【深度学习】实验02 鸢尾花数据集分析_载入fisher iris数据集

鸢尾花数据集分析

鸢尾花数据集分析指的是对鸢尾花数据集进行数据分析和建模的过程。鸢尾花数据集是一种经典的分类问题数据集，常用于机器学习和统计模型的教学和方法验证。

监督学习-决策树

# 导入机器学习相关库
from sklearn import datasets
from sklearn import tree

import matplotlib.pyplot as plt
import numpy as np

# Iris数据集是常用的分类实验数据集，
# 由Fisher, 1936收集整理。Iris也称鸢尾花卉数据集，
# 是一类多重变量分析的数据集。数据集包含150个数据集，
# 分为3类，每类50个数据，每个数据包含4个属性。
# 可通过花萼长度，花萼宽度，花瓣长度，花瓣宽度4个属性预测鸢尾花卉属于（Setosa，Versicolour，Virginica）三个种类中的哪一类。
1
2
3
4
5
6
7
8
9
10
11
12

#载入数据集
iris = datasets.load_iris()
iris
1
2
3

   {'data': array([[5.1, 3.5, 1.4, 0.2],
           [4.9, 3. , 1.4, 0.2],
           [4.7, 3.2, 1.3, 0.2],
           [4.6, 3.1, 1.5, 0.2],
           [5. , 3.6, 1.4, 0.2],
           [5.4, 3.9, 1.7, 0.4],
           [4.6, 3.4, 1.4, 0.3],
           [5. , 3.4, 1.5, 0.2],
           [4.4, 2.9, 1.4, 0.2],
           [4.9, 3.1, 1.5, 0.1],
           [5.4, 3.7, 1.5, 0.2],
           [4.8, 3.4, 1.6, 0.2],
           [4.8, 3. , 1.4, 0.1],
           [4.3, 3. , 1.1, 0.1],
           [5.8, 4. , 1.2, 0.2],
           [5.7, 4.4, 1.5, 0.4],
           [5.4, 3.9, 1.3, 0.4],
           [5.1, 3.5, 1.4, 0.3],
           [5.7, 3.8, 1.7, 0.3],
           [5.1, 3.8, 1.5, 0.3],
           [5.4, 3.4, 1.7, 0.2],
           [5.1, 3.7, 1.5, 0.4],
           [4.6, 3.6, 1. , 0.2],
           [5.1, 3.3, 1.7, 0.5],
           [4.8, 3.4, 1.9, 0.2],
           [5. , 3. , 1.6, 0.2],
           [5. , 3.4, 1.6, 0.4],
           [5.2, 3.5, 1.5, 0.2],
           [5.2, 3.4, 1.4, 0.2],
           [4.7, 3.2, 1.6, 0.2],
           [4.8, 3.1, 1.6, 0.2],
           [5.4, 3.4, 1.5, 0.4],
           [5.2, 4.1, 1.5, 0.1],
           [5.5, 4.2, 1.4, 0.2],
           [4.9, 3.1, 1.5, 0.1],
           [5. , 3.2, 1.2, 0.2],
           [5.5, 3.5, 1.3, 0.2],
           [4.9, 3.1, 1.5, 0.1],
           [4.4, 3. , 1.3, 0.2],
           [5.1, 3.4, 1.5, 0.2],
           [5. , 3.5, 1.3, 0.3],
           [4.5, 2.3, 1.3, 0.3],
           [4.4, 3.2, 1.3, 0.2],
           [5. , 3.5, 1.6, 0.6],
           [5.1, 3.8, 1.9, 0.4],
           [4.8, 3. , 1.4, 0.3],
           [5.1, 3.8, 1.6, 0.2],
           [4.6, 3.2, 1.4, 0.2],
           [5.3, 3.7, 1.5, 0.2],
           [5. , 3.3, 1.4, 0.2],
           [7. , 3.2, 4.7, 1.4],
           [6.4, 3.2, 4.5, 1.5],
           [6.9, 3.1, 4.9, 1.5],
           [5.5, 2.3, 4. , 1.3],
           [6.5, 2.8, 4.6, 1.5],
           [5.7, 2.8, 4.5, 1.3],
           [6.3, 3.3, 4.7, 1.6],
           [4.9, 2.4, 3.3, 1. ],
           [6.6, 2.9, 4.6, 1.3],
           [5.2, 2.7, 3.9, 1.4],
           [5. , 2. , 3.5, 1. ],
           [5.9, 3. , 4.2, 1.5],
           [6. , 2.2, 4. , 1. ],
           [6.1, 2.9, 4.7, 1.4],
           [5.6, 2.9, 3.6, 1.3],
           [6.7, 3.1, 4.4, 1.4],
           [5.6, 3. , 4.5, 1.5],
           [5.8, 2.7, 4.1, 1. ],
           [6.2, 2.2, 4.5, 1.5],
           [5.6, 2.5, 3.9, 1.1],
           [5.9, 3.2, 4.8, 1.8],
           [6.1, 2.8, 4. , 1.3],
           [6.3, 2.5, 4.9, 1.5],
           [6.1, 2.8, 4.7, 1.2],
           [6.4, 2.9, 4.3, 1.3],
           [6.6, 3. , 4.4, 1.4],
           [6.8, 2.8, 4.8, 1.4],
           [6.7, 3. , 5. , 1.7],
           [6. , 2.9, 4.5, 1.5],
           [5.7, 2.6, 3.5, 1. ],
           [5.5, 2.4, 3.8, 1.1],
           [5.5, 2.4, 3.7, 1. ],
           [5.8, 2.7, 3.9, 1.2],
           [6. , 2.7, 5.1, 1.6],
           [5.4, 3. , 4.5, 1.5],
           [6. , 3.4, 4.5, 1.6],
           [6.7, 3.1, 4.7, 1.5],
           [6.3, 2.3, 4.4, 1.3],
           [5.6, 3. , 4.1, 1.3],
           [5.5, 2.5, 4. , 1.3],
           [5.5, 2.6, 4.4, 1.2],
           [6.1, 3. , 4.6, 1.4],
           [5.8, 2.6, 4. , 1.2],
           [5. , 2.3, 3.3, 1. ],
           [5.6, 2.7, 4.2, 1.3],
           [5.7, 3. , 4.2, 1.2],
           [5.7, 2.9, 4.2, 1.3],
           [6.2, 2.9, 4.3, 1.3],
           [5.1, 2.5, 3. , 1.1],
           [5.7, 2.8, 4.1, 1.3],
           [6.3, 3.3, 6. , 2.5],
           [5.8, 2.7, 5.1, 1.9],
           [7.1, 3. , 5.9, 2.1],
           [6.3, 2.9, 5.6, 1.8],
           [6.5, 3. , 5.8, 2.2],
           [7.6, 3. , 6.6, 2.1],
           [4.9, 2.5, 4.5, 1.7],
           [7.3, 2.9, 6.3, 1.8],
           [6.7, 2.5, 5.8, 1.8],
           [7.2, 3.6, 6.1, 2.5],
           [6.5, 3.2, 5.1, 2. ],
           [6.4, 2.7, 5.3, 1.9],
           [6.8, 3. , 5.5, 2.1],
           [5.7, 2.5, 5. , 2. ],
           [5.8, 2.8, 5.1, 2.4],
           [6.4, 3.2, 5.3, 2.3],
           [6.5, 3. , 5.5, 1.8],
           [7.7, 3.8, 6.7, 2.2],
           [7.7, 2.6, 6.9, 2.3],
           [6. , 2.2, 5. , 1.5],
           [6.9, 3.2, 5.7, 2.3],
           [5.6, 2.8, 4.9, 2. ],
           [7.7, 2.8, 6.7, 2. ],
           [6.3, 2.7, 4.9, 1.8],
           [6.7, 3.3, 5.7, 2.1],
           [7.2, 3.2, 6. , 1.8],
           [6.2, 2.8, 4.8, 1.8],
           [6.1, 3. , 4.9, 1.8],
           [6.4, 2.8, 5.6, 2.1],
           [7.2, 3. , 5.8, 1.6],
           [7.4, 2.8, 6.1, 1.9],
           [7.9, 3.8, 6.4, 2. ],
           [6.4, 2.8, 5.6, 2.2],
           [6.3, 2.8, 5.1, 1.5],
           [6.1, 2.6, 5.6, 1.4],
           [7.7, 3. , 6.1, 2.3],
           [6.3, 3.4, 5.6, 2.4],
           [6.4, 3.1, 5.5, 1.8],
           [6. , 3. , 4.8, 1.8],
           [6.9, 3.1, 5.4, 2.1],
           [6.7, 3.1, 5.6, 2.4],
           [6.9, 3.1, 5.1, 2.3],
           [5.8, 2.7, 5.1, 1.9],
           [6.8, 3.2, 5.9, 2.3],
           [6.7, 3.3, 5.7, 2.5],
           [6.7, 3. , 5.2, 2.3],
           [6.3, 2.5, 5. , 1.9],
           [6.5, 3. , 5.2, 2. ],
           [6.2, 3.4, 5.4, 2.3],
           [5.9, 3. , 5.1, 1.8]]),
    'target': array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
           0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
           0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
           1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
           1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
           2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
           2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2]),
    'target_names': array(['setosa', 'versicolor', 'virginica'], dtype='<U10'),
    'DESCR': 'Iris Plants Database\n====================\n\nNotes\n-----\nData Set Characteristics:\n    :Number of Instances: 150 (50 in each of three classes)\n    :Number of Attributes: 4 numeric, predictive attributes and the class\n    :Attribute Information:\n        - sepal length in cm\n        - sepal width in cm\n        - petal length in cm\n        - petal width in cm\n        - class:\n                - Iris-Setosa\n                - Iris-Versicolour\n                - Iris-Virginica\n    :Summary Statistics:\n\n    ============== ==== ==== ======= ===== ====================\n                    Min  Max   Mean    SD   Class Correlation\n    ============== ==== ==== ======= ===== ====================\n    sepal length:   4.3  7.9   5.84   0.83    0.7826\n    sepal width:    2.0  4.4   3.05   0.43   -0.4194\n    petal length:   1.0  6.9   3.76   1.76    0.9490  (high!)\n    petal width:    0.1  2.5   1.20  0.76     0.9565  (high!)\n    ============== ==== ==== ======= ===== ====================\n\n    :Missing Attribute Values: None\n    :Class Distribution: 33.3% for each of 3 classes.\n    :Creator: R.A. Fisher\n    :Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)\n    :Date: July, 1988\n\nThis is a copy of UCI ML iris datasets.\nhttp://archive.ics.uci.edu/ml/datasets/Iris\n\nThe famous Iris database, first used by Sir R.A Fisher\n\nThis is perhaps the best known database to be found in the\npattern recognition literature.  Fisher\'s paper is a classic in the field and\nis referenced frequently to this day.  (See Duda & Hart, for example.)  The\ndata set contains 3 classes of 50 instances each, where each class refers to a\ntype of iris plant.  One class is linearly separable from the other 2; the\nlatter are NOT linearly separable from each other.\n\nReferences\n----------\n   - Fisher,R.A. "The use of multiple measurements in taxonomic problems"\n     Annual Eugenics, 7, Part II, 179-188 (1936); also in "Contributions to\n     Mathematical Statistics" (John Wiley, NY, 1950).\n   - Duda,R.O., & Hart,P.E. (1973) Pattern Classification and Scene Analysis.\n     (Q327.D83) John Wiley & Sons.  ISBN 0-471-22361-1.  See page 218.\n   - Dasarathy, B.V. (1980) "Nosing Around the Neighborhood: A New System\n     Structure and Classification Rule for Recognition in Partially Exposed\n     Environments".  IEEE Transactions on Pattern Analysis and Machine\n     Intelligence, Vol. PAMI-2, No. 1, 67-71.\n   - Gates, G.W. (1972) "The Reduced Nearest Neighbor Rule".  IEEE Transactions\n     on Information Theory, May 1972, 431-433.\n   - See also: 1988 MLC Proceedings, 54-64.  Cheeseman et al"s AUTOCLASS II\n     conceptual clustering system finds 3 classes in the data.\n   - Many, many more ...\n',
    'feature_names': ['sepal length (cm)',
     'sepal width (cm)',
     'petal length (cm)',
     'petal width (cm)']}
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163

X = iris['data']
Y = iris['target']
iris_target_name = ['target_name']
X, Y
1
2
3
4

   (array([[5.1, 3.5, 1.4, 0.2],
           [4.9, 3. , 1.4, 0.2],
           [4.7, 3.2, 1.3, 0.2],
           [4.6, 3.1, 1.5, 0.2],
           [5. , 3.6, 1.4, 0.2],
           [5.4, 3.9, 1.7, 0.4],
           [4.6, 3.4, 1.4, 0.3],
           [5. , 3.4, 1.5, 0.2],
           [4.4, 2.9, 1.4, 0.2],
           [4.9, 3.1, 1.5, 0.1],
           [5.4, 3.7, 1.5, 0.2],
           [4.8, 3.4, 1.6, 0.2],
           [4.8, 3. , 1.4, 0.1],
           [4.3, 3. , 1.1, 0.1],
           [5.8, 4. , 1.2, 0.2],
           [5.7, 4.4, 1.5, 0.4],
           [5.4, 3.9, 1.3, 0.4],
           [5.1, 3.5, 1.4, 0.3],
           [5.7, 3.8, 1.7, 0.3],
           [5.1, 3.8, 1.5, 0.3],
           [5.4, 3.4, 1.7, 0.2],
           [5.1, 3.7, 1.5, 0.4],
           [4.6, 3.6, 1. , 0.2],
           [5.1, 3.3, 1.7, 0.5],
           [4.8, 3.4, 1.9, 0.2],
           [5. , 3. , 1.6, 0.2],
           [5. , 3.4, 1.6, 0.4],
           [5.2, 3.5, 1.5, 0.2],
           [5.2, 3.4, 1.4, 0.2],
           [4.7, 3.2, 1.6, 0.2],
           [4.8, 3.1, 1.6, 0.2],
           [5.4, 3.4, 1.5, 0.4],
           [5.2, 4.1, 1.5, 0.1],
           [5.5, 4.2, 1.4, 0.2],
           [4.9, 3.1, 1.5, 0.1],
           [5. , 3.2, 1.2, 0.2],
           [5.5, 3.5, 1.3, 0.2],
           [4.9, 3.1, 1.5, 0.1],
           [4.4, 3. , 1.3, 0.2],
           [5.1, 3.4, 1.5, 0.2],
           [5. , 3.5, 1.3, 0.3],
           [4.5, 2.3, 1.3, 0.3],
           [4.4, 3.2, 1.3, 0.2],
           [5. , 3.5, 1.6, 0.6],
           [5.1, 3.8, 1.9, 0.4],
           [4.8, 3. , 1.4, 0.3],
           [5.1, 3.8, 1.6, 0.2],
           [4.6, 3.2, 1.4, 0.2],
           [5.3, 3.7, 1.5, 0.2],
           [5. , 3.3, 1.4, 0.2],
           [7. , 3.2, 4.7, 1.4],
           [6.4, 3.2, 4.5, 1.5],
           [6.9, 3.1, 4.9, 1.5],
           [5.5, 2.3, 4. , 1.3],
           [6.5, 2.8, 4.6, 1.5],
           [5.7, 2.8, 4.5, 1.3],
           [6.3, 3.3, 4.7, 1.6],
           [4.9, 2.4, 3.3, 1. ],
           [6.6, 2.9, 4.6, 1.3],
           [5.2, 2.7, 3.9, 1.4],
           [5. , 2. , 3.5, 1. ],
           [5.9, 3. , 4.2, 1.5],
           [6. , 2.2, 4. , 1. ],
           [6.1, 2.9, 4.7, 1.4],
           [5.6, 2.9, 3.6, 1.3],
           [6.7, 3.1, 4.4, 1.4],
           [5.6, 3. , 4.5, 1.5],
           [5.8, 2.7, 4.1, 1. ],
           [6.2, 2.2, 4.5, 1.5],
           [5.6, 2.5, 3.9, 1.1],
           [5.9, 3.2, 4.8, 1.8],
           [6.1, 2.8, 4. , 1.3],
           [6.3, 2.5, 4.9, 1.5],
           [6.1, 2.8, 4.7, 1.2],
           [6.4, 2.9, 4.3, 1.3],
           [6.6, 3. , 4.4, 1.4],
           [6.8, 2.8, 4.8, 1.4],
           [6.7, 3. , 5. , 1.7],
           [6. , 2.9, 4.5, 1.5],
           [5.7, 2.6, 3.5, 1. ],
           [5.5, 2.4, 3.8, 1.1],
           [5.5, 2.4, 3.7, 1. ],
           [5.8, 2.7, 3.9, 1.2],
           [6. , 2.7, 5.1, 1.6],
           [5.4, 3. , 4.5, 1.5],
           [6. , 3.4, 4.5, 1.6],
           [6.7, 3.1, 4.7, 1.5],
           [6.3, 2.3, 4.4, 1.3],
           [5.6, 3. , 4.1, 1.3],
           [5.5, 2.5, 4. , 1.3],
           [5.5, 2.6, 4.4, 1.2],
           [6.1, 3. , 4.6, 1.4],
           [5.8, 2.6, 4. , 1.2],
           [5. , 2.3, 3.3, 1. ],
           [5.6, 2.7, 4.2, 1.3],
           [5.7, 3. , 4.2, 1.2],
           [5.7, 2.9, 4.2, 1.3],
           [6.2, 2.9, 4.3, 1.3],
           [5.1, 2.5, 3. , 1.1],
           [5.7, 2.8, 4.1, 1.3],
           [6.3, 3.3, 6. , 2.5],
           [5.8, 2.7, 5.1, 1.9],
           [7.1, 3. , 5.9, 2.1],
           [6.3, 2.9, 5.6, 1.8],
           [6.5, 3. , 5.8, 2.2],
           [7.6, 3. , 6.6, 2.1],
           [4.9, 2.5, 4.5, 1.7],
           [7.3, 2.9, 6.3, 1.8],
           [6.7, 2.5, 5.8, 1.8],
           [7.2, 3.6, 6.1, 2.5],
           [6.5, 3.2, 5.1, 2. ],
           [6.4, 2.7, 5.3, 1.9],
           [6.8, 3. , 5.5, 2.1],
           [5.7, 2.5, 5. , 2. ],
           [5.8, 2.8, 5.1, 2.4],
           [6.4, 3.2, 5.3, 2.3],
           [6.5, 3. , 5.5, 1.8],
           [7.7, 3.8, 6.7, 2.2],
           [7.7, 2.6, 6.9, 2.3],
           [6. , 2.2, 5. , 1.5],
           [6.9, 3.2, 5.7, 2.3],
           [5.6, 2.8, 4.9, 2. ],
           [7.7, 2.8, 6.7, 2. ],
           [6.3, 2.7, 4.9, 1.8],
           [6.7, 3.3, 5.7, 2.1],
           [7.2, 3.2, 6. , 1.8],
           [6.2, 2.8, 4.8, 1.8],
           [6.1, 3. , 4.9, 1.8],
           [6.4, 2.8, 5.6, 2.1],
           [7.2, 3. , 5.8, 1.6],
           [7.4, 2.8, 6.1, 1.9],
           [7.9, 3.8, 6.4, 2. ],
           [6.4, 2.8, 5.6, 2.2],
           [6.3, 2.8, 5.1, 1.5],
           [6.1, 2.6, 5.6, 1.4],
           [7.7, 3. , 6.1, 2.3],
           [6.3, 3.4, 5.6, 2.4],
           [6.4, 3.1, 5.5, 1.8],
           [6. , 3. , 4.8, 1.8],
           [6.9, 3.1, 5.4, 2.1],
           [6.7, 3.1, 5.6, 2.4],
           [6.9, 3.1, 5.1, 2.3],
           [5.8, 2.7, 5.1, 1.9],
           [6.8, 3.2, 5.9, 2.3],
           [6.7, 3.3, 5.7, 2.5],
           [6.7, 3. , 5.2, 2.3],
           [6.3, 2.5, 5. , 1.9],
           [6.5, 3. , 5.2, 2. ],
           [6.2, 3.4, 5.4, 2.3],
           [5.9, 3. , 5.1, 1.8]]),
    array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
           0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
           0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
           1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
           1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
           2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
           2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2]))
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157

# 使用决策树训练
clf=tree.DecisionTreeClassifier(max_depth=3)
clf.fit(X,Y)
1
2
3

DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=3,
            max_features=None, max_leaf_nodes=None,
            min_impurity_decrease=0.0, min_impurity_split=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, presort=False, random_state=None,
            splitter='best')
1
2
3
4
5
6

#这里预测当前输入的值的所属分类
print('target: ', [clf.predict([[12,1,-1,10]])[0]])
print('类别是: ',iris_target_name[clf.predict([[12,1,-1,10]])[0]])
1
2
3

target:  [0]
类别是:  target_name
1
2

无监督学习-Kmeans

程序设计

# 使用无监督聚类 k-means 试试
import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D

from sklearn.cluster import KMeans
from sklearn import datasets

np.random.seed(5)

centers = [[1, 1], [-1, -1], [1, -1]]
iris = datasets.load_iris()
X = iris.data
y = iris.target

estimators = {'k_means_iris_3': KMeans(n_clusters=3),
              'k_means_iris_8': KMeans(n_clusters=8),
              'k_means_iris_bad_init': KMeans(n_clusters=3, n_init=1,
                                              init='random')}

fignum = 1
for name, est in estimators.items():
    fig = plt.figure(fignum, figsize=(4, 3))
    plt.clf()
    ax = Axes3D(fig, rect=[0, 0, .95, 1], elev=48, azim=134)

    plt.cla()
    est.fit(X)
    labels = est.labels_

    ax.scatter(X[:, 3], X[:, 0], X[:, 2], c=labels.astype(np.float))

    ax.w_xaxis.set_ticklabels([])
    ax.w_yaxis.set_ticklabels([])
    ax.w_zaxis.set_ticklabels([])
    ax.set_xlabel('Petal width')
    ax.set_ylabel('Sepal length')
    ax.set_zlabel('Petal length')
    fignum = fignum + 1

# Plot the ground truth
fig = plt.figure(fignum, figsize=(4, 3))
plt.clf()
ax = Axes3D(fig, rect=[0, 0, .95, 1], elev=48, azim=134)

plt.cla()

for name, label in [('Setosa', 0),
                    ('Versicolour', 1),
                    ('Virginica', 2)]:
    ax.text3D(X[y == label, 3].mean(),
              X[y == label, 0].mean() + 1.5,
              X[y == label, 2].mean(), name,
              horizontalalignment='center',
              bbox=dict(alpha=.5, edgecolor='w', facecolor='w'))
# Reorder the labels to have colors matching the cluster results
y = np.choose(y, [1, 2, 0]).astype(np.float)
ax.scatter(X[:, 3], X[:, 0], X[:, 2], c=y)

ax.w_xaxis.set_ticklabels([])
ax.w_yaxis.set_ticklabels([])
ax.w_zaxis.set_ticklabels([])
ax.set_xlabel('Petal width')
ax.set_ylabel('Sepal length')
ax.set_zlabel('Petal length')
plt.show()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66

程序分析

这段代码实现了利用KMeans算法对鸢尾花数据集进行聚类，并使用3D图像可视化聚类结果和真实分类结果的比较。代码主要分为以下几个部分：

1. 导入必要的库和数据集：

import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D

from sklearn.cluster import KMeans
from sklearn import datasets

np.random.seed(5)

centers = [[1, 1], [-1, -1], [1, -1]]
iris = datasets.load_iris()
X = iris.data
y = iris.target
1
2
3
4
5
6
7
8
9
10
11
12
13

2. 定义三个不同的KMeans模型，并对数据集进行拟合：

estimators = {'k_means_iris_3': KMeans(n_clusters=3),
              'k_means_iris_8': KMeans(n_clusters=8),
              'k_means_iris_bad_init': KMeans(n_clusters=3, n_init=1,
                                              init='random')}

for name, est in estimators.items():
    est.fit(X)
    labels = est.labels_
1
2
3
4
5
6
7
8

3. 使用3D图像可视化聚类结果：

fig = plt.figure(fignum, figsize=(4, 3))
plt.clf()
ax = Axes3D(fig, rect=[0, 0, .95, 1], elev=48, azim=134)

plt.cla()
ax.scatter(X[:, 3], X[:, 0], X[:, 2], c=labels.astype(np.float))

ax.w_xaxis.set_ticklabels([])
ax.w_yaxis.set_ticklabels([])
ax.w_zaxis.set_ticklabels([])
ax.set_xlabel('Petal width')
ax.set_ylabel('Sepal length')
ax.set_zlabel('Petal length')
fignum = fignum + 1
1
2
3
4
5
6
7
8
9
10
11
12
13
14

4. 使用3D图像可视化真实分类结果：

fig = plt.figure(fignum, figsize=(4, 3))
plt.clf()
ax = Axes3D(fig, rect=[0, 0, .95, 1], elev=48, azim=134)

plt.cla()

for name, label in [('Setosa', 0),
                    ('Versicolour', 1),
                    ('Virginica', 2)]:
    ax.text3D(X[y == label, 3].mean(),
              X[y == label, 0].mean() + 1.5,
              X[y == label, 2].mean(), name,
              horizontalalignment='center',
              bbox=dict(alpha=.5, edgecolor='w', facecolor='w'))
y = np.choose(y, [1, 2, 0]).astype(np.float)
ax.scatter(X[:, 3], X[:, 0], X[:, 2], c=y)

ax.w_xaxis.set_ticklabels([])
ax.w_yaxis.set_ticklabels([])
ax.w_zaxis.set_ticklabels([])
ax.set_xlabel('Petal width')
ax.set_ylabel('Sepal length')
ax.set_zlabel('Petal length')
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23

在以上代码中，我们可以看到用三种不同的KMeans模型进行聚类，其中模型1和模型3都是三个聚类中心，而模型2是八个聚类中心。我们可以通过比较不同模型的聚类结果，来判断不同聚类中心数量对聚类结果的影响。

在3D图像中，每个数据点的坐标值为鸢尾花的四个特征值，x轴对应花瓣宽度，y轴对应花萼长度，z轴对应花瓣长度。通过颜色来表示不同的聚类结果。我们可以看到，不同聚类中心数量的模型分别将数据集聚为了不同数量的簇。同时，我们也可以通过比较聚类结果和真实分类结果的图像来评估聚类的效果。

总的来说，这段代码实现了对鸢尾花数据集进行聚类，并通过可视化手段来呈现聚类结果和真实分类结果之间的差异。

附：系列文章