OneR算法python实现

OneR算法（分类应用，寻找最佳的特征值用于分类）
计算数据错误率，不属于最多类的特征值个数，把各个取值的错误率相加，选取错误率最低的特征作为唯一的分类准则(One Rule)，用于接下来的分类。
//OneR

from collections import defaultdict
from operator import itemgetter
#参数分别是数据集，类别数组，选好的特征索引值，特征值
def train_feature_value(X,y_true,feature_index,value):
    class_counts=defaultdict(int)
    for sample,y in zip(X,y_true):
        if sample[feature_index]==value:
            class_counts[y]+=1
    sorted_class_counts=sorted(class_counts.items(),key=itemgetter(1),reverse=True)
    most_frequent_class=sorted_class_counts[0][0]
    incorrect_predictions=[class_count for class_value,class_count
                       in class_counts.items()
                       if class_value!=most_frequent_class]
    error=sum(incorrect_predictions)
    return most_frequent_class,error

def train_on_feature(X,y_true,feature_index):
    values=set(X[:,feature_index])
    predictors={}
    errors=[]
    for current_value in values:
        most_frequent_class,error,error = train_feature_value(X,y_true,feature_index,current_value)
        predictors[current_value]=most_frequent_class
        errors.append(error)
    total_error=sum(errors)
    return predictors,total_error