這次僅針對CRE data的模型變數選擇，主要以下面python的forward backward selection的方式進行挑選，主要方式為：將所有資料的百分之六十切出，進行變數篩選，並使用loocv的方式比較不同變數模型的準確度差異。
讀取與切分資料
import pandas as pd
import numpy as np
df = pd.read_csv('C:/Users/User/OneDrive - student.nsysu.edu.tw/Educations/NSYSU/fu_chung/bacterial/123.csv')
from sklearn.model_selection import train_test_split
import random
cre = df[df['CRE'].isin([1])].iloc[:,:]
cre['CRE'] = 1
normal = df[df['CRE'].isin([0])].iloc[:,:]
normal['CRE'] = 0
random.seed(3)
train_nor, test_nor = train_test_split(normal, test_size = 0.6)
train_cre, test_cre = train_test_split(cre, test_size = 0.6)
data_train = pd.concat([train_nor,train_cre], axis=0)
data_test = pd.concat([test_nor,test_cre], axis=0)
f_x = train_cre.iloc[:,:]定義 forward backward selection function
from sklearn.datasets import load_boston
import pandas as pd
import numpy as np
from sklearn.linear_model import LogisticRegression
import statsmodels.api as sm
def stepwise_selection(X, y,
initial_list=[],
threshold_in=0.01,
threshold_out = 0.05,
verbose=True):
""" Perform a forward-backward feature selection
based on p-value from statsmodels.api.OLS
Arguments:
X - pandas.DataFrame with candidate features
y - list-like with the target
initial_list - list of features to start with (column names of X)
threshold_in - include a feature if its p-value < threshold_in
threshold_out - exclude a feature if its p-value > threshold_out
verbose - whether to print the sequence of inclusions and exclusions
Returns: list of selected features
Always set threshold_in < threshold_out to avoid infinite looping.
See https://en.wikipedia.org/wiki/Stepwise_regression for the details
"""
included = list(initial_list)
while True:
changed=False
# forward step
excluded = list(set(X.columns)-set(included))
new_pval = pd.Series(index=excluded)
for new_column in excluded:
model = sm.OLS(y, sm.add_constant(pd.DataFrame(X[included+[new_column]]))).fit()
new_pval[new_column] = model.pvalues[new_column]
best_pval = new_pval.min()
if best_pval < threshold_in:
best_feature = new_pval.argmin()
included.append(best_feature)
changed=True
if verbose:
print('Add {:30} with p-value {:.6}'.format(best_feature, best_pval))
# backward step
model = sm.OLS(y, sm.add_constant(pd.DataFrame(X[included]))).fit()
# use all coefs except intercept
pvalues = model.pvalues.iloc[1:]
worst_pval = pvalues.max() # null if pvalues is empty
if worst_pval > threshold_out:
changed=True
worst_feature = pvalues.argmax()
included.remove(worst_feature)
if verbose:
print('Drop {:30} with p-value {:.6}'.format(worst_feature, worst_pval))
if not changed:
break
return included挑選100次變數組合並輸出結果
f_list = {}
for i in range(100):
#m1 ,m2 = train_test_split(df, test_size = 0.6)
import time
tStart = time.time()#計時開始
train_nor, test_nor = train_test_split(normal, test_size = 0.6)
data_train = pd.concat([train_nor,train_cre], axis=0)
X = data_train.iloc[:,0:1471]
y = data_train.iloc[:,1471:1472]
result = stepwise_selection(X, y)
a = i
cname=str(a)
f_list.setdefault(cname,result)
#end of 模擬要測量的function
tEnd = time.time()#計時結束
#列印結果
print ("It cost %f sec" % (tEnd - tStart))#會自動做近位
print (tEnd - tStart)#原型長這樣Add V1201 with p-value 8.84384e-08
Add V1098 with p-value 2.85678e-06
Add V483 with p-value 5.06239e-05
Add V12 with p-value 0.00063702
Add V503 with p-value 0.00201273
Add V936 with p-value 0.0010971
Add V130 with p-value 0.0010447
Add V131 with p-value 1.43096e-07
Add V589 with p-value 0.0013715
Add V47 with p-value 0.00011529
Add V1225 with p-value 0.000221064
Add V220 with p-value 3.62875e-05
Add V354 with p-value 8.08712e-05
Add V50 with p-value 0.00585102
Add V372 with p-value 0.00478135
Add V141 with p-value 0.0055529
Add V533 with p-value 0.00270015
Add V324 with p-value 0.000643428
Add V875 with p-value 0.000698599
Add V509 with p-value 0.00418121
Add V197 with p-value 0.00646997
Add V608 with p-value 0.00819923
It cost 141.595159 sec
141.59515857696533c = pd.DataFrame(dict([(k, pd.Series(v
)) for k, v in f_list.items()]))
c3 = c
c3| 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | … | 90 | 91 | 92 | 93 | 94 | 95 | 96 | 97 | 98 | 99 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | V1201 | V1201 | V1201 | V1201 | V1139 | V1201 | V1201 | V1201 | V1201 | V1201 | … | V1201 | V1201 | V1201 | V1201 | V1201 | V1201 | V1201 | V1201 | V1201 | V1201 |
| 1 | V1098 | V1098 | V1098 | V503 | V1098 | V1098 | V1098 | V1098 | V1098 | V1098 | … | V1098 | V1098 | V1098 | V1098 | V1098 | V1098 | V1098 | V1098 | V1098 | V1098 |
| 2 | V483 | V109 | V483 | V591 | V512 | V483 | V229 | V229 | V1221 | V483 | … | V1058 | V483 | V109 | V483 | V1019 | V109 | V1019 | V109 | V109 | V1019 |
| 3 | V12 | V216 | V503 | V61 | V5 | V936 | V130 | V130 | V188 | V12 | … | V358 | V484 | V503 | V12 | V188 | V358 | V188 | V304 | V304 | V188 |
| 4 | V503 | V694 | V936 | V376 | V1072 | V148 | V456 | V456 | V247 | V936 | … | V130 | V503 | V304 | V201 | V936 | V217 | V1386 | V503 | V447 | V694 |
| 5 | V936 | V42 | V109 | V270 | V133 | V456 | V936 | V936 | V12 | V503 | … | V131 | V717 | V945 | V1352 | V39 | V887 | V336 | V1084 | V62 | V960 |
| 6 | V130 | V1438 | V185 | V1154 | V523 | V995 | V382 | V382 | V1165 | V130 | … | V614 | V945 | V1086 | V217 | V604 | V694 | V931 | V131 | V875 | V399 |
| 7 | V131 | V970 | V158 | V323 | V1 | V993 | V491 | V191 | V1068 | V131 | … | V247 | V943 | V48 | V8 | V548 | V399 | V135 | V70 | V94 | V1095 |
| 8 | V589 | V887 | V96 | V12 | V995 | V89 | V241 | V1134 | V150 | V589 | … | V6 | V708 | V59 | V269 | V9 | V1424 | V503 | V16 | V997 | V1424 |
| 9 | V47 | V600 | NaN | V455 | V1062 | V696 | V31 | V505 | V473 | V47 | … | V936 | V699 | V139 | V11 | V571 | V600 | V273 | V338 | V694 | V859 |
| 10 | V1225 | V532 | NaN | V197 | V645 | V912 | V820 | V1263 | V1142 | V1225 | … | V456 | V670 | V127 | V938 | V557 | V859 | V178 | V223 | V1112 | V887 |
| 11 | V220 | V399 | NaN | V63 | V665 | V651 | V487 | V5 | V508 | V220 | … | V1245 | V912 | V852 | V475 | V868 | V1095 | NaN | V321 | V1447 | V336 |
| 12 | V354 | V886 | NaN | V296 | V112 | V705 | V824 | V588 | V819 | V580 | … | V619 | V346 | V235 | V341 | V665 | V665 | NaN | V438 | V112 | V931 |
| 13 | V50 | V226 | NaN | V1062 | V232 | V699 | V931 | V234 | V131 | V509 | … | V955 | V705 | V611 | V573 | V914 | V394 | NaN | V138 | V665 | V226 |
| 14 | V372 | V386 | NaN | V809 | V914 | V670 | V1054 | V813 | V541 | V334 | … | V53 | V651 | V480 | V1053 | V112 | V915 | NaN | V583 | V668 | V92 |
| 15 | V141 | V1013 | NaN | V1110 | V1112 | V708 | V388 | NaN | V1166 | V952 | … | V223 | V1439 | V613 | V450 | V668 | V645 | NaN | V249 | V645 | V447 |
| 16 | V533 | V366 | NaN | V389 | V668 | V346 | V1244 | NaN | V6 | V451 | … | V515 | V641 | V33 | V129 | V645 | V1447 | NaN | V389 | V951 | V99 |
| 17 | V324 | V53 | NaN | V406 | V958 | V641 | V298 | NaN | V122 | V148 | … | V824 | V696 | V723 | V852 | V1447 | V232 | NaN | V350 | V859 | V1183 |
| 18 | V875 | V456 | NaN | V508 | V8 | V1381 | V1067 | NaN | V503 | NaN | … | V507 | V347 | V1307 | V750 | V519 | V1112 | NaN | V92 | V399 | V321 |
| 19 | V509 | V205 | NaN | V932 | V985 | V717 | V992 | NaN | NaN | NaN | … | V171 | V187 | V318 | V1120 | V1368 | V112 | NaN | V99 | V190 | V851 |
| 20 | V197 | V163 | NaN | NaN | NaN | V326 | V62 | NaN | NaN | NaN | … | V732 | V14 | V122 | V179 | V878 | V668 | NaN | V744 | V993 | V1060 |
| 21 | V608 | V613 | NaN | NaN | NaN | V241 | V851 | NaN | NaN | NaN | … | V285 | V598 | V555 | V130 | V658 | V875 | NaN | NaN | V943 | V271 |
| 22 | NaN | V1159 | NaN | NaN | NaN | V499 | V224 | NaN | NaN | NaN | … | V1223 | V604 | V468 | V586 | V1305 | V46 | NaN | NaN | V113 | V296 |
| 23 | NaN | V200 | NaN | NaN | NaN | V205 | V44 | NaN | NaN | NaN | … | V1031 | V566 | V388 | V1024 | V405 | V197 | NaN | NaN | V180 | V217 |
| 24 | NaN | V1022 | NaN | NaN | NaN | V852 | V358 | NaN | NaN | NaN | … | V568 | V1133 | V1019 | V1158 | V145 | V9 | NaN | NaN | V945 | V102 |
| 25 | NaN | V108 | NaN | NaN | NaN | V934 | NaN | NaN | NaN | NaN | … | V174 | V323 | V143 | V1133 | V129 | V22 | NaN | NaN | V1018 | V1345 |
| 26 | NaN | V1047 | NaN | NaN | NaN | V419 | NaN | NaN | NaN | NaN | … | V446 | V610 | V544 | V57 | V994 | V1026 | NaN | NaN | V853 | NaN |
| 27 | NaN | V203 | NaN | NaN | NaN | V235 | NaN | NaN | NaN | NaN | … | V1132 | V10 | V1221 | V1029 | V493 | NaN | NaN | NaN | V510 | NaN |
| 28 | NaN | V1051 | NaN | NaN | NaN | V623 | NaN | NaN | NaN | NaN | … | V1065 | V469 | V328 | V602 | V30 | NaN | NaN | NaN | V311 | NaN |
| 29 | NaN | V331 | NaN | NaN | NaN | V910 | NaN | NaN | NaN | NaN | … | V848 | V318 | V982 | NaN | NaN | NaN | NaN | NaN | V835 | NaN |
| … | … | … | … | … | … | … | … | … | … | … | … | … | … | … | … | … | … | … | … | … | … |
| 31 | NaN | V1194 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | V1232 | NaN | V617 | NaN | NaN | NaN | NaN | NaN | V485 | NaN |
| 32 | NaN | V1192 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | V23 | NaN | V816 | NaN | NaN | NaN | NaN | NaN | V502 | NaN |
| 33 | NaN | V1043 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | V822 | NaN | V837 | NaN | NaN | NaN | NaN | NaN | V51 | NaN |
| 34 | NaN | V955 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | V559 | NaN | V919 | NaN | NaN | NaN | NaN | NaN | V388 | NaN |
| 35 | NaN | V915 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | V568 | NaN |
| 36 | NaN | V1447 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 37 | NaN | V668 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 38 | NaN | V914 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 39 | NaN | V645 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 40 | NaN | V665 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 41 | NaN | V875 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 42 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 43 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 44 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 45 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 46 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 47 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 48 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 49 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 50 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 51 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 52 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 53 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 54 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 55 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 56 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 57 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 58 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 59 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
| 60 | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | … | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
61 rows × 100 columns
c3.describe()| 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | … | 90 | 91 | 92 | 93 | 94 | 95 | 96 | 97 | 98 | 99 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| count | 22 | 42 | 9 | 20 | 20 | 30 | 25 | 15 | 19 | 18 | … | 35 | 31 | 35 | 29 | 29 | 27 | 11 | 21 | 36 | 26 |
| unique | 22 | 42 | 9 | 20 | 20 | 30 | 25 | 15 | 19 | 18 | … | 35 | 31 | 35 | 29 | 29 | 27 | 11 | 21 | 36 | 26 |
| top | V608 | V875 | V158 | V1110 | V645 | V651 | V456 | V1263 | V1068 | V334 | … | V456 | V651 | V59 | V11 | V1305 | V217 | V1098 | V338 | V190 | V217 |
| freq | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | … | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 |
4 rows × 100 columns
result = np.array(c1.iloc[:,0:1])
resultarray([[‘V1201’], [‘V1098’], [‘V12’], [‘V892’], [‘V188’], [‘V205’], [‘V376’], [‘V187’], [‘V666’], [‘V1062’], [‘V1211’], [‘V692’], [‘V689’], [‘V1223’], [‘V48’], [‘V634’], [‘V668’], [‘V841’], [‘V665’], [‘V645’], [‘V490’], [‘V148’], [‘V936’], [‘V529’], [‘V472’], [‘V886’], [‘V391’], [‘V888’], [‘V1203’], [‘V667’], [‘V1457’], [‘V1155’], [‘V395’], [‘V646’], [‘V712’], [‘V931’], [‘V1340’], [‘V1341’], [‘V389’], [‘V398’]], dtype=object)
#Write the csv
c1.to_csv("c1.csv",index=False,sep=',')Models Building
# Read data
data_csv <- read.csv("C:\\Users\\User\\OneDrive - student.nsysu.edu.tw\\Educations\\NSYSU\\fu_chung\\bacterial - PCA\\20191202_1471_CRE_46-non-CRE_49_Intensity.csv")
# arrange
if (!require(tidyverse)) install.packages("tidyverse")## Loading required package: tidyverse## -- Attaching packages ------------------------------------------------------------------------------------------------ tidyverse 1.2.1 --## √ ggplot2 3.1.1 √ purrr 0.3.2
## √ tibble 2.1.1 √ dplyr 0.8.0.1
## √ tidyr 0.8.3 √ stringr 1.4.0
## √ readr 1.3.1 √ forcats 0.4.0## -- Conflicts --------------------------------------------------------------------------------------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()library(tidyverse)
#sort data by p.value
data_csv <- arrange(data_csv,p.value)
#transpose data
name_protein <- data_csv[,1]
data <- as.data.frame(t(data_csv))
data <- data[-c(1:3),]
#data name
name_variable <- names(data)
data_name <- data.frame(name_variable,name_protein)
data_name <- as.data.frame(t(data_name))
data$CRE <- as.factor(c(rep(1,46),rep(0,49)))forward backward selection
library(raster)## Loading required package: sp##
## Attaching package: 'raster'## The following object is masked from 'package:dplyr':
##
## select## The following object is masked from 'package:tidyr':
##
## extractfeature_csv <- read.csv("C:\\Users\\User\\OneDrive - student.nsysu.edu.tw\\Documents\\Python\\GAN\\feature.csv")
#best = c("V993","V322","V864","V689","V598","V1156","V240","V395","V1255","V1218","V634","V529", "V869", "V410", "V521", "V32", "V1201", "V478", "V306", "V964", "V1122", "V485", "V690", "V947", "V677", "V1444", "V832", "V1", "V517", "V351", "V9", "V109", "V872", "V518", "V1239", "V270", "V695", "V147", "V524", "V679", "V320", "V356", "V232", "V687", "V112", "V983", "V146", "V345", "V520", "V198", "V59", "V408", "V110", "V250", "V1275", "V60", "V1253", "V459", "V522", "V889", "V403", "V269", "V87", "V530", "V839", "V399", "V861", "V242", "V823", "V58", "V627", "V84", "V321", "V50", "V483", "V475", "V1396", "V1411", "V1285", "V1093", "V1378", "V413", "V525", "V671", "V30", "V95", "V1199", "V767", "V809", "V1404", "V1401", "V113", "V1198", "V1405", "V1398", "V1209", "V1407", "V1352", "V271", "V528", "V805", "V1397", "V753", "V200", "V1400", "V1408", "V1394", "V593", "V1157", "V233", "V268", "V576", "V181", "V1395", "V820", "V1257", "V514", "V669", "V943", "V489", "V937", "V486", "V513", "V1143", "V966", "V980", "V1274", "V1403", "V343", "V686", "V653", "V1281", "V234", "V1279", "V523", "V870", "V959", "V1278", "V871", "V5", "V775", "V845", "V1211", "V1110", "V1273", "V995", "V1276", "V873", "V595", "V1280", "V1034", "V1228", "V1012", "V1226", "V1094", "V511", "V944", "V1068", "V1146", "V313", "V821", "V122", "V1227", "V386", "V771", "V551", "V538", "V1220", "V1179")
num = 1
best = as.character(feature_csv[1:(61 - length(which(feature_csv[,num] == ""))),num])
bestdf = data[,best]
bestdf$CRE <- as.factor(c(rep(1,46),rep(0,49)))loocv
#tuning rf
library(randomForest)## randomForest 4.6-14## Type rfNews() to see new features/changes/bug fixes.##
## Attaching package: 'randomForest'## The following object is masked from 'package:dplyr':
##
## combine## The following object is masked from 'package:ggplot2':
##
## marginrf_model = randomForest(CRE~.,
data=data,
ntree=500 # num of decision Tree
)
plot(rf_model)
which.min(rf_model$err.rate[,1])## [1] 130A = as.data.frame(rf_model$importance)
A$names <- row.names(A)
A = A[order(A$MeanDecreaseGini,decreasing = T),]
impo <- A[1:50,2]
A[c(1:50),]## MeanDecreaseGini names
## V994 1.4081240 V994
## V609 1.1766118 V609
## V1426 1.1419769 V1426
## V1428 1.0253725 V1428
## V1251 0.8610926 V1251
## V931 0.8480539 V931
## V205 0.8263031 V205
## V172 0.7950854 V172
## V1228 0.7435799 V1228
## V37 0.6530718 V37
## V288 0.6421747 V288
## V242 0.6185031 V242
## V935 0.6005225 V935
## V1232 0.5621623 V1232
## V264 0.5597400 V264
## V227 0.5562529 V227
## V1380 0.5561197 V1380
## V32 0.5553537 V32
## V1422 0.4995243 V1422
## V819 0.4982642 V819
## V473 0.4902241 V473
## V328 0.4609527 V328
## V1383 0.4406418 V1383
## V84 0.4260847 V84
## V830 0.3931476 V830
## V1 0.3855232 V1
## V131 0.3836959 V131
## V420 0.3690650 V420
## V1072 0.3669098 V1072
## V975 0.3294655 V975
## V834 0.3249310 V834
## V92 0.3201629 V92
## V216 0.3092701 V216
## V9 0.3068394 V9
## V306 0.2959827 V306
## V129 0.2722810 V129
## V181 0.2597386 V181
## V1225 0.2537217 V1225
## V218 0.2452925 V218
## V188 0.2417646 V188
## V313 0.2398082 V313
## V187 0.2382702 V187
## V389 0.2376730 V389
## V480 0.2355510 V480
## V831 0.2245495 V831
## V228 0.2171766 V228
## V542 0.2153996 V542
## V1073 0.2140407 V1073
## V179 0.2072366 V179
## V1061 0.2019502 V1061impodf = data[,impo]
impodf$CRE <- as.factor(c(rep(1,46),rep(0,49)))output the importance list
library(randomForest)
mean_loocv <- vector()
for(j in c(1:20)){
rf_loocv_accuracy <- vector()
for(i in c(1:95)){
train = bestdf[-i, ]
test = bestdf[i, ]
rf_model = randomForest(CRE~.,
data=train,
ntree=100 # num of decision Tree
)
test.pred = predict(rf_model, test)
#Accuracy
confus.matrix = table(real=test$CRE, predict=test.pred)
rf_loocv_accuracy[i]=sum(diag(confus.matrix))/sum(confus.matrix)
}
#LOOCV test accuracy
mean_loocv[j] = mean(rf_loocv_accuracy) # Accurary with LOOCV = 0.9157895
mean(rf_loocv_accuracy)
}
mean_loocv
write.csv(mean_loocv,"mean_loocv.csv")loocv rf for 100 times 60% fb features
result <- as.data.frame(matrix())
for(k in c(1:101)){
num = k
best = as.character(feature_csv[1:(61 - length(which(feature_csv[,num] == ""))),num])
bestdf = data[,best]
bestdf$CRE <- as.factor(c(rep(1,46),rep(0,49)))
library(randomForest)
mean_loocv <- vector()
for(j in c(1:20)){
rf_loocv_accuracy <- vector()
for(i in c(1:95)){
train = bestdf[-i, ]
test = bestdf[i, ]
rf_model = randomForest(CRE~.,
data=train,
ntree=100 # num of decision Tree
)
test.pred = predict(rf_model, test)
#Accuracy
confus.matrix = table(real=test$CRE, predict=test.pred)
rf_loocv_accuracy[i]=sum(diag(confus.matrix))/sum(confus.matrix)
}
#LOOCV test accuracy
mean_loocv[j] = mean(rf_loocv_accuracy) # Accurary with LOOCV = 0.9157895
mean(rf_loocv_accuracy)
}
result <- cbind(result, as.data.frame(mean_loocv))
}
write.csv(result,"result.csv")the final result
label <- read.csv("C:\\Users\\User\\OneDrive - student.nsysu.edu.tw\\Educations\\NSYSU\\fu_chung\\bacterial - PCA\\label.csv")
label## Names loop1 loop2 loop3 loop4 loop5
## 1 best 0.9473684 0.9578947 0.9263158 0.9157895 0.9263158
## 2 impoall_50 0.9473684 0.9789474 0.9578947 0.9473684 0.9368421
## 3 impoall_60 0.9473684 0.9473684 0.9578947 0.9684211 0.9684211
## 4 impoall_80 0.9684211 0.9684211 0.9684211 0.9578947 0.9578947
## 5 impoall_100 0.9578947 0.9473684 0.9578947 0.9684211 0.9684211
## 6 fb60_1 0.8105263 0.7578947 0.7789474 0.8210526 0.7684211
## 7 fb60_2 0.8315789 0.8315789 0.8105263 0.8000000 0.8000000
## 8 fb60_3 0.6947368 0.6736842 0.7157895 0.6947368 0.7157895
## 9 fb60_4 0.7894737 0.8105263 0.8105263 0.8210526 0.8105263
## 10 fb60_5 0.8421053 0.8631579 0.8421053 0.8526316 0.8526316
## 11 fb60_6 0.8000000 0.7894737 0.7684211 0.8000000 0.7578947
## 12 fb60_7 0.8947368 0.8105263 0.8736842 0.8315789 0.8736842
## 13 fb60_8 0.7684211 0.7684211 0.7894737 0.7894737 0.7578947
## 14 fb60_9 0.8210526 0.8315789 0.8421053 0.8421053 0.8631579
## 15 fb60_10 0.7684211 0.7894737 0.8105263 0.8105263 0.8210526
## 16 fb60_11 0.7894737 0.8000000 0.7789474 0.7894737 0.7894737
## 17 fb60_12 0.8421053 0.8526316 0.8421053 0.8526316 0.8526316
## 18 fb60_13 0.7894737 0.8000000 0.7894737 0.8210526 0.7789474
## 19 fb60_14 0.7052632 0.6947368 0.7052632 0.7263158 0.6631579
## 20 fb60_15 0.8526316 0.8736842 0.8210526 0.8000000 0.8105263
## 21 fb60_16 0.6947368 0.6736842 0.6631579 0.6947368 0.6736842
## 22 fb60_17 0.6105263 0.5789474 0.6210526 0.6210526 0.6210526
## 23 fb60_18 0.8631579 0.8105263 0.8315789 0.8315789 0.8210526
## 24 fb60_19 0.8315789 0.8526316 0.8315789 0.8315789 0.8210526
## 25 fb60_20 0.8947368 0.8842105 0.8947368 0.8842105 0.9052632
## 26 fb60_21 0.8105263 0.8105263 0.8105263 0.7789474 0.8000000
## 27 fb60_22 0.7578947 0.7368421 0.7263158 0.7368421 0.7263158
## 28 fb60_23 0.6526316 0.6526316 0.6631579 0.6736842 0.6736842
## 29 fb60_24 0.7473684 0.6947368 0.7263158 0.7473684 0.7052632
## 30 fb60_25 0.6947368 0.6842105 0.6947368 0.7052632 0.7157895
## 31 fb60_26 0.6947368 0.6421053 0.6421053 0.6526316 0.6736842
## 32 fb60_27 0.8315789 0.8421053 0.8526316 0.8736842 0.8421053
## 33 fb60_28 0.8947368 0.8631579 0.8842105 0.8842105 0.9052632
## 34 fb60_29 0.8736842 0.8631579 0.8631579 0.8842105 0.8631579
## 35 fb60_30 0.8315789 0.8210526 0.8105263 0.8315789 0.8210526
## 36 fb60_31 0.8631579 0.8526316 0.8842105 0.8526316 0.8842105
## 37 fb60_32 0.8105263 0.8421053 0.8421053 0.8105263 0.8526316
## 38 fb60_33 0.8000000 0.8000000 0.8421053 0.8000000 0.8000000
## 39 fb60_34 0.8421053 0.8421053 0.8526316 0.8210526 0.8421053
## 40 fb60_35 0.8210526 0.8105263 0.7684211 0.8105263 0.8210526
## 41 fb60_36 0.8631579 0.8421053 0.8631579 0.8315789 0.8526316
## 42 fb60_37 0.9052632 0.9052632 0.9263158 0.8842105 0.9368421
## 43 fb60_38 0.8315789 0.8526316 0.8315789 0.8421053 0.8315789
## 44 fb60_39 0.8736842 0.8842105 0.8736842 0.8947368 0.8842105
## 45 fb60_40 0.8105263 0.8210526 0.8000000 0.8210526 0.8210526
## 46 fb60_41 0.7578947 0.7368421 0.7684211 0.7368421 0.7684211
## 47 fb60_42 0.7368421 0.7368421 0.7263158 0.7157895 0.7368421
## 48 fb60_43 0.7473684 0.7789474 0.7684211 0.7473684 0.7684211
## 49 fb60_44 0.8315789 0.7789474 0.8000000 0.7894737 0.7684211
## 50 fb60_45 0.7368421 0.7684211 0.7578947 0.7578947 0.7789474
## 51 fb60_46 0.8105263 0.7894737 0.8000000 0.8210526 0.8105263
## 52 fb60_47 0.7263158 0.7894737 0.7263158 0.7684211 0.7368421
## 53 fb60_48 0.8315789 0.8526316 0.7789474 0.8315789 0.8315789
## 54 fb60_49 0.8105263 0.8105263 0.8315789 0.8210526 0.8105263
## 55 fb60_50 0.7578947 0.6947368 0.7157895 0.7368421 0.7263158
## 56 fb60_51 0.8105263 0.8105263 0.8315789 0.8210526 0.8210526
## 57 fb60_52 0.7789474 0.7578947 0.7473684 0.7473684 0.7368421
## 58 fb60_53 0.8526316 0.8210526 0.8526316 0.8526316 0.8526316
## 59 fb60_54 0.8210526 0.8000000 0.7894737 0.8210526 0.8105263
## 60 fb60_55 0.7368421 0.7789474 0.7368421 0.7789474 0.7789474
## 61 fb60_56 0.8210526 0.8421053 0.8210526 0.8210526 0.8315789
## 62 fb60_57 0.8421053 0.8105263 0.8315789 0.7894737 0.7578947
## 63 fb60_58 0.7894737 0.8105263 0.8105263 0.8000000 0.8210526
## 64 fb60_59 0.8736842 0.8631579 0.8631579 0.8842105 0.8736842
## 65 fb60_60 0.9052632 0.8842105 0.8947368 0.9052632 0.8736842
## 66 fb60_61 0.8526316 0.8315789 0.8421053 0.8315789 0.8315789
## 67 fb60_62 0.8000000 0.8105263 0.8000000 0.7789474 0.8421053
## 68 fb60_63 0.8315789 0.8526316 0.8631579 0.8315789 0.8631579
## 69 fb60_64 0.7578947 0.7368421 0.7473684 0.7157895 0.7578947
## 70 fb60_65 0.6947368 0.7473684 0.7157895 0.7157895 0.7052632
## 71 fb60_66 0.6842105 0.6842105 0.6947368 0.7052632 0.7052632
## 72 fb60_67 0.6842105 0.6842105 0.6842105 0.6947368 0.6842105
## 73 fb60_68 0.8105263 0.8210526 0.8000000 0.8421053 0.8526316
## 74 fb60_69 0.8315789 0.8526316 0.8421053 0.8421053 0.8526316
## 75 fb60_70 0.8631579 0.8631579 0.8526316 0.8947368 0.8421053
## 76 fb60_71 0.8105263 0.8105263 0.7894737 0.8000000 0.8000000
## 77 fb60_72 0.6736842 0.6842105 0.7157895 0.6736842 0.6947368
## 78 fb60_73 0.6842105 0.6947368 0.7052632 0.6947368 0.6631579
## 79 fb60_74 0.6631579 0.7052632 0.7052632 0.7263158 0.7473684
## 80 fb60_75 0.7473684 0.7578947 0.7473684 0.7789474 0.7368421
## 81 fb60_76 0.8947368 0.8947368 0.9052632 0.8842105 0.8947368
## 82 fb60_77 0.7894737 0.7578947 0.7894737 0.7473684 0.8000000
## 83 fb60_78 0.7368421 0.7578947 0.7368421 0.7578947 0.7473684
## 84 fb60_79 0.8105263 0.8736842 0.8842105 0.8526316 0.8526316
## 85 fb60_80 0.7684211 0.7263158 0.7263158 0.7684211 0.7578947
## 86 fb60_81 0.6631579 0.6210526 0.6736842 0.6842105 0.6526316
## 87 fb60_82 0.6947368 0.6631579 0.7052632 0.7052632 0.7157895
## 88 fb60_83 0.7368421 0.7578947 0.7263158 0.7368421 0.7789474
## 89 fb60_84 0.7473684 0.7789474 0.7368421 0.7578947 0.7368421
## 90 fb60_85 0.7894737 0.8000000 0.7789474 0.8000000 0.7894737
## 91 fb60_86 0.8631579 0.8631579 0.8526316 0.8526316 0.8631579
## 92 fb60_87 0.8000000 0.7789474 0.7894737 0.8000000 0.8210526
## 93 fb60_88 0.8210526 0.8210526 0.8210526 0.8105263 0.8210526
## 94 fb60_89 0.7263158 0.7684211 0.7578947 0.7473684 0.7789474
## 95 fb60_90 0.8421053 0.8105263 0.8421053 0.8105263 0.8526316
## 96 fb60_91 0.8842105 0.8842105 0.8947368 0.8421053 0.8631579
## 97 fb60_92 0.8210526 0.7894737 0.8210526 0.8210526 0.8000000
## 98 fb60_93 0.8526316 0.8421053 0.8105263 0.8315789 0.8421053
## 99 fb60_94 0.8947368 0.8526316 0.8947368 0.8842105 0.8736842
## 100 fb60_95 0.8947368 0.9052632 0.9052632 0.9052632 0.9052632
## 101 fb60_96 0.8315789 0.7789474 0.8000000 0.7894737 0.8105263
## 102 fb60_97 0.8421053 0.8315789 0.8315789 0.8315789 0.8315789
## 103 fb60_98 0.8736842 0.9052632 0.8842105 0.8947368 0.8842105
## 104 fb60_99 0.7894737 0.7894737 0.8000000 0.8210526 0.7894737
## 105 fb60_100 0.9157895 0.8842105 0.9052632 0.8736842 0.8526316
## 106 fb60_101 0.9263158 0.9157895 0.9263158 0.9263158 0.9157895
## loop6 loop7 loop8 loop9 loop10 loop11 loop12
## 1 0.9263158 0.9052632 0.9473684 0.9578947 0.9473684 0.9578947 0.9578947
## 2 0.9473684 0.9684211 0.9578947 0.9368421 0.9578947 0.9578947 0.9368421
## 3 0.9578947 0.9578947 0.9578947 0.9684211 0.9684211 0.9578947 0.9684211
## 4 0.9684211 0.9684211 0.9684211 0.9578947 0.9684211 0.9578947 0.9684211
## 5 0.9368421 0.9578947 0.9473684 0.9684211 0.9368421 0.9578947 0.9578947
## 6 0.8000000 0.8000000 0.7894737 0.7789474 0.7789474 0.8421053 0.8315789
## 7 0.8210526 0.8421053 0.7894737 0.8526316 0.8105263 0.7894737 0.8000000
## 8 0.7157895 0.6947368 0.6842105 0.6842105 0.6947368 0.7157895 0.6631579
## 9 0.8210526 0.8000000 0.8000000 0.7789474 0.7789474 0.8000000 0.8000000
## 10 0.8631579 0.8105263 0.8421053 0.8421053 0.8526316 0.8315789 0.8421053
## 11 0.7578947 0.7684211 0.8000000 0.7578947 0.7684211 0.8000000 0.7789474
## 12 0.8421053 0.8526316 0.8631579 0.8631579 0.8315789 0.8526316 0.8421053
## 13 0.7684211 0.7684211 0.8000000 0.7684211 0.7789474 0.8000000 0.7789474
## 14 0.8526316 0.8421053 0.8210526 0.8315789 0.8421053 0.8421053 0.8421053
## 15 0.8000000 0.7789474 0.7894737 0.8210526 0.8105263 0.8000000 0.8000000
## 16 0.8000000 0.8000000 0.7684211 0.7894737 0.8000000 0.8000000 0.7684211
## 17 0.8421053 0.8526316 0.8210526 0.8736842 0.8210526 0.8526316 0.8421053
## 18 0.7789474 0.8105263 0.8210526 0.8000000 0.7894737 0.7684211 0.8315789
## 19 0.6842105 0.6842105 0.6947368 0.6842105 0.6736842 0.7157895 0.6842105
## 20 0.8631579 0.8105263 0.8105263 0.8421053 0.8210526 0.8421053 0.8526316
## 21 0.6842105 0.6736842 0.6947368 0.6947368 0.6631579 0.6842105 0.6842105
## 22 0.6315789 0.6105263 0.6000000 0.5894737 0.6000000 0.5789474 0.6210526
## 23 0.8526316 0.8526316 0.8210526 0.8421053 0.7894737 0.8210526 0.8315789
## 24 0.8526316 0.8315789 0.8526316 0.8315789 0.8526316 0.8421053 0.8736842
## 25 0.9157895 0.8842105 0.8736842 0.8842105 0.8842105 0.9157895 0.8947368
## 26 0.8105263 0.8421053 0.8210526 0.7684211 0.8210526 0.8000000 0.8105263
## 27 0.7578947 0.7473684 0.7368421 0.7368421 0.7263158 0.7473684 0.7473684
## 28 0.6736842 0.6526316 0.6526316 0.6315789 0.6526316 0.6315789 0.6947368
## 29 0.7157895 0.7052632 0.7368421 0.7368421 0.7263158 0.7157895 0.7157895
## 30 0.6842105 0.7157895 0.7157895 0.6947368 0.7157895 0.6947368 0.7052632
## 31 0.6526316 0.6315789 0.7157895 0.6736842 0.6526316 0.6631579 0.7263158
## 32 0.8736842 0.8526316 0.8421053 0.8631579 0.8315789 0.8526316 0.8421053
## 33 0.8842105 0.8842105 0.8842105 0.8736842 0.8842105 0.8842105 0.8631579
## 34 0.8631579 0.8526316 0.8842105 0.8736842 0.8526316 0.8526316 0.8736842
## 35 0.7894737 0.8210526 0.8000000 0.8105263 0.8421053 0.8421053 0.8421053
## 36 0.8526316 0.8631579 0.8421053 0.8315789 0.8736842 0.8736842 0.8526316
## 37 0.8000000 0.8210526 0.8000000 0.8105263 0.8210526 0.8210526 0.8000000
## 38 0.8000000 0.8210526 0.8000000 0.7894737 0.8105263 0.8105263 0.8421053
## 39 0.8421053 0.8421053 0.8526316 0.8421053 0.8526316 0.8000000 0.8421053
## 40 0.7894737 0.8105263 0.8000000 0.8000000 0.8105263 0.8000000 0.7789474
## 41 0.8421053 0.8631579 0.8315789 0.8421053 0.8421053 0.8105263 0.8526316
## 42 0.9263158 0.9052632 0.9263158 0.9052632 0.9052632 0.9052632 0.9263158
## 43 0.8526316 0.8526316 0.8526316 0.8526316 0.8315789 0.8526316 0.8526316
## 44 0.8947368 0.8842105 0.8947368 0.8736842 0.8842105 0.8947368 0.8736842
## 45 0.8315789 0.8000000 0.8210526 0.8105263 0.8105263 0.8000000 0.8000000
## 46 0.7578947 0.7368421 0.7473684 0.7368421 0.7684211 0.7473684 0.7578947
## 47 0.7473684 0.7263158 0.6842105 0.7263158 0.6947368 0.7263158 0.7263158
## 48 0.7473684 0.7578947 0.7368421 0.7894737 0.7578947 0.7684211 0.7894737
## 49 0.8315789 0.7789474 0.7789474 0.7578947 0.8105263 0.8000000 0.8105263
## 50 0.7368421 0.7263158 0.7578947 0.7578947 0.7157895 0.7789474 0.7578947
## 51 0.8000000 0.7789474 0.8000000 0.8210526 0.8000000 0.8315789 0.8526316
## 52 0.7578947 0.7368421 0.7473684 0.7789474 0.7789474 0.7263158 0.7263158
## 53 0.8315789 0.8105263 0.8315789 0.8315789 0.8105263 0.8526316 0.8526316
## 54 0.8210526 0.8315789 0.8000000 0.8000000 0.8315789 0.8000000 0.8000000
## 55 0.7368421 0.7052632 0.6947368 0.7052632 0.7052632 0.6842105 0.6947368
## 56 0.8000000 0.8105263 0.8315789 0.8210526 0.8210526 0.8105263 0.8210526
## 57 0.7684211 0.7578947 0.7578947 0.7368421 0.7473684 0.7684211 0.7473684
## 58 0.8526316 0.8736842 0.8526316 0.8315789 0.8736842 0.8421053 0.8526316
## 59 0.8210526 0.7894737 0.8210526 0.8315789 0.7894737 0.7894737 0.8105263
## 60 0.7578947 0.7578947 0.7368421 0.7578947 0.7894737 0.7894737 0.7684211
## 61 0.8105263 0.8000000 0.8105263 0.8315789 0.8105263 0.8210526 0.8000000
## 62 0.8315789 0.8105263 0.8105263 0.7578947 0.8000000 0.8000000 0.7789474
## 63 0.8000000 0.8105263 0.7789474 0.8210526 0.8210526 0.8315789 0.8105263
## 64 0.8631579 0.8631579 0.8526316 0.8736842 0.8631579 0.8526316 0.8736842
## 65 0.9052632 0.9263158 0.8947368 0.8842105 0.8947368 0.9157895 0.9157895
## 66 0.8000000 0.8526316 0.8000000 0.8210526 0.8105263 0.8315789 0.8210526
## 67 0.8421053 0.8315789 0.8210526 0.8105263 0.8421053 0.8421053 0.8210526
## 68 0.8421053 0.8631579 0.8421053 0.8421053 0.8421053 0.8736842 0.8421053
## 69 0.7473684 0.7368421 0.7263158 0.7578947 0.7368421 0.7473684 0.7157895
## 70 0.7052632 0.7157895 0.7368421 0.6947368 0.6736842 0.7473684 0.7368421
## 71 0.7052632 0.7157895 0.7052632 0.7052632 0.6947368 0.7052632 0.7368421
## 72 0.6842105 0.6947368 0.6947368 0.6947368 0.6736842 0.6736842 0.6947368
## 73 0.8315789 0.8421053 0.8421053 0.8105263 0.8421053 0.8105263 0.8315789
## 74 0.8526316 0.8421053 0.8421053 0.8631579 0.8421053 0.8631579 0.8526316
## 75 0.8210526 0.8947368 0.8526316 0.8736842 0.8210526 0.8421053 0.8736842
## 76 0.8000000 0.7684211 0.7684211 0.7894737 0.7789474 0.7789474 0.7684211
## 77 0.7157895 0.7263158 0.6947368 0.7052632 0.7052632 0.6947368 0.6947368
## 78 0.6842105 0.6736842 0.6736842 0.6736842 0.6947368 0.7157895 0.6736842
## 79 0.6631579 0.7052632 0.6947368 0.6947368 0.7052632 0.6842105 0.6736842
## 80 0.7578947 0.7578947 0.7157895 0.7789474 0.7578947 0.7473684 0.7684211
## 81 0.8736842 0.8947368 0.8842105 0.8947368 0.8842105 0.9157895 0.8947368
## 82 0.7473684 0.7894737 0.8000000 0.8000000 0.8210526 0.7684211 0.8315789
## 83 0.7263158 0.7473684 0.7368421 0.7684211 0.7368421 0.7578947 0.7473684
## 84 0.8526316 0.8736842 0.8315789 0.8421053 0.8421053 0.8526316 0.8315789
## 85 0.7789474 0.7789474 0.7263158 0.7263158 0.7052632 0.7157895 0.7263158
## 86 0.6631579 0.6526316 0.6210526 0.6631579 0.6526316 0.6736842 0.6526316
## 87 0.6842105 0.7368421 0.7263158 0.7157895 0.7052632 0.7157895 0.6736842
## 88 0.7263158 0.7578947 0.7578947 0.7473684 0.7368421 0.7578947 0.7578947
## 89 0.7473684 0.7578947 0.7263158 0.7684211 0.7473684 0.7052632 0.7263158
## 90 0.8000000 0.7789474 0.7789474 0.7578947 0.7684211 0.7684211 0.8105263
## 91 0.8210526 0.8421053 0.8526316 0.8421053 0.8210526 0.8315789 0.8526316
## 92 0.8105263 0.8315789 0.8105263 0.8000000 0.8105263 0.7789474 0.8000000
## 93 0.8105263 0.8210526 0.8105263 0.8105263 0.8210526 0.8315789 0.8105263
## 94 0.7263158 0.7368421 0.7578947 0.7473684 0.7473684 0.7894737 0.7368421
## 95 0.8315789 0.8315789 0.8315789 0.8315789 0.8315789 0.8421053 0.8210526
## 96 0.8842105 0.8947368 0.8842105 0.9052632 0.8947368 0.8736842 0.8947368
## 97 0.8000000 0.8210526 0.8000000 0.8000000 0.8315789 0.8210526 0.8210526
## 98 0.8631579 0.8631579 0.8631579 0.8631579 0.8315789 0.8526316 0.8421053
## 99 0.9052632 0.8842105 0.8631579 0.8842105 0.8736842 0.8842105 0.8631579
## 100 0.9052632 0.8947368 0.8842105 0.8947368 0.9157895 0.8947368 0.9157895
## 101 0.8000000 0.8000000 0.7894737 0.7894737 0.8210526 0.7789474 0.7894737
## 102 0.8631579 0.8421053 0.8526316 0.8105263 0.8526316 0.8631579 0.8315789
## 103 0.8947368 0.8947368 0.9052632 0.8842105 0.9052632 0.8842105 0.8842105
## 104 0.8000000 0.7684211 0.8315789 0.8210526 0.8315789 0.7894737 0.7894737
## 105 0.8947368 0.8947368 0.8947368 0.9052632 0.8736842 0.8947368 0.8947368
## 106 0.9157895 0.9263158 0.8842105 0.9052632 0.9368421 0.8842105 0.9263158
## loop13 loop14 loop15 loop16 loop17 loop18 loop19
## 1 0.9473684 0.9578947 0.9368421 0.9473684 0.9263158 0.9473684 0.9473684
## 2 0.9578947 0.9473684 0.9789474 0.9578947 0.9578947 0.9368421 0.9578947
## 3 0.9578947 0.9578947 0.9578947 0.9684211 0.9473684 0.9578947 0.9684211
## 4 0.9473684 0.9578947 0.9578947 0.9578947 0.9578947 0.9473684 0.9473684
## 5 0.9578947 0.9473684 0.9473684 0.9473684 0.9578947 0.9684211 0.9473684
## 6 0.7894737 0.7894737 0.7894737 0.7894737 0.8210526 0.7789474 0.8315789
## 7 0.7894737 0.8210526 0.8000000 0.8105263 0.8210526 0.8105263 0.8210526
## 8 0.6947368 0.6842105 0.6947368 0.6842105 0.6947368 0.6947368 0.7052632
## 9 0.7894737 0.8105263 0.8105263 0.7894737 0.8000000 0.8315789 0.8000000
## 10 0.8526316 0.8421053 0.8421053 0.8526316 0.8315789 0.8421053 0.8631579
## 11 0.7684211 0.7894737 0.7684211 0.7684211 0.7684211 0.7789474 0.7894737
## 12 0.8315789 0.9157895 0.8631579 0.8526316 0.8842105 0.8526316 0.8526316
## 13 0.7578947 0.7789474 0.7684211 0.7894737 0.8105263 0.7263158 0.7684211
## 14 0.8421053 0.8421053 0.8210526 0.8421053 0.8105263 0.8526316 0.8210526
## 15 0.7789474 0.8210526 0.8000000 0.8000000 0.8000000 0.8000000 0.7684211
## 16 0.7684211 0.8210526 0.7578947 0.7684211 0.8105263 0.8000000 0.8000000
## 17 0.8315789 0.8631579 0.8105263 0.8631579 0.8421053 0.8421053 0.8421053
## 18 0.8210526 0.8000000 0.8105263 0.7894737 0.8105263 0.8000000 0.8000000
## 19 0.7052632 0.7052632 0.6842105 0.7157895 0.7263158 0.7157895 0.6947368
## 20 0.8315789 0.8631579 0.8421053 0.8421053 0.8421053 0.8421053 0.8526316
## 21 0.6842105 0.6842105 0.6526316 0.6842105 0.6526316 0.6842105 0.6842105
## 22 0.6210526 0.5789474 0.6210526 0.6210526 0.6105263 0.6105263 0.6315789
## 23 0.8210526 0.8105263 0.8315789 0.8210526 0.8315789 0.8421053 0.8315789
## 24 0.8210526 0.8631579 0.8315789 0.8315789 0.8315789 0.8526316 0.8315789
## 25 0.8842105 0.9157895 0.8947368 0.8842105 0.8736842 0.9263158 0.8947368
## 26 0.7894737 0.8000000 0.8210526 0.7789474 0.8210526 0.7894737 0.8000000
## 27 0.7684211 0.7578947 0.7263158 0.7263158 0.7473684 0.7578947 0.7263158
## 28 0.6736842 0.6631579 0.6736842 0.6947368 0.6210526 0.6631579 0.6842105
## 29 0.7263158 0.7157895 0.7052632 0.7052632 0.7263158 0.7368421 0.7263158
## 30 0.6631579 0.7157895 0.7052632 0.6947368 0.7052632 0.7052632 0.7157895
## 31 0.6947368 0.6631579 0.6736842 0.6421053 0.6631579 0.6526316 0.6526316
## 32 0.8315789 0.8315789 0.8105263 0.7894737 0.8315789 0.8526316 0.8421053
## 33 0.8736842 0.8842105 0.8842105 0.8842105 0.9052632 0.9052632 0.8947368
## 34 0.8526316 0.8631579 0.8842105 0.8842105 0.8631579 0.8842105 0.8631579
## 35 0.8315789 0.8315789 0.8315789 0.8105263 0.8421053 0.8315789 0.8315789
## 36 0.8526316 0.8736842 0.8526316 0.8315789 0.8421053 0.8421053 0.8315789
## 37 0.8421053 0.8000000 0.8315789 0.8210526 0.8421053 0.8421053 0.8526316
## 38 0.8000000 0.8210526 0.8210526 0.8000000 0.8421053 0.8421053 0.8105263
## 39 0.8315789 0.8210526 0.8421053 0.8421053 0.8421053 0.8421053 0.8421053
## 40 0.7894737 0.8105263 0.8000000 0.8000000 0.7789474 0.7894737 0.7894737
## 41 0.8631579 0.8631579 0.8526316 0.8631579 0.8631579 0.8526316 0.8526316
## 42 0.8947368 0.8947368 0.9157895 0.8947368 0.9157895 0.9157895 0.9263158
## 43 0.8421053 0.8421053 0.8421053 0.8526316 0.8526316 0.8736842 0.8631579
## 44 0.8736842 0.8947368 0.8842105 0.8526316 0.8947368 0.8736842 0.8842105
## 45 0.8421053 0.7789474 0.8000000 0.8105263 0.8105263 0.8105263 0.7894737
## 46 0.7684211 0.7473684 0.7578947 0.7263158 0.7473684 0.7684211 0.7473684
## 47 0.7263158 0.7157895 0.7263158 0.7368421 0.7368421 0.7473684 0.7473684
## 48 0.7473684 0.7578947 0.7789474 0.7894737 0.7684211 0.7684211 0.8000000
## 49 0.8000000 0.7789474 0.7578947 0.8105263 0.8105263 0.8315789 0.8105263
## 50 0.7578947 0.7368421 0.7263158 0.7368421 0.7578947 0.7473684 0.7684211
## 51 0.8000000 0.8105263 0.8105263 0.7894737 0.7894737 0.7894737 0.7894737
## 52 0.7473684 0.7684211 0.7684211 0.7473684 0.7789474 0.7684211 0.7473684
## 53 0.8421053 0.8210526 0.8421053 0.8210526 0.8210526 0.8105263 0.8315789
## 54 0.8210526 0.8105263 0.8105263 0.8315789 0.8105263 0.8315789 0.7894737
## 55 0.6736842 0.7263158 0.6842105 0.7157895 0.6947368 0.7263158 0.7263158
## 56 0.8315789 0.8105263 0.8105263 0.8105263 0.8210526 0.8210526 0.8105263
## 57 0.7368421 0.7684211 0.7473684 0.7578947 0.7473684 0.7578947 0.7789474
## 58 0.8526316 0.8315789 0.8421053 0.8631579 0.8421053 0.8631579 0.8526316
## 59 0.8210526 0.8105263 0.8000000 0.8210526 0.7789474 0.8315789 0.8105263
## 60 0.7473684 0.7578947 0.7894737 0.7684211 0.7578947 0.7473684 0.7894737
## 61 0.8315789 0.8421053 0.7789474 0.8105263 0.8105263 0.8105263 0.8105263
## 62 0.7789474 0.7894737 0.8105263 0.7789474 0.8000000 0.8000000 0.8000000
## 63 0.8105263 0.8000000 0.8105263 0.8000000 0.8105263 0.8210526 0.8105263
## 64 0.8631579 0.8631579 0.8631579 0.8631579 0.8631579 0.8947368 0.8736842
## 65 0.8842105 0.8736842 0.9157895 0.9052632 0.8947368 0.8842105 0.8947368
## 66 0.8210526 0.8315789 0.8315789 0.8421053 0.8000000 0.8421053 0.8315789
## 67 0.8526316 0.8105263 0.8210526 0.8000000 0.8315789 0.8105263 0.8210526
## 68 0.8315789 0.8315789 0.8631579 0.8210526 0.8315789 0.8631579 0.8315789
## 69 0.7473684 0.7263158 0.7473684 0.7263158 0.7263158 0.7368421 0.7263158
## 70 0.7263158 0.7052632 0.6842105 0.7052632 0.7263158 0.7157895 0.7473684
## 71 0.7157895 0.6842105 0.7263158 0.7052632 0.7052632 0.6736842 0.6947368
## 72 0.7157895 0.6947368 0.6631579 0.6947368 0.6947368 0.7157895 0.7052632
## 73 0.8421053 0.8315789 0.8210526 0.8210526 0.8315789 0.8631579 0.8315789
## 74 0.8631579 0.8315789 0.8631579 0.8526316 0.8315789 0.8526316 0.8421053
## 75 0.8736842 0.8736842 0.8421053 0.8000000 0.8736842 0.8736842 0.8631579
## 76 0.7578947 0.7684211 0.7789474 0.7789474 0.7789474 0.7684211 0.8000000
## 77 0.6842105 0.6947368 0.6947368 0.7052632 0.7052632 0.7157895 0.6842105
## 78 0.6631579 0.7052632 0.7157895 0.7052632 0.6736842 0.6631579 0.7157895
## 79 0.6842105 0.7052632 0.6842105 0.6736842 0.7263158 0.7157895 0.7263158
## 80 0.7789474 0.7894737 0.7578947 0.7368421 0.7368421 0.7263158 0.7368421
## 81 0.9157895 0.8947368 0.8842105 0.8947368 0.9052632 0.8842105 0.9052632
## 82 0.7578947 0.7789474 0.7684211 0.7684211 0.7684211 0.7578947 0.7894737
## 83 0.7789474 0.7473684 0.7368421 0.7473684 0.7578947 0.7263158 0.7368421
## 84 0.8631579 0.8421053 0.8842105 0.8631579 0.8210526 0.8736842 0.8631579
## 85 0.7368421 0.7368421 0.7578947 0.7368421 0.7368421 0.7684211 0.7052632
## 86 0.6631579 0.6421053 0.6526316 0.6421053 0.6631579 0.6631579 0.6315789
## 87 0.6842105 0.7052632 0.7052632 0.7052632 0.7263158 0.7157895 0.6947368
## 88 0.7368421 0.7157895 0.7368421 0.7578947 0.7263158 0.7473684 0.7473684
## 89 0.7578947 0.7368421 0.7789474 0.7368421 0.7473684 0.7052632 0.7263158
## 90 0.7789474 0.7789474 0.7894737 0.7789474 0.7894737 0.8105263 0.7894737
## 91 0.8736842 0.8210526 0.8631579 0.8526316 0.8631579 0.8210526 0.8631579
## 92 0.8105263 0.8105263 0.7894737 0.8000000 0.8105263 0.8000000 0.8315789
## 93 0.8000000 0.8421053 0.8210526 0.8210526 0.8105263 0.8210526 0.8315789
## 94 0.7473684 0.7789474 0.7789474 0.7578947 0.7684211 0.7473684 0.7473684
## 95 0.8421053 0.7894737 0.8526316 0.8210526 0.8210526 0.8105263 0.8526316
## 96 0.8842105 0.8631579 0.8736842 0.8631579 0.8842105 0.8842105 0.8842105
## 97 0.8210526 0.8105263 0.8315789 0.8210526 0.7789474 0.8000000 0.8421053
## 98 0.8736842 0.8842105 0.8842105 0.8526316 0.8421053 0.8842105 0.8736842
## 99 0.8842105 0.8947368 0.8947368 0.8947368 0.8736842 0.8947368 0.8421053
## 100 0.8842105 0.8947368 0.9052632 0.8842105 0.9052632 0.8736842 0.9157895
## 101 0.8000000 0.8105263 0.8105263 0.8105263 0.7789474 0.8210526 0.8000000
## 102 0.8421053 0.8315789 0.8210526 0.8526316 0.8631579 0.8315789 0.8526316
## 103 0.8842105 0.8947368 0.8842105 0.8947368 0.9052632 0.8842105 0.8947368
## 104 0.8421053 0.7789474 0.8105263 0.8000000 0.7578947 0.8210526 0.8000000
## 105 0.8842105 0.8947368 0.8842105 0.8947368 0.8947368 0.8947368 0.8842105
## 106 0.9052632 0.9052632 0.9263158 0.9157895 0.9052632 0.9052632 0.9052632
## loop20 mean
## 1 0.9473684 0.9415789
## 2 0.9473684 0.9536842
## 3 0.9789474 0.9610526
## 4 0.9684211 0.9610526
## 5 0.9473684 0.9542105
## 6 0.8315789 0.7989474
## 7 0.8105263 0.8131579
## 8 0.6947368 0.6947368
## 9 0.8105263 0.8031579
## 10 0.8526316 0.8457895
## 11 0.7684211 0.7773684
## 12 0.8736842 0.8578947
## 13 0.7684211 0.7752632
## 14 0.8000000 0.8352632
## 15 0.8315789 0.8000000
## 16 0.7894737 0.7894737
## 17 0.8421053 0.8442105
## 18 0.7578947 0.7984211
## 19 0.6947368 0.6978947
## 20 0.8421053 0.8378947
## 21 0.6736842 0.6789474
## 22 0.6105263 0.6094737
## 23 0.8210526 0.8289474
## 24 0.8421053 0.8405263
## 25 0.9157895 0.8952632
## 26 0.8105263 0.8047368
## 27 0.7473684 0.7421053
## 28 0.6421053 0.6610526
## 29 0.7263158 0.7221053
## 30 0.6947368 0.7010526
## 31 0.6736842 0.6668421
## 32 0.8210526 0.8405263
## 33 0.8947368 0.8857895
## 34 0.8526316 0.8673684
## 35 0.8105263 0.8242105
## 36 0.8631579 0.8557895
## 37 0.8421053 0.8252632
## 38 0.8421053 0.8147368
## 39 0.8421053 0.8389474
## 40 0.7894737 0.7984211
## 41 0.8631579 0.8505263
## 42 0.9052632 0.9110526
## 43 0.8631579 0.8484211
## 44 0.8842105 0.8826316
## 45 0.7894737 0.8089474
## 46 0.7684211 0.7526316
## 47 0.7368421 0.7278947
## 48 0.7789474 0.7673684
## 49 0.8210526 0.7978947
## 50 0.7473684 0.7505263
## 51 0.8000000 0.8047368
## 52 0.7684211 0.7547368
## 53 0.8210526 0.8278947
## 54 0.8105263 0.8142105
## 55 0.7263158 0.7115789
## 56 0.8210526 0.8173684
## 57 0.7684211 0.7557895
## 58 0.8736842 0.8515789
## 59 0.8421053 0.8105263
## 60 0.7157895 0.7621053
## 61 0.8105263 0.8163158
## 62 0.7789474 0.7978947
## 63 0.8000000 0.8084211
## 64 0.8631579 0.8673684
## 65 0.8842105 0.8968421
## 66 0.8210526 0.8273684
## 67 0.8000000 0.8194737
## 68 0.8631579 0.8463158
## 69 0.7263158 0.7373684
## 70 0.6947368 0.7147368
## 71 0.7368421 0.7042105
## 72 0.6947368 0.6910526
## 73 0.8421053 0.8310526
## 74 0.8421053 0.8478947
## 75 0.8105263 0.8552632
## 76 0.7789474 0.7836842
## 77 0.7368421 0.7000000
## 78 0.6842105 0.6878947
## 79 0.7157895 0.7000000
## 80 0.7894737 0.7552632
## 81 0.8842105 0.8942105
## 82 0.7789474 0.7805263
## 83 0.7473684 0.7468421
## 84 0.8315789 0.8521053
## 85 0.7684211 0.7426316
## 86 0.6526316 0.6542105
## 87 0.7157895 0.7047368
## 88 0.7473684 0.7447368
## 89 0.7263158 0.7426316
## 90 0.8000000 0.7868421
## 91 0.8842105 0.8500000
## 92 0.8000000 0.8042105
## 93 0.8315789 0.8194737
## 94 0.7684211 0.7557895
## 95 0.8315789 0.8300000
## 96 0.8736842 0.8805263
## 97 0.8421053 0.8147368
## 98 0.8526316 0.8552632
## 99 0.8842105 0.8810526
## 100 0.8947368 0.8989474
## 101 0.8000000 0.8005263
## 102 0.8421053 0.8410526
## 103 0.8842105 0.8910526
## 104 0.8315789 0.8031579
## 105 0.8736842 0.8894737
## 106 0.8947368 0.9126316The link of the label.csv:https://reurl.cc/e5ejOQ