# OneR算法實(shí)現(xiàn)
import numpy as np
from sklearn.datasets import load_iris
# 加載iris數(shù)據(jù)集
dataset = load_iris()
# 加載iris數(shù)據(jù)集中的data數(shù)組（數(shù)據(jù)集的特征）
X = dataset.data
# 加載iris數(shù)據(jù)集中的target數(shù)組（數(shù)據(jù)集的類(lèi)別）
y_true = dataset.target
# 計(jì)算每一項(xiàng)特征的平均值
attribute_means = X.mean(axis=0)
# 與平均值比較，大于等于的為“1”，小于的為“0”.將連續(xù)性的特征值變?yōu)殡x散性的類(lèi)別型。
x = np.array(X >= attribute_means, dtype="int")


from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(x, y_true, random_state=14)
from operator import itemgetter
from collections import defaultdict
# 找到一個(gè)特征下的不同值的所屬的類(lèi)別。
def train_feature_class(x, y_true, feature_index, feature_values):
  num_class = defaultdict(int)
  for sample, y in zip(x, y_true):
    if sample[feature_index] == feature_values:
      num_class[y] += 1
  # 進(jìn)行排序，找出最多的類(lèi)別。按從大到小排列
  sorted_num_class = sorted(num_class.items(), key=itemgetter(1), reverse=True)
  most_frequent_class = sorted_num_class[0][0]
  error = sum(value_num for class_num , value_num in sorted_num_class if class_num != most_frequent_class)
  return most_frequent_class, error
# print train_feature_class(x_train, y_train, 0, 1)
# 接著定義一個(gè)以特征為自變量的函數(shù)，找出錯(cuò)誤率最低的最佳的特征，以及該特征下的各特征值所屬的類(lèi)別。
def train_feature(x, y_true, feature_index):
  n_sample, n_feature = x.shape
  assert 0 <= feature_index < n_feature
  value = set(x[:, feature_index])
  predictors = {}
  errors = []
  for current_value in value:
    most_frequent_class, error = train_feature_class(x, y_true, feature_index, current_value)
    predictors[current_value] = most_frequent_class
    errors.append(error)
  total_error = sum(errors)
  return predictors, total_error
# 找到所有特征下的各特征值的類(lèi)別，格式就如：{0：({0: 0, 1: 2}, 41)}首先為一個(gè)字典，字典的鍵是某個(gè)特征，字典的值由一個(gè)集合構(gòu)成，這個(gè)集合又是由一個(gè)字典和一個(gè)值組成，字典的鍵是特征值，字典的值為類(lèi)別，最后一個(gè)單獨(dú)的值是錯(cuò)誤率。
all_predictors = {feature: train_feature(x_train, y_train, feature) for feature in xrange(x_train.shape[1])}
# print all_predictors
# 篩選出每個(gè)特征下的錯(cuò)誤率出來(lái)
errors = {feature: error for feature, (mapping, error) in all_predictors.items()}
# 對(duì)錯(cuò)誤率排序，得到最優(yōu)的特征和最低的錯(cuò)誤率，以此為模型和規(guī)則。這就是one Rule（OneR）算法。
best_feature, best_error = sorted(errors.items(), key=itemgetter(1), reverse=False)[0]
# print "The best model is based on feature {0} and has error {1:.2f}".format(best_feature, best_error)
# print all_predictors[best_feature][0]
# 建立模型
model = {"feature": best_feature, "predictor": all_predictors[best_feature][0]}
# print model
# 開(kāi)始測(cè)試——對(duì)最優(yōu)特征下的特征值所屬類(lèi)別進(jìn)行分類(lèi)。
def predict(x_test, model):
  feature = model["feature"]
  predictor = model["predictor"]
  y_predictor = np.array([predictor[int(sample[feature])] for sample in x_test])
  return y_predictor

y_predictor = predict(x_test, model)
# print y_predictor
# 在這個(gè)最優(yōu)特征下，各特征值的所屬類(lèi)別與測(cè)試數(shù)據(jù)集相對(duì)比，得到準(zhǔn)確率。
accuracy = np.mean(y_predictor == y_test) * 100
print "The test accuracy is {0:.2f}%".format(accuracy)

from sklearn.metrics import classification_report

# print(classification_report(y_test, y_predictor))