更新2.KNN文件位置

This commit is contained in:
jiangzhonglian
2017-04-07 16:43:54 +08:00
parent ebc6bbad78
commit a1b53e46fa
2894 changed files with 5 additions and 5 deletions

View File

@@ -0,0 +1,105 @@
#!/usr/bin/python
# coding:utf8
# '''
# Created on 2017-03-10
# Update on 2017-03-10
# author: jiangzhonglian
# content: 回归树
# '''
# print(__doc__)
# # Import the necessary modules and libraries
# import numpy as np
# from sklearn.tree import DecisionTreeRegressor
# import matplotlib.pyplot as plt
# # Create a random dataset
# rng = np.random.RandomState(1)
# X = np.sort(5 * rng.rand(80, 1), axis=0)
# y = np.sin(X).ravel()
# print X, '\n\n\n-----------\n\n\n', y
# y[::5] += 3 * (0.5 - rng.rand(16))
# # Fit regression model
# regr_1 = DecisionTreeRegressor(max_depth=2, min_samples_leaf=5)
# regr_2 = DecisionTreeRegressor(max_depth=5, min_samples_leaf=5)
# regr_1.fit(X, y)
# regr_2.fit(X, y)
# # Predict
# X_test = np.arange(0.0, 5.0, 0.01)[:, np.newaxis]
# y_1 = regr_1.predict(X_test)
# y_2 = regr_2.predict(X_test)
# # Plot the results
# plt.figure()
# plt.scatter(X, y, c="darkorange", label="data")
# plt.plot(X_test, y_1, color="cornflowerblue", label="max_depth=2", linewidth=2)
# plt.plot(X_test, y_2, color="yellowgreen", label="max_depth=5", linewidth=2)
# plt.xlabel("data")
# plt.ylabel("target")
# plt.title("Decision Tree Regression")
# plt.legend()
# plt.show()
'''
Created on 2017-03-10
Update on 2017-03-10
author: jiangzhonglian
content: 模型树
'''
print(__doc__)
# Author: Noel Dawe <noel.dawe@gmail.com>
#
# License: BSD 3 clause
# importing necessary libraries
import numpy as np
import matplotlib.pyplot as plt
from sklearn.tree import DecisionTreeRegressor
from sklearn.ensemble import AdaBoostRegressor
# Create the dataset
rng = np.random.RandomState(1)
X = np.linspace(0, 6, 100)[:, np.newaxis]
y = np.sin(X).ravel() + np.sin(6 * X).ravel() + rng.normal(0, 0.1, X.shape[0])
# Fit regression model
regr_1 = DecisionTreeRegressor(max_depth=4)
regr_2 = AdaBoostRegressor(DecisionTreeRegressor(max_depth=4),
n_estimators=300, random_state=rng)
regr_1.fit(X, y)
regr_2.fit(X, y)
# Predict
y_1 = regr_1.predict(X)
y_2 = regr_2.predict(X)
# Plot the results
plt.figure()
plt.scatter(X, y, c="k", label="training samples")
plt.plot(X, y_1, c="g", label="n_estimators=1", linewidth=2)
plt.plot(X, y_2, c="r", label="n_estimators=300", linewidth=2)
plt.xlabel("data")
plt.ylabel("target")
plt.title("Boosted Decision Tree Regression")
plt.legend()
plt.show()

View File

@@ -0,0 +1,343 @@
#!/usr/bin/python
# coding:utf8
'''
Created on Feb 4, 2011
Update on 2017-03-02
Tree-Based Regression Methods Source Code for Machine Learning in Action Ch. 9
@author: Peter Harrington/片刻
'''
print(__doc__)
from numpy import *
# 默认解析的数据是用tab分隔,并且是数值类型
# general function to parse tab -delimited floats
def loadDataSet(fileName):
"""loadDataSet(解析每一行,并转化为float类型)
Args:
fileName 文件名
Returns:
dataMat 每一行的数据集array类型
Raises:
"""
# 假定最后一列是结果值
# assume last column is target value
dataMat = []
fr = open(fileName)
for line in fr.readlines():
curLine = line.strip().split('\t')
# 将所有的元素转化为float类型
# map all elements to float()
fltLine = map(float, curLine)
dataMat.append(fltLine)
return dataMat
def binSplitDataSet(dataSet, feature, value):
"""binSplitDataSet(将数据集,按照feature列的value进行 二元切分)
Args:
dataMat 数据集
feature 特征列
value 特征列要比较的值
Returns:
mat0 小于的数据集在左边
mat1 大于的数据集在右边
Raises:
"""
# # 测试案例
# print 'dataSet[:, feature]=', dataSet[:, feature]
# print 'nonzero(dataSet[:, feature] > value)[0]=', nonzero(dataSet[:, feature] > value)[0]
# print 'nonzero(dataSet[:, feature] <= value)[0]=', nonzero(dataSet[:, feature] <= value)[0]
# dataSet[:, feature] 取去每一行中,第1列的值(从0开始算)
# nonzero(dataSet[:, feature] > value) 返回结果为true行的index下标
mat0 = dataSet[nonzero(dataSet[:, feature] <= value)[0], :]
mat1 = dataSet[nonzero(dataSet[:, feature] > value)[0], :]
return mat0, mat1
# 返回每一个叶子结点的均值
# returns the value used for each leaf
def regLeaf(dataSet):
return mean(dataSet[:, -1])
# 计算总方差=方差*样本数
def regErr(dataSet):
# shape(dataSet)[0] 表示行数
return var(dataSet[:, -1]) * shape(dataSet)[0]
# 1.用最佳方式切分数据集
# 2.生成相应的叶节点
def chooseBestSplit(dataSet, leafType=regLeaf, errType=regErr, ops=(1, 4)):
"""chooseBestSplit(用最佳方式切分数据集 和 生成相应的叶节点)
Args:
dataSet 加载的原始数据集
leafType 建立叶子点的函数
errType 误差计算函数(求总方差)
ops [容许误差下降值,切分的最少样本数]
Returns:
bestIndex feature的index坐标
bestValue 切分的最优值
Raises:
"""
tolS = ops[0]
tolN = ops[1]
# 如果结果集(最后一列为1个变量),就返回推出
# .T 对数据集进行转置
# .tolist()[0] 转化为数组并取第0列
if len(set(dataSet[:, -1].T.tolist()[0])) == 1:
# exit cond 1
return None, leafType(dataSet)
# 计算行列值
m, n = shape(dataSet)
# 无分类误差的总方差和
# the choice of the best feature is driven by Reduction in RSS error from mean
S = errType(dataSet)
# inf 正无穷大
bestS, bestIndex, bestValue = inf, 0, 0
# 循环处理每一列对应的feature值
for featIndex in range(n-1):
# [0]表示这一列的[所有行],不要[0]就是一个array[[所有行]]
for splitVal in set(dataSet[:, featIndex].T.tolist()[0]):
# 对该列进行分组,然后组内的成员的val值进行 二元切分
mat0, mat1 = binSplitDataSet(dataSet, featIndex, splitVal)
# 判断二元切分的方式的元素数量是否符合预期
if (shape(mat0)[0] < tolN) or (shape(mat1)[0] < tolN):
continue
newS = errType(mat0) + errType(mat1)
# 如果二元切分,算出来的误差在可接受范围内,那么就记录切分点,并记录最小误差
if newS < bestS:
bestIndex = featIndex
bestValue = splitVal
bestS = newS
# 判断二元切分的方式的元素误差是否符合预期
# if the decrease (S-bestS) is less than a threshold don't do the split
if (S - bestS) < tolS:
return None, leafType(dataSet)
mat0, mat1 = binSplitDataSet(dataSet, bestIndex, bestValue)
# 对整体的成员进行判断,是否符合预期
if (shape(mat0)[0] < tolN) or (shape(mat1)[0] < tolN):
return None, leafType(dataSet)
return bestIndex, bestValue
# assume dataSet is NumPy Mat so we can array filtering
def createTree(dataSet, leafType=regLeaf, errType=regErr, ops=(1, 4)):
"""createTree(获取回归树)
Args:
dataSet 加载的原始数据集
leafType 建立叶子点的函数
errType 误差计算函数
ops=(1, 4) [容许误差下降值,切分的最少样本数]
Returns:
retTree 决策树最后的结果
"""
# 选择最好的切分方式: feature索引值,最优切分值
# choose the best split
feat, val = chooseBestSplit(dataSet, leafType, errType, ops)
# if the splitting hit a stop condition return val
if feat is None:
return val
retTree = {}
retTree['spInd'] = feat
retTree['spVal'] = val
# 大于在右边,小于在左边,分为2个数据集
lSet, rSet = binSplitDataSet(dataSet, feat, val)
# 递归的进行调用
retTree['left'] = createTree(lSet, leafType, errType, ops)
retTree['right'] = createTree(rSet, leafType, errType, ops)
return retTree
# 判断节点是否是一个字典
def isTree(obj):
return (type(obj).__name__ == 'dict')
# 计算左右枝丫的均值
def getMean(tree):
if isTree(tree['right']):
tree['right'] = getMean(tree['right'])
if isTree(tree['left']):
tree['left'] = getMean(tree['left'])
return (tree['left']+tree['right'])/2.0
# 检查是否适合合并分枝
def prune(tree, testData):
# 判断是否测试数据集没有数据,如果没有,就直接返回tree本身的均值
if shape(testData)[0] == 0:
return getMean(tree)
# 判断分枝是否是dict字典,如果是就将测试数据集进行切分
if (isTree(tree['right']) or isTree(tree['left'])):
lSet, rSet = binSplitDataSet(testData, tree['spInd'], tree['spVal'])
# 如果是左边分枝是字典,就传入左边的数据集和左边的分枝,进行递归
if isTree(tree['left']):
tree['left'] = prune(tree['left'], lSet)
# 如果是右边分枝是字典,就传入左边的数据集和左边的分枝,进行递归
if isTree(tree['right']):
tree['right'] = prune(tree['right'], rSet)
# 如果左右两边同时都不是dict字典,那么分割测试数据集。
# 1. 如果正确
# * 那么计算一下总方差 和 该结果集的本身不分枝的总方差比较
# * 如果 合并的总方差 < 不合并的总方差,那么就进行合并
# 注意返回的结果: 如果可以合并,原来的dict就变为了 数值
if not isTree(tree['left']) and not isTree(tree['right']):
lSet, rSet = binSplitDataSet(testData, tree['spInd'], tree['spVal'])
# power(x, y)表示x的y次方
errorNoMerge = sum(power(lSet[:, -1] - tree['left'], 2)) + sum(power(rSet[:, -1] - tree['right'], 2))
treeMean = (tree['left'] + tree['right'])/2.0
errorMerge = sum(power(testData[:, -1] - treeMean, 2))
# 如果 合并的总方差 < 不合并的总方差,那么就进行合并
if errorMerge < errorNoMerge:
print "merging"
return treeMean
else:
return tree
else:
return tree
# 得到模型的ws系数:f(x) = x0 + x1*featrue1+ x3*featrue2 ...
# create linear model and return coeficients
def modelLeaf(dataSet):
ws, X, Y = linearSolve(dataSet)
return ws
# 计算线性模型的误差值
def modelErr(dataSet):
ws, X, Y = linearSolve(dataSet)
yHat = X * ws
# print corrcoef(yHat, Y, rowvar=0)
return sum(power(Y - yHat, 2))
# helper function used in two places
def linearSolve(dataSet):
m, n = shape(dataSet)
# 产生一个关于1的矩阵
X = mat(ones((m, n)))
Y = mat(ones((m, 1)))
# X的0列为1,常数项,用于计算平衡误差
X[:, 1: n] = dataSet[:, 0: n-1]
Y = dataSet[:, -1]
# 转置矩阵*矩阵
xTx = X.T * X
# 如果矩阵的逆不存在,会造成程序异常
if linalg.det(xTx) == 0.0:
raise NameError('This matrix is singular, cannot do inverse,\ntry increasing the second value of ops')
# 最小二乘法求最优解: w0*1+w1*x1=y
ws = xTx.I * (X.T * Y)
return ws, X, Y
# 回归树测试案例
def regTreeEval(model, inDat):
return float(model)
# 模型树测试案例
def modelTreeEval(model, inDat):
n = shape(inDat)[1]
X = mat(ones((1, n+1)))
X[:, 1: n+1] = inDat
# print X, model
return float(X * model)
# 计算预测的结果
def treeForeCast(tree, inData, modelEval=regTreeEval):
if not isTree(tree):
return modelEval(tree, inData)
if inData[tree['spInd']] <= tree['spVal']:
if isTree(tree['left']):
return treeForeCast(tree['left'], inData, modelEval)
else:
return modelEval(tree['left'], inData)
else:
if isTree(tree['right']):
return treeForeCast(tree['right'], inData, modelEval)
else:
return modelEval(tree['right'], inData)
# 预测结果
def createForeCast(tree, testData, modelEval=regTreeEval):
m = len(testData)
yHat = mat(zeros((m, 1)))
for i in range(m):
yHat[i, 0] = treeForeCast(tree, mat(testData[i]), modelEval)
return yHat
if __name__ == "__main__":
# # 测试数据集
# testMat = mat(eye(4))
# print testMat
# print type(testMat)
# mat0, mat1 = binSplitDataSet(testMat, 1, 0.5)
# print mat0, '\n-----------\n', mat1
# # 回归树
# myDat = loadDataSet('input/09.RegTrees/data1.txt')
# # myDat = loadDataSet('input/09.RegTrees/data2.txt')
# # print 'myDat=', myDat
# myMat = mat(myDat)
# # print 'myMat=', myMat
# myTree = createTree(myMat)
# print myTree
# # 1. 预剪枝就是:提起设置最大误差数和最少元素数
# myDat = loadDataSet('input/09.RegTrees/data3.txt')
# myMat = mat(myDat)
# myTree = createTree(myMat, ops=(0, 1))
# print myTree
# # 2. 后剪枝就是:通过测试数据,对预测模型进行合并判断
# myDatTest = loadDataSet('input/09.RegTrees/data3test.txt')
# myMat2Test = mat(myDatTest)
# myFinalTree = prune(myTree, myMat2Test)
# print '\n\n\n-------------------'
# print myFinalTree
# # --------
# # 模型树求解
# myDat = loadDataSet('input/09.RegTrees/data4.txt')
# myMat = mat(myDat)
# myTree = createTree(myMat, modelLeaf, modelErr)
# print myTree
# 回归树 VS 模型树 VS 线性回归
trainMat = mat(loadDataSet('input/09.RegTrees/bikeSpeedVsIq_train.txt'))
testMat = mat(loadDataSet('input/09.RegTrees/bikeSpeedVsIq_test.txt'))
# 回归树
myTree1 = createTree(trainMat, ops=(1, 20))
print myTree1
yHat1 = createForeCast(myTree1, testMat[:, 0])
print "回归树:", corrcoef(yHat1, testMat[:, 1],rowvar=0)[0, 1]
# 模型树
myTree2 = createTree(trainMat, modelLeaf, modelErr, ops=(1, 20))
yHat2 = createForeCast(myTree2, testMat[:, 0], modelTreeEval)
print myTree2
print "模型树:", corrcoef(yHat2, testMat[:, 1],rowvar=0)[0, 1]
# 线性回归
ws, X, Y = linearSolve(trainMat)
print ws
m = len(testMat[:, 0])
yHat3 = mat(zeros((m, 1)))
for i in range(shape(testMat)[0]):
yHat3[i] = testMat[i, 0]*ws[1, 0] + ws[0, 0]
print "线性回归:", corrcoef(yHat3, testMat[:, 1],rowvar=0)[0, 1]

View File

@@ -0,0 +1,122 @@
#!/usr/bin/python
# coding:utf8
'''
Created on 2017-03-08
Update on 2017-03-08
Tree-Based Regression Methods Source Code for Machine Learning in Action Ch. 9
@author: Peter/片刻
'''
import regTrees
from Tkinter import *
from numpy import *
import matplotlib
from matplotlib.figure import Figure
from matplotlib.backends.backend_tkagg import FigureCanvasTkAgg
matplotlib.use('TkAgg')
def test_widget_text(root):
mylabel = Label(root, text="helloworld")
# 相当于告诉 布局管理器(Geometry Manager),如果不设定位置,默认在 0行0列的位置
mylabel.grid()
# 最大为误差, 最大子叶节点的数量
def reDraw(tolS, tolN):
# clear the figure
reDraw.f.clf()
reDraw.a = reDraw.f.add_subplot(111)
# 检查复选框是否选中
if chkBtnVar.get():
if tolN < 2:
tolN = 2
myTree = regTrees.createTree(reDraw.rawDat, regTrees.modelLeaf, regTrees.modelErr, (tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat, regTrees.modelTreeEval)
else:
myTree = regTrees.createTree(reDraw.rawDat, ops=(tolS, tolN))
yHat = regTrees.createForeCast(myTree, reDraw.testDat)
# use scatter for data set
reDraw.a.scatter(reDraw.rawDat[:, 0], reDraw.rawDat[:, 1], s=5)
# use plot for yHat
reDraw.a.plot(reDraw.testDat, yHat, linewidth=2.0, c='red')
reDraw.canvas.show()
def getInputs():
try:
tolN = int(tolNentry.get())
except:
tolN = 10
print "enter Integer for tolN"
tolNentry.delete(0, END)
tolNentry.insert(0, '10')
try:
tolS = float(tolSentry.get())
except:
tolS = 1.0
print "enter Float for tolS"
tolSentry.delete(0, END)
tolSentry.insert(0, '1.0')
return tolN, tolS
# 画新的tree
def drawNewTree():
# #get values from Entry boxes
tolN, tolS = getInputs()
reDraw(tolS, tolN)
def main(root):
# 标题
Label(root, text="Plot Place Holder").grid(row=0, columnspan=3)
# 输入栏1, 叶子的数量
Label(root, text="tolN").grid(row=1, column=0)
global tolNentry
tolNentry = Entry(root)
tolNentry.grid(row=1, column=1)
tolNentry.insert(0, '10')
# 输入栏2, 误差量
Label(root, text="tolS").grid(row=2, column=0)
global tolSentry
tolSentry = Entry(root)
tolSentry.grid(row=2, column=1)
# 设置输出值
tolSentry.insert(0,'1.0')
# 设置提交的按钮
Button(root, text="确定", command=drawNewTree).grid(row=1, column=2, rowspan=3)
# 设置复选按钮
global chkBtnVar
chkBtnVar = IntVar()
chkBtn = Checkbutton(root, text="Model Tree", variable = chkBtnVar)
chkBtn.grid(row=3, column=0, columnspan=2)
# 退出按钮
Button(root, text="退出", fg="black", command=quit).grid(row=1, column=2)
# 创建一个画板 canvas
reDraw.f = Figure(figsize=(5, 4), dpi=100)
reDraw.canvas = FigureCanvasTkAgg(reDraw.f, master=root)
reDraw.canvas.show()
reDraw.canvas.get_tk_widget().grid(row=0, columnspan=3)
reDraw.rawDat = mat(regTrees.loadDataSet('testData/RT_sine.txt'))
reDraw.testDat = arange(min(reDraw.rawDat[:, 0]), max(reDraw.rawDat[:, 0]), 0.01)
reDraw(1.0, 10)
if __name__ == "__main__":
# 创建一个事件
root = Tk()
# test_widget_text(root)
main(root)
# 启动事件循环
root.mainloop()