def runBoost(X_train, y_train, X_test, y_test, numClassifiers=10):
'''
initialize AdaBoost
'''
boost = ab.Boost()
boost.train(X_train, y_train, cNum=numClassifiers)
# test with training data
pred_boost_train = boost.predict(X_train)
error_rate_boost_train = (sum([
0 if pred == true else 1
for (pred, true) in zip(y_train, pred_boost_train)
]) / float(len(y_train)))
# now test with remaining data
pred_boost_test = boost.predict(X_test)
error_rate_boost_test = (sum([
0 if pred == true else 1
for (pred, true) in zip(y_test, pred_boost_test)
]) / float(len(y_test)))
'''
Add prints for diagnostics and results here:
'''
'''print('')
print('***** RESULTS ADABOOST *****')
decisions = [c.root.splitCriteria for c in boost.classifiers]
print('Decision Criteria per trees used: ', decisions)
decision_columns = [c for c,_ in decisions]
unique_cols = np.unique(decision_columns)
col_counts = Counter(decision_columns).most_common()
print('unique columns and frequency of split columns: ', col_counts)
print('')
print('Training Error: ', error_rate_boost_train)
print('Test Error : ', error_rate_boost_test)'''
return error_rate_boost_train, error_rate_boost_test
print('')
print('***** RESULTS DECISION TREE *****')
print('Depth: ', tree.depth)
print('')
print('Training Error: ', error_rate_tree_train)
print('Test Error : ', error_rate_tree_test)
cNums = range(1, 31)
train_errs = list()
test_errs = list()
for i in cNums:
trains = list()
tests = list()
for j in range(20):
boost = ab.Boost()
boost.train(X_train, y_train, cNum=i, verbose=False)
pred_boost_train = boost.predict(X_train)
pred_boost_test = boost.predict(X_test[0])
error_rate_boost_test = (sum([
0 if pred == true else 1
for (pred, true) in zip(y_test, pred_boost_test)
]) / float(len(y_test)))
error_rate_boost_train = (sum([
0 if pred == true else 1
for (pred, true) in zip(y_train, pred_boost_train)
]) / float(len(y_train)))
trains.append(error_rate_boost_train)
tests.append(error_rate_boost_test)
train_errs.append(np.mean(trains))
test_errs.append(np.mean(tests))