import pandas as pd
import sklearn.metrics as met
from sklearn import preprocessing
from sklearn.cluster import KMeans, AgglomerativeClustering, DBSCAN
import matplotlib.pyplot as plt
import matplotlib



df = pd.read_csv("unbalance.csv")


#prikaz imena kolona + 5 prvih instanci
print('Prvih 5 instanci', df.head(), sep='\n')
print('\n\n')


featurs = df.columns[:2].tolist()

print(featurs)
x_original=df[featurs]

#standardizacija atributa
x=pd.DataFrame(preprocessing.scale(x_original))

#normalizacija
#x=pd.DataFrame(preprocessing.MinMaxScaler().fit_transform(x_original))

#dodeljivanje imena kolonama
x.columns = featurs

colors = ['darkcyan', 'red', 'green', 'gold', 'blue',  'm', 'plum', 'orange', 'black']

font = {'family' : 'normal',
        'size'   : 6}

matplotlib.rc('font', **font)

fig = plt.figure()
plt_ind=1

for i in range(5, 9):
    estimators= { 'K_means': KMeans(n_clusters=i),
                  'hijerarhijsko': AgglomerativeClustering(n_clusters=i, linkage='average'),
                  'DBSCAN': DBSCAN(eps=(i-2)*0.1)
                  }

    for name, est in estimators.items():
        est.fit(x)
        df['labels']= est.labels_

        fig.add_subplot(4, 3, plt_ind)

        if name=='DBSCAN':
            num_clusters = max(est.labels_) + 1
            min=-1
        else:
            num_clusters=i
            min=0
        for j in range(min,num_clusters):
            cluster= df.loc[lambda x: x['labels'] == j, :]
            plt.scatter(cluster['x'], cluster['y'], color=colors[j], s=10, marker='o', label="cluster %d"%j)

        plt.title('Algorithm %s, num clasters: %d'%(name, num_clusters), fontsize=8)
        plt_ind += 1

plt.tight_layout()
plt.show()