def test_balance_weights():
weights = _balance_weights([0, 0, 1, 1])
assert_array_equal(weights, [1., 1., 1., 1.])
weights = _balance_weights([0, 1, 1, 1, 1])
assert_array_equal(weights, [1., 0.25, 0.25, 0.25, 0.25])
weights = _balance_weights([0, 0])
assert_array_equal(weights, [1., 1.])
def test_unbalanced_iris():
"""Check class rebalancing."""
unbalanced_X = iris.data[:125]
unbalanced_y = iris.target[:125]
sample_weight = _balance_weights(unbalanced_y)
for name, TreeClassifier in CLF_TREES.items():
clf = TreeClassifier(random_state=0)
clf.fit(unbalanced_X, unbalanced_y, sample_weight=sample_weight)
assert_almost_equal(clf.predict(unbalanced_X), unbalanced_y)
def test_unbalanced_iris():
"""Check class rebalancing."""
unbalanced_X = iris.data[:125]
unbalanced_y = iris.target[:125]
sample_weight = _balance_weights(unbalanced_y)
for name, TreeClassifier in CLF_TREES.items():
clf = TreeClassifier(random_state=0)
clf.fit(unbalanced_X, unbalanced_y, sample_weight=sample_weight)
assert_almost_equal(clf.predict(unbalanced_X), unbalanced_y)
def create_and_train_rf(criterion,num_trees,train_predictors,train_responses, test_predictors):
# print(type(train_predictors))
sample_weight = _weights._balance_weights(train_responses)
print '\t\tcreating random forest'
rf = RandomForestClassifier(n_estimators=num_trees, criterion=criterion, class_weight='auto', max_depth=10,
n_jobs=4)
print '\t\trandom forest created successfully'
print '\t\ttraining random forest'
fit = rf.fit(train_predictors, train_responses, sample_weight=sample_weight)
print "RF Fitted"
#score = rf.score(train_predictors, train_responses)
#prob_pos = rf.predict_proba(test_predictors)
print '\t\trandom forest successfully trained'
return rf
def main():
_weights._balance_weights()
