import random
from pandas import read_csv
from sklearn.cross_validation import train_test_split
import numpy
import csv
import urllib.request
from sklearn import decomposition
from sklearn import preprocessing
from pandas import read_csv
import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
from sklearn.cross_validation import cross_val_score, cross_val_predict
from sklearn import metrics
from sklearn.model_selection import KFold

import pandas as pd
from sklearn import datasets, linear_model
from sklearn.model_selection import train_test_split
from matplotlib import pyplot as plt
from sklearn import svm
from sklearn.model_selection import cross_val_score

dataset = read_csv('c:\\users\jane\desktop\pcaCSV.csv', header = None)
dataset = dataset.as_matrix()
#print (dataset)
data = []

temp = []
for i in range(0, int(len(dataset)/3)):
    for j in range(0, 3):
        temp.append(float(dataset[i][j]))
    data.append(temp)
    temp = []
#print(dataset[0][0])
#print(data)


dataset2 = read_csv('c:\\users\jane\desktop\Data.csv', header = None)
dataset2 = dataset2.as_matrix()

print("////////////////////////////////////")
labels=dataset2[:,4]
i = 0

la = preprocessing.LabelEncoder()
la.fit(labels)
labels = la.transform(labels)
#enkodiranite target klasi: ('Iris-setosa', 0), ('Iris-versicolour', 1), ('Iris-virginica', 2)
#print (labels)

for l in data:
    l.append(labels[i])
    i += 1

#print(data)
#random.shuffle(data)

x_train, x_test, y_train, y_test = train_test_split(dataset, labels, test_size=0.3)