Directorio de artículos
Análisis del conjunto de datos del iris.
árbol de decisión
# 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。
#载入数据集
iris = datasets.load_iris()
iris
{'datos': matriz ([[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]]),
'destino': matriz([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, 2]),
'target_names': array(['setosa', 'versicolor', 'virginica'], dtype='<U10'),
Valores de atributos faltantes: Ninguno\n :Distribución de clases: 33,3 % para cada una de las 3 clases.\n :Creador: RA Fisher\n :Donante: Michael Marshall (MARSHALL%[email protected])\n :Fecha : julio de 1988\n\nEsta es una copia de los conjuntos de datos de iris de UCI ML.\nhttp://archive.ics.uci.edu/ml/datasets/Iris\n\nLa famosa base de datos Iris, utilizada por primera vez por Sir RA Fisher\ n\nEsta es quizás la base de datos más conocida que se encuentra en la\nliteratura sobre reconocimiento de patrones. El artículo de Fisher es un clásico en este campo y se hace referencia a él con frecuencia hasta el día de hoy. (Consulte Duda & Hart, por ejemplo). El\nconjunto de datos contiene 3 clases de 50 instancias cada una, donde cada clase se refiere a un\ntipo de planta de iris. Una clase es linealmente separable de las otras 2; estos\núltimos NO son linealmente separables entre sí.\n\nReferencias\n----------\n - Fisher,RA “El uso de múltiples medidas en problemas taxonómicos”\n Annual Eugenics, 7, Part II, 179-188 (1936); también en “Contributions to\n Mathematical Statistics” (John Wiley, NY, 1950).\n - Duda,RO, & Hart,PE (1973) Clasificación de patrones y análisis de escenas.\n (Q327.D83) John Wiley & Sons . ISBN 0-471-22361-1. Consulte la página 218.\n - Dasarathy, BV (1980) “Husmeando en el vecindario: un nuevo sistema\n estructura y regla de clasificación para el reconocimiento en entornos\n parcialmente expuestos”. Transacciones IEEE sobre análisis de patrones e inteligencia de máquinas, vol. PAMI-2, No. 1, 67-71.\n - Gates, GW (1972) “La regla del vecino más cercano reducido”. IEEE Transactions\n on Information Theory, mayo de 1972, 431-433.\n - Véase también: 1988 MLC Proceedings, 54-64. El sistema de agrupamiento conceptual AUTOCLASS II\n de Cheeseman et al encuentra 3 clases en los datos.\n - Muchas,
'feature_names': ['largo del sépalo (cm)',
'ancho del sépalo (cm)',
'largo del pétalo (cm)',
'ancho del pétalo (cm)']}
X = iris['data']
Y = iris['target']
iris_target_name = ['target_name']
X, Y
(matriz([[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]]),
matriz([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, 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, 2]))
# 使用决策树训练
clf=tree.DecisionTreeClassifier(max_depth=3)
clf.fit(X,Y)
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')
#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]])
target: [0]
类别是: target_name
K-medias
# 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()
