from sklearn import datasets

iris = datasets.load_iris()
print iris.data[0:10]

from sklearn import preprocessing
import numpy as np

glass_data = np.loadtxt('../data/glass_data.csv', delimiter=',')
glass_target = np.loadtxt('../data/glass_target.csv')
print glass_data[0:5], glass_target[0:5]

import csv

car_data = list(csv.DictReader(open('../data/cardata.csv', 'rU')))
car_target = list(csv.reader(open('../data/cartarget.csv', 'rU')))

car_data[10]

from sklearn.feature_extraction import DictVectorizer

vec = DictVectorizer()
car_data = vec.fit_transform(car_data).toarray()

print 'Vectorized:', car_data[10]
print 'Unvectorized:', vec.inverse_transform(car_data[10])

from sklearn import preprocessing

le = preprocessing.LabelEncoder()
le.fit(["unacc", "acc", "good", "vgood"])
target = le.transform(car_target[0])

print 'Transformed:', target[10] 
print 'Inverse transformed:', le.inverse_transform(target[10])

from sklearn.cross_validation import train_test_split

car_data_train, car_data_test, target_train, target_test = train_test_split(car_data, target)

print 'Training set:', len(car_data_train)
print 'Test set:', len(car_data_test)