from sklearn.datasets import load_iris

 from sklearn.cross_validation import train_test_split

 from sklearn.preprocessing import StandardScaler

 from sklearn.neighbors import KNeighborsClassifier

 from sklearn.metrics import classification_report

 '''

 k近邻分类器

 通过数据的分布对预测数据做出决策

 属于无参数估计的一种

 非常高的计算复杂度和内存消耗

 '''

 '''

 1 准备数据

 '''

 # 读取鸢尾花数据集

 iris = load_iris()

 # 检查数据规模

 # print(iris.data.shape)    # (150, 4)

 # 查看数据说明

 # print(iris.DESCR)

 '''

 Iris Plants Database

 ====================

 Notes

 -----

 Data Set Characteristics:

     :Number of Instances: 150 (50 in each of three classes)

     :Number of Attributes: 4 numeric, predictive attributes and the class

     :Attribute Information:

         - sepal length in cm

         - sepal width in cm

         - petal length in cm

         - petal width in cm

         - class:

                 - Iris-Setosa

                 - Iris-Versicolour

                 - Iris-Virginica

     :Summary Statistics:

     ============== ==== ==== ======= ===== ====================

                     Min  Max   Mean    SD   Class Correlation

     ============== ==== ==== ======= ===== ====================

     sepal length:   4.3  7.9   5.84   0.83    0.7826

     sepal width:    2.0  4.4   3.05   0.43   -0.4194

     petal length:   1.0  6.9   3.76   1.76    0.9490  (high!)

     petal width:    0.1  2.5   1.20  0.76     0.9565  (high!)

     ============== ==== ==== ======= ===== ====================

     :Missing Attribute Values: None

     :Class Distribution: 33.3% for each of 3 classes.

     :Creator: R.A. Fisher

     :Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)

     :Date: July, 1988

 This is a copy of UCI ML iris datasets.

 http://archive.ics.uci.edu/ml/datasets/Iris

 The famous Iris database, first used by Sir R.A Fisher

 This is perhaps the best known database to be found in the

 pattern recognition literature.  Fisher's paper is a classic in the field and

 is referenced frequently to this day.  (See Duda & Hart, for example.)  The

 data set contains 3 classes of 50 instances each, where each class refers to a

 type of iris plant.  One class is linearly separable from the other 2; the

 latter are NOT linearly separable from each other.

 References

 ----------

    - Fisher,R.A. "The use of multiple measurements in taxonomic problems"

      Annual Eugenics, 7, Part II, 179-188 (1936); also in "Contributions to

      Mathematical Statistics" (John Wiley, NY, 1950).

    - Duda,R.O., & Hart,P.E. (1973) Pattern Classification and Scene Analysis.

      (Q327.D83) John Wiley & Sons.  ISBN 0-471-22361-1.  See page 218.

    - Dasarathy, B.V. (1980) "Nosing Around the Neighborhood: A New System

      Structure and Classification Rule for Recognition in Partially Exposed

      Environments".  IEEE Transactions on Pattern Analysis and Machine

      Intelligence, Vol. PAMI-2, No. 1, 67-71.

    - Gates, G.W. (1972) "The Reduced Nearest Neighbor Rule".  IEEE Transactions

      on Information Theory, May 1972, 431-433.

    - See also: 1988 MLC Proceedings, 54-64.  Cheeseman et al"s AUTOCLASS II

      conceptual clustering system finds 3 classes in the data.

    - Many, many more ...

    共有150个数据样本

    均匀分布在3个亚种上

    每个样本采样4个花瓣、花萼的形状描述

 '''

 '''

 2 划分训练集合和测试集合

 '''

 x_train, x_test, y_train, y_test = train_test_split(iris.data,

                                                     iris.target,

                                                     test_size=0.25,

                                                     random_state=33)

 '''

 3 k近邻分类器 学习模型和预测

 '''

 # 训练数据和测试数据进行标准化

 ss = StandardScaler()

 x_train = ss.fit_transform(x_train)

 x_test = ss.transform(x_test)

 # 建立一个k近邻模型对象

 knc = KNeighborsClassifier()

 # 输入训练数据进行学习建模

 knc.fit(x_train, y_train)

 # 对测试数据进行预测

 y_predict = knc.predict(x_test)

 '''

 4 模型评估

 '''

 print("准确率：", knc.score(x_test, y_test))

 print("其他指标:\n", classification_report(y_test, y_predict, target_names=iris.target_names))

 '''

 准确率： 0.8947368421052632

 其他指标:

               precision    recall  f1-score   support

      setosa       1.00      1.00      1.00         8

  versicolor       0.73      1.00      0.85        11

   virginica       1.00      0.79      0.88        19

 avg / total       0.92      0.89      0.90        38

 '''