return list_columns
else:
return [columns for _ in range(k)]
if __name__ == '__main__':
args = parse()
data = pd.read_csv(args.path, sep=args.sep)
if args.numeric_attributes:
data = normalizer.min_max(data, args.numeric_attributes, True)
list_train, list_test = splitter.cross_validation(data, args.target, 2)
results = []
for train_data, test_data in zip(list_train, list_test):
fold_result = []
sets = splitter.bootstrap(train_data, N_TREE)
roots = []
columns = list(train_data.columns[:-1])
list_columns = random_columns(columns, n_max=len(columns) - 1)
for i in range(N_TREE):
roots.append(dt.DecisionNode(sets[i][0], args.target))
roots[-1].fit(list_columns[i].copy())
list_results = []
for test_index in range(test_data.shape[0]):
for i in range(N_TREE):
list_results.append(roots[i].test(test_data.iloc[test_index]))
fold_result.append(
(test_data.iloc[test_index][args.target],
pd.Series(list_results).value_counts().index[0]))
results.append(fold_result)
print(results)
