def main(): dataSet=[[1,2,'yes'], [1,2,'yes'], [1,0,'no'], [1,1,'no'], [0,2,'no'], ] dataSet = [[u'青年', u'否', u'否', u'一般', u'拒绝'], [u'青年', u'否', u'否', u'好', u'拒绝'], [u'青年', u'是', u'否', u'好', u'同意'], [u'青年', u'是', u'是', u'一般', u'同意'], [u'青年', u'否', u'否', u'一般', u'拒绝'], [u'中年', u'否', u'否', u'一般', u'拒绝'], [u'中年', u'否', u'否', u'好', u'拒绝'], [u'中年', u'是', u'是', u'好', u'同意'], [u'中年', u'否', u'是', u'非常好', u'同意'], [u'中年', u'否', u'是', u'非常好', u'同意'], [u'老年', u'否', u'是', u'非常好', u'同意'], [u'老年', u'否', u'是', u'好', u'同意'], [u'老年', u'是', u'否', u'好', u'同意'], [u'老年', u'是', u'否', u'非常好', u'同意'], [u'老年', u'否', u'否', u'一般', u'拒绝'], ] tree=fit(dataSet) print(tree) treePlotter2.createPlot(tree)
def main():
dataSet = [
[1, 2, 'yes'],
[1, 2, 'yes'],
[1, 0, 'no'],
[1, 1, 'no'],
[0, 2, 'no'],
]
tree = fit(dataSet)
print(tree)
treePlotter2.createPlot(tree)
def main():
dataSet, label = createDataSet()
Ent = calcShannonEnt(dataSet)
print(Ent)
feature = chooseBestFeatureToSplit(dataSet)
print(feature)
myTree1 = creatTree(dataSet, label)
print(myTree1)
# 测试决策树的构建
treePlotter2.createPlot(myTree1)
def main():
dataSet, label = createDataSet()
feature = chooseBestFeatureToSplit(dataSet)
myTree1 = creatTree(dataSet, label)
print(myTree1)
mpl.rcParams['font.sans-serif'] = ['SimHei'] # 指定默认字体
mpl.rcParams['axes.unicode_minus'] = False # 解决保存图像时负号'-'显示为方块的问题
# 测试决策树的构建
treePlotter2.createPlot(myTree1)
def main():
# dataSet,label=createDataSet()
dataSet_ = createD()
dataSet = featureSplit(dataSet_, step_num=3)
label = [i for i in range(len(dataSet[0]))]
# print(label)
Ent = calcShannonEnt(dataSet)
# print(Ent)
feature = chooseBestFeatureToSplit(dataSet)
# print(feature)
myTree1 = creatTree(dataSet, label)
# print(myTree1)
mpl.rcParams['font.sans-serif'] = ['SimHei'] # 指定默认字体
mpl.rcParams['axes.unicode_minus'] = False # 解决保存图像时负号'-'显示为方块的问题
# 测试决策树的构建
treePlotter2.createPlot(myTree1)
# -*- coding: utf-8 -*-
# Filename : 07store_grab.py
from numpy import *
from math import log
from ID3DTree import *
import copy
import treePlotter2
import matplotlib.pyplot as plt
dtree = ID3DTree()
dtree.loadDataSet("dataset.dat",["age","revenue","student","credit"])
# dtree.loadDataSet("lenses.txt",['age','prescript','astigmatic','tearRate'])
dtree.train()
print dtree.tree
treePlotter2.createPlot(dtree.tree)
dataSet = load_csv(filename)
for i in range(0, len(dataSet[0]) - 1):
str_column_to_float(dataSet, i)
str_column_to_int(dataSet, len(dataSet[0]) - 1)
max_depth = 10
min_size = 3
print(len(dataSet))
tree = build_tree(dataSet[0:200], max_depth, min_size)
print(tree)
####可视化
import treePlotter2
from pylab import *
mpl.rcParams['font.sans-serif'] = ['SimHei'] # 指定默认字体
mpl.rcParams['axes.unicode_minus'] = False # 解决保存图像时负号'-'显示为方块的问题
# 测试决策树的构建
treePlotter2.createPlot(tree)
###可视化
predictions = [predict(tree, row) for row in dataSet[150:]]
realLabels = [row[-1] for row in dataSet[150:]]
current = 0
for i in range(len(predictions)):
if predictions[i] == realLabels[i]:
current += 1
print(current / len(predictions))
str_column_to_float(dataSet, i)
str_column_to_int(dataSet, len(dataSet[0]) - 1)
max_depth = 10
min_size = 2
print(len(dataSet))
tree = fit(dataSet[0:150], max_depth, min_size)
print(tree)
####可视化
import treePlotter2
from pylab import *
mpl.rcParams['font.sans-serif'] = ['SimHei'] # 指定默认字体
mpl.rcParams['axes.unicode_minus'] = False # 解决保存图像时负号'-'显示为方块的问题
treePlotter2.createPlot(tree)
##可视化
##剪枝
import ART_punning
punning_tree = ART_punning.prune(tree, dataSet[150:200])
treePlotter2.createPlot(punning_tree)
##可视化
##
predictions = [predict(tree, row) for row in dataSet[150:]]
realLabels = [row[-1] for row in dataSet[150:]]
current = 0
for i in range(len(predictions)):
if predictions[i] > 0.5:
# -*- coding: utf-8 -*-
from numpy import *
from math import log
from C45DTree import *
import treePlotter2
dtree = C45DTree()
dtree.loadDataSet("dataset.dat",["age","revenue","student","credit"])
dtree.train()
print dtree.tree
treePlotter2.createPlot(dtree.tree)