数据挖掘
文章平均质量分 77
zilangboya
这个作者很懒,什么都没留下…
展开
-
Python实现朴素贝叶斯分类器
# -*-coding:utf-8-*-''' 朴素贝叶斯算法'''from __future__ import division global classNameclassName = "class"def calc_class(train, classValue): # 计算分类的概率 _num_cls = 0原创 2015-05-26 17:07:08 · 2092 阅读 · 0 评论 -
KNN算法
# -*- coding:utf-8-*-from __future__ import divisionimport matplotlib.pyplot as pltimport mpl_toolkits.mplot3dimport numpy as npimport operatorimport osdef createDataSet(): group = [[1.0,1原创 2015-06-29 21:05:53 · 418 阅读 · 0 评论 -
Python实现决策树算法
# -*-coding:utf-8-*-''' 决策树算法'''from __future__ import divisionimport matplotlib.pyplot as pltfrom math import logimport operatorimport pickledef createDataSet(): dataset = [[1,1,'yes原创 2015-06-30 21:00:48 · 988 阅读 · 1 评论 -
Logistic回归
# -*-coding:utf-8-*-''' 逻辑回归算法'''from __future__ import divisionimport numpy as npimport matplotlib.pyplot as pltimport randomdef loadDataSet(): ''' 训练数据 ---> 训练数据列表,分类标号向量原创 2015-07-01 21:53:29 · 443 阅读 · 0 评论 -
adaBoost
# -*-coding:utf-8-*-'''Adaboost'''from __future__ import division import numpy as npdef LoadSimpleData(): dataMat = np.matrix([[ 1. , 2.1], [ 2. , 1.1], [ 1.3, 1. ],原创 2015-07-09 21:39:12 · 469 阅读 · 0 评论 -
回归 regression
# -*-coding:utf-8import numpy as npimport matplotlib.pyplot as pltdef loadDataSet(fileName): f = open(fileName) _numFeat = len(f.readline().split('\t')) - 1 # 训练数据的特征总数 dataMat = []原创 2015-07-11 09:50:54 · 670 阅读 · 0 评论 -
Kmeans
# -*-coding:utf-8import numpy as npdef loadDataSet(fileName): dataMat = [] f = open(fileName) for _line_ in f.readlines(): _curLine = _line_.strip().split('\t') _fitLin原创 2015-07-14 19:52:44 · 466 阅读 · 0 评论 -
Apriori
# -*-coding:utf-8-*-'''Apriori'''import numpy as npdef loadDataSet(): return [[1,3,4],[2,3,5],[1,2,3,5],[2,5]] def createC1(dataSet): ''' 大小为1的所有候选项集合 ''' C1 = []原创 2015-07-18 09:05:28 · 426 阅读 · 0 评论