from sklearn import datasets

datasets.load_iris()
iris = datasets.load_iris()

print iris.DESCR

iris.target_names

from IPython.core.display import Image 

Image(filename='Iris_setosa.jpg') # from Wikipedia

Image(filename='Iris_versicolor.jpg')

Image(filename='Iris_virginica.jpg')

iris.feature_names

Image(filename="Petal-sepal.jpg")

iris.data[:3]

iris.target[:3]

colors = ('r', '#66ff66', '#4444ff')
X = iris.data
Y = iris.target

i, j = 2, 3
pylab.figure(figsize=(10, 10))
pylab.xlabel(iris.feature_names[i], fontsize = 20)
pylab.ylabel(iris.feature_names[j], fontsize = 20)
pylab.scatter(X[:, i], X[:, j], c=[colors[y] for y in Y], s=50)

mean([x for i, x in enumerate(iris.data)
      if iris.target[i] == 0], axis=0)

mean([x for i, x in enumerate(iris.data)
      if iris.target[i] == 1], axis=0)

mean([x for i, x in enumerate(iris.data)
      if iris.target[i] == 2], axis=0)

from sklearn import neighbors

knc = neighbors.KNeighborsClassifier(n_neighbors=5, warn_on_equidistant=False)
step = 5
knc.fit(X[::step], Y[::step])

knc.predict([5.93, 2.77, 4.23, 1.3])

knc.predict_proba([5.93, 2.77, 4.23, 1.3])

Y_pred = knc.predict(X)

i, j = 2, 3

X_ok = array([x for k, x in enumerate(X) if Y[k] == Y_pred[k]])
Y_ok = [y for k, y in enumerate(Y) if y == Y_pred[k]]
X_bad = array([x for k, x in enumerate(X) if Y[k] != Y_pred[k]])

pylab.figure(figsize=(10, 10))
pylab.xlabel(iris.feature_names[i], fontsize = 20)
pylab.ylabel(iris.feature_names[j], fontsize = 20)

pylab.scatter(X_ok[:, i], X_ok[:, j], c=[colors[y] for y in Y_ok], s=50)
pylab.scatter(X[::step, i], X[::step, j], c="w", marker="s", s=15)
pylab.scatter(X_bad[:, i], X_bad[:, j], marker="x", s=50)

from sklearn import cross_validation

cross_val = cross_validation.KFold(n = len(X), k=10, shuffle=True)

def avg_miss(Y_true, Y_pred):
    return (Y_true != Y_pred).sum() / float(len(Y_true))

cross_validation.cross_val_score(knc, X, Y,
                                 cv=cross_val, score_func=avg_miss)