def test_loadDataSet(self):
dataArr, labelArr = adaboost.loadDataSet('train.txt')
print "[dataArr]", dataArr
print "[labelArr]", labelArr
classifierArray = adaboost.adaBoostTrainDS(dataArr, labelArr, 9)
testArr, testLabelArr = adaboost.loadDataSet('test.txt')
prediction10 = adaboost.adaClassify(testArr, classifierArray)
errArr = mat(ones((67, 1)))
print errArr[prediction10 != mat(testLabelArr).T].sum()
def main():
import adaboost
from numpy import mat, ones
datMat, classLabels = adaboost.loadSimpleData()
D = mat(ones((5, 1)) / 5)
bestStump, minError, bestClasEst = adaboost.buildStump(
datMat, classLabels, D)
classifierArr, aggClassEst = adaboost.adaBoostTrainDS(datMat, classLabels, 9)
adaboost.adaClassify([[5, 5], [0, 0]], classifierArr)
def main():
print '---------------------training--------------------'
datArr, labelArr = loadDataSet('horseColicTraining2.txt')
#the last input is the number of classifier
classifierArray, aggClassEst= ab.adaBoostTrainDS(datArr, labelArr, 50)
print '---------------------testing---------------------'
testArr, testLabelArr = loadDataSet('horseColicTest2.txt')
prediction10 = ab.adaClassify(testArr, classifierArray)
errArr = mat(ones((67,1)))
print 'error rate:', errArr[prediction10 != mat(testLabelArr).T].sum()/67
def main():
print '---------------------training--------------------'
datArr, labelArr = loadDataSet('horseColicTraining2.txt')
#the last input is the number of classifier
classifierArray, aggClassEst = ab.adaBoostTrainDS(datArr, labelArr, 50)
print '---------------------testing---------------------'
testArr, testLabelArr = loadDataSet('horseColicTest2.txt')
prediction10 = ab.adaClassify(testArr, classifierArray)
errArr = mat(ones((67, 1)))
print 'error rate:', errArr[prediction10 != mat(testLabelArr).T].sum() / 67
def test():
datMat, classLabels = adaboost.loadSimpleData()
print("dataMat: [%s] classLabels: [%s]" % (datMat, classLabels))
#adaboost.plt(datMat, classLabels)
D = mat(ones((5,1))/5)
bestStump, minError, bestClassEst = adaboost.buildStump(datMat, classLabels, D)
print("bestStump: ", bestStump, " minError:", minError, " bestClasEst:", bestClassEst)
classifierArray, classifierEst = adaboost.adaBoostTrainDS(datMat, classLabels, 9)
print("classifierArray:", classifierArray)
print(adaboost.adaClassify([0,0], classifierArray))
print(adaboost.adaClassify([[5,5],[0,0]], classifierArray))
def testHolic():
datArr,labelArr = adaboost.loadDataSet('horseColicTraining2.txt')
classifierArray, classifierEst = adaboost.adaBoostTrainDS(datArr, labelArr, 10)
testArr, testLabelArr = adaboost.loadDataSet('horseColicTest2.txt')
prediction10 = adaboost.adaClassify(testArr, classifierArray)
print("prediction:", prediction10)
errArr = mat(ones((67,1)))
errCnt = errArr[prediction10 != mat(testLabelArr).T].sum()
print("err count:%d error rate:%.2f" % (errCnt, float(errCnt)/67))
adaboost.plotROC(classifierEst.T, labelArr)
import adaboost
from numpy import *
#datMat, classLabels = adaboost.loadSimpleData()
datMat, classLabels = adaboost.loadDataSet('horseColicTraining2.txt')
classifierArray, aggClassEst = adaboost.adaBoostTrainDS(
datMat, classLabels, 10)
adaboost.plotROC(aggClassEst.T, classLabels)
labelArr[i] = -1
#adaboost只能区分-1和1的标签
# dataArr=dataMat
label = labelArr
skf = StratifiedKFold(n_splits=10)
for train, test in skf.split(dataArr, labelArr):
print("%s %s" % (train, test))
train.tolist()
train_in = dataArr[train]
test_in = dataArr[test]
train_out = label[train]
test_out = label[test]
train_in, train_out = RandomOverSampler().fit_sample(
train_in, train_out) #训练集过采样，平衡样本
classifierArray, aggClassEst = adaboost.adaBoostTrainDS(
train_in, train_out, 200)
prediction_train, prob_train = adaboost.adaClassify(
train_in, classifierArray)
#测试训练集
prediction_test, prob_test = adaboost.adaClassify(test_in, classifierArray)
#测试测试集
tmp_train, fp_train_tmp = adaboost.evaluatemodel(train_out,
prediction_train,
prob_train)
#evaluate_train=np.array(evaluate_train);
evaluate_train.extend(tmp_train)
#训练集结果评估
fp_train.extend(fp_train_tmp)
import adaboost
datmat, classlabel=adaboost.loadSimpData()
from numpy import *
d = mat(ones((5,1))/5)
#print(adaboost.buildStump(datmat,classlabel,d))
#classifier,aggClassEst = adaboost.adaBoostTrainDS(datmat,classlabel,9)
#print(classifier)
#print(aggClassEst)
#print(adaboost.adaClassify([[0,0],[1,1]],classifier))
datarr,labelarr = adaboost.loadDataSet('horseColicTraining2.txt')
classifier,aggClassEst = adaboost.adaBoostTrainDS(datarr,labelarr,40)
testarr,testlabelarr = adaboost.loadDataSet('horseColicTest2.txt')
prediction = adaboost.adaClassify(testarr,classifier)
errarr = mat(ones((67,1)))
print(errarr[prediction != mat(testlabelarr).T].sum())
adaboost.plotROC(aggClassEst.T,labelarr)
import adaboost
from numpy import *
'''
datMat, classLabels= adaboost.loadSimpData()
D = mat(ones((5,1))/5)
adaboost.draw(datMat,classLabels)
weakClassArr = classifyierArray = adaboost.adaBoostTrainDS(datMat, classLabels, 9)
#print('bestStump = ',bestStump)
#print('minError = ',minError)
#print('bestClasEst = ',bestClasEst)
print('weakClassArr = ',weakClassArr)
datToClass = [[5,5],[0,0]]
adaboost.adaClassify(datToClass,weakClassArr)
'''
dataMat, labelMat = adaboost.loadDataSet("horseColicTraining2.txt")
weakClassArr, aggClassEst = adaboost.adaBoostTrainDS(dataMat, labelMat, 10)
testMat, testlabelMat = adaboost.loadDataSet("horseColicTest2.txt")
prediction = adaboost.adaClassify(testMat, weakClassArr)
print("prediction= ", prediction)
errorRate = adaboost.errorRate(testlabelMat, prediction)
print("errorRate= ", errorRate)
adaboost.plotROC(aggClassEst.T, labelMat)
import adaboost
from numpy import *
datArr, labelArr = adaboost.loadDataSet('horseColicTraining2.txt')
#classifierArray = adaboost.adaBoostTrainDS(datArr, labelArr, 10)
#testArr, testLabelArr = adaboost.loadDataSet('horseColicTest2.txt')
#prediction10 = adaboost.adaClassify(testArr, classifierArray)
#errArr = mat(ones((67, 1)))
#print errArr[prediction10!=mat(testLabelArr).T].sum()
classifierArray, aggClassEst = adaboost.adaBoostTrainDS(datArr, labelArr, 10)
adaboost.plotROC(aggClassEst.T, labelArr)
def test_adaboost_train_ds(self):
#print "test_adaboost_train_ds"
dataMat, classLabels = adaboost.loadSimpleData()
classifierArray = adaboost.adaBoostTrainDS(dataMat, classLabels, 9)
import adaboost from numpy import * datMat, classLabels = adaboost.loadSimpData() D = mat(ones((5, 1)) / 5) print adaboost.buildStump(datMat, classLabels, D) classifierArray = adaboost.adaBoostTrainDS(datMat, classLabels, 9) print classifierArray datArr, labelArr = adaboost.loadSimpData() classifierArr = adaboost.adaBoostTrainDS(datArr, labelArr, 30) print adaboost.adaClassify([0, 0], classifierArr) print adaboost.adaClassify([[5, 5], [0, 0]], classifierArr)
Created on Thu Jun 11 12:57:27 2015 @author: LiuLongpo """ import optunity import adaboost import matplotlib.pyplot as plt from numpy import * dataMat,classLabels = adaboost.loadSimpData() #plt.scatter(dataMat[:,0],dataMat[:,1]) # D是样本的权重矩阵 D = mat(ones((5,1))/5) #adaboost.buildStump(dataMat,classLabels,D) print 'data train...' classifierArr = adaboost.adaBoostTrainDS(dataMat,classLabels,30) print 'getClassifier:',classifierArr print 'data predict...' # 学习得到3个分类器，predict时，每一个分类器级联分类得到的预测累加值 # aggClassEst越来越远离0，也就是正越大或负越大，也就是分类结果越来越强 adaboost.adaClassify([[1,0.8],[1.8,2]],classifierArr) # 0,lt,1.3 1,lt,1.0 0,lt,0.9 plt.figure() I = nonzero(classLabels>0)[0] plt.scatter(dataMat[I,0],dataMat[I,1],s=60,c=u'r',marker=u'o') I = nonzero(classLabels<0)[0] plt.scatter(dataMat[I,0],dataMat[I,1],s=60,c=u'b',marker=u'o') plt.plot([1.32,1.32],[0.5,2.5]) plt.plot([0.5,2.5],[1.42,1.42])
import adaboost
import numpy as np
#dataMat ,classlabel = adaboost.loadSimpData()
#print(dataMat)
#D = np.mat(np.ones((5,1)))/5
#print(adaboost.buildStump(dataMat,classlabel,D))
#classifierArray,aggest = adaboost.adaBoostTrainDS(dataMat,classlabel,9)
#print(aggest)
file = open('data.txt', 'r')
datalist = []
classlabel = []
for line in file.readlines():
data = line.split()[:-4]
label = int(line.split()[-1])
datalist.append(list(map(float, data)))
classlabel.append(label)
dataMat = np.mat(datalist)
classlabels = np.mat(classlabel)
classifierArray, aggest = adaboost.adaBoostTrainDS(dataMat, classlabel, 40,
100)
print(classifierArray)
adaboost.plotROC(aggest.T, classlabel)
import adaboost datArr, labelArr = adaboost.loadSimpData() classifierArr = adaboost.adaBoostTrainDS(datArr, labelArr, 30) adaboost.adaClassify([0, 0], classifierArr) adaboost.adaClassify([[5, 5], [0, 0]], classifierArr)
#!usr/bin/env python3 # -*- coding:utf-8 -*- """ #@author:Benny.Chen #@file: main.py #@time: 2020/6/6 16:23 #@email:[email protected] """ import adaboost as ada if __name__ == '__main__': dataArr,classLabel = ada.loadSimpData() ada.adaBoostTrainDS(dataArr,classLabel,10)
@author: laiwei
date: 2017年3月4日
'''
import adaboost
from numpy import *
#datMat, classLabels = adaboost.loadSimpData()
#adaboost.plotData(datMat, classLabels)
datMat, classLabels = adaboost.loadDataSet('horseColicTraining2.txt')
#D = mat(ones((5, 1))/5)
#bestStump,minError,bestClasEst = adaboost.buildStump(datMat, classLabels, D)
#print(bestStump);print(minError);print(bestClasEst)
weakClassArr, aggClassEst = adaboost.adaBoostTrainDS(datMat, classLabels, 37)
#aggClassEst[0,0] = -0.2
#classLabels[0] = -1
#print(weakClassArr);print(aggClassEst)
#print(adaboost.adaClassify([[0,0],[5,5]], weakClassArr))
# 当预测label按大小排序，对应真实label不是先全部-1，再全部+1，而是中间有错乱时，曲线下弯
#adaboost.plotROC(mat(classLabels), classLabels)
adaboost.plotROC(aggClassEst.T, classLabels)
testdatMat, testclassLabels = adaboost.loadDataSet('horseColicTest2.txt')
testResult = adaboost.adaClassify(testdatMat, weakClassArr)
errArr = mat(ones((len(testclassLabels), 1)))
print(errArr[testResult != mat(testclassLabels).T].sum(), "of total",
shape(testclassLabels))
from numpy import *
import numpy as np
import adaboost
D = mat(ones((5,1))/5)
datMat , classLabels = adaboost.loadSimpData()
# print adaboost.buildStump(datMat,classLabels,D)
classifierArray = adaboost.adaBoostTrainDS(datMat, classLabels,9)
# print classifierArray
print adaboost.adaClassify([0,0],classifierArray)
print adaboost.adaClassify([[5,5],[0,0]],classifierArray)
# datArr, labelArr = adaboost.loadDataSet('horseColicTraining2.txt')
# classifierArray = adaboost.adaBoostTrainDS(datArr,labelArr,10)
# print classifierArray
# testArr,testlabelArr = adaboost.loadDataSet('horseColicTest2.txt')
# prediction10 = adaboost.adaClassify(testArr,classifierArray)
# errArr = mat(ones((67,1)))
# e=errArr[prediction10!=mat(testlabelArr).T].sum()
# -*- coding:utf-8 -*-
import adaboost
from numpy import *
myData,myLabels = adaboost.loadSimpData()
'''
print ('myData is ' , myData)
print ('myLabels is' , myLabels)
D = mat(ones((5,1))/5)
print ('D is', D)
myBStump,myMError,myBCE = adaboost.buildStump(myData, myLabels, D)
print ('myBStump is', myBStump)
print ('myMError is', myMError)
print ('myBCE is', myBCE)
'''
classiFierArray,classEst = adaboost.adaBoostTrainDS(myData,myLabels,30)
print ('classiFierArray is ',classiFierArray)
aggClassEst = adaboost.adaClassify([[5,5],[0,0]], classiFierArray)
print ('aggClassEst is ' , aggClassEst)
import adaboost from numpy import * datMat, classLabels = adaboost.loadSimpData() D = mat(ones((5, 1))/5) print adaboost.buildStump(datMat, classLabels, D) classifierArray = adaboost.adaBoostTrainDS(datMat, classLabels, 9) print classifierArray datArr, labelArr = adaboost.loadSimpData() classifierArr = adaboost.adaBoostTrainDS(datArr, labelArr, 30) print adaboost.adaClassify([0, 0], classifierArr) print adaboost.adaClassify([[5, 5], [0, 0]], classifierArr)
import os # homedir= os.getcwd()+'/machinelearninginaction/ch07/' #绝对路径 homedir = '' #相对路径 #7.3 基于单层决策树构建弱分类器 datMat, classLabels = adaboost.loadSimpData() D = mat(ones((5, 1)) / 5) print "datMat:", datMat print "classLabels:", classLabels print "D:", D print ":", adaboost.buildStump(datMat, classLabels, D) #7.4 完整AdaBoost算法的实现 classifierArr = adaboost.adaBoostTrainDS(datMat, classLabels, 9) print "classifierArr:", classifierArr #7.5 测试算法：基于AdaBoost的分类 datMat, classLabels = adaboost.loadSimpData() classifierArr = adaboost.adaBoostTrainDS(datMat, classLabels, 30) print "分类1:", adaboost.adaClassify([0, 0], classifierArr) print "分类2:", adaboost.adaClassify([[5, 5], [0, 0]], classifierArr) #7.6 示例：在一个难数据集上应用AdaBoost datArr, labelArr = adaboost.loadDataSet(homedir + 'horseColicTraining2.txt') print "datArr:", datArr print "labelArr:", labelArr classifierArray = adaboost.adaBoostTrainDS(datArr, labelArr, 500) testArr, testLabelArr = adaboost.loadDataSet(homedir + 'horseColicTest2.txt') prediction10 = adaboost.adaClassify(testArr, classifierArray)
def test_ada_classify(self):
print "test_ada_classify"
dataMat, classLabels = adaboost.loadSimpleData()
classifierArr = adaboost.adaBoostTrainDS(dataMat, classLabels, 9)
Created on Thu Jun 11 12:57:27 2015 @author: LiuLongpo """ import optunity import adaboost import matplotlib.pyplot as plt from numpy import * dataMat, classLabels = adaboost.loadSimpData() #plt.scatter(dataMat[:,0],dataMat[:,1]) # D是样本的权重矩阵 D = mat(ones((5, 1)) / 5) #adaboost.buildStump(dataMat,classLabels,D) print 'data train...' classifierArr = adaboost.adaBoostTrainDS(dataMat, classLabels, 30) print 'getClassifier:', classifierArr print 'data predict...' # 学习得到3个分类器，predict时，每一个分类器级联分类得到的预测累加值 # aggClassEst越来越远离0，也就是正越大或负越大，也就是分类结果越来越强 adaboost.adaClassify([[1, 0.8], [1.8, 2]], classifierArr) # 0,lt,1.3 1,lt,1.0 0,lt,0.9 plt.figure() I = nonzero(classLabels > 0)[0] plt.scatter(dataMat[I, 0], dataMat[I, 1], s=60, c=u'r', marker=u'o') I = nonzero(classLabels < 0)[0] plt.scatter(dataMat[I, 0], dataMat[I, 1], s=60, c=u'b', marker=u'o') plt.plot([1.32, 1.32], [0.5, 2.5]) plt.plot([0.5, 2.5], [1.42, 1.42]) plt.plot([0.97, 0.97], [0.5, 2.5])
# print(bestStump)
# print(minError)
# print(bestClasEst)
# classifierArr = adaboost.adaBoostTrainDS(dataMat, labelMat, 40)
# print(classifierArr)
# result = adaboost.adaClassify([[1, 5], [2, 4]], classifierArr)
# print(result)
dataMat, labelMat = adaboost.loadDataSet("horseColicTraining2.txt")
classifierArr, aggClassEst = adaboost.adaBoostTrainDS(dataMat, labelMat, 50)
print(classifierArr)
print(aggClassEst.T.shape)
adaboost.plotROC(aggClassEst.T, labelMat)
# dataMat, labelMat = adaboost.loadDataSet("horseColicTest2.txt")
# pred = adaboost.adaClassify(dataMat, classifierArr)
# print(np.mat(labelMat).shape)
# print(np.mat(labelMat).T.shape)
# print(len(dataMat))
# errorMat = np.mat(np.ones((len(dataMat), 1)))
# rate = (errorMat[pred != np.mat(labelMat).T].sum() / len(dataMat))
def main():
datArr, labelArr = hc.loadDataSet('horseColicTraining2.txt')
classiferArray, aggClassEst = ab.adaBoostTrainDS(datArr, labelArr, 10)
plotRoc(aggClassEst.T, labelArr)
lines = list(fr.readlines())
linesLen = len(lines)
print(linesLen)
numFeat = len(lines[0].strip().split('\t'))
dataMat = []
labelMat = []
for i in range(linesLen):
lineArr = []
curLine = lines[i].strip().split('\t')
for j in range(numFeat - 1):
lineArr.append(float(curLine[j]))
dataMat.append(lineArr)
labelMat.append(float(curLine[-1]))
return dataMat, labelMat
if __name__ == '__main__':
import adaboost
import adaboostDemo
datMat, labelMat = adaboostDemo.loadDataSet(
'C:/Users/v_wangdehong/PycharmProjects/MachineLearning_V/6.AdaBoost/input_data/horseColicTraining2.txt'
)
classifierArray = adaboost.adaBoostTrainDS(datMat, labelMat, 10)
testArr, testLabelArr = adaboostDemo.loadDataSet(
'C:/Users/v_wangdehong/PycharmProjects/MachineLearning_V/6.AdaBoost/input_data/horseColicTest2.txt'
)
prediction10 = adaboost.adaClassify(testArr, classifierArray)
errArr = mat(ones((67, 1)))
print(shape(mat(testLabelArr)), shape(prediction10))
print(errArr[prediction10 != mat(testLabelArr).T].sum())
#coding:utf-8 import adaboost from numpy import * datMat, classLabels = adaboost.loadSimpData() #print datMat,classLabels D = mat(ones((5, 1)) / 5) #print adaboost.buildStump(datMat,classLabels,D) classifierArray = adaboost.adaBoostTrainDS(datMat, classLabels, 9) print classifierArray
import adaboost
datArr, labelArr = adaboost.loadDataSet('horseColicTraining2.txt')
classifierArray, aggClassEst = adaboost.adaBoostTrainDS(datArr, labelArr, 10)
adaboost.plotROC(aggClassEst.T, labelArr)
# -*- coding: utf-8 -*-
import adaboost
from numpy import *
da, la = adaboost.loadDataSet('horseColicTraining.txt')
ca = adaboost.adaBoostTrainDS(da, la, 10)
tda, tla = adaboost.loadDataSet('horseColicTest.txt')
prediction10 = adaboost.adaClassify(tda, ca)
errArr = mat(ones((67, 1)))
errArr[prediction10 != mat(tla).T].sum()
reload(adaboost)
da, la = adaboost.loadDataSet('horseColicTraining.txt')
ca, ace = adaboost.adaBoostTrainDS(da, la, 40)
adaboost.plotROC(ace.T, la)
# -*- coding: utf-8 -*-
import adaboost
# dataMat,classLabels=stumpTree.loadData()
# stumpTree.adaBoostTrainDS(dataMat,classLabels)
dataMat, classLabels = adaboost.file2Matrix(
'/home/lvsolo/python/adaBoosting/horseColicTraining2.txt')
weakClassify = adaboost.adaBoostTrainDS(dataMat, classLabels, 50)
dataTest, testLabels = adaboost.file2Matrix(
'/home/lvsolo/python/adaBoosting/horseColicTest2.txt')
adaboost.adaBoostTest(dataTest, testLabels, weakClassify)
#!/usr/bin/env python
# encoding=utf-8
import logging
import numpy as np
import matplotlib.pyplot as plt
import adaboost
logging.basicConfig(
level=logging.DEBUG,
# level=logging.INFO,
format='[%(levelname)s %(module)s line:%(lineno)d] %(message)s',
)
TRACE = logging.DEBUG - 1
datArr, labelArr = adaboost.loadDataSet('horseColicTraining2.txt')
weekClassArr, aggClassEst = adaboost.adaBoostTrainDS(datArr, labelArr, 20)
testDatArr, testLabelArr = adaboost.loadDataSet('horseColicTest2.txt')
prediction = adaboost.addClassify(testDatArr, weekClassArr)
errArr = np.mat(np.ones((67, 1)))
errArr[prediction != np.mat(testLabelArr).T]
errArr[prediction != np.mat(testLabelArr).T].sum() / 67
def AdaFeature(train_in, train_out, test_in):
classifierArray, aggClassEst = adaboost.adaBoostTrainDS(
train_in, train_out, 200)
test_predict, prob_test = adaboost.adaClassify(test_in, classifierArray)
# 测试测试集
return test_predict
label_1 = train_set.ix[:int(0.3 * len(train_set)), :]
label_0 = train_set.ix[-int(0.3 * len(train_set)):, :]
label_1['train_ret'] = 1
label_0['train_ret'] = 0
feature_one = pd.concat([label_1,
label_0]).iloc[:, 2:-2].values.tolist()
for i in range(len(feature_one)):
features.append(feature_one[i])
label_one = pd.concat([label_1,
label_0])['train_ret'].values.tolist()
for i in range(len(label_one)):
labels.append(label_one[i])
# train classifier
classifierArr = adaboost.adaBoostTrainDS(mat(features), labels, 30)
old_trading_day = trading_date_open[
trading_date_open['calendarDate'] <
trading_day]['calendarDate'].values[-1]
predict_data = pd.read_csv('data/factor_old' + old_trading_day +
'.csv')
predict_data = predict_data.dropna()
predict_data.iloc[:, 3:] = predict_data.iloc[:, 3:].rank(
method='first').apply(lambda x: x / len(predict_data))
x = predict_data.iloc[:, 3:].values.tolist()
# predict
y = adaboost.adaClassify(x, classifierArr)
predict_label = predict_data.loc[:, ['secID', 'tradeDate']]
label_1=train_set.ix[:int(0.3*len(train_set)),:]
label_0=train_set.ix[-int(0.3*len(train_set)):,:]
label_1['train_ret']=1
label_0['train_ret']=0
feature_one=pd.concat([label_1,label_0]).iloc[:,2:-2].values.tolist()
for i in range(len(feature_one)):
features.append(feature_one[i])
label_one=pd.concat([label_1,label_0])['train_ret'].values.tolist()
for i in range(len(label_one)):
labels.append(label_one[i])
# train classifier
classifierArr = adaboost.adaBoostTrainDS(mat(features), labels, 30)
old_trading_day=trading_date_open[trading_date_open['calendarDate'] < trading_day]['calendarDate'].values[-1]
predict_data = pd.read_csv('data/factor_old'+old_trading_day+'.csv')
predict_data=predict_data.dropna()
predict_data.iloc[:,3:]=predict_data.iloc[:,3:].rank(method='first').apply(lambda x : x/len(predict_data))
x=predict_data.iloc[:,3:].values.tolist()
# predict
y=adaboost.adaClassify(x,classifierArr)
predict_label=predict_data.loc[:,['secID','tradeDate']]
predict_label['pro']=y
predict_label['label']=sign(y)
buy=predict_label[predict_label['label'] == 1]
buy=buy.sort(columns=['pro'],ascending=False)[:45]
# -*- coding:utf-8 -*-
import adaboost
from numpy import *
import time
time_start = time.time()
datArr,labelArr = adaboost.loadDataSet('horseColicTraining2.txt')
classifierArr,aggBestEst = adaboost.adaBoostTrainDS(datArr, labelArr, 30)
testArr,testLabelArr = adaboost.loadDataSet('horseColicTest2.txt')
prediction10 = adaboost.adaClassify(testArr, classifierArr)
m = shape(testArr)[0]
errArr = mat(ones((m,1)))
errCount = errArr[prediction10 != mat(testLabelArr).T].sum()
print ('errCount is ' , errCount , 'error rate is ',errCount/m)
time_end = time.time()
print ("the program spend %d s" % (time_end - time_start))
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
'7.6'
__author__ = 'lxp'
import adaboost
import numpy as np
datArr, labelArr = adaboost.loadDataSet('horseColicTraining2.txt')
classifierArray = adaboost.adaBoostTrainDS(datArr, labelArr, 10)
testArr, testLabelArr = adaboost.loadDataSet('horseColicTest2.txt')
prediction10 = adaboost.adaClassify(testArr, classifierArray)
errArr = np.mat(np.ones((67, 1)))
print(errArr[prediction10 != np.mat(testLabelArr).T].sum())
def main():
datArr, labelArr = hc.loadDataSet('horseColicTraining2.txt')
classiferArray, aggClassEst = ab.adaBoostTrainDS(datArr, labelArr, 10)
plotRoc(aggClassEst.T, labelArr)
