diff --git a/function.py b/function.py index caf597b..014351d 100644 --- a/function.py +++ b/function.py @@ -106,6 +106,20 @@ def predict_svm(inX, weights): if __name__ == "__main__": + # 取得列信息 + with open("resources/horse-colic.names", 'r', encoding='utf-8') as f: + data_names = f.read() + data_columns = re.findall(r'(?<=[0-9]:).*', data_names) + data_columns = [col.strip() for col in data_columns[:-3]] + data_columns + + # 离散列 + columns_discrete = ['surgery?', 'Age', 'temperature of extremities', 'peripheral pulse', + 'mucous membranes', 'capillary refill time', 'pain - a subjective judgement of the horse\'s pain level', 'peristalsis', + 'abdominal distension', 'nasogastric tube', 'nasogastric reflux', 'rectal examination - feces', 'abdomen', 'abdominocentesis appearance'] + + # 独热编码列 + col_oneHot = ['surgery?', 'Age'] # 加载训练集 X_train, y_train = load_data("./data/horse-colic.data") # 加载测试集