In [7]:

    

import numpy as np
from sklearn.ensemble import RandomForestClassifier
from sklearn.cross_validation import train_test_split
from sklearn import metrics
from sklearn import datasets
from sklearn import tree


    

In [2]:

    

iris = datasets.load_iris()


    

In [3]:

    

x = iris.data[:,2:]
y = iris.target


    

In [8]:

    

x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25,train_size=0.75)


    

In [17]:

    

forest = RandomForestClassifier(n_estimators=5)
forest.fit(x_train, y_train)


    

    
Out[17]:





RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',
            max_depth=None, max_features='auto', max_leaf_nodes=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, n_estimators=5, n_jobs=1,
            oob_score=False, random_state=None, verbose=0,
            warm_start=False)

In [20]:

    

print("accuracy on training set: %f" % forest.score(x_train, y_train))
print("accuracy on test set: %f" % forest.score(x_test, y_test))


    

    




accuracy on training set: 0.991071
accuracy on test set: 0.894737

In [ ]: