_instance = nullptr;

// Detect std::begin(x), std::end(x).
template <class T, class = void>
struct is_range : std::false_type {};

template <class T>
struct is_range<T, std::void_t<
    decltype(std::begin(std::declval<T&>())),
    decltype(std::end(std::declval<T&>()))
>> : std::true_type {};

template <class T>
inline constexpr bool is_range_v = is_range<T>::value;

template <class T>
using range_reference_t = decltype(*std::begin(std::declval<T&>()));

template <class T>
using range_value_t = std::remove_cv_t<std::remove_reference_t<range_reference_t<T>>>;

template <class T, class = void>
struct range_stored_value {
    using type = range_value_t<T>;
};

template <class T>
struct range_stored_value<T, std::void_t<typename std::remove_cv_t<std::remove_reference_t<T>>::value_type>> {
    using type = typename std::remove_cv_t<std::remove_reference_t<T>>::value_type;
};

template <class T>
using range_stored_value_t = typename range_stored_value<T>::type;

// Treat strings and C strings as scalar output objects, not as ranges.
template <class T>
struct is_char_array : std::false_type {};

template <class T, std::size_t N>
struct is_char_array<T[N]>
    : std::bool_constant<std::is_same_v<std::remove_cv_t<T>, char>> {};

template <class T>
struct is_string_like
    : std::bool_constant<
          std::is_same_v<std::decay_t<T>, std::string>
          || std::is_same_v<std::decay_t<T>, const char*>
          || std::is_same_v<std::decay_t<T>, char*>
          || is_char_array<std::remove_reference_t<T>>::value
      > {};

template <class T>
inline constexpr bool is_string_like_v = is_string_like<T>::value;

// ModInt-like type: x.val() is printable, and x can be assigned from long long.
template <class T, class = void>
struct has_val_method : std::false_type {};

template <class T>
struct has_val_method<T, std::void_t<decltype(std::declval<const T&>().val())>>
    : std::true_type {};

template <class T>
inline constexpr bool has_val_method_v = has_val_method<T>::value;

template <class T, class = void>
struct has_static_mod_raw : std::false_type {};

template <class T>
struct has_static_mod_raw<
    T, std::void_t<decltype(T::mod()), decltype(T::raw(std::declval<uint32_t>()))>>
    : std::true_type {};

template <class T>
inline constexpr bool has_static_mod_raw_v = has_static_mod_raw<T>::value;

// libstdc++ before GCC 16 does not classify __int128 as an integral type in
// strict ISO modes such as -std=c++23. Keep the fast-I/O interface independent
// of that implementation detail.
template <class T>
inline constexpr bool is_integral_v =
    std::is_integral_v<T>
    || std::is_same_v<std::remove_cv_t<T>, __int128_t>
    || std::is_same_v<std::remove_cv_t<T>, __uint128_t>;

template <class T>
inline constexpr bool is_signed_v =
    std::is_signed_v<T>
    || std::is_same_v<std::remove_cv_t<T>, __int128_t>;

template <class T>
struct make_unsigned {
    using type = std::make_unsigned_t<T>;
};

template <>
struct make_unsigned<__int128_t> {
    using type = __uint128_t;
};

template <>
struct make_unsigned<__uint128_t> {
    using type = __uint128_t;
};

template <class T>
using make_unsigned_t = typename make_unsigned<std::remove_cv_t<T>>::type;

}  // namespace internal

struct FastInput {
    static constexpr int buffer_size = 1 << 20;

   private:
    std::FILE* _stream;
    char _buffer[buffer_size];
    int _position;
    int _length;
    int _file_descriptor;
    bool _streaming;

    bool refill() {
        _position = 0;
        if (_streaming) {
            ssize_t length;
            do {
                length = ::read(_file_descriptor, _buffer, buffer_size);
            } while (length < 0 && errno == EINTR);
            if (length <= 0) {
                _length = 0;
                return false;
            }
            _length = int(length);
        } else {
            _length = int(std::fread(_buffer, 1, buffer_size, _stream));
        }
        return _length != 0;
    }

    template <class T>
    bool read_integer_from_stream(T& value) {
        if (!skip_spaces()) return false;
        int c = read_char_raw();

        bool negative = false;
        if (c == '-') {
            negative = true;
            c = read_char_raw();
        }

        if constexpr (internal::is_signed_v<T>) {
            T result = 0;
            while ('0' <= c && c <= '9') {
                result = negative ? result * 10 - (c - '0')
                                  : result * 10 + (c - '0');
                c = read_char_raw();
            }
            value = result;
        } else {
            T result = 0;
            while ('0' <= c && c <= '9') {
                result = result * 10 + T(c - '0');
                c = read_char_raw();
            }
            value = negative ? T(0) - result : result;
        }
        return true;
    }

    bool prepare_number() {
        if (_length - _position >= 64) return true;
        const int remaining = _length - _position;
        if (remaining > 0) std::memmove(_buffer, _buffer + _position, remaining);
        const int added = int(std::fread(_buffer + remaining, 1, buffer_size - remaining, _stream));
        _position = 0;
        _length = remaining + added;
        if (_length < buffer_size) _buffer[_length] = '\0';
        return _length != 0;
    }

   public:
    explicit FastInput(std::FILE* stream = stdin)
        : _stream(stream),
          _position(0),
          _length(0),
          _file_descriptor(::fileno(stream)),
          _streaming([&] {
              struct stat status;
              return _file_descriptor >= 0
                     && ::fstat(_file_descriptor, &status) == 0
                     && !S_ISREG(status.st_mode);
          }()) {}

    FastInput(const FastInput&) = delete;
    FastInput& operator=(const FastInput&) = delete;

    int read_char_raw() {
        if (_position == _length && !refill()) return EOF;
        return _buffer[_position++];
    }

    bool skip_spaces() {
        int c = read_char_raw();
        while (c != EOF && c <= ' ') c = read_char_raw();
        if (c == EOF) return false;
        --_position;
        return true;
    }

    bool read(char& value) {
        if (!skip_spaces()) return false;
        value = char(read_char_raw());
        return true;
    }

    bool read(std::string& value) {
        if (!skip_spaces()) return false;
        value.clear();
        while (true) {
            const int begin = _position;
            while (_position < _length &&
                   static_cast<unsigned char>(_buffer[_position]) > ' ') {
                ++_position;
            }
            value.append(_buffer + begin, _position - begin);
            if (_position < _length) {
                ++_position;
                return true;
            }
            if (!refill()) return true;
        }
    }

    bool read(bool& value) {
        int x;
        if (!read(x)) return false;
        value = x != 0;
        return true;
    }

    template <class T>
    std::enable_if_t<
        internal::is_integral_v<T>
            && !std::is_same_v<std::remove_cv_t<T>, bool>
            && !std::is_same_v<std::remove_cv_t<T>, char>,
        bool
    >
    read(T& value) {
        if (_streaming) return read_integer_from_stream(value);
        if (!prepare_number()) return false;
        int c = static_cast<unsigned char>(_buffer[_position++]);
        while (c <= ' ') c = static_cast<unsigned char>(_buffer[_position++]);

        bool negative = false;
        if (c == '-') {
            negative = true;
            c = static_cast<unsigned char>(_buffer[_position++]);
        }

        if constexpr (internal::is_signed_v<T>) {
            T result = 0;
            while ('0' <= c && c <= '9') {
                const int first = c - '0';
                const int second = static_cast<unsigned char>(_buffer[_position]) - '0';
                if (0 <= second && second <= 9) {
                    result = negative ? result * 100 - (first * 10 + second)
                                      : result * 100 + (first * 10 + second);
                    ++_position;
                } else {
                    result = negative ? result * 10 - first : result * 10 + first;
                }
                c = static_cast<unsigned char>(_buffer[_position++]);
            }
            value = result;
        } else {
            T result = 0;
            while ('0' <= c && c <= '9') {
                const unsigned first = unsigned(c - '0');
                const int second = static_cast<unsigned char>(_buffer[_position]) - '0';
                if (0 <= second && second <= 9) {
                    result = result * 100 + T(first * 10 + unsigned(second));
                    ++_position;
                } else {
                    result = result * 10 + T(first);
                }
                c = static_cast<unsigned char>(_buffer[_position++]);
            }
            value = negative ? T(0) - result : result;
        }
        if (_position > _length) _position = _length;
        return true;
    }

    template <class T>
    std::enable_if_t<std::is_floating_point_v<T>, bool>
    read(T& value) {
        if (!skip_spaces()) return false;
        int c = read_char_raw();
        bool negative = false;
        if (c == '-' || c == '+') {
            negative = c == '-';
            c = read_char_raw();
        }

        long double result = 0;
        while ('0' <= c && c <= '9') {
            result = result * 10 + (c - '0');
            c = read_char_raw();
        }
        if (c == '.') {
            long double place = 0.1L;
            c = read_char_raw();
            while ('0' <= c && c <= '9') {
                result += (c - '0') * place;
                place *= 0.1L;
                c = read_char_raw();
            }
        }
        if (c == 'e' || c == 'E') {
            c = read_char_raw();
            bool exponent_negative = false;
            if (c == '-' || c == '+') {
                exponent_negative = c == '-';
                c = read_char_raw();
            }
            int exponent = 0;
            while ('0' <= c && c <= '9') {
                exponent = exponent * 10 + (c - '0');
                c = read_char_raw();
            }
            long double scale = 1;
            long double power = 10;
            while (exponent > 0) {
                if (exponent & 1) scale *= power;
                power *= power;
                exponent >>= 1;
            }
            result = exponent_negative ? result / scale : result * scale;
        }
        value = static_cast<T>(negative ? -result : result);
        return true;
    }

    template <class T>
    std::enable_if_t<
        internal::has_val_method_v<T>
            && !internal::is_integral_v<T>
            && !internal::is_range_v<T>,
        bool
    >
    read(T& value) {
        long long x;
        if (!read(x)) return false;
        if constexpr (internal::has_static_mod_raw_v<T>) {
            if (x >= 0 && uint64_t(x) < uint64_t(T::mod())) {
                value = T::raw(uint32_t(x));
            } else {
                value = T(x);
            }
        } else {
            value = T(x);
        }
        return true;
    }

    template <class First, class Second>
    bool read(std::pair<First, Second>& value) {
        if (!read(value.first)) return false;
        return read(value.second);
    }

    template <class Range>
    std::enable_if_t<
        internal::is_range_v<Range>
            && !internal::is_string_like_v<Range>,
        bool
    >
    read(Range& range) {
        using StoredValue = internal::range_stored_value_t<Range>;
        constexpr bool nested = internal::is_range_v<StoredValue>
                                && !internal::is_string_like_v<StoredValue>;

        for (auto&& value : range) {
            if constexpr (std::is_same_v<StoredValue, bool> && !nested) {
                bool x;
                if (!read(x)) return false;
                value = x;
            } else {
                if (!read(value)) return false;
            }
        }
        return true;
    }

    template <class First, class Second, class... Rest>
    bool read(First& first, Second& second, Rest&... rest) {
        if (!read(first)) return false;
        return read(second, rest...);
    }

    template <class T>
    FastInput& operator>>(T& value) {
        if (!read(value)) std::abort();
        return *this;
    }
};

struct FastOutput {
    static constexpr int buffer_size = 1 << 20;

   private:
    inline static const auto digit_quads = [] {
        std::array<char, 40000> result{};
        for (int i = 0; i < 10000; i++) {
            int value = i;
            for (int j = 3; j >= 0; j--) {
                result[4 * i + j] = char('0' + value % 10);
                value /= 10;
            }
        }
        return result;
    }();

    std::FILE* _stream;
    char _buffer[buffer_size];
    int _position;
    int _precision;
    std::chars_format _float_format;
    char _range_separator;
    std::string* _capture = nullptr;

    template <class T>
    std::string format_cell(const T& value) {
        std::string result;
        struct CaptureGuard {
            std::string*& target;
            std::string* previous;
            ~CaptureGuard() { target = previous; }
        } guard{_capture, _capture};
        _capture = &result;
        write(value);
        return result;
    }

    template <class Matrix>
    void write_aligned_matrix(const Matrix& matrix) {
        std::vector<std::vector<std::string>> rows;
        std::vector<std::size_t> widths;
        for (const auto& row : matrix) {
            auto& cells = rows.emplace_back();
            std::size_t column = 0;
            for (const auto& value : row) {
                cells.push_back(format_cell(value));
                if (column == widths.size()) widths.push_back(0);
                widths[column] = std::max(widths[column], cells.back().size());
                ++column;
            }
        }
        bool first = true;
        for (const auto& row : rows) {
            if (!first) write_char('\n');
            first = false;
            for (std::size_t column = 0; column < row.size(); ++column) {
                if (column != 0) write_char(_range_separator);
                for (std::size_t padding = row[column].size();
                     padding < widths[column]; ++padding) {
                    write_char(' ');
                }
                write(row[column]);
            }
        }
    }

   public:
    explicit FastOutput(std::FILE* stream = stdout)
        : _stream(stream),
          _position(0),
          _precision(6),
          _float_format(std::chars_format::general),
          _range_separator(' ') {
        if (_stream == stdout
            && internal::standard_output_instance == nullptr) {
            internal::standard_output_instance = this;
        }
    }

    FastOutput(const FastOutput&) = delete;
    FastOutput& operator=(const FastOutput&) = delete;

    ~FastOutput() {
        flush();
        if (internal::standard_output_instance == this) {
            internal::standard_output_instance = nullptr;
        }
    }

    void flush() {
        if (_position != 0) {
            std::fwrite(_buffer, 1, _position, _stream);
            _position = 0;
        }
        std::fflush(_stream);
    }

    void write_char(char c) {
        if (_capture != nullptr) {
            _capture->push_back(c);
            return;
        }
        if (_position == buffer_size) flush();
        _buffer[_position++] = c;
    }

    void write(const char* s) {
        while (*s != '\0') write_char(*s++);
    }

    void write(const std::string& s) {
        if (_capture != nullptr) {
            _capture->append(s);
            return;
        }
        std::size_t position = 0;
        while (position < s.size()) {
            if (_position == buffer_size) flush();
            const std::size_t copied =
                std::min<std::size_t>(buffer_size - _position, s.size() - position);
            std::memcpy(_buffer + _position, s.data() + position, copied);
            _position += int(copied);
            position += copied;
        }
    }

    void write(char c) {
        write_char(c);
    }

    void write(bool value) {
        write_char(value ? '1' : '0');
    }

    template <class T>
    std::enable_if_t<std::is_floating_point_v<T>>
    write(T value) {
        char digits[128];
        auto [end, error] = std::to_chars(
            digits,
            digits + sizeof(digits),
            value,
            _float_format,
            _precision
        );
        if (error != std::errc()) std::abort();
        for (const char* pointer = digits; pointer != end; pointer++) {
            write_char(*pointer);
        }
    }

    template <class T>
    std::enable_if_t<
        internal::is_integral_v<T>
            && !std::is_same_v<std::remove_cv_t<T>, bool>
            && !std::is_same_v<std::remove_cv_t<T>, char>
    >
    write(T value) {
        using Raw = std::remove_cv_t<T>;
        using Unsigned = internal::make_unsigned_t<Raw>;

        Unsigned magnitude;
        if constexpr (internal::is_signed_v<Raw>) {
            if (value < 0) {
                write_char('-');
                magnitude = Unsigned(0) - Unsigned(value);
            } else {
                magnitude = Unsigned(value);
            }
        } else {
            magnitude = value;
        }

        if (magnitude == 0) {
            write_char('0');
            return;
        }

        unsigned chunks[16];
        int count = 0;
        while (magnitude >= 10000) {
            const Unsigned quotient = magnitude / 10000;
            chunks[count++] = unsigned(magnitude - quotient * 10000);
            magnitude = quotient;
        }
        if (_capture == nullptr && _position > buffer_size - 64) flush();
        char captured[64];
        char* const begin = _capture != nullptr ? captured : _buffer + _position;
        char* destination = begin;
        const unsigned leading = unsigned(magnitude);
        const char* first = digit_quads.data() + 4 * leading;
        int skip = leading < 10 ? 3 : leading < 100 ? 2 : leading < 1000 ? 1 : 0;
        for (; skip < 4; skip++) *destination++ = first[skip];
        while (count--) {
            const char* digits = digit_quads.data() + 4 * chunks[count];
            std::memcpy(destination, digits, 4);
            destination += 4;
        }
        if (_capture != nullptr) {
            _capture->append(begin, destination - begin);
        } else {
            _position += int(destination - begin);
        }
    }

    template <class T>
    std::enable_if_t<
        internal::has_val_method_v<T>
            && !internal::is_integral_v<T>
            && !internal::is_range_v<T>
    >
    write(const T& value) {
        write(value.val());
    }

    template <class First, class Second>
    void write(const std::pair<First, Second>& value) {
        write(value.first);
        write_char(' ');
        write(value.second);
    }

    template <class Range>
    std::enable_if_t<
        internal::is_range_v<Range>
            && !internal::is_string_like_v<Range>
    >
    write(const Range& range) {
        using StoredValue = internal::range_stored_value_t<const Range>;
        constexpr bool nested = internal::is_range_v<StoredValue>
                                && !internal::is_string_like_v<StoredValue>;

        bool first = true;
        for (const auto& value : range) {
            if (!first) write_char(nested ? '\n' : _range_separator);
            first = false;
            if constexpr (std::is_same_v<StoredValue, bool> && !nested) {
                write(static_cast<bool>(value));
            } else {
                write(value);
            }
        }
    }

    template <class First, class... Rest>
    void print(const First& first, const Rest&... rest) {
        write(first);
        ((write_char(' '), write(rest)), ...);
    }

    void println() {
        write_char('\n');
    }

    void set_precision(int precision) {
        _precision = precision;
    }

    void set_fixed(int precision = 6) {
        _float_format = std::chars_format::fixed;
        _precision = precision;
    }

    void set_general(int precision = 6) {
        _float_format = std::chars_format::general;
        _precision = precision;
    }

    void set_range_separator(char separator) {
        _range_separator = separator;
    }

    template <class Matrix>
    void write_aligned(const Matrix& matrix) {
        using Row = internal::range_stored_value_t<const Matrix>;
        using Cell = internal::range_stored_value_t<const Row>;
        static_assert(internal::is_range_v<Row> && !internal::is_string_like_v<Row>,
                      "write_aligned requires a two-dimensional range");
        static_assert(!internal::is_range_v<Cell> || internal::is_string_like_v<Cell>,
                      "write_aligned requires scalar cells");
        write_aligned_matrix(matrix);
    }

    template <class Matrix>
    void println_aligned(const Matrix& matrix) {
        write_aligned(matrix);
        write_char('\n');
    }

    template <class... Args>
    void println(const Args&... args) {
        print(args...);
        write_char('\n');
    }

    template <class T>
    FastOutput& operator<<(const T& value) {
        write(value);
        return *this;
    }
};

}  // namespace utilities
}  // namespace m1une


#line 6 "verify/optimization/hungarian.test.cpp"
#include <limits>
#line 8 "verify/optimization/hungarian.test.cpp"

#line 1 "optimization/hungarian.hpp"



#line 9 "optimization/hungarian.hpp"

namespace m1une {
namespace opt {

template <class T>
struct HungarianResult {
    T cost;
    std::vector<int> row_to_col;
    std::vector<int> col_to_row;

    int matching_size() const {
        int result = 0;
        for (int col : row_to_col) {
            if (col != -1) result++;
        }
        return result;
    }

    std::vector<std::pair<int, int>> matching() const {
        std::vector<std::pair<int, int>> result;
        for (int row = 0; row < int(row_to_col.size()); row++) {
            if (row_to_col[row] != -1) result.push_back({row, row_to_col[row]});
        }
        return result;
    }
};

namespace detail {

template <class T>
T assignment_cost(const std::vector<std::vector<T>>& cost, const std::vector<int>& row_to_col) {
    T result = T();
    for (int row = 0; row < int(row_to_col.size()); row++) {
        if (row_to_col[row] != -1) result += cost[row][row_to_col[row]];
    }
    return result;
}

}  // namespace detail

template <class T>
HungarianResult<T> hungarian_min(const std::vector<std::vector<T>>& cost) {
    int row_count = int(cost.size());
    int col_count = row_count == 0 ? 0 : int(cost[0].size());
    for (const auto& row : cost) assert(int(row.size()) == col_count);

    HungarianResult<T> result;
    result.cost = T();
    result.row_to_col.assign(row_count, -1);
    result.col_to_row.assign(col_count, -1);
    if (row_count == 0 || col_count == 0) return result;

    bool transposed = row_count > col_count;
    int n = transposed ? col_count : row_count;
    int m = transposed ? row_count : col_count;
    T inf = std::numeric_limits<T>::max() / T(4);

    std::vector<T> u(n + 1, T()), v(m + 1, T()), minv(m + 1);
    std::vector<int> p(m + 1, 0), way(m + 1, 0);

    auto value = [&](int i, int j) -> T {
        return transposed ? cost[j][i] : cost[i][j];
    };

    for (int i = 1; i <= n; i++) {
        p[0] = i;
        int j0 = 0;
        std::fill(minv.begin(), minv.end(), inf);
        std::vector<char> used(m + 1, false);

        do {
            used[j0] = true;
            int i0 = p[j0];
            int j1 = 0;
            T delta = inf;

            for (int j = 1; j <= m; j++) {
                if (used[j]) continue;
                T cur = value(i0 - 1, j - 1) - u[i0] - v[j];
                if (cur < minv[j]) {
                    minv[j] = cur;
                    way[j] = j0;
                }
                if (minv[j] < delta) {
                    delta = minv[j];
                    j1 = j;
                }
            }

            for (int j = 0; j <= m; j++) {
                if (used[j]) {
                    u[p[j]] += delta;
                    v[j] -= delta;
                } else {
                    minv[j] -= delta;
                }
            }
            j0 = j1;
        } while (p[j0] != 0);

        do {
            int j1 = way[j0];
            p[j0] = p[j1];
            j0 = j1;
        } while (j0 != 0);
    }

    for (int j = 1; j <= m; j++) {
        if (p[j] == 0) continue;
        int i = p[j] - 1;
        int matched = j - 1;
        if (transposed) {
            int row = matched;
            int col = i;
            result.row_to_col[row] = col;
            result.col_to_row[col] = row;
        } else {
            int row = i;
            int col = matched;
            result.row_to_col[row] = col;
            result.col_to_row[col] = row;
        }
    }
    result.cost = detail::assignment_cost(cost, result.row_to_col);
    return result;
}

template <class T>
HungarianResult<T> hungarian_max(const std::vector<std::vector<T>>& cost) {
    std::vector<std::vector<T>> negated = cost;
    for (auto& row : negated) {
        for (auto& x : row) x = -x;
    }
    auto result = hungarian_min(negated);
    result.cost = detail::assignment_cost(cost, result.row_to_col);
    return result;
}

template <class T>
HungarianResult<T> hungarian(const std::vector<std::vector<T>>& cost) {
    return hungarian_min(cost);
}

}  // namespace opt
}  // namespace m1une


#line 10 "verify/optimization/hungarian.test.cpp"

long long brute_min(const std::vector<std::vector<long long>>& cost) {
    int h = int(cost.size());
    int w = h == 0 ? 0 : int(cost[0].size());
    if (h == 0 || w == 0) return 0;

    long long best = std::numeric_limits<long long>::max() / 4;
    if (h <= w) {
        std::vector<int> perm(w);
        for (int i = 0; i < w; i++) perm[i] = i;
        do {
            long long sum = 0;
            for (int i = 0; i < h; i++) sum += cost[i][perm[i]];
            best = std::min(best, sum);
        } while (std::next_permutation(perm.begin(), perm.end()));
    } else {
        std::vector<int> perm(h);
        for (int i = 0; i < h; i++) perm[i] = i;
        do {
            long long sum = 0;
            for (int j = 0; j < w; j++) sum += cost[perm[j]][j];
            best = std::min(best, sum);
        } while (std::next_permutation(perm.begin(), perm.end()));
    }
    return best;
}

long long brute_max(const std::vector<std::vector<long long>>& cost) {
    std::vector<std::vector<long long>> negated = cost;
    for (auto& row : negated) {
        for (auto& x : row) x = -x;
    }
    return -brute_min(negated);
}

void check_result(const std::vector<std::vector<long long>>& cost,
                  const m1une::opt::HungarianResult<long long>& result,
                  long long expected) {
    int h = int(cost.size());
    int w = h == 0 ? 0 : int(cost[0].size());
    assert(int(result.row_to_col.size()) == h);
    assert(int(result.col_to_row.size()) == w);
    assert(result.matching_size() == std::min(h, w));
    assert(result.cost == expected);

    std::vector<bool> used_cols(w, false);
    long long sum = 0;
    for (int i = 0; i < h; i++) {
        int j = result.row_to_col[i];
        if (j == -1) continue;
        assert(0 <= j && j < w);
        assert(!used_cols[j]);
        assert(result.col_to_row[j] == i);
        used_cols[j] = true;
        sum += cost[i][j];
    }
    for (int j = 0; j < w; j++) {
        int i = result.col_to_row[j];
        if (i == -1) continue;
        assert(0 <= i && i < h);
        assert(result.row_to_col[i] == j);
    }
    assert(sum == result.cost);

    auto pairs = result.matching();
    assert(int(pairs.size()) == result.matching_size());
    for (auto [row, col] : pairs) assert(result.row_to_col[row] == col);
}

void test_hungarian_min() {
    std::vector<std::vector<long long>> square = {
        {4, 1, 3},
        {2, 0, 5},
        {3, 2, 2},
    };
    auto sq = m1une::opt::hungarian_min(square);
    check_result(square, sq, 5);

    std::vector<std::vector<long long>> wide = {
        {7, 4, 6, 8},
        {5, 9, 3, 1},
    };
    check_result(wide, m1une::opt::hungarian(wide), brute_min(wide));

    std::vector<std::vector<long long>> tall = {
        {9, 4},
        {6, 7},
        {5, 8},
        {1, 3},
    };
    auto tall_result = m1une::opt::hungarian_min(tall);
    check_result(tall, tall_result, brute_min(tall));
    assert(tall_result.col_to_row[0] != -1);
    assert(tall_result.col_to_row[1] != -1);

    std::vector<std::vector<long long>> negative = {
        {-4, 2, 0},
        {3, -5, 1},
    };
    check_result(negative, m1une::opt::hungarian_min(negative), brute_min(negative));

    std::vector<std::vector<long long>> zero_cols(3);
    check_result(zero_cols, m1une::opt::hungarian_min(zero_cols), 0);
}

void test_hungarian_max() {
    std::vector<std::vector<long long>> cost = {
        {1, 8, 2},
        {5, 3, 4},
        {6, 7, 0},
    };
    check_result(cost, m1une::opt::hungarian_max(cost), brute_max(cost));
}

void test_against_bruteforce() {
    for (int h = 1; h <= 4; h++) {
        for (int w = 1; w <= 4; w++) {
            std::vector<std::vector<long long>> cost(h, std::vector<long long>(w));
            for (int i = 0; i < h; i++) {
                for (int j = 0; j < w; j++) {
                    cost[i][j] = ((i + 2) * (j + 3) * 5 + i * 7 - j * 11) % 17 - 8;
                }
            }
            check_result(cost, m1une::opt::hungarian_min(cost), brute_min(cost));
            check_result(cost, m1une::opt::hungarian_max(cost), brute_max(cost));
        }
    }
}

int main() {
    m1une::utilities::FastInput fast_input;
    m1une::utilities::FastOutput fast_output;

    test_hungarian_min();
    test_hungarian_max();
    test_against_bruteforce();
    int n;
    fast_input >> n;
    std::vector<std::vector<long long>> cost(n, std::vector<long long>(n));
    for (int i = 0; i < n; i++) {
        for (int j = 0; j < n; j++) {
            fast_input >> cost[i][j];
        }
    }

    auto result = m1une::opt::hungarian_min(cost);
    fast_output << result.cost << '\n';
    for (int i = 0; i < n; i++) {
        if (i) fast_output << ' ';
        fast_output << result.row_to_col[i];
    }
    fast_output << '\n';
}
Back to top page