sklearn实战-乳腺癌细胞数据挖掘(博客主亲自录制视频教程)

https://study.163.com/course/introduction.htm?courseId=1005269003&utm_campaign=commission&utm_source=cp-400000000398149&utm_medium=share

医药统计项目联系:QQ231469242

#mental
group1=[2,2,3,4,4,5,3,4,4,4]
#physical
group2=[4,4,3,5,4,1,1,2,3,3]
#medical
group3=[1,2,2,2,3,2,3,1,3,1]

多重检验结果和贾俊平的LSD结果不一样,经过T配对试验,多重检验和T配对试验一致,LSD对小样本可能不准确

# -*- coding: utf-8 -*-# Import standard packages
import numpy as np
import matplotlib.pyplot as plt
from scipy import stats
import pandas as pd
import os
# additional packages
import sys
sys.path.append(os.path.join('..', '..', 'Utilities'))try:
# Import formatting commands if directory "Utilities" is availablefrom ISP_mystyle import showData except ImportError:
# Ensure correct performance otherwisedef showData(*options):plt.show()return# Other required packages
from statsmodels.stats.multicomp import (pairwise_tukeyhsd,MultiComparison)
from statsmodels.formula.api import ols
from statsmodels.stats.anova import anova_lm
from statsmodels.stats.libqsturng import psturngdef setData():''' Set up the data, as a structured array. '''# The first and last field are 32-bit intergers; the second field is an# 8-byte string. Note that here we can also give names to the individual# fields!data = np.rec.array([(  1,   'mental',  2 ),(  2,   'mental',  2 ),(  3,   'mental',  3 ),(  4,   'mental',  4 ),(  5,   'mental',  4 ),(  6,   'mental',  5 ),(  7,   'mental',  3 ),(  8,   'mental',  4 ),(  9,   'mental',  4 ),( 10,   'mental',  4 ),( 11, 'physical',  4 ),( 12, 'physical',  4 ),( 13, 'physical',  3 ),( 14, 'physical',  5 ),( 15, 'physical',  4 ),( 16, 'physical',  1 ),( 17, 'physical',  1 ),( 18, 'physical',  2 ),( 19, 'physical',  3 ),( 20, 'physical',  3 ),( 21,  'medical',  1 ),( 22,  'medical',  2 ),( 23,  'medical',  2 ),( 24,  'medical',  2 ),( 25,  'medical',  3 ),( 26,  'medical',  2 ),( 27,  'medical',  3 ),( 28,  'medical',  1 ),( 29,  'medical',  3 ),( 30,  'medical',  1 )], dtype=[('idx', '<i4'),('Treatment', '|S8'),('StressReduction', '<i4')])return datadef doAnova(data):'''one-way ANOVA'''df = pd.DataFrame(data)model = ols('StressReduction ~ C(Treatment)',df).fit()anovaResults =  anova_lm(model)print(anovaResults)if anovaResults['PR(>F)'][0] < 0.05:print('One of the groups is different.')def doTukey(data, multiComp):    '''Do a pairwise comparison, and show the confidence intervals'''print((multiComp.tukeyhsd().summary()))# Calculate the p-values:res2 = pairwise_tukeyhsd(data['StressReduction'], data['Treatment'])df = pd.DataFrame(data)numData = len(df)numTreatments = len(df.Treatment.unique())dof = numData - numTreatments# Show the group namesprint((multiComp.groupsunique))# Generate a print -------------------# Get the dataxvals = np.arange(3)res2 = pairwise_tukeyhsd(data['StressReduction'], data['Treatment'])errors = np.ravel(np.diff(res2.confint)/2)# Plot themplt.plot(xvals, res2.meandiffs, 'o')plt.errorbar(xvals, res2.meandiffs, yerr=errors, fmt='o')# Put on labelspair_labels = multiComp.groupsunique[np.column_stack(res2._multicomp.pairindices)]plt.xticks(xvals, pair_labels)# Format the plotxlim = -0.5, 2.5plt.hlines(0, *xlim)plt.xlim(*xlim)plt.title('Multiple Comparison of Means - Tukey HSD, FWER=0.05' +'\n Pairwise Mean Differences')          # Save to outfile, and show the dataoutFile = 'multComp.png'showData(outFile)def Holm_Bonferroni(multiComp):''' Instead of the Tukey's test, we can do pairwise t-test '''# First, with the "Holm" correctionrtp = multiComp.allpairtest(stats.ttest_rel, method='Holm')print((rtp[0]))# and then with the Bonferroni correctionprint((multiComp.allpairtest(stats.ttest_rel, method='b')[0]))# Any value, for testing the program for correct executioncheckVal = rtp[1][0][0,0]return checkValdef main():# Get the datadata = setData()# Do a one-way ANOVAdoAnova(data)#Then, do the multiple testingmultiComp = MultiComparison(data['StressReduction'], data['Treatment'])doTukey(data, multiComp)    # Tukey's HSD testcheckVal = Holm_Bonferroni(multiComp)  # Alternatives to Tukey's HSD testreturn checkVal     # this is only for regression testing of the programif __name__ == '__main__':main()

多重检验结果和贾俊平的LSD结果不一样,经过T配对试验,多重检验和T配对试验一致,LSD对小样本可能不准确

# -*- coding: utf-8 -*-import scipy,math
from scipy.stats import f
import numpy as np
import matplotlib.pyplot as plt
import scipy.stats as stats
# additional packages
from statsmodels.stats.diagnostic import lillifors
#多重比较
from statsmodels.sandbox.stats.multicomp import multipletests
#用于排列组合
import itertools
#独立T检验
from scipy.stats import ttest_ind
#配对T检验
from scipy.stats import ttest_rel #mental
group1=[2,2,3,4,4,5,3,4,4,4]
#physical
group2=[4,4,3,5,4,1,1,2,3,3]
#medical
group3=[1,2,2,2,3,2,3,1,3,1]list_groups=[group1,group2,group3]
list_total=group1+group2+group3
a=0.05#one within group error,also know as random error
def SE(group):se=0mean1=np.mean(group)for i in group:error=i-mean1se+=error**2return se'''
>>> SE(group1)
22.0
>>> SE(group2)
18.0
>>> SE(group3)
14.0
'''
#sum of squares within group error,also know as random error
def SSE(list_groups): sse=0for group in list_groups:se=SE(group)sse+=sereturn sse#误差总平方和
def SST(list_total):sst=0mean1=np.mean(list_total)for i in list_total:error=i-mean1sst+=error**2return sst#SSA,between-group sum of squares 组间平方和,公式1:ssa=sst-sse
def SSA(list_groups,list_total):sse=SSE(list_groups)sst=SST(list_total)ssa=sst-ssereturn ssa#SSA,between-group sum of squares 组间平方和
def SSA1(list_groups,list_total):mean_total=np.mean(list_total)ssa=0for group in list_groups:group_mean=np.mean(group)distance=(mean_total-group_mean)**2ssa+=distancessa=ssa*5return ssa       #处理效应均方
def MSA(list_groups,list_total):ssa=SSA(list_groups,list_total)msa=ssa/(len(list_groups)-1)*1.0return msa# 误差均方
def MSE(list_groups,list_total):sse=SSE(list_groups)mse=sse/(len(list_total)-1*len(list_groups))*1.0 return mse             #F score
def F(list_groups,list_total):msa=MSA(list_groups,list_total)mse=MSE(list_groups,list_total)ratio=msa/mse*1.0return ratio
'''
>>> F(list_groups,list_total)
22.592592592592595
'''#LSD检验有问题,需要核对,不如配对T检验准确
#LSD(least significant difference)最小显著差异
def LSD(list_groups,list_total,sample1,sample2):mean1=np.mean(sample1)mean2=np.mean(sample2)distance=abs(mean1-mean2)print"distance:",distance#t检验的自由度df=len(list_total)-1*len(list_groups)mse=MSE(list_groups,list_total)print"MSE:",mset_value=stats.t(df).isf(a/2)print"t value:",t_valuelsd=t_value*math.sqrt(mse*(1.0/len(sample1)+1.0/len(sample2)))print "LSD:",lsdif distance<lsd:print"no significant difference between:",sample1,sample2else:print"there is significant difference between:",sample1,sample2#正态分布测试
def check_normality(testData):#20<样本数<50用normal test算法检验正态分布性if 20<len(testData) <50:p_value= stats.normaltest(testData)[1]if p_value<0.05:print"use normaltest"print "data are not normal distributed"return  Falseelse:print"use normaltest"print "data are normal distributed"return True#样本数小于50用Shapiro-Wilk算法检验正态分布性if len(testData) <50:p_value= stats.shapiro(testData)[1]if p_value<0.05:print "use shapiro:"print "data are not normal distributed"return  Falseelse:print "use shapiro:"print "data are normal distributed"return Trueif 300>=len(testData) >=50:p_value= lillifors(testData)[1]if p_value<0.05:print "use lillifors:"print "data are not normal distributed"return  Falseelse:print "use lillifors:"print "data are normal distributed"return Trueif len(testData) >300: p_value= stats.kstest(testData,'norm')[1]if p_value<0.05:print "use kstest:"print "data are not normal distributed"return  Falseelse:print "use kstest:"print "data are normal distributed"return True#对所有样本组进行正态性检验
def NormalTest(list_groups):for group in list_groups:#正态性检验status=check_normality(group1)if status==False :return False#排列组合函数
def Combination(list_groups):combination= []for i in range(1,len(list_groups)+1):iter = itertools.combinations(list_groups,i)combination.append(list(iter))#需要排除第一个和最后一个return combination[1:-1][0]
'''
Out[57]:
[[([2, 3, 7, 2, 6], [10, 8, 7, 5, 10]),([2, 3, 7, 2, 6], [10, 13, 14, 13, 15]),([10, 8, 7, 5, 10], [10, 13, 14, 13, 15])]]
'''       #多重比较
def Multiple_test(list_groups):combination=Combination(list_groups)for pair in combination:LSD(list_groups,list_total,pair[0],pair[1])#discriptive statistcs
print "discriptive statistcs----------------------------------------------"
print "group1 mean",np.mean(group1)
print "group2 mean",np.mean(group2)
print "group3 mean",np.mean(group3)  #对所有样本组进行正态性检验
print"M=Normality test:-----------------------------------"
NormalTest(list_groups)#方差齐性检测
print"levene test:-----------------------------------"
leveneResult=scipy.stats.levene(group1,group2,group3)
leveneScore=leveneResult[0]
p_levene=leveneResult[1]
if p_levene<0.05:print"levene test is not fit,be attention!"
else:print"levene test is ok"
'''
H0成立,三组数据方差无显著差异
Out[9]: LeveneResult(statistic=0.24561403508771934, pvalue=0.7860617221429711)
'''print "result--------------------------------------------------"
f_score=F(list_groups,list_total)
print"F score:",f_score
#sf 为生存函数survival function
#组数自由度
df1=len(list_groups)-1
#所有样本的自由度
df2=len(list_total)-1*len(list_groups)
probability=f.sf(f_score,df1,df2)
print"p value:",probability
'''
Out[28]: 8.5385924542746692e-05
'''
if probability<0.05:print"there is significance,H1 win"
else:print"there is no significance,H0 win"#多重比较
print"multiple test----------------------------------------------"
print"Multiple test",Multiple_test
Multiple_test(list_groups)

贾俊平书里的例子,综合多重检验和LSD方法结果一致

#居民区
group1=[265,310,220,290,350,300,445,480,500,430,428,530]
#商业区
group2=[410,305,450,380,310,390,590,480,510,470,415,390]
#写字楼
group3=[180,290,330,220,170,256,290,283,260,246,275,320]

# -*- coding: utf-8 -*-# Import standard packages
import numpy as np
import matplotlib.pyplot as plt
from scipy import stats
import pandas as pd
import os
# additional packages
import sys
sys.path.append(os.path.join('..', '..', 'Utilities'))try:
# Import formatting commands if directory "Utilities" is availablefrom ISP_mystyle import showData except ImportError:
# Ensure correct performance otherwisedef showData(*options):plt.show()return# Other required packages
from statsmodels.stats.multicomp import (pairwise_tukeyhsd,MultiComparison)
from statsmodels.formula.api import ols
from statsmodels.stats.anova import anova_lm
from statsmodels.stats.libqsturng import psturngdef setData():''' Set up the data, as a structured array. '''# The first and last field are 32-bit intergers; the second field is an# 8-byte string. Note that here we can also give names to the individual# fields!data = np.rec.array([(  1,   'resident', 265 ),(  2,   'resident', 310 ),(  3,   'resident', 220 ),(  4,   'resident', 290 ),(  5,   'resident', 350 ),(  6,   'resident', 300 ),(  7,   'resident', 445 ),(  8,   'resident', 480 ),(  9,   'resident', 500 ),( 10,   'resident', 430),( 11,   'resident', 428),( 12,   'resident', 530 ),( 13, 'commercial', 410 ),( 14, 'commercial', 305 ),( 15, 'commercial', 450 ),( 16, 'commercial', 380 ),( 17, 'commercial', 310 ),( 18, 'commercial', 390 ),( 19, 'commercial', 590 ),( 20, 'commercial', 480 ),( 21, 'commercial', 510 ),( 22, 'commercial', 470 ),( 23, 'commercial', 415 ),( 24, 'commercial', 390 ),( 25, 'officeBuilding', 180 ),( 26, 'officeBuilding', 290 ),( 27, 'officeBuilding', 330 ),( 28, 'officeBuilding', 220 ),( 29, 'officeBuilding', 170),( 30, 'officeBuilding', 256),( 31, 'officeBuilding', 290 ),( 32, 'officeBuilding', 283 ),( 33, 'officeBuilding', 260),( 34, 'officeBuilding', 246),( 35, 'officeBuilding', 275),( 36, 'officeBuilding', 320),], dtype=[('idx', '<i4'),('Treatment', '|S8'),('StressReduction', '<i4')])return datadef doAnova(data):'''one-way ANOVA'''df = pd.DataFrame(data)model = ols('StressReduction ~ C(Treatment)',df).fit()anovaResults =  anova_lm(model)print(anovaResults)if anovaResults['PR(>F)'][0] < 0.05:print('One of the groups is different.')def doTukey(data, multiComp):    '''Do a pairwise comparison, and show the confidence intervals'''print((multiComp.tukeyhsd().summary()))# Calculate the p-values:res2 = pairwise_tukeyhsd(data['StressReduction'], data['Treatment'])df = pd.DataFrame(data)numData = len(df)numTreatments = len(df.Treatment.unique())dof = numData - numTreatments# Show the group namesprint((multiComp.groupsunique))# Generate a print -------------------# Get the dataxvals = np.arange(3)res2 = pairwise_tukeyhsd(data['StressReduction'], data['Treatment'])errors = np.ravel(np.diff(res2.confint)/2)# Plot themplt.plot(xvals, res2.meandiffs, 'o')plt.errorbar(xvals, res2.meandiffs, yerr=errors, fmt='o')# Put on labelspair_labels = multiComp.groupsunique[np.column_stack(res2._multicomp.pairindices)]plt.xticks(xvals, pair_labels)# Format the plotxlim = -0.5, 2.5plt.hlines(0, *xlim)plt.xlim(*xlim)plt.title('Multiple Comparison of Means - Tukey HSD, FWER=0.05' +'\n Pairwise Mean Differences')          # Save to outfile, and show the dataoutFile = 'multComp.png'showData(outFile)def Holm_Bonferroni(multiComp):''' Instead of the Tukey's test, we can do pairwise t-test '''# First, with the "Holm" correctionrtp = multiComp.allpairtest(stats.ttest_rel, method='Holm')print((rtp[0]))# and then with the Bonferroni correctionprint((multiComp.allpairtest(stats.ttest_rel, method='b')[0]))# Any value, for testing the program for correct executioncheckVal = rtp[1][0][0,0]return checkValdef main():# Get the datadata = setData()# Do a one-way ANOVAdoAnova(data)#Then, do the multiple testingmultiComp = MultiComparison(data['StressReduction'], data['Treatment'])doTukey(data, multiComp)    # Tukey's HSD testcheckVal = Holm_Bonferroni(multiComp)  # Alternatives to Tukey's HSD testreturn checkVal     # this is only for regression testing of the programif __name__ == '__main__':main()

贾俊平书里的例子,综合多重检验和LSD方法结果一致

#居民区
group1=[265,310,220,290,350,300,445,480,500,430,428,530]
#商业区
group2=[410,305,450,380,310,390,590,480,510,470,415,390]
#写字楼
group3=[180,290,330,220,170,256,290,283,260,246,275,320]

# -*- coding: utf-8 -*-import scipy,math
from scipy.stats import f
import numpy as np
import matplotlib.pyplot as plt
import scipy.stats as stats
# additional packages
from statsmodels.stats.diagnostic import lillifors
#多重比较
from statsmodels.sandbox.stats.multicomp import multipletests
#用于排列组合
import itertools
#独立T检验
from scipy.stats import ttest_ind
#配对T检验
from scipy.stats import ttest_rel #居民区
group1=[265,310,220,290,350,300,445,480,500,430,428,530]
#商业区
group2=[410,305,450,380,310,390,590,480,510,470,415,390]
#写字楼
group3=[180,290,330,220,170,256,290,283,260,246,275,320]list_groups=[group1,group2,group3]
list_total=group1+group2+group3
a=0.05#one within group error,also know as random error
def SE(group):se=0mean1=np.mean(group)for i in group:error=i-mean1se+=error**2return se'''
>>> SE(group1)
22.0
>>> SE(group2)
18.0
>>> SE(group3)
14.0
'''
#sum of squares within group error,also know as random error
def SSE(list_groups): sse=0for group in list_groups:se=SE(group)sse+=sereturn sse#误差总平方和
def SST(list_total):sst=0mean1=np.mean(list_total)for i in list_total:error=i-mean1sst+=error**2return sst#SSA,between-group sum of squares 组间平方和,公式1:ssa=sst-sse
def SSA(list_groups,list_total):sse=SSE(list_groups)sst=SST(list_total)ssa=sst-ssereturn ssa#SSA,between-group sum of squares 组间平方和
def SSA1(list_groups,list_total):mean_total=np.mean(list_total)ssa=0for group in list_groups:group_mean=np.mean(group)distance=(mean_total-group_mean)**2ssa+=distancessa=ssa*5return ssa       #处理效应均方
def MSA(list_groups,list_total):ssa=SSA(list_groups,list_total)msa=ssa/(len(list_groups)-1)*1.0return msa# 误差均方
def MSE(list_groups,list_total):sse=SSE(list_groups)mse=sse/(len(list_total)-1*len(list_groups))*1.0 return mse             #F score
def F(list_groups,list_total):msa=MSA(list_groups,list_total)mse=MSE(list_groups,list_total)ratio=msa/mse*1.0return ratio
'''
>>> F(list_groups,list_total)
22.592592592592595
'''#LSD检验有问题,需要核对,不如配对T检验准确
#LSD(least significant difference)最小显著差异
def LSD(list_groups,list_total,sample1,sample2):mean1=np.mean(sample1)mean2=np.mean(sample2)distance=abs(mean1-mean2)print"distance:",distance#t检验的自由度df=len(list_total)-1*len(list_groups)mse=MSE(list_groups,list_total)print"MSE:",mset_value=stats.t(df).isf(a/2)print"t value:",t_valuelsd=t_value*math.sqrt(mse*(1.0/len(sample1)+1.0/len(sample2)))print "LSD:",lsdif distance<lsd:print"no significant difference between:",sample1,sample2else:print"there is significant difference between:",sample1,sample2#正态分布测试
def check_normality(testData):#20<样本数<50用normal test算法检验正态分布性if 20<len(testData) <50:p_value= stats.normaltest(testData)[1]if p_value<0.05:print"use normaltest"print "data are not normal distributed"return  Falseelse:print"use normaltest"print "data are normal distributed"return True#样本数小于50用Shapiro-Wilk算法检验正态分布性if len(testData) <50:p_value= stats.shapiro(testData)[1]if p_value<0.05:print "use shapiro:"print "data are not normal distributed"return  Falseelse:print "use shapiro:"print "data are normal distributed"return Trueif 300>=len(testData) >=50:p_value= lillifors(testData)[1]if p_value<0.05:print "use lillifors:"print "data are not normal distributed"return  Falseelse:print "use lillifors:"print "data are normal distributed"return Trueif len(testData) >300: p_value= stats.kstest(testData,'norm')[1]if p_value<0.05:print "use kstest:"print "data are not normal distributed"return  Falseelse:print "use kstest:"print "data are normal distributed"return True#对所有样本组进行正态性检验
def NormalTest(list_groups):for group in list_groups:#正态性检验status=check_normality(group1)if status==False :return False#排列组合函数
def Combination(list_groups):combination= []for i in range(1,len(list_groups)+1):iter = itertools.combinations(list_groups,i)combination.append(list(iter))#需要排除第一个和最后一个return combination[1:-1][0]
'''
Out[57]:
[[([2, 3, 7, 2, 6], [10, 8, 7, 5, 10]),([2, 3, 7, 2, 6], [10, 13, 14, 13, 15]),([10, 8, 7, 5, 10], [10, 13, 14, 13, 15])]]
'''       #多重比较
def Multiple_test(list_groups):combination=Combination(list_groups)for pair in combination:LSD(list_groups,list_total,pair[0],pair[1])#discriptive statistcs
print "discriptive statistcs----------------------------------------------"
print "group1 mean",np.mean(group1)
print "group2 mean",np.mean(group2)
print "group3 mean",np.mean(group3)  #对所有样本组进行正态性检验
print"M=Normality test:-----------------------------------"
NormalTest(list_groups)#方差齐性检测
print"levene test:-----------------------------------"
leveneResult=scipy.stats.levene(group1,group2,group3)
leveneScore=leveneResult[0]
p_levene=leveneResult[1]
if p_levene<0.05:print"levene test is not fit,be attention!"
else:print"levene test is ok"
'''
H0成立,三组数据方差无显著差异
Out[9]: LeveneResult(statistic=0.24561403508771934, pvalue=0.7860617221429711)
'''print "result--------------------------------------------------"
f_score=F(list_groups,list_total)
print"F score:",f_score
#sf 为生存函数survival function
#组数自由度
df1=len(list_groups)-1
#所有样本的自由度
df2=len(list_total)-1*len(list_groups)
probability=f.sf(f_score,df1,df2)
print"p value:",probability
'''
Out[28]: 8.5385924542746692e-05
'''
if probability<0.05:print"there is significance,H1 win"
else:print"there is no significance,H0 win"#多重比较
print"multiple test----------------------------------------------"
print"Multiple test",Multiple_test
Multiple_test(list_groups)

python风控评分卡建模和风控常识(博客主亲自录制视频教程)

https://study.163.com/course/introduction.htm?courseId=1005214003&utm_campaign=commission&utm_source=cp-400000000398149&utm_medium=share

转载于:https://www.cnblogs.com/webRobot/p/6902000.html

多重检验_LSD方法不准确性相关推荐

  1. 如何比较两种估算方法的准确性?

    有公司在做软件规模估算时,采用了经验法估计了代码行,又设置了难度系数,重用率,重用规模系数三个调整参数.如果初始估计规模为1KLOC,难度系数为1.1,重用率为20%,重用规模系数为50%,则调整后的 ...

  2. 基于点云描述子的立体视觉里程计快速鲁棒的位置识别方法

    点云PCL免费知识星球,点云论文速读. 文章:A Fast and Robust Place Recognition Approach for Stereo Visual Odometry Using ...

  3. 一种全自动的牙齿CBCT三维个体识别和分割方法

    点击上方"小白学视觉",选择加"星标"或"置顶" 重磅干货,第一时间送达 小白导读 论文是学术研究的精华和未来发展的明灯.小白决心每天为大家 ...

  4. Peer J:整合高通量绝对丰度定量方法解析土壤细菌群落及动态

    本文转自"上海天昊生物",已获授权 英文题目: Assessing soil bacterial community and dynamics by integrated high ...

  5. 《预训练周刊》第23期:Smart Bird:解决变换器性能瓶颈的新方法、Prompt:如何提升预训练模型的迁移效果...

    No.23 智源社区 预训练组 预 训 练 研究 观点 资源 活动 关于周刊 超大规模预训练模型是当前人工智能领域研究的热点,为了帮助研究与工程人员了解这一领域的进展和资讯,智源社区整理了第23期&l ...

  6. 基于cnn的短文本分类_基于时频分布和CNN的信号调制识别分类方法

    文章来源:IET Radar, Sonar & Navigation, 2018, Vol. 12, Iss. 2, pp. 244-249. 作者:Juan Zhang1, Yong Li2 ...

  7. 判断一个数是否是素数的 n 多种方法

    素数:只能除以1和自身的数(需要大于1)就是素数,又叫质数. 方法 从2开始一直除到该数之前的那个自然数,如果有能被整除的就不是素数 bool isPrime(int n) {if (n == 1) ...

  8. NLPCC'22 | 一种兼具准确性和多样性的图像风格化描述生成框架

    每天给你送来NLP技术干货! 来自:南大NLP 01 研究动机 在本文中,我们研究了图像描述(Image Captioning)领域一个新兴的问题--图像风格化描述(Stylized Image Ca ...

  9. matlab 去条带噪声,一种图像条带噪声及坏线消除方法

    一种图像条带噪声及坏线消除方法 [技术领域] [0001] 本发明属于遥感图像处理领域,具体涉及一种图像条带噪声及坏线消除方法. [背景技术] [0002] 目前多数航空或航天光学遥感图像均以线阵推扫 ...

  10. 用于自动驾驶的激光雷达里程计方法综述

    文章:LiDAR Odometry Methodologies for Autonomous Driving: A Survey 作者:Nikhil Jonnavithula1 , Yecheng L ...

最新文章

  1. python 3d绘图-python - 轻松学会Matplotlib 3D绘图
  2. fastadmin的基本用法 自动生成crud模块
  3. 【转】C# using的三种使用方法
  4. SQL判断语句用法和多表查询
  5. Qt configure 参数不完全说明
  6. php 系统交互 删除文件_FileSystemMap:与文件系统交互的自然方法
  7. php 开启,PHP服务的开启详细步骤
  8. java中static、final、static final浅析
  9. 软件质量包括哪些特性?软件质量保证的主要任务是什么?
  10. mysql下载是port报错_mysql group replication添加复制节点报错
  11. deeplearning中卷积后尺寸的变化
  12. windows 2008 r2 AD密码策略
  13. Java学习系列(十三)Java面向对象之界面编程
  14. 12个有趣的C语言问答_sunyrising-ChinaUnix博客
  15. C++ TBB 文档手册地址
  16. centos7镜像在虚拟机上安装centos7详细教程
  17. 服务器要使用两张网卡做bond0以实现网络冗余和提高带宽
  18. EasyExcel导出合并单元格
  19. 麻省理工学院计算机科学与工程博士,2020年麻省理工学院博士读几年
  20. 《商务与经济统计》(四)

热门文章

  1. NPN和PNP三极管搭建推挽电路实验
  2. 如何计算置信区间,RMSE均方根误差/标准误差:误差平方和的平均数开方
  3. 需要作废的增值税发票丢失了怎么办
  4. GitHub远程拉取仓库项目提示Please use a personal access token instead.解决方法
  5. Android Gradle Build Error:Some file crunching failed, see logs for details解决办法
  6. easyui事件方法onChange()、onSelect()、 onLoadSuccess()
  7. stm32usb做虚拟串口和键盘_在MINI STM32 板子上实现USB虚拟串口
  8. 凡泰极客:远程办公,你礼貌吗?
  9. “萌新”商家应该如何选择电商直播平台呢?
  10. el-checkbox-group 的坑