# Učitaj osnovne biblioteke...
import scipy as sp
import sklearn
%pylab inline

seven_X = sp.array([[2,1],[2,3],[1,2],[3,2],[5,2],[5,4],[6,3]])
seven_y = sp.array([1,1,1,1,-1,-1,-1])

def plot_problem(X, y, h=None, surfaces=True) :
    '''
    Plots a two-dimensional labeled dataset (X,y) and, if function h(x) is given, 
    the decision boundaries (surfaces=False) or decision surfaces (surfaces=True)
    '''
    assert X.shape[1] == 2, "Dataset is not two-dimensional"
    if h!=None : 
        # Create a mesh to plot in
        r = 0.02  # mesh resolution
        x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
        y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
        xx, yy = np.meshgrid(np.arange(x_min, x_max, r),
                             np.arange(y_min, y_max, r))
        XX=np.c_[xx.ravel(), yy.ravel()]
        try:
            Z_test = h(XX)
            if shape(Z_test) == () :
                # h returns a scalar when applied to a matrix; map explicitly
                Z = sp.array(map(h,XX))
            else :
                Z = Z_test
        except ValueError:
            # can't apply to a matrix; map explicitly
            Z = sp.array(map(h,XX))
        # Put the result into a color plot
        Z = Z.reshape(xx.shape)
        if surfaces :
            plt.contourf(xx, yy, Z, cmap=plt.cm.Pastel1)
        else :
            plt.contour(xx, yy, Z)
    # Plot the dataset
    scatter(X[:,0],X[:,1],c=y, cmap=plt.cm.Paired,marker='o',s=50);

plot_problem(seven_X, seven_y)

from sklearn.svm import SVC

from sklearn.linear_model import Perceptron, LogisticRegression

X = sp.append(seven_X,[[12,8]],axis=0)
y = sp.append(seven_y,-1)

from sklearn.metrics import hinge_loss

X1, y1 = sp.append(seven_X, [[3,3]], axis=0), sp.append(seven_y, -1)
X2, y2 = sp.append(seven_X, [[2,2]], axis=0), sp.append(seven_y, -1)

from sklearn.datasets import make_classification
from sklearn.cross_validation import train_test_split

def plot_error_surface(err,(c1,c2),(g1,g2)) :
    xticks(range(0,g2-g1+1,5),range(g1,g2,5)); xlabel("gamma")
    yticks(range(0,c2-c1+1,5),range(c1,c2,5)); ylabel("C")
    p = contour(err);
    imshow(1-err, interpolation='bilinear', origin='lower',cmap=cm.gray)
    clabel(p, inline=1, fontsize=10);
    show();

from sklearn.datasets import make_classification
from sklearn.cross_validation import train_test_split

from sklearn.datasets import make_classification

X, y = make_classification(n_samples=500,n_features=2,n_classes=2,n_redundant=0,n_clusters_per_class=1)
X[:,1] = X[:,1]*100+1000
X[0,1] = 3000

plot_problem(X,y)

from sklearn.preprocessing import StandardScaler, MinMaxScaler

data = sp.loadtxt("/home/jan/Downloads/glass.data", delimiter=",")
glass_X, glass_y = data[:,1:10], data[:,10]

from sklearn import cross_validation
X_train, X_test, y_train, y_test = cross_validation.train_test_split(glass_X,glass_y,train_size=2.0/3,random_state=42)
print X_train.shape, X_test.shape