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 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 cross_validation(iter_):
data_num, data_size = train_data_.shape
fold_size = int(data_num / N_fold)
residual = data_num - fold_size * N_fold
min_error = math.inf
train_data = np.zeros((data_num - fold_size, data_size))
train_label = np.zeros(data_num - fold_size)
test_data = np.zeros((fold_size, data_size))
test_label = np.zeros(fold_size)
total_error = 0
for i in range(0, N_fold):
if i == 0:
train_data[:, :] = train_data_[fold_size:, :]
train_label[:] = train_label_[fold_size:]
test_data[:, :] = train_data_[0:fold_size, :]
test_label[:] = train_label_[0:fold_size]
else:
train_data[:, :] = np.append(train_data_[0:i * fold_size, :],
train_data_[(i + 1) * fold_size:, :],
axis=0)
train_label[:] = np.append(train_label_[0:i * fold_size],
train_label_[(i + 1) * fold_size:])
test_data[:, :] = train_data_[i * fold_size:(i + 1) * fold_size, :]
test_label[:] = train_label_[i * fold_size:(i + 1) * fold_size]
best = adaboost.Adaboost(train_data, train_label, 'validation', iter_)
error = adaboost.adaClassify(test_data, test_label, 'validation', best)
total_error = total_error + error
CV_error = total_error / N_fold
print('[Result] Cross-Validation Error of T =', iter_, 'is', CV_error)
return iter_, CV_error
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():
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 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
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)
from adaboost import adaboost_trian,adaClassify
from load_data import read_data
if __name__ =='__main__':
data,label = read_data()
classifier_array = adaboost_trian(data,label,9)
# print(classifier_array)
re = adaClassify([[5,5],[0,0]],classifier_array)
print(re)
# -*- coding: utf-8 -*-
import adaboost
from numpy import *
dataArr, labelArr = adaboost.loadDataSet('horseColicTraining2.txt')
classfierArray = adaboost.adaBoostTrainDS(dataArr, labelArr, 10)
testArr, testlabelArr = adaboost.loadDataSet('horseColicTest2.txt')
prediction10 = adaboost.adaClassify(testArr, testlabelArr)
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)
# This is a sample Python script.
# Press Shift+F10 to execute it or replace it with your code.
# Press Double Shift to search everywhere for classes, files, tool windows, actions, and settings.
import adaboost
# Press the green button in the gutter to run the script.
if __name__ == '__main__':
datMat, classLabels = adaboost.loadSimpData()
classifierArray, aggClassEst = adaboost.adaBoostTrainDS(
datMat, classLabels, 30)
# adaboost.adaClassify([0, 0], classifierArray) #一个数据
result = adaboost.adaClassify([[5, 5], [0, 0]], classifierArray) # 多个数据
print(result)
# 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)
tmp_test, fp_test_tmp = adaboost.evaluatemodel(test_out, prediction_test,
prob_test)
evaluate_test.extend(tmp_test)
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)
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) errArr = mat(ones((67, 1))) errorNum = errArr[prediction10 != mat(testLabelArr).T].sum() errorrate = errorNum / 67 print "prediction10:", prediction10 print "errArr:", errArr print "errorrate:", errorrate
best_T)
out_hypothesis = []
for i in range(best_T):
out_hypothesis.append([
best_hypothesis[i]['iter'], best_hypothesis[i]['dim'],
best_hypothesis[i]['thresh'], best_hypothesis[i]['inequal'],
best_hypothesis[i]['alpha']
])
with open(str(N_fold) + '_fold_output_AdaBoost_hypothesis_header.csv',
'w',
newline='') as f:
w = csv.writer(f)
w.writerow([
'iteration_index', 'attribute_index', 'threshold', 'direction',
'boosting_parameter'
])
w.writerows(out_hypothesis)
train_accu, _ = adaboost.adaClassify(train_data_, train_label_, 'testing',
best_hypothesis)
test_accu, predict_output = adaboost.adaClassify(test_data, test_label,
'testing', best_hypothesis)
predict_output = predict_output.tolist()
with open(str(N_fold) + '_fold_predict_output', 'w', newline='') as f:
w = csv.writer(f, delimiter=',')
w.writerow(predict_output)
print('Training Accuracy =', train_accu, '%')
print('Testing Accuracy =', test_accu, '%')
#!/usr/bin/python from numpy import * import adaboost datMat, classLabels = adaboost.loadDataSet() #D = matrix(ones((5,1))/5) #adaboost.buildStump(datMat, classLabels, D) classifierArr = adaboost.adaBoostTrainDS(datMat, classLabels,9) adaboost.adaClassify([0,0],classifierArr)
for i in range(len(classifierArr)):
classEst = stumpClassify(
dataMatrix, classifierArr[i]['dim'], classifierArr[i]['thresh'],
classifierArr[i]['ineq']) #call stump classify
aggClassEst += classifierArr[i]['alpha'] * classEst
print(aggClassEst)
return sign(aggClassEst)
if __name__ == "__main__":
import numpy as np
import adaboost
dataMat, classLabels = loadSimpData()
print(dataMat, "\n", classLabels)
D = np.mat((np.ones((5, 1))) / 5)
#print(D)
print(adaboost.buildStump(dataMat, classLabels, D))
classifierArray = adaboost.adaBoostTrainDS(dataMat, classLabels, 9)
print("\nclassifierArray:\n", classifierArray)
print("\nadaboost.adaClassify([0, 0]:")
print(adaboost.adaClassify([0, 0], classifierArray))
print("\nadaboost.adaClassify([[5,5],[0,0]]:")
print(adaboost.adaClassify([[5, 5], [0, 0]], classifierArray))
datArr, labelArr = adaboost.loadDataSet('horseColicTraining2.txt')
classifierArray = adaboost.adaBoostTrainDS(datArr, labelArr, 10)
print(classifierArray)
@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))
# encoding=utf-8 import adaboost from numpy import * datMat, classLabels = adaboost.loadSimData() #print datMat #print classLabels D = mat(ones((5, 1)) / 5) bestStump, minError, bestClasEst = adaboost.buildStump(datMat, classLabels, D) #print bestStump #print minError #print bestClasEst classifierArray = adaboost.adaBoostTrainDS(datMat, classLabels, 30) adaboost.adaClassify([0, 0], classifierArray)
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")
classifyierArray = adaboost.adaBoostTrainDS(dataMat, labelMat, 10)
testMat, testlabelMat = adaboost.loadDataSet("horseColicTest2.txt")
prediction = adaboost.adaClassify(testMat, classifyierArray)
print("prediction= ", prediction)
errorRate = adaboost.errorRate(testlabelMat, prediction)
print("errorRate= ", errorRate)
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
# -*- 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)
# 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]
buy_list_one=buy['secID'].values.tolist()
buy_list_all.append(buy_list_one)
for i in range(len(buy_list_all)):
buylist_one=buy_list_all[i]
if trading_day < '2015-12-31':
next_trading_day = monthend_day[monthend_day['calendarDate']>trading_day]['calendarDate'].values[0]
buy_price_one = DataAPI.MktEqudAdjGet(tradeDate=trading_day,secID=buylist_one,field=["tradeDate", "secID", "ticker", "closePrice","isOpen"],pandas="1")
#!/usr/bin/env python
#-*- coding:utf-8 -*-
import adaboost
from numpy import *
#dataMat,classLabels=adaboost.loadSimData()
# D=mat(ones((5,1))/5)
# print D
#
# bestStump,minError,bestClasEst=adaboost.buildStump(dataMat,classLabels,D)
# print bestStump
# classifierArray=adaboost.adaBoostTrainDS(dataMat,classLabels,30)
# print adaboost.adaClassify([[5,5],[0,0]],classifierArray)
dataArr,labelArr=adaboost.loadDataSet('./dataSet/horseColicTraining2.txt')
classifierArray,aggClassEst=adaboost.adaBoostTrainDS(dataArr,labelArr,10)
adaboost.plotROC(aggClassEst.T,labelArr)
testArr,testLabelArr=adaboost.loadDataSet('./dataSet/horseColicTest2.txt')
prediction10=adaboost.adaClassify(testArr,classifierArray)
errArr=mat(ones((67,1)))
print errArr[prediction10!=mat(testLabelArr).T].sum()
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]) ''' 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]
#adaboost只能区分-1和1的标签
for ii in range(len(labelBrr)):
if labelBrr[ii] == 0:
labelBrr[ii] = -1
#adaboost只能区分-1和1的标签
train_in = dataArr.tolist()
train_out = labelArr.tolist()
test_in = dataBrr.tolist()
test_out = labelBrr
classifierArray, aggClassEst = adaboost.adaBoostTrainDS(
train_in, train_out, 50)
# prediction_train=adaboost.adaClassify(train_in,classifierArray);#测试训练集
prob = adaboost.adaClassify(test_in, classifierArray)
#测试测试集
y_pred = sign(prob)
score.append(prob)
label.append(y_pred)
# tmp_test=adaboost.evaluatemodel(test_out,y_pred);
# evaluate_test.extend(tmp_test);
# evaluate_test=np.array(evaluate_test);
#混淆矩阵参数
tn, fp, fn, tp = confusion_matrix(test_out, y_pred).ravel()
TPR = tp / (tp + fn)
SPC = tn / (fp + tn)
PPV = tp / (tp + fp)
NPV = tn / (tn + fn)
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)
#设置ROI区域
cv2.rectangle(frame,(int(3*frame.shape[1]/8),int(3*frame.shape[0]/8)),(int(5*frame.shape[1]/8),int(5*frame.shape[0]/8)),[0,0,255])
cv2.imshow('frame',frame)
if (cv2.waitKey(1) == 27):
capture.release()
break
cv2.destroyAllWindows()
#截取ROI部分
img = frame[int(3*frame.shape[0]/8)+2:int(5*frame.shape[0]/8)-1,int(3*frame.shape[1]/8)+2:int(5*frame.shape[1]/8)-1,:].copy()
#提取包围数字的最小ROI,转化为32*32大小，并存入一个向量之中
roi = cv.findROI(img)
roi32 = cv.roiTo32(roi)
vec1024 = cv.roi2Vect(roi32)
#开始分类
print "Start finding..."
predict = adaboost.adaClassify(vec1024,weakClassArr)
if sign(predict) == sign(-1):
print "识别结果：","0"
else:
print "识别结果：","非0"
#显示32*32图像，并等待循环
cv2.imshow('roi',roi32)
char = cv2.waitKey()
cv2.destroyAllWindows()
if char == 27 :break
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]) ''' plt.figure() I = nonzero(classLabels>0)[0]
# -*- 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)
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]
buy_list_one = buy['secID'].values.tolist()
buy_list_all.append(buy_list_one)
for i in range(len(buy_list_all)):
buylist_one = buy_list_all[i]
if trading_day < '2015-12-31':
next_trading_day = monthend_day[
monthend_day['calendarDate'] >
trading_day]['calendarDate'].values[0]
buy_price_one = DataAPI.MktEqudAdjGet(tradeDate=trading_day,
#!/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())
datArr,labelArr=adaboost.loadDataSet('horseColicTraining2.txt')
classifierArray,aggClassEst=adaboost.adaBoostTrainDS(datArr,labelArr,40)
#print(classifierArray)
#print(aggClassEst[0:10])
#print(shape(aggClassEst.T))
#sortedIndicies = aggClassEst.T.argsort()
#print(shape(sortedIndicies))
#print(sortedIndicies[0,:10])
#print(sortedIndicies[0])
#print(len(classifierArray))
#adaboost.plotROC(aggClassEst.T,labelArr)
##利用测试集作检测
datatest,labeltest=adaboost.loadDataSet('horseColicTest2.txt')
pre=adaboost.adaClassify(datatest,classifierArray)
s=0
wrong=0
for i in range(len(pre)):
s+=1
if pre[i]!=labeltest[i]:
wrong+=1
print(wrong/s)
