from sklearn.datasets import load_iris
iris = load_iris()

X = iris.data
y = iris.target

print X.shape
print y.shape

from sklearn.svm import LinearSVC

#LinearSVC?

clf = LinearSVC(loss = 'l2')

print clf

clf = clf.fit(X, y)

clf.coef_
# shape of clf.coef_ [n_classes x n_features] (coefficients are the weights used in inner product)

clf.intercept_
# shape of clf.intercept [n_classes x 1] (Constants in decision function.)

X_new = [[ 5.0,  3.6,  1.3,  0.25]]
print clf.predict(X_new)

%matplotlib inline

import numpy as np
import matplotlib.pyplot as plt

from sklearn import svm

X = iris.data[:, 2:4]  # we only take the first two features. We could
y = iris.target
h = .02  # step size in the mesh

# we create an instance of SVM and fit out data. We do not scale our
# data since we want to plot the support vectors
C = 1.0  # SVM regularization parameter
svc = svm.SVC(kernel='linear', C=C).fit(X, y)
rbf_svc = svm.SVC(kernel='rbf', gamma=0.7, C=C).fit(X, y)
poly_svc = svm.SVC(kernel='poly', degree=3, C=C).fit(X, y)
lin_svc = svm.LinearSVC(C=C).fit(X, y)

# create a mesh to plot in
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, h),
                     np.arange(y_min, y_max, h))

# title for the plots
titles = ['SVC with linear kernel',
          'LinearSVC (linear kernel)',
          'SVC with RBF kernel',
          'SVC with polynomial (degree 3) kernel']


plt.figure(figsize=(16,10))
for i, clf in enumerate((svc, lin_svc, rbf_svc, poly_svc)):
    # Plot the decision boundary. For that, we will assign a color to each
    # point in the mesh [x_min, m_max]x[y_min, y_max].
    plt.subplot(2, 2, i + 1)
    plt.subplots_adjust(wspace=0.1, hspace=0.25)

    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])

    # Put the result into a color plot
    Z = Z.reshape(xx.shape)
    plt.contourf(xx, yy, Z, cmap=plt.cm.Paired, alpha=0.8)

    # Plot also the training points
    plt.scatter(X[:, 0], X[:, 1], s=80, c=y, cmap=plt.cm.Paired)
    plt.xlabel('Sepal length (first feature)',fontsize=15)
    plt.ylabel('Sepal width (second feature)',fontsize=15)
    plt.xlim(xx.min(), xx.max())
    plt.ylim(yy.min(), yy.max())
    plt.xticks(())
    plt.yticks(())
    plt.title(titles[i],fontsize=15)

plt.show()

from sklearn import linear_model



#linear_model.LogisticRegression?

clf2 = linear_model.LogisticRegression(C=1e5)

X = iris.data [:,2:4]
y = iris.target
clf2.fit (X, y)

X_new = [[3.6, 0.25]]
print clf2.predict_proba(X_new)

# Plot the decision boundary. For that, we will assign a color to each
# point in the mesh [x_min, m_max]x[y_min, y_max].
x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5
y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5
xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
Z = clf2.predict(np.c_[xx.ravel(), yy.ravel()])
Zprob = clf2.predict_proba(np.c_[xx.ravel(), yy.ravel()])

# Put the result into a color plot
Z = Z.reshape(xx.shape)
Zprob = Zprob.reshape(xx.shape[0],xx.shape[1],3)
plt.figure(figsize=(16,10))

# title for the plots
titles = ['Logistic regression (LR)',
          'LR class 1 - probabilities',
          'LR class 2 - probabilities',
          'LR class 3 - probabilities']
labels = ['class 1', 'class 2', 'class 3']

# number of classes and plot colors
n_classes = np.amax(y)+1
plot_colors = 'rgy'

for i, boundaries in enumerate((Z, Zprob[:,:,0], Zprob[:,:,1], Zprob[:,:,2])):
    # Plot the decision boundary. For that, we will assign a color to each
    # point in the mesh [x_min, m_max]x[y_min, y_max].
    plt.subplot(2, 2, i + 1)
    plt.subplots_adjust(wspace=0.1, hspace=0.25)
    plt.pcolormesh(xx, yy, boundaries, cmap=plt.cm.Paired)
    plt.colorbar()

    # Plot also the training
    for j, color in zip(range(n_classes), plot_colors):
        idx = np.where(y == j)
        plt.scatter(X[idx, 0], X[idx, 1], s=100, c=color, label=labels[j], cmap=plt.cm.Paired)
    
    #plt.scatter(X[:, 0], X[:, 1], s=100, c=y, edgecolors='k', cmap=plt.cm.Paired)
    
    plt.xlabel('Sepal length', fontsize=15)
    plt.ylabel('Sepal width', fontsize=15)

    plt.xlim(xx.min(), xx.max())
    plt.ylim(yy.min(), yy.max())
    plt.xticks(())
    plt.yticks(())
    plt.title(titles[i],fontsize=15)
    plt.legend(loc='upper left')

plt.show()

y_model = clf2.predict(X)
print y_model == y
print "Accuracy:", float(np.sum(y_model == y)) / len(y)

from sklearn.cross_validation import cross_val_score
# evaluate the model using 10-fold cross-validation
scores = cross_val_score(linear_model.LogisticRegression(C=1e2), X, y, scoring='accuracy', cv=10)
print scores
print scores.mean()