# -*- coding: utf-8 -*-
"""
Created on Tue Jun  4 12:23:21 2019

@author: lancernik
"""





import numpy as np
import pandas as pd
from sklearn.decomposition import PCA
from sklearn import datasets
from sklearn.preprocessing import StandardScaler

# c)   PCA

iris = datasets.load_iris()
X = iris.data
y = iris.target

#Standaryzacja danych
X = StandardScaler().fit_transform(X)

#PCA
pca = PCA(n_components=2)
principalComponents = pca.fit_transform(X)
x2 = pd.DataFrame(data = principalComponents
             , columns = ['1','2'])

#Szukanie wartosci wariancji > 90%
total_variance = 0
for i in range(4):
    total_variance = np.sum(pca.explained_variance_ratio_[i]+total_variance)
    if total_variance > 0.90:
        break
print(total_variance)




# SVM po redukcji wymiarowosci

from sklearn import svm
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
from sklearn.metrics import accuracy_score
from sklearn import metrics
import seaborn as sns


clf = svm.SVC(kernel='rbf', C=1000)
clf.fit(x2, y)

X_train, X_test, y_train, y_test = train_test_split(x2, y, test_size=0.30)


classy = svm.SVC(kernel = 'rbf', gamma="auto")
classy.fit(X_train, y_train)
y_pred = classy.predict(X_test)

print(classification_report(y_test, y_pred))
accuracy = accuracy_score(y_test, y_pred)
ZPCA = accuracy
print("accuracy = ", accuracy * 100, "%")


cnf_matrix = metrics.confusion_matrix(y_test, y_pred)
print(cnf_matrix)

conf_matrix = metrics.confusion_matrix(y_test, y_pred )
class_names=[0,1]
fig, ax = plt.subplots()
tick_marks = [0,1]
plt.xticks(tick_marks, class_names)
plt.yticks(tick_marks, class_names)
sns.heatmap(pd.DataFrame(conf_matrix), annot=True, cmap="YlGnBu" ,fmt='g')
ax.xaxis.set_label_position("top")
plt.tight_layout()
plt.title('Matrix pomyłek - z PCA i standaryzacja', y=1.1)
plt.ylabel('Actual label')
plt.xlabel('Przewidywania')







# -*- coding: utf-8 -*-
"""
Created on Tue Jun  4 14:16:36 2019

@author: laura
"""

import pandas as pd
import pylab as pl
import numpy as np
import scipy.optimize as opt
from sklearn import preprocessing
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
from sklearn import svm
from sklearn.metrics import classification_report
from sklearn.metrics import accuracy_score
import seaborn as sns
from sklearn.metrics import confusion_matrix
from sklearn import metrics

data = pd.read_csv('Data/iris.csv')

x= data.iloc[:,0:4]
y= data.iloc[:,4]
#drugi sposob
#x = data[['sepal.length', 'sepal.width', 'petal.length', 'petal.width']]
#y = np.ravel(data[['variety']], order="C")

X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.30)


classy = svm.SVC(kernel = 'rbf', gamma="scale")
#'kluczowym parametrem jest odpowiedni dobor kernela
classy.fit(X_train, y_train)
y_pred = classy.predict(X_test)

print(classification_report(y_test, y_pred))
accuracy = accuracy_score(y_test, y_pred)
BezPCA = accuracy
print("accuracy = ", accuracy * 100, "%")


cnf_matrix = metrics.confusion_matrix(y_test, y_pred)
print(cnf_matrix)

conf_matrix = metrics.confusion_matrix(y_test, y_pred )
class_names=[0,1]
fig, ax = plt.subplots()
tick_marks = [0,1]
plt.xticks(tick_marks, class_names)
plt.yticks(tick_marks, class_names)
sns.heatmap(pd.DataFrame(conf_matrix), annot=True, cmap="YlGnBu" ,fmt='g')
ax.xaxis.set_label_position("top")
plt.tight_layout()
plt.title('Matrix pomyłek - bez PCA', y=1.1)
plt.ylabel('Actual label')
plt.xlabel('Predicted label')
plt.show()

print("Bez PCA i standaryzacji {}".format(BezPCA))
print("Z PCA i standaryzacja {}".format(ZPCA))


#Lepszy wynik uzyskujemy przy podziale bez PCA, gdyż ten zbiór danych
#zawiera wiecej informacji, nasz zbiór po PCA zawiera wiecej niż 90%,
#ale to ciągle mniej niż 100%




# 3)

iris = datasets.load_iris()
x = iris.data
y = iris.target

X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.30)