import itertools as it
import random


class GAOptimizedRandomGenerator:
    """Generate even random sequences according to a predefined TL ration (Ralph, 2014)"""

    def __init__(self, choices, trials=64, tl=1, pool_size=100, n=2):
        """
        Initialize the genetic algorithm optimizer for n-back sequences.
        :param choices:
        :param trials:
        :param tl:
        :param pool_size:
        :param n:
        """
        self.tl, self.trials, self.choices, self.pool_size, self.n = tl, trials, choices, pool_size, n
        self.pool = []
        self.__init_pool(pool_size)

    def generate(self):
        """
        Generate a sequence of trials based on passed parameters. TL ratio and distribution are expected to be
        close to the desired ones but not exactly the same.
        :return: a sequence of items in "list" format.
        """
        generation = 0
        best_parent = self.__find_best_parents(1)[0]
        while self.fitness(best_parent) > 0.1 and generation < 100000:
            generation += 1
            self.pool = self.mutate()
            self.pool = self.crossover_all()
            best_parent = self.__find_best_parents(1)[0]
            print(best_parent, ' ', self.calculate_tl_ratio(best_parent, self.n))
        return best_parent

    def __init_pool(self, pool_size):
        """

        :param pool_size: DNA size or number of parents in the GA pool.
        :return: A DNA or pool in list format.
        """
        self.pool.clear()
        all_comb = it.combinations_with_replacement(self.choices, self.trials)
        sample = random.sample(list(all_comb), pool_size)
        self.pool.extend(map(lambda sampi: ''.join(sampi), sample))
        return self.pool

    def __find_best_parents(self, count=1):
        """
        Find best gene(s) or parent(s) from the current pool.
        :param count: Number of desired best parents to be returned. Default is 1.
        :return: A list of most fit sequences.
        """
        sorted_pool = sorted(self.pool, key=lambda ss: self.fitness(ss))
        return sorted_pool[:count]

    def __dist_fitness(self, seq, trials):
        """
        Calculate fitness according to the similarity to the desired uniform distribution.
        :param seq:
        :param trials:
        :return:
        """
        pass

    def fitness(self, seq):
        """
        Calculate overall fitness of a sequence (block of trials). It's cost, so we try to minimize this cost.
        :param seq:
        :return:
        """
        # add fitness for uniform distribution of all stimuli
        return abs(self.calculate_tl_ratio(seq, self.n) - self.tl)

    def crossover_all(self):
        """
        Do random crossover for all pairs.
        :return:
        """
        new_pool = []
        for i in range(int(self.pool_size/2)):
            seq1 = self.pool[i*2]      # change to weighted random
            seq2 = self.pool[i*2 + 1]  # change to weighted random
            new_pool.extend(self.crossover(seq1, seq2))

        return new_pool

    def crossover(self, seq1, seq2):
        """
        Crossover two sequences.
        :param seq1:
        :param seq2:
        :return:
        """
        pos = random.randint(0, self.trials)
        return [seq1[:pos] + seq2[pos:], seq2[:pos] + seq1[pos:]]

    def mutate(self):
        # pass
        return self.pool

    @staticmethod
    def calculate_tl_ratio(seq, N):
        """Calculates the T/L ratio in a block of trials."""
        targets = 0.0
        lures = 0.0
        for index in range(N, len(seq)):
            item = seq[index]
            if item == seq[index - N]:
                targets += 1.0
            elif item == seq[index - (N-1)] or item == seq[index - (N+1)]:
                lures += 1.0
        if lures - 0.0 < 0.001:  # avoid division by zero
            lures = 0.001
        return targets/lures


if __name__ == '__main__':
    generator = GAOptimizedRandomGenerator(['a', 'b', 'c', 'd', 'e', 'f'], trials=32)
    s = generator.generate()
    tl_ratio = generator.calculate_tl_ratio(s, 2)

    print('GA-Optimized Sequence: %s' % s, 'with tl_ratio=%f' % tl_ratio)