Basic sklearn with ROOT file input

gistfile1.py

import numpy as np
from sklearn.ensemble import RandomForestClassifier
from sklearn.cross_calidation import train_test_split
from root_numpy import root2array


signal = root2array("MySignalFile.root",
                    "MyDecayTree",
                    ["names", "of", "branches", "to", "use",
                     "for", "classifying"])
backgr = root2array("MyBackgrondFile.root",
                    "MyDecayTree",
                    ["names", "of", "branches", "to", "use",
                     "for", "classifying"])
                     
X = np.concatenate((signal, backgr))
y = np.concatenate((np.ones(signal.shape[1]), np.zeros(backgr.shape[1])))

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)

tree = RandomForestClassifier()
tree.fit(X_train, y_train)

# do what ever you have to do
# for some plotting see: http://betatim.github.io/posts/matching-machine-learning/