In [1]:
from tpot import TPOT
from sklearn.datasets import load_iris
from sklearn.cross_validation import train_test_split

Load the IRIS data set and explore its contents.


In [2]:
iris = load_iris()
iris.data[0:5], iris.target


Out[2]:
(array([[ 5.1,  3.5,  1.4,  0.2],
        [ 4.9,  3. ,  1.4,  0.2],
        [ 4.7,  3.2,  1.3,  0.2],
        [ 4.6,  3.1,  1.5,  0.2],
        [ 5. ,  3.6,  1.4,  0.2]]),
 array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
        0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
        0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
        1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
        2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
        2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2]))

Split the data set in train and test.


In [3]:
X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target,
                                                    train_size=0.75, test_size=0.25)
X_train.shape, X_test.shape, y_train.shape, y_test.shape


Out[3]:
((112, 4), (38, 4), (112,), (38,))

In [4]:
tpot = TPOT(generations=5)
tpot.fit(X_train, y_train)
print(tpot.score(X_test, y_test))


0.918414918415

In [5]:
tpot.export('tpot_iris_pipeline.py')

In [ ]: