def test_incremental_learning(self):
# Test that we can initialize the RF, add a feature, score, add features, score.
rf = RF(y, mtry=0.8, n_jobs=2, seed=2001)
rf.fit(X0)
prediction1 = rf.score(X0)
rf.fit(X1)
prediction2 = rf.score(column_stack((X0, X1)))
assert_almost_equal(
prediction1,
y,
err_msg="Feature X0 is a leaking feature - overfit on it!")
assert_almost_equal(
prediction2,
y,
err_msg="Feature X0 is a leaking feature - overfit on it!")
class RFWrapper:
"""
Online Random Forest.
"""
def __init__(self, y, X_t, y_t, n_jobs, mtry, random_state):
self.rf = RF(y, n_jobs=n_jobs, mtry=mtry, seed=random_state)
self.X_t = X_t
self.y_t = y_t
def fit(self, x):
self.rf.fit(x)
def get_auc(self):
prediction = self.rf.score(self.X_t)
fpr, tpr, thresholds = metrics.roc_curve(self.y_t,
prediction,
pos_label=1)
return metrics.auc(fpr, tpr)