python机器学习实现oneR算法(以鸢尾data为例)

import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.datasets import load_iris
from collections import defaultdict
from operator import itemgetter
import warnings
from sklearn.metrics import classification_report

# 加载内置iris数据，并保存
dataset = load_iris()  
X = dataset.data
y = dataset.target

attribute_means = X.mean(axis=0)  # 得到一个列表，列表元素个数为特征值个数，列表值为每个特征的均值
X_d = np.array(X >= attribute_means, dtype='int')  # 转bool类型

X_train, X_test, y_train, y_test = train_test_split(X_d, y, random_state=random_state)

def train_feature_value(X, y_true, feature, value):
    class_counts = defaultdict(int)
    for sample, y_t in zip(X, y_true):
        if sample[feature] == value:
            class_counts[y_t] += 1
    sorted_class_counts = sorted(class_counts.items(), key=itemgetter(1), reverse=True) # 降序
    most_frequent_class = sorted_class_counts[0][0]
    error = sum([class_count for class_value, class_count in class_counts.items()
                 if class_value != most_frequent_class])
    return most_frequent_class, error

def train(X, y_true, feature):
    n_samples, n_features = X.shape
    assert 0 <= feature < n_features
    # 获取样本中某特征所有可能的取值
    values = set(X[:, feature])
    predictors = dict()
    errors = []
    for current_value in values:
        most_frequent_class, error = train_feature_value(X, y_true, feature, current_value)
        predictors[current_value] = most_frequent_class
        errors.append(error)
    total_error = sum(errors)
    return predictors, total_error

all_predictors = {variable: train(X_train, y_train, variable) for variable in range(X_train.shape[1])}
Errors = {variable: error for variable, (mapping, error) in all_predictors.items()}
# 找到错误率最低的特征
best_variable, best_error = sorted(Errors.items(), key=itemgetter(1))[0]  # 升序
print("The best model is based on feature {0} and has error {1:.2f}".format(best_variable, best_error))
# 找到最佳特征值，创建model模型
model = {'variable': best_variable,
         'predictor': all_predictors[best_variable][0]}
print(model)

print(all_predictors)
print(all_predictors[best_variable])
print(all_predictors[best_variable][0])

def predict(X_test, model):
    variable = model['variable']
    predictor = model['predictor']
    y_predicted = np.array([predictor[int(sample[variable])] for sample in X_test])
    return y_predicted

# 对测试集数据进行预测
y_predicted = predict(X_test, model)
print(y_predicted)

# 统计预测准确率
accuracy = np.mean(y_predicted == y_test) * 100
print("The test accuracy is {:.1f}%".format(accuracy))

# 屏蔽警告
warnings.filterwarnings("ignore") 
# 打印模型评估报告
print(classification_report(y_test, y_predicted))  # 参数为测试集的真实数据和预测数据