init stuff

import pandas as pd
from Lista02 import FuncoesML as fun
from sklearn.cluster import KMeans
import numpy as np
from random import randint
from Lista03.pso import pso
from sklearn.metrics import pairwise_distances

KCLUSTERS = 3

#FUNCTIONS ---------------------------------------------------------------------

def WCSS(distance):

    retorno = []
    for x in distance:
        soma = 0
        for z in x:
            soma += z**2
        retorno.append(soma)

    return retorno

def break_vectors(vector):

    global KCLUSTERS
    retorno =np.split(vector,KCLUSTERS)
    return retorno

def wcssGenetic(centers):

    global KCLUSTERS
    array = break_vectors(centers)

    kmeans = KMeans(KCLUSTERS,init=pd.DataFrame(array),max_iter=1,n_init=1)
    kmeans.fit(pd.DataFrame(wine))

    return kmeans.inertia_


def generatepopulation(X,numberpopu, K, rng):

    population = []

    for x in range(numberpopu):
        first = rng.permutation(X.shape[0])[:K]
        population.append(np.concatenate(X[first]))

    return population


# def pso_algorithm(base, rng,K):
#     population = generatepopulation(base, 20, K,rng)
#
#     p = pso(20, wcssGenetic, -1000, 1000, 36, 100, init= population)
#     return p.get_Gbest()

#FUNCTIONS ---------------------------------------------------------------------

wine = pd.read_csv('C:/Users/Auricelia/Desktop/DataSetsML/glass.csv')
wine2 = pd.read_csv('C:/Users/Auricelia/Desktop/DataSetsML/glass.csv')

del wine2['Class']
del wine2['ID']

wine2 = np.array(wine2)

wine = fun.normalizar(wine)

del wine[0]
del wine[10]

wine = np.array(wine)


winedataframe = pd.DataFrame(wine)


dictionary = {}
dictionary2 = {}

for y2 in range(0,50):

    distance2 = []
    h2 = randint(1,10000)
    rng2 = np.random.RandomState(h2)
    centers2, labels2, distance2 = fun.find_clusters(wine2, KCLUSTERS, rng2,100)
    retorno2 = WCSS(distance2)

    num2 = retorno2[len(retorno2) - 1]
    dictionary2[h2] = num2


resultsKmeans = []
resultKmeansHybrid = []
for y in range(10):

    resultparcial = []
    distance = []
    h = randint(1,10)
    rng = np.random.RandomState(h)

    for algumacoisa in range(20):
        centers, labels, distance = fun.find_clusters(wine, KCLUSTERS, rng,100)
        retorno = WCSS(distance)
        resultparcial.append(retorno[len(retorno) - 1])

    resultparcial = np.sort(resultparcial)

    resultsKmeans.append(resultparcial[0])

    population = generatepopulation(wine, 20, KCLUSTERS,rng)


    p = pso(20, wcssGenetic, 0, 500, 27, 100, init= population)
    array = np.array(p.get_Gbest())
    array = np.split(array,3)

    cen, lbl, dis = fun.find_clustersGENETIC(wine, KCLUSTERS, 100, array)

    ret = WCSS(dis)
    resultKmeansHybrid.append(ret[len(ret) - 1])



    # num = retorno[len(retorno) - 1]
    # dictionary[h] = num

#
# print("Distancias" ,distance)

resultKmeansHybrid = np.sort(resultKmeansHybrid)
resultsKmeans = np.sort(resultsKmeans)
print("Media Hibrido" , np.mean(resultKmeansHybrid))
print("Media sem hibrido" , np.mean(resultsKmeans))
print(resultKmeansHybrid)
print("Nao hibrido", resultsKmeans)
# print("centers", centers)
# print("Quantas vezes rodou", len(distance))

wine = pd.DataFrame(wine)
#
wine['Class'] = labels
#
print(wine)


# dictionary = sorted(dictionary.items(), key=lambda x: x[1])
# dictionary2 = sorted(dictionary2.items(), key=lambda x: x[1])

# print("\n\n\n\n",dictionary)
# print("\n\n\n\n",dictionary2)