Classification on Spotify(Overall #Streams)-R Notebook
Here we are going to do classification on Spotify. When this approach was used,analyzing popularity overall, the regression and classification trees method indicated that rap and trap were the two most important features for our model.
#install.packages("rpart")
#install.packages("partykit")
#install.packages("randomForest")
#install.packages("xgboost")
#install.packages("caret")library(rpart)
library(partykit)## Loading required package: grid## Loading required package: libcoin## Loading required package: mvtnormlibrary(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':
##
## combinelibrary(xgboost)##
## Attaching package: 'xgboost'## The following object is masked from 'package:dplyr':
##
## slicelibrary(caret)## Loading required package: lattice## Loading required package: ggplot2##
## Attaching package: 'ggplot2'## The following object is masked from 'package:randomForest':
##
## marginlibrary(e1071)Let us make sure we are in the right working directory.
getwd()## [1] "C:/Users/Norge/Documents"Let us define the dataset project by reading the csv file spotify2.
project<-read.csv("spotify2.csv",sep = ",",header = TRUE)head(project)Above we can see that our dataset consists of 17 columns. Besides the top eight genres, we included other variables such as fusion genres, artist,primary artist, track,streams and week starting.
The function summary is returning the five number summary for the quantitative variables and the lenght,class,and mode for the qualitative ones(character).
summary(project)## Track Artist Primary.Artist Streams
## Length:4276 Length:4276 Length:4276 Min. : 968095
## Class :character Class :character Class :character 1st Qu.: 1613945
## Mode :character Mode :character Mode :character Median : 2114108
## Mean : 3197605
## 3rd Qu.: 3511572
## Max. :30433574
## Week.Starting rap pop.rap trap
## Length:4276 Length:4276 Length:4276 Length:4276
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
## pop hip.hop post.teen.pop dance.pop
## Length:4276 Length:4276 Length:4276 Length:4276
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
## southern.hip.hop pop.genre hip.hop.genre rap.genre
## Length:4276 Length:4276 Length:4276 Length:4276
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
## popularity
## Length:4276
## Class :character
## Mode :character
##
##
## Let us make sure we understand and realize the data type for each column.
str(project)## 'data.frame': 4276 obs. of 17 variables:
## $ Track : chr "Caroline" "Chill Bill (feat. J. Davi$ & Spooks)" "Jingle Bell Rock" "Juju on That Beat (TZ Anthem)" ...
## $ Artist : chr "Amin?" "Rob $tone" "Bobby Helms" "Zay Hilfigerrr, Zayion McCall" ...
## $ Primary.Artist : chr "Amin?" "Rob $tone" "Bobby Helms" "Zay Hilfigerrr" ...
## $ Streams : int 4865290 3536430 2904013 1880453 1773788 1581791 1554969 1326118 1234946 1066962 ...
## $ Week.Starting : chr "Thursday, December 29, 2016" "Thursday, December 29, 2016" "Thursday, December 29, 2016" "Thursday, December 29, 2016" ...
## $ rap : chr "no" "no" "no" "no" ...
## $ pop.rap : chr "no" "no" "no" "no" ...
## $ trap : chr "no" "no" "no" "no" ...
## $ pop : chr "no" "no" "no" "no" ...
## $ hip.hop : chr "no" "no" "no" "no" ...
## $ post.teen.pop : chr "no" "no" "no" "no" ...
## $ dance.pop : chr "no" "no" "no" "no" ...
## $ southern.hip.hop: chr "no" "no" "no" "no" ...
## $ pop.genre : chr "no" "no" "no" "no" ...
## $ hip.hop.genre : chr "no" "no" "no" "no" ...
## $ rap.genre : chr "yes" "yes" "no" "no" ...
## $ popularity : chr "very popular" "very popular" "popular" "popular" ...We observed that popularity is a character, so let us delete any missing value and then proceed to make our dependent variable a factor.
mydata1<-na.omit(project)#View(mydata1)mydata1$popularity<-ifelse(mydata1$Streams>=2500000,"very popular","popular")str(mydata1)## 'data.frame': 4276 obs. of 17 variables:
## $ Track : chr "Caroline" "Chill Bill (feat. J. Davi$ & Spooks)" "Jingle Bell Rock" "Juju on That Beat (TZ Anthem)" ...
## $ Artist : chr "Amin?" "Rob $tone" "Bobby Helms" "Zay Hilfigerrr, Zayion McCall" ...
## $ Primary.Artist : chr "Amin?" "Rob $tone" "Bobby Helms" "Zay Hilfigerrr" ...
## $ Streams : int 4865290 3536430 2904013 1880453 1773788 1581791 1554969 1326118 1234946 1066962 ...
## $ Week.Starting : chr "Thursday, December 29, 2016" "Thursday, December 29, 2016" "Thursday, December 29, 2016" "Thursday, December 29, 2016" ...
## $ rap : chr "no" "no" "no" "no" ...
## $ pop.rap : chr "no" "no" "no" "no" ...
## $ trap : chr "no" "no" "no" "no" ...
## $ pop : chr "no" "no" "no" "no" ...
## $ hip.hop : chr "no" "no" "no" "no" ...
## $ post.teen.pop : chr "no" "no" "no" "no" ...
## $ dance.pop : chr "no" "no" "no" "no" ...
## $ southern.hip.hop: chr "no" "no" "no" "no" ...
## $ pop.genre : chr "no" "no" "no" "no" ...
## $ hip.hop.genre : chr "no" "no" "no" "no" ...
## $ rap.genre : chr "yes" "yes" "no" "no" ...
## $ popularity : chr "very popular" "very popular" "very popular" "popular" ...mydata1$popularity<-as.factor(mydata1$popularity)data1<-mydata1[,-c(1:5)]#View(data1)mydata2<-data1[,-c(9:11)]#View(mydata2)str(mydata2)## 'data.frame': 4276 obs. of 9 variables:
## $ rap : chr "no" "no" "no" "no" ...
## $ pop.rap : chr "no" "no" "no" "no" ...
## $ trap : chr "no" "no" "no" "no" ...
## $ pop : chr "no" "no" "no" "no" ...
## $ hip.hop : chr "no" "no" "no" "no" ...
## $ post.teen.pop : chr "no" "no" "no" "no" ...
## $ dance.pop : chr "no" "no" "no" "no" ...
## $ southern.hip.hop: chr "no" "no" "no" "no" ...
## $ popularity : Factor w/ 2 levels "popular","very popular": 2 2 2 1 1 1 1 1 1 1 ...mydata3 <-mydata2 %>%
mutate_if(is.character, factor)Train and Test Data
The purpose of creating two different datasets from the original one is to improve our ability so as to accurately predict the previously unused or unseen data.
There are a number of ways to proportionally split our data into train and test sets: 50/50, 60/40, 70/30, 80/20, and so forth. The data split that you select should be based on your experience and judgment. For this exercise, we will use a 80/20 split, as follows:
set.seed(123) # random number generator
ind <- sample(2, nrow(mydata3), replace = TRUE, prob = c(0.8, 0.2))train1 <- mydata3[ind==1, ] #the training set
test1 <- mydata3[ind==2, ] # the testing set dim(train1)## [1] 3406 9dim(test1)## [1] 870 9table(train1$popularity)##
## popular very popular
## 2090 1316table(test1$popularity)##
## popular very popular
## 542 328tree.data<-rpart(popularity~.,data = train1)
tree.data$cptable## CP nsplit rel error xerror xstd
## 1 0.0406535 0 1.000000 1.0000000 0.02159349
## 2 0.0100000 2 0.918693 0.9179331 0.02121627plot(as.party(tree.data))
cp<-min(tree.data$cptable[1,])
prune.tree.data<-prune(tree.data,cp<-cp)
plot(as.party(prune.tree.data))
rparty.test<-predict(tree.data,newdata = test1,
type ="class")
table(rparty.test,test1$popularity)##
## rparty.test popular very popular
## popular 485 249
## very popular 57 79rparty<-as.factor(rparty.test)rparty## 4 5 8 11 16 20
## popular popular popular popular popular popular
## 21 24 31 32 50 59
## popular popular popular popular popular popular
## 65 67 68 87 88 89
## popular popular popular popular popular popular
## 104 106 107 111 114 118
## popular popular popular popular popular popular
## 126 132 137 139 145 151
## popular popular popular popular popular popular
## 173 179 181 189 190 193
## popular popular popular popular popular popular
## 195 202 206 219 220 222
## popular popular popular popular popular popular
## 230 238 240 248 249 260
## popular popular popular popular popular popular
## 261 262 264 271 277 294
## popular popular popular popular popular popular
## 296 297 316 317 320 321
## popular popular popular popular very popular very popular
## 327 330 334 340 347 352
## very popular very popular very popular very popular very popular very popular
## 356 360 363 373 376 380
## very popular very popular very popular very popular very popular very popular
## 386 391 400 401 403 412
## very popular very popular very popular very popular very popular very popular
## 417 425 430 431 434 445
## popular popular popular popular popular popular
## 456 457 461 470 472 482
## popular popular popular popular popular popular
## 485 490 491 496 509 513
## popular popular popular popular popular popular
## 520 527 529 531 534 538
## popular very popular very popular popular popular popular
## 541 543 546 548 549 554
## popular popular popular popular popular popular
## 562 568 570 572 575 581
## popular popular popular popular popular popular
## 582 583 585 589 593 596
## popular popular popular popular popular popular
## 599 606 608 614 617 619
## popular popular popular popular popular popular
## 621 622 628 632 637 639
## popular popular very popular very popular very popular popular
## 643 652 656 657 661 662
## popular popular popular popular popular popular
## 667 677 683 684 685 701
## popular popular popular popular popular popular
## 704 719 724 727 732 734
## popular popular popular popular popular popular
## 737 738 741 750 758 771
## popular popular popular popular popular popular
## 772 774 780 782 785 790
## popular popular popular popular popular popular
## 791 795 806 814 824 841
## popular popular popular popular popular popular
## 847 853 857 860 875 879
## popular popular popular popular popular popular
## 882 886 895 901 903 908
## popular popular popular popular popular popular
## 909 913 916 921 924 931
## popular popular popular popular popular popular
## 935 938 939 941 953 956
## popular popular popular popular popular popular
## 965 973 977 983 985 996
## popular popular popular popular popular popular
## 1004 1005 1025 1041 1049 1050
## popular popular popular popular popular popular
## 1052 1053 1069 1072 1073 1074
## popular popular popular popular popular popular
## 1089 1091 1097 1101 1105 1108
## popular popular popular popular popular popular
## 1109 1112 1118 1127 1132 1141
## popular popular popular popular popular popular
## 1144 1151 1154 1158 1170 1174
## popular popular popular very popular very popular very popular
## 1184 1197 1199 1201 1202 1206
## very popular very popular very popular very popular very popular very popular
## 1212 1216 1218 1220 1224 1225
## very popular very popular very popular very popular very popular very popular
## 1229 1239 1245 1251 1256 1259
## very popular very popular very popular very popular very popular very popular
## 1268 1270 1275 1282 1291 1294
## very popular very popular very popular very popular very popular very popular
## 1299 1304 1313 1321 1323 1325
## very popular very popular very popular popular popular popular
## 1339 1346 1358 1363 1376 1378
## popular popular popular popular popular popular
## 1383 1385 1388 1391 1396 1408
## popular popular popular popular popular popular
## 1410 1412 1421 1424 1428 1429
## popular popular popular popular popular popular
## 1431 1434 1438 1459 1461 1463
## popular popular popular popular popular popular
## 1466 1467 1478 1479 1480 1483
## popular popular popular popular popular popular
## 1484 1485 1490 1493 1496 1497
## popular popular popular popular popular popular
## 1501 1502 1512 1513 1531 1533
## popular popular popular popular popular popular
## 1539 1550 1551 1560 1563 1568
## popular very popular very popular very popular very popular very popular
## 1570 1585 1592 1604 1605 1607
## very popular popular popular popular popular popular
## 1614 1615 1626 1630 1635 1636
## popular popular popular popular popular popular
## 1642 1644 1646 1648 1658 1661
## popular popular popular popular popular popular
## 1667 1683 1690 1694 1695 1696
## popular popular popular popular popular popular
## 1697 1704 1705 1709 1714 1716
## popular popular popular popular popular popular
## 1719 1721 1731 1734 1735 1738
## popular popular popular popular popular popular
## 1739 1740 1742 1747 1749 1751
## popular popular popular popular popular popular
## 1752 1755 1757 1760 1766 1767
## popular popular popular popular popular popular
## 1770 1787 1790 1794 1798 1802
## popular popular popular popular popular popular
## 1807 1809 1821 1824 1826 1828
## popular popular popular popular popular popular
## 1831 1833 1839 1851 1852 1857
## popular popular popular popular popular popular
## 1860 1864 1868 1872 1876 1879
## popular popular popular popular popular popular
## 1881 1892 1895 1898 1904 1919
## popular popular popular popular popular popular
## 1923 1930 1938 1946 1949 1961
## popular popular popular popular popular popular
## 1969 1972 1979 1993 1996 2011
## popular popular popular popular popular popular
## 2015 2021 2023 2038 2039 2045
## popular popular popular popular popular popular
## 2046 2047 2053 2055 2062 2064
## popular popular very popular popular popular popular
## 2069 2070 2072 2079 2088 2097
## popular popular popular popular popular very popular
## 2104 2109 2110 2120 2121 2125
## popular popular popular popular popular popular
## 2127 2130 2138 2139 2152 2158
## popular popular popular popular popular popular
## 2161 2166 2168 2175 2178 2181
## popular popular popular popular popular popular
## 2187 2194 2195 2201 2223 2225
## popular popular popular popular popular popular
## 2229 2232 2237 2240 2244 2245
## popular popular popular popular popular popular
## 2246 2251 2252 2260 2262 2268
## popular popular popular popular popular popular
## 2275 2276 2277 2282 2292 2295
## popular popular popular popular very popular very popular
## 2298 2300 2302 2309 2316 2338
## very popular very popular very popular very popular very popular very popular
## 2339 2340 2343 2344 2352 2364
## very popular very popular very popular very popular very popular very popular
## 2371 2377 2380 2383 2385 2395
## popular popular popular popular popular popular
## 2396 2400 2404 2405 2411 2415
## popular popular popular popular popular popular
## 2422 2428 2446 2451 2455 2456
## popular popular popular popular popular popular
## 2463 2479 2485 2494 2496 2497
## popular very popular very popular popular popular popular
## 2501 2509 2526 2530 2531 2535
## popular popular popular popular popular popular
## 2539 2540 2541 2546 2548 2555
## popular popular popular popular popular popular
## 2562 2566 2570 2583 2587 2588
## popular popular popular popular popular popular
## 2596 2599 2604 2620 2621 2637
## popular popular popular popular popular popular
## 2642 2645 2647 2651 2652 2653
## popular popular popular popular popular popular
## 2678 2683 2684 2688 2690 2696
## popular popular popular popular popular popular
## 2698 2700 2706 2707 2708 2709
## popular popular popular popular popular popular
## 2711 2716 2721 2724 2725 2726
## popular popular popular popular popular popular
## 2733 2735 2740 2745 2758 2776
## popular popular popular popular popular popular
## 2784 2785 2787 2790 2795 2800
## popular popular popular popular popular popular
## 2808 2810 2811 2814 2815 2818
## popular popular popular popular popular popular
## 2824 2834 2837 2840 2843 2851
## popular popular popular popular popular popular
## 2855 2858 2868 2876 2880 2883
## popular popular popular popular popular popular
## 2886 2890 2892 2901 2905 2907
## popular popular popular popular popular popular
## 2913 2915 2928 2942 2946 2953
## popular popular popular popular popular popular
## 2956 2961 2967 2977 2979 2986
## popular popular popular very popular very popular popular
## 2987 2993 2995 2997 3002 3009
## popular popular popular popular popular popular
## 3010 3011 3017 3019 3026 3027
## very popular popular popular popular popular popular
## 3028 3030 3040 3050 3053 3056
## popular popular popular popular popular popular
## 3060 3061 3068 3071 3072 3076
## popular popular popular popular popular popular
## 3081 3087 3091 3102 3107 3109
## popular popular popular popular popular popular
## 3116 3118 3123 3124 3126 3130
## popular popular popular popular popular popular
## 3133 3141 3148 3152 3163 3174
## popular popular popular popular popular popular
## 3177 3180 3182 3194 3195 3213
## popular very popular very popular very popular very popular very popular
## 3215 3217 3219 3221 3223 3235
## very popular very popular very popular very popular very popular very popular
## 3237 3243 3244 3246 3247 3255
## very popular very popular very popular very popular very popular very popular
## 3258 3259 3266 3267 3273 3275
## very popular very popular very popular very popular very popular very popular
## 3276 3285 3287 3289 3297 3300
## very popular very popular very popular popular popular popular
## 3305 3314 3317 3321 3328 3333
## popular popular popular popular popular popular
## 3335 3339 3342 3343 3348 3349
## popular popular popular popular popular popular
## 3351 3353 3359 3364 3367 3374
## popular popular popular popular popular popular
## 3376 3378 3381 3387 3396 3407
## popular popular very popular popular popular popular
## 3409 3414 3415 3417 3419 3423
## popular popular popular popular popular popular
## 3437 3438 3461 3466 3467 3480
## popular popular popular popular popular popular
## 3487 3488 3489 3494 3497 3503
## popular popular popular popular popular very popular
## 3510 3511 3529 3530 3532 3537
## very popular very popular very popular very popular very popular very popular
## 3542 3545 3546 3551 3554 3556
## very popular very popular very popular very popular very popular very popular
## 3566 3568 3571 3574 3575 3584
## very popular very popular very popular very popular very popular very popular
## 3585 3596 3598 3606 3607 3609
## very popular very popular popular popular popular popular
## 3626 3635 3643 3646 3650 3651
## popular popular popular popular popular popular
## 3655 3659 3664 3674 3675 3677
## popular popular popular popular popular popular
## 3682 3684 3687 3688 3689 3703
## popular popular popular popular popular popular
## 3705 3713 3718 3721 3724 3731
## popular popular popular popular popular popular
## 3736 3737 3739 3741 3743 3751
## popular popular popular popular popular popular
## 3753 3762 3764 3766 3768 3771
## popular popular popular popular popular popular
## 3772 3773 3776 3777 3783 3785
## popular popular popular popular popular popular
## 3794 3796 3798 3801 3806 3807
## popular popular popular popular popular popular
## 3819 3821 3825 3831 3836 3843
## popular popular popular popular popular popular
## 3850 3851 3863 3868 3870 3872
## popular popular popular popular popular popular
## 3875 3880 3881 3885 3899 3908
## popular popular popular popular popular popular
## 3909 3919 3920 3923 3927 3930
## popular popular popular popular popular popular
## 3931 3932 3933 3936 3941 3947
## popular popular popular popular popular popular
## 3948 3951 3952 3963 3969 3972
## popular popular popular popular popular popular
## 3974 3975 3978 3979 3983 3986
## popular popular popular popular popular popular
## 3994 4002 4004 4007 4010 4012
## popular popular popular popular popular popular
## 4016 4017 4031 4036 4043 4045
## popular popular popular popular popular popular
## 4050 4057 4075 4076 4077 4078
## popular popular popular popular popular popular
## 4084 4086 4098 4104 4107 4110
## popular very popular very popular popular popular popular
## 4120 4121 4122 4125 4126 4134
## very popular very popular very popular popular popular popular
## 4140 4153 4154 4160 4170 4172
## popular popular popular popular popular popular
## 4181 4184 4198 4208 4212 4229
## popular popular popular popular popular popular
## 4234 4242 4247 4249 4250 4251
## popular popular popular popular popular popular
## 4254 4256 4266 4267 4270 4272
## popular popular popular very popular popular popular
## Levels: popular very popularModeling and Evaluation
We will use the function glm() (from base R) for the logistic regression model.
An R installation comes with the glm() function fitting the generalized linear models, which are a class of models that includes logistic regression. The code syntax is similar to the lm() function that we used for linear regression. One difference is that we must use the family = binomial argument in the function, which tells R to run a logistic regression method instead of the other versions of the generalized linear models. We will start by creating a model that includes all of the features on the train set and see how it performs on the test set:
full.fit <- glm(popularity ~ ., family = binomial, data = train1)Create a summary of the model:
summary(full.fit)##
## Call:
## glm(formula = popularity ~ ., family = binomial, data = train1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -1.5521 -0.9465 -0.7698 1.2568 2.0634
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.79116 0.07181 -11.017 < 2e-16 ***
## rapyes 1.43177 0.13488 10.615 < 2e-16 ***
## pop.rapyes -0.28682 0.10067 -2.849 0.00439 **
## trapyes -0.82543 0.12776 -6.461 1.04e-10 ***
## popyes 0.49432 0.11852 4.171 3.04e-05 ***
## hip.hopyes -0.14558 0.11874 -1.226 0.22017
## post.teen.popyes 0.57953 0.13878 4.176 2.97e-05 ***
## dance.popyes -0.85361 0.13473 -6.336 2.36e-10 ***
## southern.hip.hopyes -0.44750 0.15311 -2.923 0.00347 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 4544.3 on 3405 degrees of freedom
## Residual deviance: 4318.6 on 3397 degrees of freedom
## AIC: 4336.6
##
## Number of Fisher Scoring iterations: 4You cannot translate the coefficients in logistic regression as “the change in Y is based on one-unit change in X”.
This is where the odds ratio can be quite helpful. The beta coefficients from the log function can be converted to odds ratios with an exponent (beta).
In order to produce the odds ratios in R, we will use the following exp(coef()) syntax:
exp(coef(full.fit))## (Intercept) rapyes pop.rapyes trapyes
## 0.4533196 4.1861184 0.7506500 0.4380450
## popyes hip.hopyes post.teen.popyes dance.popyes
## 1.6393866 0.8645207 1.7852023 0.4258764
## southern.hip.hopyes
## 0.6392221The interpretation of an odds ratio is the change in the outcome odds resulting from a unit change in the feature. If the value is greater than 1, it indicates that, as the feature increases, the odds of the outcome increase. Conversely, a value less than 1 would mean that, as the feature increases, the odds of the outcome decrease.
Testing the model
You will first have to create a vector of the predicted probabilities, as follows:
train.probs <- predict(full.fit, type = "response")
# inspect the first 5 probabilities
#train.probs[1:5]Next, we need to evaluate how well the model performed in training and then evaluate how it fits on the test set. A quick way to do this is to produce a confusion matrix. The default value by which the function selects either very popular or popular is 0.50, which is to say that any probability at or above 0.50 is classified as very popular:
y <- ifelse(mydata3$popularity == "very popular", 1, 0)
trainY1<-y[ind==1]
testY1<-y[ind==2]#install.packages("InformationValue")library(InformationValue)##
## Attaching package: 'InformationValue'## The following objects are masked from 'package:caret':
##
## confusionMatrix, precision, sensitivity, specificityconfusionMatrix(trainY1,train.probs)misClassError(trainY1, train.probs)## [1] 0.3526test.probs <- predict(full.fit, newdata = test1, type = "response")
#misclassification error
misClassError(testY1, test.probs)## [1] 0.3414# confusion matrix
confusionMatrix(testY1, test.probs)#install.packages("nnet")library(nnet)modelANN<-nnet(popularity~.,data=train1,size = 3,decay = 0.0001,maxit = 500)## # weights: 31
## initial value 2633.427934
## iter 10 value 2166.139977
## iter 20 value 2136.416823
## iter 30 value 2126.094577
## iter 40 value 2122.224012
## iter 50 value 2121.374062
## iter 60 value 2121.003099
## iter 70 value 2120.725536
## iter 80 value 2120.546573
## iter 90 value 2120.080351
## iter 100 value 2119.951912
## iter 110 value 2119.778207
## iter 120 value 2119.763345
## iter 130 value 2119.743264
## iter 140 value 2119.741148
## iter 150 value 2119.691713
## iter 160 value 2119.273908
## iter 170 value 2119.162497
## iter 180 value 2119.129043
## iter 190 value 2119.122976
## final value 2119.119594
## convergedtest1$pred_nnet<-predict(modelANN,test1,type="class")#confmat<-data.frame("Prediction"=test1$pred_nnet,"Actual"=te#st1$popularity)#accuracyANN<-data.frame("Accuracy"=nrow(subset(confumatNaive#,Actual==Prediction))/nrow(confumatNaive))
#accuracyANN#Function for different sizes and different samples in ANN
accuracyANNsize<-function(trials){
acc <- data.frame(i = integer(),j= integer(),Accuracy= integer())
for(i in 450:trials) {
# random sample
smp_size <- floor(0.80 * nrow(mydata3))
## set the seed to make the partition reproducible
set.seed(i)
train_ind <- sample(seq_len(nrow(mydata3)), size = smp_size)
trainC <- mydata3[train_ind, ]
testC <- mydata3[-train_ind, ]
for(j in 2:8){
modelANNC<-nnet(popularity~.,data=trainC,size = j,decay = 0.0001,maxit = 500)
testC$pred_nnet<-predict(modelANNC,testC,type="class")
confmatC<-data.frame(Prediction=testC$pred_nnet,Actual=testC$popularity)
accuracy<-nrow(subset(confmatC,Actual==Prediction))/nrow(confmatC)
Size=j
trial=i
attempt <- data.frame(Trial = trial, Size=Size,Accuracy = accuracy)
acc <- rbind(acc,attempt)
}
}
return(acc)
}#Running the function for 77 combinations between sizes and random samples
accuracyANN10<-accuracyANNsize(460)## # weights: 21
## initial value 2285.669929
## iter 10 value 2169.799526
## iter 20 value 2149.310337
## iter 30 value 2137.800580
## iter 40 value 2135.736108
## iter 50 value 2135.291595
## iter 60 value 2134.961070
## iter 70 value 2134.460388
## iter 80 value 2133.970086
## iter 90 value 2133.011088
## iter 100 value 2132.585407
## iter 110 value 2132.128143
## iter 120 value 2132.053523
## iter 130 value 2132.032270
## final value 2132.027689
## converged
## # weights: 31
## initial value 2382.220713
## iter 10 value 2156.730592
## iter 20 value 2141.012998
## iter 30 value 2136.703801
## iter 40 value 2129.039271
## iter 50 value 2123.888584
## iter 60 value 2122.910207
## iter 70 value 2122.448305
## iter 80 value 2121.979721
## iter 90 value 2121.443005
## iter 100 value 2121.192757
## iter 110 value 2121.073344
## iter 120 value 2120.933567
## iter 130 value 2120.810453
## iter 140 value 2120.766834
## iter 150 value 2120.552084
## iter 160 value 2120.311118
## iter 170 value 2120.097929
## iter 180 value 2119.923607
## iter 190 value 2119.760400
## iter 200 value 2119.755151
## iter 210 value 2119.725489
## iter 220 value 2119.587414
## iter 230 value 2119.512632
## iter 240 value 2119.446070
## iter 250 value 2119.391278
## iter 260 value 2119.358776
## iter 270 value 2119.355726
## iter 280 value 2119.317761
## iter 290 value 2119.170466
## iter 300 value 2119.035502
## iter 310 value 2118.985257
## iter 320 value 2118.978512
## iter 320 value 2118.978501
## iter 320 value 2118.978495
## final value 2118.978495
## converged
## # weights: 41
## initial value 2343.220261
## iter 10 value 2186.690211
## iter 20 value 2146.909495
## iter 30 value 2137.760610
## iter 40 value 2133.359712
## iter 50 value 2131.378189
## iter 60 value 2130.528792
## iter 70 value 2129.789400
## iter 80 value 2128.374049
## iter 90 value 2128.171682
## iter 100 value 2127.968699
## iter 110 value 2126.963175
## iter 120 value 2126.424488
## iter 130 value 2126.003348
## iter 140 value 2125.236806
## iter 150 value 2124.128036
## iter 160 value 2123.581364
## iter 170 value 2123.368587
## iter 180 value 2123.269509
## iter 190 value 2122.902867
## iter 200 value 2122.677912
## iter 210 value 2122.618267
## iter 220 value 2122.572365
## iter 230 value 2122.521943
## iter 240 value 2122.406544
## iter 250 value 2122.362374
## final value 2122.362004
## converged
## # weights: 51
## initial value 2860.733667
## iter 10 value 2153.942064
## iter 20 value 2138.309438
## iter 30 value 2131.477183
## iter 40 value 2124.469059
## iter 50 value 2122.390518
## iter 60 value 2121.854296
## iter 70 value 2121.614764
## iter 80 value 2120.780364
## iter 90 value 2119.613989
## iter 100 value 2119.324278
## iter 110 value 2119.230676
## iter 120 value 2119.199563
## iter 130 value 2119.009427
## iter 140 value 2118.872553
## iter 150 value 2118.611392
## iter 160 value 2118.530573
## iter 170 value 2118.452080
## iter 180 value 2118.390248
## iter 190 value 2118.365148
## iter 200 value 2118.320484
## iter 210 value 2118.255717
## iter 220 value 2118.245974
## iter 230 value 2118.188826
## iter 240 value 2117.944187
## iter 250 value 2117.598025
## iter 260 value 2117.429097
## iter 270 value 2117.320081
## iter 280 value 2117.243598
## iter 290 value 2117.194522
## iter 300 value 2117.135249
## iter 310 value 2117.100921
## iter 320 value 2117.099029
## final value 2117.096887
## converged
## # weights: 61
## initial value 2452.733452
## iter 10 value 2154.075552
## iter 20 value 2135.675068
## iter 30 value 2126.943851
## iter 40 value 2122.844561
## iter 50 value 2120.874371
## iter 60 value 2119.994285
## iter 70 value 2118.831166
## iter 80 value 2118.100192
## iter 90 value 2117.756300
## iter 100 value 2117.695130
## iter 110 value 2117.651802
## iter 120 value 2117.599987
## iter 130 value 2117.568713
## iter 140 value 2117.556480
## iter 150 value 2117.500615
## iter 160 value 2117.464254
## iter 170 value 2117.436274
## iter 180 value 2117.420660
## iter 190 value 2117.405229
## iter 200 value 2117.381155
## iter 210 value 2117.361427
## iter 220 value 2117.341725
## iter 230 value 2117.321282
## iter 240 value 2117.290127
## iter 250 value 2117.275296
## iter 260 value 2117.274168
## iter 270 value 2117.272822
## iter 280 value 2117.259414
## iter 290 value 2117.235568
## iter 300 value 2117.223396
## iter 310 value 2117.207088
## iter 320 value 2117.194617
## iter 330 value 2117.184544
## iter 340 value 2117.177349
## iter 350 value 2117.171579
## iter 360 value 2117.168480
## iter 370 value 2117.164053
## final value 2117.163973
## converged
## # weights: 71
## initial value 2424.092856
## iter 10 value 2162.027070
## iter 20 value 2134.872202
## iter 30 value 2126.955994
## iter 40 value 2122.452208
## iter 50 value 2121.444505
## iter 60 value 2120.265520
## iter 70 value 2119.177390
## iter 80 value 2118.248502
## iter 90 value 2117.801822
## iter 100 value 2117.542957
## iter 110 value 2117.450102
## iter 120 value 2117.425243
## iter 130 value 2117.400487
## iter 140 value 2117.353494
## iter 150 value 2117.336311
## iter 160 value 2117.333385
## iter 170 value 2117.319570
## iter 180 value 2117.271134
## iter 190 value 2117.245464
## iter 200 value 2117.220674
## iter 210 value 2117.155449
## iter 220 value 2117.091636
## iter 230 value 2117.034889
## iter 240 value 2116.973199
## iter 250 value 2116.956453
## iter 260 value 2116.946427
## iter 270 value 2116.932269
## iter 280 value 2116.925696
## final value 2116.919616
## converged
## # weights: 81
## initial value 2335.190304
## iter 10 value 2160.203244
## iter 20 value 2137.806194
## iter 30 value 2129.298956
## iter 40 value 2125.377618
## iter 50 value 2121.390061
## iter 60 value 2119.612121
## iter 70 value 2118.718265
## iter 80 value 2117.917851
## iter 90 value 2117.369870
## iter 100 value 2117.225514
## iter 110 value 2117.156147
## iter 120 value 2117.132961
## iter 130 value 2117.096880
## iter 140 value 2117.061826
## iter 150 value 2117.033318
## iter 160 value 2117.019225
## iter 170 value 2117.017510
## iter 180 value 2117.015584
## iter 190 value 2116.996003
## iter 200 value 2116.969930
## iter 210 value 2116.957418
## iter 220 value 2116.948573
## iter 230 value 2116.942849
## iter 240 value 2116.934296
## iter 250 value 2116.921907
## iter 260 value 2116.906656
## iter 270 value 2116.892485
## iter 280 value 2116.884316
## final value 2116.884079
## converged
## # weights: 21
## initial value 2638.512547
## iter 10 value 2170.492592
## iter 20 value 2140.761919
## iter 30 value 2135.577991
## iter 40 value 2133.680933
## iter 50 value 2133.157883
## iter 60 value 2132.871206
## iter 70 value 2132.599716
## iter 80 value 2132.056185
## iter 90 value 2131.100812
## iter 100 value 2130.970968
## iter 110 value 2130.708180
## iter 120 value 2130.382924
## iter 130 value 2130.239614
## iter 140 value 2130.198000
## iter 150 value 2130.193698
## iter 160 value 2130.156687
## iter 170 value 2130.139177
## final value 2130.138544
## converged
## # weights: 31
## initial value 2835.731348
## iter 10 value 2164.657002
## iter 20 value 2142.509413
## iter 30 value 2131.702729
## iter 40 value 2124.568506
## iter 50 value 2122.560910
## iter 60 value 2122.019664
## iter 70 value 2121.952029
## iter 80 value 2121.650692
## iter 90 value 2121.333723
## iter 100 value 2121.169821
## iter 110 value 2120.977760
## iter 120 value 2120.931751
## iter 130 value 2120.922787
## iter 140 value 2120.918879
## iter 150 value 2120.888031
## iter 160 value 2120.540653
## iter 170 value 2120.258013
## iter 180 value 2119.803717
## iter 190 value 2119.436932
## iter 200 value 2119.410304
## iter 210 value 2119.258039
## iter 220 value 2119.242661
## iter 230 value 2119.230927
## iter 240 value 2119.202181
## iter 250 value 2119.178249
## iter 260 value 2119.167721
## iter 270 value 2119.163547
## iter 280 value 2119.130290
## iter 290 value 2119.072344
## iter 300 value 2118.916875
## iter 310 value 2118.440474
## iter 320 value 2118.250282
## iter 330 value 2118.103129
## iter 340 value 2117.549300
## iter 350 value 2117.133771
## iter 360 value 2116.990310
## iter 370 value 2116.958777
## iter 380 value 2116.922949
## iter 390 value 2116.841748
## iter 400 value 2116.794805
## iter 410 value 2116.786829
## iter 420 value 2116.772677
## iter 430 value 2116.735820
## iter 440 value 2116.729603
## iter 450 value 2116.651699
## iter 460 value 2116.473245
## iter 470 value 2116.404841
## iter 480 value 2116.269473
## iter 490 value 2116.199578
## iter 500 value 2116.193467
## final value 2116.193467
## stopped after 500 iterations
## # weights: 41
## initial value 2282.570084
## iter 10 value 2155.529612
## iter 20 value 2131.979498
## iter 30 value 2123.496313
## iter 40 value 2120.878260
## iter 50 value 2118.923992
## iter 60 value 2117.501885
## iter 70 value 2116.547148
## iter 80 value 2115.363290
## iter 90 value 2115.209907
## iter 100 value 2115.040179
## iter 110 value 2114.820610
## iter 120 value 2114.575848
## iter 130 value 2113.993801
## iter 140 value 2113.763258
## iter 150 value 2113.677473
## iter 160 value 2113.575135
## iter 170 value 2113.529306
## iter 180 value 2113.527199
## iter 190 value 2113.517195
## iter 200 value 2113.498973
## iter 210 value 2113.458431
## iter 220 value 2113.407984
## iter 230 value 2113.284975
## iter 240 value 2113.225174
## iter 250 value 2113.204615
## final value 2113.199558
## converged
## # weights: 51
## initial value 2327.292046
## iter 10 value 2169.873329
## iter 20 value 2132.479124
## iter 30 value 2120.387348
## iter 40 value 2118.338038
## iter 50 value 2116.381377
## iter 60 value 2115.326290
## iter 70 value 2114.667167
## iter 80 value 2114.260868
## iter 90 value 2113.940863
## iter 100 value 2113.826711
## iter 110 value 2113.773235
## iter 120 value 2113.719490
## iter 130 value 2113.569990
## iter 140 value 2113.486627
## iter 150 value 2113.403045
## iter 160 value 2113.360443
## iter 170 value 2113.342178
## iter 180 value 2113.279444
## iter 190 value 2113.118727
## iter 200 value 2113.025919
## iter 210 value 2112.893608
## iter 220 value 2112.885661
## iter 230 value 2112.856456
## iter 240 value 2112.792704
## iter 250 value 2112.699487
## iter 260 value 2112.649651
## iter 270 value 2112.619535
## iter 280 value 2112.597953
## iter 290 value 2112.588362
## iter 300 value 2112.573323
## iter 310 value 2112.564951
## final value 2112.564667
## converged
## # weights: 61
## initial value 2673.013511
## iter 10 value 2148.905277
## iter 20 value 2134.575669
## iter 30 value 2124.238421
## iter 40 value 2121.157469
## iter 50 value 2118.334102
## iter 60 value 2117.127095
## iter 70 value 2116.634530
## iter 80 value 2115.716685
## iter 90 value 2114.662474
## iter 100 value 2114.172274
## iter 110 value 2114.061292
## iter 120 value 2113.935080
## iter 130 value 2113.906702
## iter 140 value 2113.842105
## iter 150 value 2113.673117
## iter 160 value 2113.393802
## iter 170 value 2113.237215
## iter 180 value 2113.192991
## iter 190 value 2113.146243
## iter 200 value 2113.106011
## iter 210 value 2113.060115
## iter 220 value 2113.020050
## iter 230 value 2112.988725
## iter 240 value 2112.956035
## iter 250 value 2112.945073
## iter 250 value 2112.945056
## final value 2112.944987
## converged
## # weights: 71
## initial value 2482.746997
## iter 10 value 2151.992344
## iter 20 value 2128.583912
## iter 30 value 2120.482375
## iter 40 value 2117.793732
## iter 50 value 2115.851550
## iter 60 value 2114.585995
## iter 70 value 2113.863034
## iter 80 value 2113.467980
## iter 90 value 2113.061106
## iter 100 value 2112.859549
## iter 110 value 2112.790641
## iter 120 value 2112.742681
## iter 130 value 2112.718105
## iter 140 value 2112.689636
## iter 150 value 2112.680641
## iter 160 value 2112.675919
## iter 170 value 2112.665193
## iter 180 value 2112.627282
## iter 190 value 2112.607405
## iter 200 value 2112.600710
## iter 210 value 2112.590120
## iter 220 value 2112.576987
## iter 230 value 2112.561491
## iter 240 value 2112.546332
## iter 250 value 2112.528574
## iter 260 value 2112.514090
## iter 270 value 2112.504283
## iter 280 value 2112.491346
## final value 2112.487235
## converged
## # weights: 81
## initial value 2279.603764
## iter 10 value 2152.475063
## iter 20 value 2131.243528
## iter 30 value 2125.081771
## iter 40 value 2121.632999
## iter 50 value 2115.492722
## iter 60 value 2113.818522
## iter 70 value 2113.453396
## iter 80 value 2113.210992
## iter 90 value 2113.101348
## iter 100 value 2113.028275
## iter 110 value 2112.983569
## iter 120 value 2112.955410
## iter 130 value 2112.923682
## iter 140 value 2112.901184
## iter 150 value 2112.830886
## iter 160 value 2112.772768
## iter 170 value 2112.743875
## iter 180 value 2112.733233
## iter 190 value 2112.691555
## iter 200 value 2112.635999
## iter 210 value 2112.622323
## iter 220 value 2112.603661
## iter 230 value 2112.581874
## iter 240 value 2112.573198
## iter 250 value 2112.565223
## iter 260 value 2112.550807
## iter 270 value 2112.541092
## iter 280 value 2112.534105
## iter 290 value 2112.525725
## iter 300 value 2112.512742
## iter 310 value 2112.503666
## iter 320 value 2112.494937
## iter 330 value 2112.489427
## final value 2112.489129
## converged
## # weights: 21
## initial value 2323.284712
## iter 10 value 2258.637501
## iter 20 value 2194.915555
## iter 30 value 2186.443804
## iter 40 value 2178.661544
## iter 50 value 2166.103504
## iter 60 value 2161.334218
## iter 70 value 2160.528092
## iter 80 value 2156.940886
## iter 90 value 2154.303363
## iter 100 value 2153.422177
## iter 110 value 2153.294912
## iter 120 value 2152.342056
## iter 130 value 2151.927228
## iter 140 value 2151.839048
## iter 150 value 2151.822533
## iter 160 value 2151.807210
## iter 170 value 2149.775617
## iter 180 value 2147.799182
## iter 190 value 2146.598632
## iter 200 value 2146.188611
## iter 210 value 2145.996320
## iter 220 value 2145.787439
## iter 230 value 2145.782122
## iter 230 value 2145.782101
## iter 230 value 2145.782101
## final value 2145.782101
## converged
## # weights: 31
## initial value 2313.361273
## iter 10 value 2187.935220
## iter 20 value 2163.330422
## iter 30 value 2148.555920
## iter 40 value 2143.148253
## iter 50 value 2141.440324
## iter 60 value 2139.705218
## iter 70 value 2139.353118
## iter 80 value 2139.046295
## iter 90 value 2138.872610
## iter 100 value 2138.740379
## iter 110 value 2138.539436
## iter 120 value 2137.899938
## iter 130 value 2137.549988
## iter 140 value 2137.488358
## iter 150 value 2137.361271
## iter 160 value 2137.308722
## iter 170 value 2137.259136
## iter 180 value 2137.206040
## iter 190 value 2137.160534
## final value 2137.160073
## converged
## # weights: 41
## initial value 2567.375751
## iter 10 value 2166.654803
## iter 20 value 2151.463407
## iter 30 value 2142.809417
## iter 40 value 2138.752258
## iter 50 value 2137.770700
## iter 60 value 2136.154688
## iter 70 value 2135.280885
## iter 80 value 2134.682462
## iter 90 value 2134.436712
## iter 100 value 2134.356641
## iter 110 value 2134.173375
## iter 120 value 2133.872212
## iter 130 value 2133.223780
## iter 140 value 2133.047728
## iter 150 value 2132.948345
## iter 160 value 2132.649215
## iter 170 value 2132.156415
## iter 180 value 2131.953265
## iter 190 value 2131.453940
## iter 200 value 2131.087576
## iter 210 value 2130.957951
## iter 220 value 2130.897123
## iter 230 value 2130.859485
## iter 240 value 2130.829434
## iter 250 value 2130.584345
## iter 260 value 2130.489107
## iter 270 value 2130.287516
## iter 280 value 2129.830059
## iter 290 value 2129.561459
## iter 300 value 2129.424653
## iter 310 value 2129.389151
## iter 320 value 2129.351931
## iter 330 value 2129.327169
## iter 340 value 2129.314043
## iter 350 value 2129.304664
## iter 360 value 2129.220642
## iter 370 value 2129.116911
## iter 380 value 2129.006936
## iter 390 value 2128.972080
## iter 400 value 2128.954019
## iter 410 value 2128.939712
## iter 420 value 2128.927540
## final value 2128.927410
## converged
## # weights: 51
## initial value 2537.045370
## iter 10 value 2169.552800
## iter 20 value 2153.065200
## iter 30 value 2145.302211
## iter 40 value 2141.922238
## iter 50 value 2139.750312
## iter 60 value 2138.916497
## iter 70 value 2137.944285
## iter 80 value 2137.016252
## iter 90 value 2136.814138
## iter 100 value 2136.759445
## iter 110 value 2136.735006
## iter 120 value 2136.691030
## iter 130 value 2136.380877
## iter 140 value 2135.500161
## iter 150 value 2133.597236
## iter 160 value 2132.739075
## iter 170 value 2131.866911
## iter 180 value 2131.557311
## iter 190 value 2131.282693
## iter 200 value 2131.089676
## iter 210 value 2130.936551
## iter 220 value 2130.891358
## iter 230 value 2130.777775
## iter 240 value 2130.592103
## iter 250 value 2130.502804
## iter 260 value 2130.457152
## iter 270 value 2130.395262
## iter 280 value 2130.335081
## iter 290 value 2130.272967
## iter 300 value 2130.225998
## iter 310 value 2130.105200
## iter 320 value 2130.081584
## iter 330 value 2129.961642
## iter 340 value 2129.573648
## iter 350 value 2129.491118
## iter 360 value 2129.393792
## iter 370 value 2129.145631
## iter 380 value 2128.985530
## iter 390 value 2128.905319
## iter 400 value 2128.860262
## iter 410 value 2128.801536
## iter 420 value 2128.775233
## iter 430 value 2128.757719
## iter 440 value 2128.705747
## iter 450 value 2128.584495
## iter 460 value 2128.514262
## iter 470 value 2128.496034
## iter 480 value 2128.466920
## iter 490 value 2128.435240
## iter 500 value 2128.384296
## final value 2128.384296
## stopped after 500 iterations
## # weights: 61
## initial value 2331.630141
## iter 10 value 2166.890283
## iter 20 value 2147.794341
## iter 30 value 2139.548991
## iter 40 value 2134.985833
## iter 50 value 2131.949928
## iter 60 value 2130.818555
## iter 70 value 2129.750096
## iter 80 value 2129.057351
## iter 90 value 2128.800781
## iter 100 value 2128.604917
## iter 110 value 2128.537215
## iter 120 value 2128.472537
## iter 130 value 2128.462947
## iter 140 value 2128.459660
## iter 150 value 2128.437012
## iter 160 value 2128.391842
## iter 170 value 2128.351709
## iter 180 value 2128.296928
## iter 190 value 2128.259140
## iter 200 value 2128.249254
## iter 210 value 2128.243082
## iter 220 value 2128.225419
## iter 230 value 2128.218257
## iter 240 value 2128.209197
## iter 250 value 2128.202693
## iter 250 value 2128.202676
## iter 250 value 2128.202676
## final value 2128.202676
## converged
## # weights: 71
## initial value 2331.145573
## iter 10 value 2175.067213
## iter 20 value 2151.115490
## iter 30 value 2143.061759
## iter 40 value 2138.760821
## iter 50 value 2135.627496
## iter 60 value 2133.917334
## iter 70 value 2132.494739
## iter 80 value 2130.290195
## iter 90 value 2129.434857
## iter 100 value 2129.039007
## iter 110 value 2128.928895
## iter 120 value 2128.859379
## iter 130 value 2128.771580
## iter 140 value 2128.718946
## iter 150 value 2128.702439
## iter 160 value 2128.693540
## iter 170 value 2128.644725
## iter 180 value 2128.572661
## iter 190 value 2128.526305
## iter 200 value 2128.501812
## iter 210 value 2128.486953
## final value 2128.477869
## converged
## # weights: 81
## initial value 2342.495625
## iter 10 value 2175.940329
## iter 20 value 2151.035595
## iter 30 value 2136.892956
## iter 40 value 2133.542691
## iter 50 value 2132.236399
## iter 60 value 2131.284057
## iter 70 value 2130.969259
## iter 80 value 2130.840889
## iter 90 value 2130.737788
## iter 100 value 2130.659634
## iter 110 value 2130.586242
## iter 120 value 2130.493516
## iter 130 value 2130.347120
## iter 140 value 2130.081209
## iter 150 value 2129.998107
## iter 160 value 2129.956380
## iter 170 value 2129.922403
## iter 180 value 2129.914303
## iter 190 value 2129.881838
## iter 200 value 2129.822519
## iter 210 value 2129.719617
## iter 220 value 2129.515371
## iter 230 value 2128.691362
## iter 240 value 2128.530213
## iter 250 value 2128.357687
## iter 260 value 2128.319191
## iter 270 value 2128.298174
## iter 280 value 2128.286037
## iter 290 value 2128.273070
## iter 300 value 2128.264057
## iter 310 value 2128.252529
## iter 320 value 2128.214403
## iter 320 value 2128.214398
## iter 320 value 2128.214398
## final value 2128.214398
## converged
## # weights: 21
## initial value 2314.814128
## iter 10 value 2162.168118
## iter 20 value 2150.382881
## iter 30 value 2148.121445
## iter 40 value 2144.494527
## iter 50 value 2143.677581
## iter 60 value 2143.044672
## iter 70 value 2142.850646
## iter 80 value 2142.814625
## iter 90 value 2142.775552
## iter 100 value 2142.769212
## iter 110 value 2142.749213
## iter 120 value 2142.727807
## iter 130 value 2142.717050
## final value 2142.716822
## converged
## # weights: 31
## initial value 2290.463325
## iter 10 value 2207.020796
## iter 20 value 2159.681582
## iter 30 value 2151.104087
## iter 40 value 2147.898238
## iter 50 value 2145.118841
## iter 60 value 2144.445843
## iter 70 value 2144.364335
## iter 80 value 2144.244409
## iter 90 value 2143.734598
## iter 100 value 2143.652599
## iter 110 value 2143.625087
## iter 120 value 2143.517680
## iter 130 value 2143.363182
## iter 140 value 2143.317266
## iter 150 value 2143.112144
## iter 160 value 2143.048927
## iter 170 value 2143.007570
## iter 180 value 2142.940533
## iter 190 value 2142.935216
## iter 190 value 2142.935207
## final value 2142.935207
## converged
## # weights: 41
## initial value 2570.818343
## iter 10 value 2178.780371
## iter 20 value 2148.251217
## iter 30 value 2144.210012
## iter 40 value 2143.008711
## iter 50 value 2142.859726
## iter 60 value 2142.501233
## iter 70 value 2140.596198
## iter 80 value 2138.572324
## iter 90 value 2133.530406
## iter 100 value 2132.081722
## iter 110 value 2131.577091
## iter 120 value 2131.456982
## iter 130 value 2131.389697
## iter 140 value 2131.357865
## iter 150 value 2131.318257
## iter 160 value 2131.226570
## iter 170 value 2131.211037
## iter 180 value 2131.162761
## iter 190 value 2131.083016
## iter 200 value 2130.991120
## iter 210 value 2130.905147
## iter 220 value 2130.866659
## iter 230 value 2130.829161
## iter 240 value 2130.811122
## iter 250 value 2130.788147
## iter 260 value 2130.780828
## iter 270 value 2130.746955
## iter 280 value 2130.732709
## iter 290 value 2130.726383
## iter 300 value 2130.714654
## iter 310 value 2130.709828
## iter 320 value 2130.707769
## final value 2130.705346
## converged
## # weights: 51
## initial value 2699.183533
## iter 10 value 2169.089824
## iter 20 value 2146.050386
## iter 30 value 2139.984185
## iter 40 value 2137.771916
## iter 50 value 2133.514521
## iter 60 value 2132.275183
## iter 70 value 2131.713839
## iter 80 value 2130.850083
## iter 90 value 2130.638737
## iter 100 value 2130.500685
## iter 110 value 2129.625860
## iter 120 value 2129.238761
## iter 130 value 2128.533615
## iter 140 value 2128.006724
## iter 150 value 2127.558990
## iter 160 value 2126.447593
## iter 170 value 2125.665878
## iter 180 value 2125.237974
## iter 190 value 2124.954704
## iter 200 value 2124.844181
## iter 210 value 2124.821478
## iter 220 value 2124.739736
## iter 230 value 2124.624828
## iter 240 value 2124.577748
## iter 250 value 2124.538063
## iter 260 value 2124.487398
## iter 270 value 2124.431782
## iter 280 value 2124.348187
## iter 290 value 2124.124192
## iter 300 value 2124.083797
## final value 2124.083750
## converged
## # weights: 61
## initial value 2682.675744
## iter 10 value 2158.767558
## iter 20 value 2139.251185
## iter 30 value 2133.862236
## iter 40 value 2131.546181
## iter 50 value 2129.917949
## iter 60 value 2127.844484
## iter 70 value 2126.202703
## iter 80 value 2125.837231
## iter 90 value 2125.610168
## iter 100 value 2125.480189
## iter 110 value 2125.423441
## iter 120 value 2125.371038
## iter 130 value 2125.357224
## iter 140 value 2125.353138
## iter 150 value 2125.352374
## iter 160 value 2125.334202
## iter 170 value 2125.299841
## iter 180 value 2125.276885
## iter 190 value 2125.255218
## iter 200 value 2125.240566
## iter 210 value 2125.222190
## iter 220 value 2125.209544
## iter 230 value 2125.202611
## iter 240 value 2125.184108
## iter 250 value 2125.168697
## iter 260 value 2125.164089
## final value 2125.162391
## converged
## # weights: 71
## initial value 2635.329839
## iter 10 value 2161.242350
## iter 20 value 2143.340484
## iter 30 value 2134.303223
## iter 40 value 2130.536933
## iter 50 value 2128.165773
## iter 60 value 2127.269717
## iter 70 value 2126.215752
## iter 80 value 2125.411641
## iter 90 value 2124.907478
## iter 100 value 2124.663408
## iter 110 value 2124.520668
## iter 120 value 2124.418403
## iter 130 value 2124.366422
## iter 140 value 2124.316901
## final value 2124.306355
## converged
## # weights: 81
## initial value 2313.791597
## iter 10 value 2176.719637
## iter 20 value 2149.486381
## iter 30 value 2135.274985
## iter 40 value 2130.991628
## iter 50 value 2129.568946
## iter 60 value 2127.711326
## iter 70 value 2126.787692
## iter 80 value 2125.949441
## iter 90 value 2125.453164
## iter 100 value 2125.320096
## iter 110 value 2125.265835
## iter 120 value 2125.207929
## iter 130 value 2125.158332
## iter 140 value 2125.130846
## iter 150 value 2125.112829
## iter 160 value 2124.959062
## iter 170 value 2124.895160
## iter 180 value 2124.880437
## iter 190 value 2124.773732
## iter 200 value 2123.970280
## iter 210 value 2123.551927
## iter 220 value 2123.468074
## iter 230 value 2123.443821
## iter 240 value 2123.427753
## final value 2123.417327
## converged
## # weights: 21
## initial value 2555.334871
## iter 10 value 2175.195444
## iter 20 value 2153.166733
## iter 30 value 2140.453908
## iter 40 value 2134.021140
## iter 50 value 2132.722512
## iter 60 value 2130.371231
## iter 70 value 2129.104903
## iter 80 value 2127.903305
## iter 90 value 2124.370356
## iter 100 value 2123.155504
## iter 110 value 2122.778272
## iter 120 value 2122.342550
## iter 130 value 2122.264747
## iter 140 value 2122.258928
## iter 150 value 2122.219463
## iter 160 value 2122.160137
## iter 170 value 2122.150684
## iter 180 value 2122.139494
## iter 190 value 2122.138460
## iter 200 value 2122.131763
## final value 2122.129068
## converged
## # weights: 31
## initial value 2300.358857
## iter 10 value 2147.981441
## iter 20 value 2133.861609
## iter 30 value 2129.877417
## iter 40 value 2125.789535
## iter 50 value 2121.671784
## iter 60 value 2119.796918
## iter 70 value 2118.705420
## iter 80 value 2117.179030
## iter 90 value 2116.433217
## iter 100 value 2116.037919
## iter 110 value 2115.518625
## iter 120 value 2115.036769
## iter 130 value 2114.897760
## iter 140 value 2114.857270
## iter 150 value 2114.775154
## iter 160 value 2114.720356
## iter 170 value 2114.679526
## iter 180 value 2114.638407
## iter 190 value 2114.596718
## iter 200 value 2114.592781
## iter 210 value 2114.567560
## iter 220 value 2114.556348
## iter 230 value 2114.540978
## iter 240 value 2114.533395
## iter 250 value 2114.502117
## iter 260 value 2114.479850
## final value 2114.475255
## converged
## # weights: 41
## initial value 2427.214978
## iter 10 value 2140.510732
## iter 20 value 2125.270471
## iter 30 value 2120.631429
## iter 40 value 2117.741642
## iter 50 value 2115.673358
## iter 60 value 2114.829743
## iter 70 value 2114.112893
## iter 80 value 2113.581266
## iter 90 value 2113.463938
## iter 100 value 2113.298211
## iter 110 value 2112.704866
## iter 120 value 2112.090482
## iter 130 value 2111.696168
## iter 140 value 2111.216812
## iter 150 value 2111.041052
## iter 160 value 2110.939250
## iter 170 value 2110.913751
## iter 180 value 2110.908380
## iter 190 value 2110.874833
## iter 200 value 2110.801147
## iter 210 value 2110.695566
## iter 220 value 2110.586503
## iter 230 value 2110.509476
## iter 240 value 2110.424626
## iter 250 value 2110.223340
## iter 260 value 2110.193234
## iter 270 value 2110.111202
## iter 280 value 2109.973228
## iter 290 value 2109.811699
## iter 300 value 2109.640675
## iter 310 value 2109.556791
## iter 320 value 2109.508715
## iter 330 value 2109.474616
## iter 340 value 2109.465994
## iter 350 value 2109.464512
## iter 360 value 2109.455260
## iter 370 value 2109.434831
## iter 380 value 2109.419295
## iter 390 value 2109.412104
## iter 400 value 2109.407326
## iter 410 value 2109.402639
## final value 2109.401001
## converged
## # weights: 51
## initial value 2635.090254
## iter 10 value 2143.175774
## iter 20 value 2130.005149
## iter 30 value 2121.939890
## iter 40 value 2120.137935
## iter 50 value 2118.876601
## iter 60 value 2117.878070
## iter 70 value 2116.022145
## iter 80 value 2115.158231
## iter 90 value 2114.217974
## iter 100 value 2113.410635
## iter 110 value 2112.181151
## iter 120 value 2111.564742
## iter 130 value 2111.016166
## iter 140 value 2110.538309
## iter 150 value 2110.386900
## iter 160 value 2110.207519
## iter 170 value 2110.194714
## iter 180 value 2110.125891
## iter 190 value 2110.014557
## iter 200 value 2109.948009
## iter 210 value 2109.917054
## iter 220 value 2109.869953
## iter 230 value 2109.840907
## iter 240 value 2109.798627
## iter 250 value 2109.730409
## iter 260 value 2109.702377
## iter 270 value 2109.693754
## iter 280 value 2109.690910
## iter 290 value 2109.676952
## iter 300 value 2109.664682
## iter 310 value 2109.643660
## iter 320 value 2109.627212
## iter 330 value 2109.608657
## iter 340 value 2109.597277
## iter 350 value 2109.591436
## iter 360 value 2109.580468
## final value 2109.573528
## converged
## # weights: 61
## initial value 2449.417729
## iter 10 value 2148.597911
## iter 20 value 2126.487337
## iter 30 value 2118.265679
## iter 40 value 2113.150788
## iter 50 value 2111.573374
## iter 60 value 2110.394226
## iter 70 value 2109.576729
## iter 80 value 2109.288669
## iter 90 value 2109.174817
## iter 100 value 2109.081574
## iter 110 value 2109.040266
## iter 120 value 2109.026860
## final value 2109.015173
## converged
## # weights: 71
## initial value 2285.136353
## iter 10 value 2159.159909
## iter 20 value 2125.068860
## iter 30 value 2119.629694
## iter 40 value 2115.556180
## iter 50 value 2113.598580
## iter 60 value 2112.399675
## iter 70 value 2111.688081
## iter 80 value 2111.091481
## iter 90 value 2110.440178
## iter 100 value 2110.215013
## iter 110 value 2110.084319
## iter 120 value 2109.934041
## iter 130 value 2109.650635
## iter 140 value 2109.465686
## iter 150 value 2109.415290
## iter 160 value 2109.397791
## iter 170 value 2109.308664
## iter 180 value 2109.208200
## iter 190 value 2109.157566
## iter 200 value 2109.103249
## iter 210 value 2109.070893
## iter 220 value 2109.055563
## iter 230 value 2109.023069
## iter 240 value 2108.992379
## iter 250 value 2108.920292
## iter 260 value 2108.873393
## iter 270 value 2108.809446
## iter 280 value 2108.780420
## iter 290 value 2108.759221
## iter 300 value 2108.755628
## iter 310 value 2108.751285
## iter 320 value 2108.732532
## iter 330 value 2108.711570
## iter 340 value 2108.700442
## iter 350 value 2108.691271
## iter 360 value 2108.675444
## iter 370 value 2108.659186
## iter 380 value 2108.640248
## iter 390 value 2108.612823
## iter 400 value 2108.606301
## iter 410 value 2108.595422
## iter 420 value 2108.589778
## iter 430 value 2108.584674
## final value 2108.583750
## converged
## # weights: 81
## initial value 2375.056202
## iter 10 value 2146.061377
## iter 20 value 2125.726041
## iter 30 value 2117.939684
## iter 40 value 2113.051700
## iter 50 value 2111.997041
## iter 60 value 2111.019839
## iter 70 value 2110.181125
## iter 80 value 2109.741811
## iter 90 value 2109.537285
## iter 100 value 2109.317705
## iter 110 value 2109.181881
## iter 120 value 2109.110033
## iter 130 value 2109.081990
## iter 140 value 2109.029215
## iter 150 value 2108.965678
## iter 160 value 2108.935424
## iter 170 value 2108.922839
## iter 180 value 2108.908179
## iter 190 value 2108.832602
## iter 200 value 2108.771993
## iter 210 value 2108.732235
## iter 220 value 2108.712626
## iter 230 value 2108.704092
## iter 240 value 2108.691283
## iter 250 value 2108.674840
## iter 260 value 2108.656823
## iter 270 value 2108.634414
## iter 280 value 2108.607734
## iter 290 value 2108.593011
## iter 300 value 2108.585788
## iter 310 value 2108.577333
## iter 320 value 2108.569648
## iter 330 value 2108.565239
## iter 340 value 2108.564492
## iter 340 value 2108.564486
## iter 340 value 2108.564471
## final value 2108.564471
## converged
## # weights: 21
## initial value 2319.561709
## iter 10 value 2253.111295
## iter 20 value 2156.942147
## iter 30 value 2145.123013
## iter 40 value 2143.450228
## iter 50 value 2142.576550
## iter 60 value 2141.786788
## iter 70 value 2141.283094
## iter 80 value 2141.021198
## iter 90 value 2140.829257
## iter 100 value 2140.712090
## iter 110 value 2140.610493
## iter 120 value 2140.480106
## iter 130 value 2140.352350
## iter 140 value 2140.348787
## final value 2140.345949
## converged
## # weights: 31
## initial value 2682.097390
## iter 10 value 2202.863203
## iter 20 value 2151.290337
## iter 30 value 2142.518926
## iter 40 value 2138.755225
## iter 50 value 2137.844843
## iter 60 value 2137.378579
## iter 70 value 2137.091786
## iter 80 value 2137.038718
## iter 90 value 2136.894964
## iter 100 value 2136.708120
## iter 110 value 2136.686933
## iter 120 value 2136.674573
## iter 130 value 2136.670543
## final value 2136.670491
## converged
## # weights: 41
## initial value 2648.905200
## iter 10 value 2164.643151
## iter 20 value 2146.518080
## iter 30 value 2136.001037
## iter 40 value 2131.840999
## iter 50 value 2130.618022
## iter 60 value 2130.150730
## iter 70 value 2129.982414
## iter 80 value 2129.823117
## iter 90 value 2129.808613
## iter 100 value 2129.807340
## iter 110 value 2129.783391
## iter 120 value 2129.720607
## iter 130 value 2129.685447
## iter 140 value 2129.666687
## iter 150 value 2129.428542
## iter 160 value 2128.952880
## iter 170 value 2128.242232
## iter 180 value 2127.953259
## iter 190 value 2127.895886
## iter 200 value 2127.751882
## iter 210 value 2127.614984
## iter 220 value 2127.553324
## iter 230 value 2127.395007
## iter 240 value 2126.999029
## iter 250 value 2126.839242
## iter 260 value 2126.553251
## iter 270 value 2126.526741
## iter 280 value 2126.352003
## iter 290 value 2125.148817
## iter 300 value 2124.759708
## iter 310 value 2124.387982
## iter 320 value 2124.216773
## iter 330 value 2124.069896
## iter 340 value 2124.014684
## iter 350 value 2124.007464
## iter 360 value 2124.000436
## iter 370 value 2123.985308
## iter 380 value 2123.960759
## iter 390 value 2123.925563
## iter 400 value 2123.865029
## iter 410 value 2123.819196
## iter 420 value 2123.789424
## iter 430 value 2123.777488
## final value 2123.777375
## converged
## # weights: 51
## initial value 2309.596931
## iter 10 value 2170.720658
## iter 20 value 2150.004718
## iter 30 value 2142.580662
## iter 40 value 2136.063657
## iter 50 value 2134.059026
## iter 60 value 2133.212304
## iter 70 value 2132.806356
## iter 80 value 2131.740563
## iter 90 value 2131.171434
## iter 100 value 2130.535817
## iter 110 value 2130.375362
## iter 120 value 2130.258812
## iter 130 value 2129.541728
## iter 140 value 2127.952080
## iter 150 value 2127.384327
## iter 160 value 2127.089676
## iter 170 value 2126.855205
## iter 180 value 2126.639539
## iter 190 value 2126.048884
## iter 200 value 2125.895380
## iter 210 value 2125.832055
## iter 220 value 2125.829109
## iter 230 value 2125.815851
## iter 240 value 2125.755452
## iter 250 value 2125.709376
## iter 260 value 2125.601090
## iter 270 value 2125.519218
## iter 280 value 2125.470851
## iter 290 value 2125.430271
## iter 300 value 2125.378745
## iter 310 value 2125.204763
## iter 320 value 2125.191505
## iter 330 value 2125.100789
## iter 340 value 2124.829814
## iter 350 value 2124.215571
## iter 360 value 2124.032393
## iter 370 value 2123.946018
## iter 380 value 2123.919153
## iter 390 value 2123.885275
## iter 400 value 2123.856212
## iter 410 value 2123.831982
## final value 2123.828566
## converged
## # weights: 61
## initial value 2348.614998
## iter 10 value 2189.584498
## iter 20 value 2150.433689
## iter 30 value 2137.083220
## iter 40 value 2131.593189
## iter 50 value 2128.075093
## iter 60 value 2125.230909
## iter 70 value 2124.398921
## iter 80 value 2124.043440
## iter 90 value 2123.989317
## iter 100 value 2123.918803
## iter 110 value 2123.865873
## iter 120 value 2123.853623
## final value 2123.844823
## converged
## # weights: 71
## initial value 2277.226733
## iter 10 value 2172.581641
## iter 20 value 2147.559342
## iter 30 value 2138.619495
## iter 40 value 2131.437252
## iter 50 value 2127.815078
## iter 60 value 2126.277082
## iter 70 value 2125.293756
## iter 80 value 2124.718613
## iter 90 value 2124.600002
## iter 100 value 2124.501872
## iter 110 value 2124.378053
## iter 120 value 2124.309521
## iter 130 value 2124.227984
## iter 140 value 2124.149589
## iter 150 value 2124.140887
## iter 160 value 2124.128556
## iter 170 value 2124.050753
## iter 180 value 2123.977528
## iter 190 value 2123.925307
## iter 200 value 2123.902250
## iter 210 value 2123.886941
## iter 220 value 2123.859952
## iter 230 value 2123.819705
## iter 240 value 2123.790357
## iter 250 value 2123.760813
## iter 260 value 2123.740247
## iter 270 value 2123.728331
## iter 280 value 2123.718701
## iter 290 value 2123.712912
## iter 290 value 2123.712906
## final value 2123.712836
## converged
## # weights: 81
## initial value 2711.068273
## iter 10 value 2164.552474
## iter 20 value 2144.816407
## iter 30 value 2135.670955
## iter 40 value 2129.305114
## iter 50 value 2126.653042
## iter 60 value 2125.080552
## iter 70 value 2124.590902
## iter 80 value 2124.304798
## iter 90 value 2124.210508
## iter 100 value 2124.107605
## iter 110 value 2124.030110
## iter 120 value 2123.969253
## iter 130 value 2123.914659
## iter 140 value 2123.879098
## iter 150 value 2123.840377
## iter 160 value 2123.822818
## iter 170 value 2123.805031
## iter 180 value 2123.803673
## iter 190 value 2123.792150
## iter 200 value 2123.770055
## iter 210 value 2123.754825
## iter 220 value 2123.737576
## iter 230 value 2123.725072
## iter 240 value 2123.705222
## iter 250 value 2123.681728
## iter 260 value 2123.658087
## iter 270 value 2123.643353
## iter 280 value 2123.638617
## iter 290 value 2123.631325
## iter 300 value 2123.625250
## iter 310 value 2123.621895
## iter 320 value 2123.620328
## iter 330 value 2123.618312
## final value 2123.618100
## converged
## # weights: 21
## initial value 2292.717544
## iter 10 value 2189.204636
## iter 20 value 2172.681456
## iter 30 value 2170.839919
## iter 40 value 2158.207805
## iter 50 value 2152.191719
## iter 60 value 2150.991140
## iter 70 value 2150.853412
## iter 80 value 2150.843770
## iter 90 value 2150.744797
## iter 100 value 2150.458416
## iter 110 value 2150.321494
## iter 120 value 2150.307479
## iter 130 value 2150.300627
## iter 140 value 2150.287837
## iter 150 value 2150.282929
## final value 2150.281401
## converged
## # weights: 31
## initial value 2443.340936
## iter 10 value 2255.264571
## iter 20 value 2211.706704
## iter 30 value 2175.191639
## iter 40 value 2167.912296
## iter 50 value 2159.734326
## iter 60 value 2151.739051
## iter 70 value 2150.685959
## iter 80 value 2150.511726
## iter 90 value 2150.110862
## iter 100 value 2149.587691
## iter 110 value 2149.443677
## iter 120 value 2149.379433
## iter 130 value 2149.315874
## iter 140 value 2148.619262
## iter 150 value 2145.346326
## iter 160 value 2144.830632
## iter 170 value 2144.660302
## iter 180 value 2144.496525
## iter 190 value 2143.987842
## iter 200 value 2142.839565
## iter 210 value 2142.716719
## iter 220 value 2142.304312
## iter 230 value 2142.153026
## iter 240 value 2142.119665
## iter 250 value 2142.004129
## iter 260 value 2141.817223
## iter 270 value 2141.778357
## iter 280 value 2141.715894
## iter 290 value 2141.655851
## iter 300 value 2141.643888
## iter 310 value 2141.632152
## iter 320 value 2141.618083
## iter 330 value 2141.567136
## iter 340 value 2140.904426
## iter 350 value 2137.379078
## iter 360 value 2136.054377
## iter 370 value 2135.619922
## iter 380 value 2135.294213
## iter 390 value 2135.237190
## iter 400 value 2135.224240
## final value 2135.223301
## converged
## # weights: 41
## initial value 2488.215536
## iter 10 value 2176.632119
## iter 20 value 2152.542560
## iter 30 value 2144.533393
## iter 40 value 2141.703328
## iter 50 value 2138.568558
## iter 60 value 2137.493443
## iter 70 value 2136.815650
## iter 80 value 2136.638395
## iter 90 value 2136.588859
## iter 100 value 2136.389317
## iter 110 value 2136.167229
## iter 120 value 2135.878516
## iter 130 value 2135.680436
## iter 140 value 2135.060595
## iter 150 value 2134.663310
## iter 160 value 2134.241770
## iter 170 value 2134.081295
## iter 180 value 2134.046890
## iter 190 value 2133.896777
## iter 200 value 2133.543291
## iter 210 value 2133.461845
## iter 220 value 2133.344453
## iter 230 value 2133.218396
## iter 240 value 2133.138630
## iter 250 value 2133.018871
## iter 260 value 2133.008954
## iter 270 value 2132.965786
## iter 280 value 2132.883394
## iter 290 value 2132.657185
## iter 300 value 2131.801289
## iter 310 value 2131.074293
## iter 320 value 2130.651429
## iter 330 value 2130.146815
## iter 340 value 2130.085894
## iter 350 value 2129.987800
## iter 360 value 2129.810885
## iter 370 value 2129.702576
## iter 380 value 2129.643023
## iter 390 value 2129.613489
## iter 400 value 2129.597620
## iter 410 value 2129.579920
## iter 420 value 2129.572212
## final value 2129.571998
## converged
## # weights: 51
## initial value 3771.834632
## iter 10 value 2167.991279
## iter 20 value 2144.586293
## iter 30 value 2137.288403
## iter 40 value 2131.553073
## iter 50 value 2127.821856
## iter 60 value 2127.031561
## iter 70 value 2125.865661
## iter 80 value 2125.476345
## iter 90 value 2125.267820
## iter 100 value 2125.097233
## iter 110 value 2125.045890
## iter 120 value 2125.019748
## iter 130 value 2124.921450
## iter 140 value 2124.871534
## iter 150 value 2124.803879
## iter 160 value 2124.710303
## iter 170 value 2124.672720
## iter 180 value 2124.614669
## iter 190 value 2124.559647
## iter 200 value 2124.508504
## iter 210 value 2124.484933
## iter 220 value 2124.480591
## iter 230 value 2124.466769
## iter 240 value 2124.425375
## final value 2124.423434
## converged
## # weights: 61
## initial value 3027.748969
## iter 10 value 2165.573612
## iter 20 value 2148.201059
## iter 30 value 2141.403015
## iter 40 value 2135.539135
## iter 50 value 2128.945716
## iter 60 value 2127.736221
## iter 70 value 2126.559664
## iter 80 value 2125.928405
## iter 90 value 2125.604334
## iter 100 value 2125.418182
## iter 110 value 2125.270255
## iter 120 value 2125.211458
## iter 130 value 2125.195085
## iter 140 value 2125.182647
## iter 150 value 2125.095963
## iter 160 value 2125.028142
## iter 170 value 2124.978404
## iter 180 value 2124.933671
## iter 190 value 2124.873985
## iter 200 value 2124.711494
## iter 210 value 2124.592829
## iter 220 value 2124.522808
## iter 230 value 2124.482810
## iter 240 value 2124.459532
## iter 250 value 2124.422643
## iter 260 value 2124.420302
## iter 270 value 2124.415314
## iter 280 value 2124.393978
## iter 290 value 2124.356337
## iter 300 value 2124.334827
## iter 310 value 2124.312414
## iter 320 value 2124.296753
## iter 330 value 2124.278683
## iter 340 value 2124.268547
## iter 350 value 2124.256804
## iter 360 value 2124.245029
## iter 370 value 2124.231897
## final value 2124.225372
## converged
## # weights: 71
## initial value 2494.421444
## iter 10 value 2175.478654
## iter 20 value 2140.382249
## iter 30 value 2130.830932
## iter 40 value 2127.642422
## iter 50 value 2126.134886
## iter 60 value 2125.326243
## iter 70 value 2124.823680
## iter 80 value 2124.595218
## iter 90 value 2124.531452
## iter 100 value 2124.493226
## iter 110 value 2124.434554
## iter 120 value 2124.381421
## iter 130 value 2124.303633
## iter 140 value 2124.276199
## iter 150 value 2124.273239
## iter 160 value 2124.272473
## iter 160 value 2124.272453
## iter 160 value 2124.272445
## final value 2124.272445
## converged
## # weights: 81
## initial value 2314.636430
## iter 10 value 2170.383035
## iter 20 value 2147.362632
## iter 30 value 2138.642892
## iter 40 value 2132.924531
## iter 50 value 2130.158552
## iter 60 value 2128.829581
## iter 70 value 2128.430359
## iter 80 value 2128.177952
## iter 90 value 2127.450904
## iter 100 value 2126.083383
## iter 110 value 2125.586626
## iter 120 value 2124.889023
## iter 130 value 2124.771989
## iter 140 value 2124.692297
## iter 150 value 2124.619682
## iter 160 value 2124.540179
## iter 170 value 2124.525316
## iter 180 value 2124.509860
## iter 190 value 2124.452267
## iter 200 value 2124.414036
## iter 210 value 2124.398593
## iter 220 value 2124.388580
## iter 230 value 2124.381426
## iter 240 value 2124.371070
## iter 250 value 2124.361481
## iter 260 value 2124.338900
## iter 270 value 2124.323258
## iter 280 value 2124.313682
## iter 290 value 2124.303464
## iter 300 value 2124.293730
## iter 310 value 2124.284310
## iter 320 value 2124.279900
## iter 330 value 2124.277983
## final value 2124.277754
## converged
## # weights: 21
## initial value 2486.811108
## iter 10 value 2194.681116
## iter 20 value 2174.018303
## iter 30 value 2169.961073
## iter 40 value 2157.740156
## iter 50 value 2156.450916
## iter 60 value 2156.024149
## iter 70 value 2156.003877
## iter 80 value 2155.912440
## iter 90 value 2155.772232
## iter 100 value 2155.706175
## iter 110 value 2155.560994
## iter 120 value 2155.385398
## iter 130 value 2155.249169
## iter 140 value 2155.221150
## iter 150 value 2155.183109
## iter 160 value 2155.076693
## iter 170 value 2155.012023
## iter 180 value 2154.997233
## iter 190 value 2154.995071
## iter 200 value 2154.989820
## iter 210 value 2154.967948
## iter 210 value 2154.967944
## iter 210 value 2154.967944
## final value 2154.967944
## converged
## # weights: 31
## initial value 2331.730201
## iter 10 value 2183.887261
## iter 20 value 2154.115222
## iter 30 value 2150.194774
## iter 40 value 2150.026187
## iter 50 value 2149.921304
## iter 60 value 2148.913006
## iter 70 value 2147.696630
## iter 80 value 2145.884269
## iter 90 value 2141.847311
## iter 100 value 2138.318574
## iter 110 value 2136.887611
## iter 120 value 2135.377395
## iter 130 value 2134.315649
## iter 140 value 2133.967130
## iter 150 value 2133.929383
## iter 160 value 2133.901907
## iter 170 value 2133.886459
## iter 180 value 2133.764667
## iter 190 value 2133.561263
## iter 200 value 2133.304556
## iter 210 value 2133.189469
## iter 220 value 2133.092054
## iter 230 value 2132.914774
## iter 240 value 2132.778251
## iter 250 value 2132.711920
## iter 260 value 2132.684676
## iter 270 value 2132.665777
## iter 280 value 2132.660645
## iter 290 value 2132.594422
## iter 300 value 2132.513536
## iter 310 value 2132.415844
## iter 320 value 2132.232976
## iter 330 value 2132.018859
## iter 340 value 2131.987559
## iter 350 value 2131.864104
## iter 360 value 2131.747278
## iter 370 value 2131.708440
## iter 380 value 2131.444255
## iter 390 value 2131.382857
## iter 400 value 2131.369307
## iter 410 value 2131.349762
## iter 420 value 2131.146495
## iter 430 value 2131.062124
## iter 440 value 2130.995653
## iter 450 value 2130.955421
## iter 460 value 2130.905651
## final value 2130.897408
## converged
## # weights: 41
## initial value 2496.917858
## iter 10 value 2172.265199
## iter 20 value 2150.093719
## iter 30 value 2140.621054
## iter 40 value 2138.120363
## iter 50 value 2136.088595
## iter 60 value 2134.706409
## iter 70 value 2133.725901
## iter 80 value 2133.099108
## iter 90 value 2132.901374
## iter 100 value 2132.790225
## iter 110 value 2132.534818
## iter 120 value 2132.337919
## iter 130 value 2131.754227
## iter 140 value 2131.467872
## iter 150 value 2131.256302
## iter 160 value 2131.086927
## iter 170 value 2130.990418
## iter 180 value 2130.981532
## iter 190 value 2130.914538
## iter 200 value 2130.810869
## iter 210 value 2130.695062
## iter 220 value 2130.557071
## iter 230 value 2130.369711
## iter 240 value 2130.269375
## iter 250 value 2130.008285
## iter 260 value 2129.966506
## iter 270 value 2129.874453
## iter 280 value 2129.624988
## iter 290 value 2129.452222
## iter 300 value 2129.310739
## iter 310 value 2128.928274
## iter 320 value 2128.764825
## iter 330 value 2128.726710
## iter 340 value 2128.713973
## iter 350 value 2128.703742
## iter 360 value 2128.637099
## iter 370 value 2128.572355
## iter 380 value 2128.548412
## iter 390 value 2128.524126
## iter 400 value 2128.512719
## iter 410 value 2128.497265
## final value 2128.475849
## converged
## # weights: 51
## initial value 2520.729391
## iter 10 value 2157.896617
## iter 20 value 2142.912021
## iter 30 value 2138.916772
## iter 40 value 2135.498535
## iter 50 value 2133.274759
## iter 60 value 2131.513625
## iter 70 value 2129.878826
## iter 80 value 2129.027455
## iter 90 value 2128.580928
## iter 100 value 2128.199055
## iter 110 value 2128.125828
## iter 120 value 2128.032919
## iter 130 value 2127.826156
## iter 140 value 2127.534638
## iter 150 value 2127.358723
## iter 160 value 2127.298449
## iter 170 value 2127.275443
## iter 180 value 2127.262506
## iter 190 value 2127.258029
## iter 200 value 2127.245716
## iter 210 value 2127.238319
## final value 2127.238061
## converged
## # weights: 61
## initial value 2295.446330
## iter 10 value 2165.955905
## iter 20 value 2144.003178
## iter 30 value 2138.300111
## iter 40 value 2134.381784
## iter 50 value 2132.524499
## iter 60 value 2131.715379
## iter 70 value 2131.044000
## iter 80 value 2130.442782
## iter 90 value 2130.026485
## iter 100 value 2129.559195
## iter 110 value 2129.119544
## iter 120 value 2128.562574
## iter 130 value 2128.404487
## iter 140 value 2128.289274
## iter 150 value 2128.101268
## iter 160 value 2127.838130
## iter 170 value 2127.695749
## iter 180 value 2127.542686
## iter 190 value 2127.441330
## iter 200 value 2127.390736
## iter 210 value 2127.348181
## iter 220 value 2127.323015
## iter 230 value 2127.301045
## iter 240 value 2127.293322
## iter 250 value 2127.276021
## iter 260 value 2127.273771
## iter 270 value 2127.271826
## final value 2127.271302
## converged
## # weights: 71
## initial value 2796.547068
## iter 10 value 2171.353723
## iter 20 value 2148.519342
## iter 30 value 2139.115713
## iter 40 value 2134.740986
## iter 50 value 2132.964757
## iter 60 value 2131.351521
## iter 70 value 2130.851170
## iter 80 value 2130.469298
## iter 90 value 2130.205150
## iter 100 value 2130.119788
## iter 110 value 2130.080501
## iter 120 value 2130.012601
## iter 130 value 2129.942126
## iter 140 value 2129.843309
## iter 150 value 2129.789129
## iter 160 value 2129.770566
## iter 170 value 2129.699924
## iter 180 value 2129.377489
## iter 190 value 2128.328182
## iter 200 value 2127.536109
## iter 210 value 2127.372635
## iter 220 value 2127.309692
## iter 230 value 2127.286494
## iter 240 value 2127.270792
## iter 250 value 2127.255182
## iter 260 value 2127.241709
## iter 270 value 2127.228950
## iter 280 value 2127.210831
## iter 290 value 2127.196611
## iter 300 value 2127.194340
## final value 2127.194055
## converged
## # weights: 81
## initial value 2338.983598
## iter 10 value 2171.381672
## iter 20 value 2145.193402
## iter 30 value 2140.214812
## iter 40 value 2135.974385
## iter 50 value 2133.053362
## iter 60 value 2130.679728
## iter 70 value 2129.574771
## iter 80 value 2128.977196
## iter 90 value 2128.715290
## iter 100 value 2128.531320
## iter 110 value 2128.406170
## iter 120 value 2128.305189
## iter 130 value 2128.203224
## iter 140 value 2128.125669
## iter 150 value 2128.054649
## iter 160 value 2128.005853
## iter 170 value 2127.986791
## iter 180 value 2127.979501
## iter 190 value 2127.938352
## iter 200 value 2127.892071
## iter 210 value 2127.857641
## iter 220 value 2127.828363
## iter 230 value 2127.799567
## iter 240 value 2127.770561
## iter 250 value 2127.651684
## iter 260 value 2127.496604
## iter 270 value 2127.485152
## iter 280 value 2127.465348
## iter 290 value 2127.433329
## iter 300 value 2127.422105
## iter 310 value 2127.387796
## iter 320 value 2127.361138
## iter 330 value 2127.337857
## iter 340 value 2127.336381
## iter 350 value 2127.333510
## iter 360 value 2127.306146
## iter 370 value 2127.267156
## iter 380 value 2127.247042
## iter 390 value 2127.232434
## iter 400 value 2127.217021
## iter 410 value 2127.204372
## iter 420 value 2127.188619
## iter 430 value 2127.172113
## iter 440 value 2127.153241
## iter 450 value 2127.137696
## iter 460 value 2127.127544
## iter 470 value 2127.103000
## iter 480 value 2127.092407
## iter 490 value 2127.087679
## final value 2127.086944
## converged
## # weights: 21
## initial value 2293.548761
## iter 10 value 2156.141156
## iter 20 value 2139.439794
## iter 30 value 2136.877119
## iter 40 value 2133.419781
## iter 50 value 2132.237847
## iter 60 value 2130.979808
## iter 70 value 2128.229367
## iter 80 value 2126.358150
## iter 90 value 2125.830342
## iter 100 value 2125.320344
## iter 110 value 2124.585151
## iter 120 value 2124.151282
## iter 130 value 2123.915545
## iter 140 value 2123.911911
## iter 150 value 2123.861709
## iter 160 value 2123.798938
## iter 170 value 2123.767987
## iter 180 value 2123.763330
## iter 180 value 2123.763319
## iter 180 value 2123.763299
## final value 2123.763299
## converged
## # weights: 31
## initial value 2327.724475
## iter 10 value 2165.345145
## iter 20 value 2138.282298
## iter 30 value 2128.847171
## iter 40 value 2125.221598
## iter 50 value 2123.518634
## iter 60 value 2123.037111
## iter 70 value 2122.783124
## iter 80 value 2122.710893
## iter 90 value 2122.457479
## iter 100 value 2122.400423
## iter 110 value 2122.320728
## iter 120 value 2122.186486
## iter 130 value 2122.053667
## iter 140 value 2122.032709
## iter 150 value 2121.963867
## iter 160 value 2121.900890
## iter 170 value 2121.875872
## iter 180 value 2121.871920
## iter 190 value 2121.870631
## final value 2121.870104
## converged
## # weights: 41
## initial value 2278.293815
## iter 10 value 2176.541268
## iter 20 value 2130.044534
## iter 30 value 2121.519091
## iter 40 value 2117.896551
## iter 50 value 2114.322802
## iter 60 value 2111.445268
## iter 70 value 2110.081174
## iter 80 value 2109.659315
## iter 90 value 2109.521769
## iter 100 value 2109.449721
## iter 110 value 2109.255004
## iter 120 value 2109.130070
## iter 130 value 2109.062036
## iter 140 value 2108.974540
## iter 150 value 2108.909658
## iter 160 value 2108.839766
## iter 170 value 2108.805646
## iter 180 value 2108.804086
## iter 190 value 2108.800704
## iter 200 value 2108.775668
## iter 210 value 2108.752669
## iter 220 value 2108.723306
## iter 230 value 2108.697753
## iter 240 value 2108.679869
## iter 250 value 2108.662736
## final value 2108.662024
## converged
## # weights: 51
## initial value 2306.202021
## iter 10 value 2151.208744
## iter 20 value 2127.751159
## iter 30 value 2120.161695
## iter 40 value 2114.820193
## iter 50 value 2112.983652
## iter 60 value 2111.864659
## iter 70 value 2111.098962
## iter 80 value 2110.381544
## iter 90 value 2109.979035
## iter 100 value 2109.903469
## iter 110 value 2109.891548
## iter 120 value 2109.878924
## iter 130 value 2109.849851
## iter 140 value 2109.811111
## iter 150 value 2109.783103
## iter 160 value 2109.773046
## iter 170 value 2109.763040
## iter 180 value 2109.757076
## iter 190 value 2109.747836
## iter 200 value 2109.737346
## iter 210 value 2109.716628
## final value 2109.716056
## converged
## # weights: 61
## initial value 2385.588128
## iter 10 value 2159.006531
## iter 20 value 2130.397961
## iter 30 value 2121.349998
## iter 40 value 2117.359374
## iter 50 value 2115.409564
## iter 60 value 2113.591546
## iter 70 value 2111.711615
## iter 80 value 2110.774608
## iter 90 value 2110.034270
## iter 100 value 2109.406527
## iter 110 value 2109.017526
## iter 120 value 2108.907126
## iter 130 value 2108.870179
## iter 140 value 2108.859679
## iter 150 value 2108.826531
## iter 160 value 2108.783333
## iter 170 value 2108.725821
## iter 180 value 2108.688659
## iter 190 value 2108.667235
## iter 200 value 2108.652414
## iter 210 value 2108.626282
## iter 220 value 2108.579664
## iter 230 value 2108.566221
## iter 240 value 2108.545110
## iter 250 value 2108.523627
## iter 260 value 2108.521563
## iter 260 value 2108.521555
## iter 270 value 2108.520888
## final value 2108.520474
## converged
## # weights: 71
## initial value 3205.143697
## iter 10 value 2146.909497
## iter 20 value 2126.051628
## iter 30 value 2117.587511
## iter 40 value 2113.455980
## iter 50 value 2112.138803
## iter 60 value 2111.668854
## iter 70 value 2111.080640
## iter 80 value 2110.764528
## iter 90 value 2110.550036
## iter 100 value 2110.195376
## iter 110 value 2109.803209
## iter 120 value 2109.388880
## iter 130 value 2109.189580
## iter 140 value 2109.060958
## iter 150 value 2109.025762
## iter 160 value 2109.018339
## iter 170 value 2108.950660
## iter 180 value 2108.871844
## iter 190 value 2108.825212
## iter 200 value 2108.800585
## iter 210 value 2108.776077
## iter 220 value 2108.751191
## iter 230 value 2108.724561
## iter 240 value 2108.677162
## iter 250 value 2108.642454
## iter 260 value 2108.601343
## iter 270 value 2108.571984
## iter 280 value 2108.556920
## iter 290 value 2108.542449
## final value 2108.541705
## converged
## # weights: 81
## initial value 2763.341820
## iter 10 value 2156.760339
## iter 20 value 2131.339112
## iter 30 value 2121.093980
## iter 40 value 2115.130413
## iter 50 value 2111.334694
## iter 60 value 2109.927681
## iter 70 value 2109.039434
## iter 80 value 2108.765905
## iter 90 value 2108.705012
## iter 100 value 2108.664448
## iter 110 value 2108.629109
## iter 120 value 2108.609410
## iter 130 value 2108.588307
## iter 140 value 2108.548752
## iter 150 value 2108.530232
## iter 160 value 2108.522896
## iter 170 value 2108.521465
## iter 180 value 2108.513167
## iter 190 value 2108.494869
## iter 200 value 2108.483992
## iter 210 value 2108.475987
## iter 220 value 2108.468168
## iter 230 value 2108.463407
## iter 240 value 2108.457804
## iter 250 value 2108.438021
## iter 260 value 2108.418144
## iter 270 value 2108.406753
## iter 280 value 2108.401924
## iter 290 value 2108.391215
## iter 300 value 2108.386121
## iter 310 value 2108.384507
## iter 320 value 2108.380595
## iter 330 value 2108.378791
## iter 330 value 2108.378775
## iter 330 value 2108.378759
## final value 2108.378759
## converged
## # weights: 21
## initial value 2294.232422
## iter 10 value 2199.988275
## iter 20 value 2157.833916
## iter 30 value 2136.391868
## iter 40 value 2134.451271
## iter 50 value 2133.527731
## iter 60 value 2133.309074
## iter 70 value 2133.232164
## iter 80 value 2133.067066
## iter 90 value 2132.850575
## iter 100 value 2132.795163
## iter 110 value 2132.732596
## iter 120 value 2132.697150
## iter 130 value 2132.664265
## iter 140 value 2132.136210
## iter 150 value 2129.551051
## iter 160 value 2128.128167
## iter 170 value 2127.130744
## iter 180 value 2126.331251
## iter 190 value 2126.275016
## iter 200 value 2126.264343
## iter 210 value 2126.243512
## iter 220 value 2126.184077
## final value 2126.182172
## converged
## # weights: 31
## initial value 2307.595892
## iter 10 value 2164.190015
## iter 20 value 2139.556554
## iter 30 value 2129.772063
## iter 40 value 2126.690750
## iter 50 value 2123.504537
## iter 60 value 2121.110858
## iter 70 value 2120.075738
## iter 80 value 2119.864783
## iter 90 value 2119.848275
## iter 100 value 2119.835000
## final value 2119.828036
## converged
## # weights: 41
## initial value 2281.325511
## iter 10 value 2153.682311
## iter 20 value 2133.137613
## iter 30 value 2121.592882
## iter 40 value 2118.854116
## iter 50 value 2116.302321
## iter 60 value 2115.827756
## iter 70 value 2115.576253
## iter 80 value 2115.382664
## iter 90 value 2115.335962
## iter 100 value 2115.244909
## iter 110 value 2114.967020
## iter 120 value 2114.436746
## iter 130 value 2114.033838
## iter 140 value 2113.538998
## iter 150 value 2113.257301
## iter 160 value 2112.930036
## iter 170 value 2112.860205
## iter 180 value 2112.849859
## iter 190 value 2112.794930
## iter 200 value 2112.640778
## iter 210 value 2112.588215
## iter 220 value 2112.454479
## iter 230 value 2112.393286
## iter 240 value 2112.341349
## iter 250 value 2112.262501
## iter 260 value 2112.248552
## iter 270 value 2112.231416
## iter 280 value 2112.175217
## iter 290 value 2112.095485
## iter 300 value 2112.001981
## iter 310 value 2111.970515
## iter 320 value 2111.941943
## iter 330 value 2111.914183
## iter 340 value 2111.886953
## iter 350 value 2111.882602
## iter 360 value 2111.855364
## iter 370 value 2111.785467
## iter 380 value 2111.692787
## iter 390 value 2111.581250
## iter 400 value 2111.506135
## iter 410 value 2111.438790
## iter 420 value 2111.401238
## iter 430 value 2111.399500
## iter 440 value 2111.393243
## iter 450 value 2111.357194
## iter 460 value 2111.331585
## iter 470 value 2111.312395
## iter 480 value 2111.289920
## iter 490 value 2111.270738
## iter 500 value 2111.258387
## final value 2111.258387
## stopped after 500 iterations
## # weights: 51
## initial value 2428.831025
## iter 10 value 2148.129378
## iter 20 value 2132.141332
## iter 30 value 2125.076065
## iter 40 value 2123.036333
## iter 50 value 2121.579777
## iter 60 value 2120.961626
## iter 70 value 2120.766678
## iter 80 value 2120.599697
## iter 90 value 2120.063884
## iter 100 value 2116.827648
## iter 110 value 2116.286619
## iter 120 value 2115.811121
## iter 130 value 2115.285865
## iter 140 value 2115.034590
## iter 150 value 2113.417158
## iter 160 value 2113.185563
## iter 170 value 2113.062447
## iter 180 value 2112.971845
## iter 190 value 2112.932861
## iter 200 value 2112.915151
## iter 210 value 2112.855234
## iter 220 value 2112.815321
## iter 230 value 2112.650284
## iter 240 value 2112.392261
## iter 250 value 2112.304619
## iter 260 value 2111.897838
## iter 270 value 2111.531340
## iter 280 value 2111.357713
## iter 290 value 2111.243591
## iter 300 value 2111.091295
## iter 310 value 2110.998799
## iter 320 value 2110.978193
## iter 330 value 2110.910995
## iter 340 value 2110.802510
## iter 350 value 2110.731000
## iter 360 value 2110.680577
## iter 370 value 2110.667971
## iter 380 value 2110.652380
## final value 2110.650650
## converged
## # weights: 61
## initial value 2451.026111
## iter 10 value 2154.791185
## iter 20 value 2135.429337
## iter 30 value 2125.723283
## iter 40 value 2119.739415
## iter 50 value 2117.938919
## iter 60 value 2115.791267
## iter 70 value 2113.658892
## iter 80 value 2113.095692
## iter 90 value 2112.712418
## iter 100 value 2112.531244
## iter 110 value 2112.358947
## iter 120 value 2112.273691
## iter 130 value 2112.222102
## iter 140 value 2112.168153
## iter 150 value 2111.968668
## iter 160 value 2111.671812
## iter 170 value 2111.293540
## iter 180 value 2111.036645
## iter 190 value 2110.945223
## iter 200 value 2110.846852
## iter 210 value 2110.768376
## iter 220 value 2110.725718
## iter 230 value 2110.689715
## iter 240 value 2110.656204
## iter 250 value 2110.627178
## iter 260 value 2110.623678
## iter 270 value 2110.618903
## iter 280 value 2110.582053
## iter 290 value 2110.550514
## iter 300 value 2110.523688
## iter 310 value 2110.501557
## iter 320 value 2110.475151
## iter 330 value 2110.447125
## iter 340 value 2110.410465
## iter 350 value 2110.392401
## iter 360 value 2110.381832
## iter 370 value 2110.372702
## final value 2110.371911
## converged
## # weights: 71
## initial value 2304.490310
## iter 10 value 2151.017440
## iter 20 value 2130.995175
## iter 30 value 2119.711835
## iter 40 value 2116.141194
## iter 50 value 2113.313993
## iter 60 value 2112.631830
## iter 70 value 2112.183892
## iter 80 value 2111.735081
## iter 90 value 2111.467194
## iter 100 value 2110.995032
## iter 110 value 2110.850830
## iter 120 value 2110.767249
## iter 130 value 2110.716387
## iter 140 value 2110.670400
## iter 150 value 2110.652812
## iter 160 value 2110.645333
## iter 170 value 2110.589496
## iter 180 value 2110.551783
## iter 190 value 2110.529337
## iter 200 value 2110.516928
## iter 210 value 2110.503742
## iter 220 value 2110.492605
## iter 230 value 2110.456491
## iter 240 value 2110.422494
## iter 250 value 2110.388655
## iter 260 value 2110.349404
## iter 270 value 2110.324524
## iter 280 value 2110.304234
## final value 2110.299942
## converged
## # weights: 81
## initial value 2320.249171
## iter 10 value 2149.312591
## iter 20 value 2127.732893
## iter 30 value 2121.367297
## iter 40 value 2116.909906
## iter 50 value 2114.524531
## iter 60 value 2112.728896
## iter 70 value 2111.958386
## iter 80 value 2111.147250
## iter 90 value 2110.774953
## iter 100 value 2110.591367
## iter 110 value 2110.446365
## iter 120 value 2110.378177
## iter 130 value 2110.349233
## iter 140 value 2110.336252
## iter 150 value 2110.315666
## iter 160 value 2110.302211
## iter 170 value 2110.295909
## final value 2110.295555
## converged
## # weights: 21
## initial value 2278.516414
## iter 10 value 2182.307559
## iter 20 value 2164.833599
## iter 30 value 2160.639084
## iter 40 value 2157.947450
## iter 50 value 2155.941008
## iter 60 value 2154.793120
## iter 70 value 2154.646471
## iter 80 value 2154.588597
## iter 90 value 2154.577813
## iter 100 value 2153.641170
## iter 110 value 2153.332381
## iter 120 value 2152.647207
## iter 130 value 2150.751472
## iter 140 value 2150.453706
## iter 150 value 2150.394850
## iter 160 value 2150.376973
## iter 170 value 2150.337478
## iter 180 value 2149.962236
## iter 190 value 2149.861110
## iter 200 value 2149.840429
## iter 210 value 2149.810594
## iter 220 value 2149.764971
## iter 230 value 2149.722649
## final value 2149.704237
## converged
## # weights: 31
## initial value 2635.604492
## iter 10 value 2157.804201
## iter 20 value 2138.942383
## iter 30 value 2130.393124
## iter 40 value 2128.973005
## iter 50 value 2127.497631
## iter 60 value 2125.646894
## iter 70 value 2124.763696
## iter 80 value 2124.106445
## iter 90 value 2123.706322
## iter 100 value 2123.298959
## iter 110 value 2123.202632
## iter 120 value 2122.800468
## iter 130 value 2122.614771
## iter 140 value 2122.583552
## iter 150 value 2122.530180
## iter 160 value 2122.487710
## iter 170 value 2122.479169
## iter 180 value 2122.472701
## iter 190 value 2122.449624
## iter 200 value 2122.436953
## iter 210 value 2122.434591
## iter 220 value 2122.415685
## iter 230 value 2122.377523
## iter 240 value 2122.367458
## iter 250 value 2122.364384
## iter 260 value 2122.357801
## iter 270 value 2122.354405
## iter 280 value 2122.352042
## iter 290 value 2122.347157
## iter 300 value 2122.339071
## iter 310 value 2122.303672
## iter 320 value 2122.253020
## iter 330 value 2122.234327
## iter 340 value 2122.232157
## iter 350 value 2122.230820
## iter 360 value 2122.215957
## iter 370 value 2122.119965
## iter 380 value 2121.863868
## iter 390 value 2121.333965
## iter 400 value 2121.113822
## iter 410 value 2121.063047
## iter 420 value 2120.755341
## iter 430 value 2120.508541
## iter 440 value 2120.399408
## iter 450 value 2120.298104
## iter 460 value 2120.251588
## iter 470 value 2120.242086
## iter 480 value 2120.237082
## iter 490 value 2120.212289
## iter 500 value 2120.154344
## final value 2120.154344
## stopped after 500 iterations
## # weights: 41
## initial value 2499.686628
## iter 10 value 2165.483044
## iter 20 value 2148.765346
## iter 30 value 2138.090805
## iter 40 value 2130.627577
## iter 50 value 2126.718492
## iter 60 value 2124.375446
## iter 70 value 2124.014545
## iter 80 value 2123.195449
## iter 90 value 2122.981240
## iter 100 value 2122.651999
## iter 110 value 2122.360352
## iter 120 value 2122.246018
## iter 130 value 2122.136331
## iter 140 value 2121.996099
## iter 150 value 2121.886869
## iter 160 value 2121.846501
## iter 170 value 2121.808333
## iter 180 value 2121.807307
## iter 180 value 2121.807290
## iter 180 value 2121.807288
## final value 2121.807288
## converged
## # weights: 51
## initial value 2512.468298
## iter 10 value 2160.220497
## iter 20 value 2134.967881
## iter 30 value 2130.361304
## iter 40 value 2124.968198
## iter 50 value 2123.037433
## iter 60 value 2122.137626
## iter 70 value 2120.983740
## iter 80 value 2120.310291
## iter 90 value 2119.953384
## iter 100 value 2119.745758
## iter 110 value 2119.678358
## iter 120 value 2119.645320
## iter 130 value 2119.560989
## iter 140 value 2119.484358
## iter 150 value 2119.460059
## iter 160 value 2119.422643
## iter 170 value 2119.387358
## iter 180 value 2119.374736
## iter 190 value 2119.356239
## iter 200 value 2119.338618
## final value 2119.332103
## converged
## # weights: 61
## initial value 2266.176352
## iter 10 value 2162.380059
## iter 20 value 2137.341218
## iter 30 value 2131.436967
## iter 40 value 2127.749333
## iter 50 value 2125.097734
## iter 60 value 2123.325711
## iter 70 value 2122.474395
## iter 80 value 2121.881182
## iter 90 value 2121.660340
## iter 100 value 2121.559838
## iter 110 value 2121.527370
## iter 120 value 2121.496712
## iter 130 value 2121.488477
## iter 140 value 2121.485696
## iter 150 value 2121.467368
## iter 160 value 2121.447573
## iter 170 value 2121.437041
## iter 180 value 2121.419792
## iter 190 value 2121.409110
## iter 200 value 2121.402857
## iter 210 value 2121.397176
## iter 220 value 2121.386566
## iter 230 value 2121.376412
## iter 240 value 2121.372738
## final value 2121.368098
## converged
## # weights: 71
## initial value 2591.806052
## iter 10 value 2154.860163
## iter 20 value 2135.589563
## iter 30 value 2129.075053
## iter 40 value 2125.344752
## iter 50 value 2123.942024
## iter 60 value 2122.904313
## iter 70 value 2122.318780
## iter 80 value 2121.460014
## iter 90 value 2121.144079
## iter 100 value 2120.798620
## iter 110 value 2120.325109
## iter 120 value 2120.110482
## iter 130 value 2120.029050
## iter 140 value 2119.968030
## iter 150 value 2119.938343
## iter 160 value 2119.918067
## iter 170 value 2119.861434
## iter 180 value 2119.773989
## iter 190 value 2119.720248
## iter 200 value 2119.689650
## iter 210 value 2119.666302
## iter 220 value 2119.648983
## iter 230 value 2119.625777
## iter 240 value 2119.580707
## iter 250 value 2119.536227
## iter 260 value 2119.502012
## iter 270 value 2119.457056
## iter 280 value 2119.424124
## iter 290 value 2119.409096
## iter 300 value 2119.407275
## iter 310 value 2119.402992
## iter 320 value 2119.393413
## iter 330 value 2119.382811
## iter 340 value 2119.372023
## iter 350 value 2119.359912
## iter 360 value 2119.354769
## iter 370 value 2119.338519
## iter 380 value 2119.327747
## iter 390 value 2119.324097
## iter 400 value 2119.320926
## iter 410 value 2119.311443
## iter 420 value 2119.309600
## iter 430 value 2119.306006
## final value 2119.305827
## converged
## # weights: 81
## initial value 2336.722744
## iter 10 value 2159.420348
## iter 20 value 2138.151485
## iter 30 value 2129.364734
## iter 40 value 2124.440122
## iter 50 value 2122.477771
## iter 60 value 2121.680686
## iter 70 value 2121.366692
## iter 80 value 2121.065915
## iter 90 value 2120.875559
## iter 100 value 2120.473640
## iter 110 value 2120.098700
## iter 120 value 2119.862166
## iter 130 value 2119.716898
## iter 140 value 2119.655494
## iter 150 value 2119.602773
## iter 160 value 2119.567141
## iter 170 value 2119.557830
## iter 180 value 2119.548629
## iter 190 value 2119.496029
## iter 200 value 2119.460735
## iter 210 value 2119.447753
## iter 220 value 2119.439941
## iter 230 value 2119.429413
## iter 240 value 2119.415985
## iter 250 value 2119.393868
## iter 260 value 2119.366821
## iter 270 value 2119.352782
## iter 280 value 2119.343745
## iter 290 value 2119.324274
## iter 300 value 2119.315031
## iter 310 value 2119.311991
## iter 320 value 2119.309491
## iter 330 value 2119.304760
## final value 2119.304678
## convergedhead(accuracyANN10,100)#Function accuracy values per different samples
accuracyANN<-function(trials){
acc <- data.frame(i = integer(),Accuracy= integer())
for(i in 450:trials) {
# random sample
smp_size <- floor(0.80 * nrow(mydata3))
## set the seed to make the partition reproducible
set.seed(i)
train_ind <- sample(seq_len(nrow(mydata3)), size = smp_size)
trainC <- mydata3[train_ind, ]
testC <- mydata3[-train_ind, ]
modelANNC<-nnet(popularity~.,data=trainC,size = 3,decay = 0.0001,maxit = 500)
testC$pred_nnet<-predict(modelANNC,testC,type="class")
confmatC<-data.frame(Prediction=testC$pred_nnet,Actual=testC$popularity)
accuracy<-nrow(subset(confmatC,Actual==Prediction))/nrow(confmatC)
trial=i
attempt <- data.frame(Trial = trial, Accuracy = accuracy)
acc <- rbind(acc,attempt)
}
return(acc)
}accuracyANN30<-accuracyANN(480)## # weights: 31
## initial value 2466.521200
## iter 10 value 2163.519303
## iter 20 value 2138.900613
## iter 30 value 2131.513872
## iter 40 value 2129.845608
## iter 50 value 2127.905836
## iter 60 value 2126.746207
## iter 70 value 2125.675868
## iter 80 value 2124.810553
## iter 90 value 2124.205001
## iter 100 value 2123.892638
## iter 110 value 2123.809981
## iter 120 value 2123.726981
## iter 130 value 2123.663099
## iter 140 value 2123.645158
## iter 150 value 2123.604307
## iter 160 value 2123.561668
## iter 170 value 2123.538786
## iter 180 value 2123.513711
## iter 190 value 2123.491509
## final value 2123.491370
## converged
## # weights: 31
## initial value 2289.556681
## iter 10 value 2161.670219
## iter 20 value 2137.294564
## iter 30 value 2127.993554
## iter 40 value 2124.379450
## iter 50 value 2123.592819
## iter 60 value 2123.303486
## iter 70 value 2122.671090
## iter 80 value 2122.210138
## iter 90 value 2121.158559
## iter 100 value 2120.499047
## iter 110 value 2120.219834
## iter 120 value 2120.149625
## iter 130 value 2120.125138
## iter 140 value 2120.120756
## iter 150 value 2120.107623
## iter 160 value 2120.058165
## iter 170 value 2120.000715
## iter 180 value 2119.923115
## iter 190 value 2119.884964
## iter 200 value 2119.858740
## iter 210 value 2119.824798
## iter 220 value 2119.763257
## iter 230 value 2119.710259
## iter 240 value 2119.658340
## iter 250 value 2119.216810
## iter 260 value 2118.747871
## iter 270 value 2118.575555
## iter 280 value 2118.157310
## iter 290 value 2117.860586
## iter 300 value 2117.613783
## iter 310 value 2117.459577
## iter 320 value 2117.415065
## iter 330 value 2117.409557
## iter 340 value 2117.289768
## iter 350 value 2117.094464
## iter 360 value 2116.911379
## iter 370 value 2116.817487
## iter 380 value 2116.764647
## iter 390 value 2116.724865
## iter 400 value 2116.700319
## iter 410 value 2116.629170
## iter 420 value 2116.603864
## iter 430 value 2116.589320
## iter 440 value 2116.585197
## final value 2116.583594
## converged
## # weights: 31
## initial value 2406.323391
## iter 10 value 2179.243903
## iter 20 value 2150.272417
## iter 30 value 2139.710153
## iter 40 value 2136.358233
## iter 50 value 2134.645675
## iter 60 value 2133.844895
## iter 70 value 2133.577012
## iter 80 value 2133.465965
## iter 90 value 2133.205311
## iter 100 value 2132.992556
## iter 110 value 2132.937690
## iter 120 value 2132.928039
## iter 130 value 2132.905212
## final value 2132.905091
## converged
## # weights: 31
## initial value 2266.482682
## iter 10 value 2180.577172
## iter 20 value 2159.779328
## iter 30 value 2142.480533
## iter 40 value 2138.555189
## iter 50 value 2136.864997
## iter 60 value 2135.729982
## iter 70 value 2134.971805
## iter 80 value 2133.976322
## iter 90 value 2132.695328
## iter 100 value 2131.813366
## iter 110 value 2131.182724
## iter 120 value 2130.975561
## iter 130 value 2130.878662
## iter 140 value 2130.823194
## iter 150 value 2130.595098
## iter 160 value 2130.263311
## iter 170 value 2130.182832
## iter 180 value 2130.135534
## iter 190 value 2130.101547
## final value 2130.101052
## converged
## # weights: 31
## initial value 2416.636583
## iter 10 value 2162.891121
## iter 20 value 2142.595734
## iter 30 value 2134.742024
## iter 40 value 2126.158402
## iter 50 value 2122.352385
## iter 60 value 2121.672317
## iter 70 value 2121.109632
## iter 80 value 2120.335567
## iter 90 value 2119.840757
## iter 100 value 2119.661568
## iter 110 value 2119.565796
## iter 120 value 2119.503487
## iter 130 value 2119.124667
## iter 140 value 2118.502333
## iter 150 value 2117.819518
## iter 160 value 2117.564959
## iter 170 value 2117.452849
## iter 180 value 2117.230964
## iter 190 value 2117.120462
## iter 200 value 2117.103291
## iter 210 value 2117.014151
## iter 220 value 2116.821609
## iter 230 value 2116.664235
## iter 240 value 2116.332328
## iter 250 value 2116.071962
## iter 260 value 2116.029171
## iter 270 value 2115.989812
## iter 280 value 2115.475965
## iter 290 value 2114.693284
## iter 300 value 2114.061032
## iter 310 value 2113.732052
## iter 320 value 2113.603488
## iter 330 value 2113.545898
## iter 340 value 2113.283026
## iter 350 value 2113.058274
## iter 360 value 2112.901467
## iter 370 value 2112.766317
## iter 380 value 2112.684645
## iter 390 value 2112.674919
## iter 400 value 2112.595803
## iter 410 value 2112.454167
## iter 420 value 2112.422168
## iter 430 value 2112.375637
## iter 440 value 2112.331750
## iter 450 value 2112.325124
## iter 460 value 2112.324071
## final value 2112.323812
## converged
## # weights: 31
## initial value 2317.406959
## iter 10 value 2166.650021
## iter 20 value 2148.037114
## iter 30 value 2145.467741
## iter 40 value 2144.300698
## iter 50 value 2143.768041
## iter 60 value 2143.466634
## iter 70 value 2142.832109
## iter 80 value 2142.667261
## iter 90 value 2142.551098
## iter 100 value 2142.514782
## iter 110 value 2142.460239
## iter 120 value 2142.401898
## iter 130 value 2141.687273
## iter 140 value 2140.449042
## iter 150 value 2139.036531
## iter 160 value 2137.713034
## iter 170 value 2137.422712
## iter 180 value 2137.083739
## iter 190 value 2136.516546
## iter 200 value 2136.449458
## iter 210 value 2136.412354
## iter 220 value 2136.308407
## iter 230 value 2136.214531
## iter 240 value 2136.150501
## iter 250 value 2136.068173
## iter 260 value 2136.009039
## iter 270 value 2136.000036
## iter 280 value 2135.991810
## iter 290 value 2135.985341
## iter 300 value 2135.973720
## iter 310 value 2135.969851
## iter 320 value 2135.940279
## iter 330 value 2135.918390
## iter 340 value 2135.907050
## iter 350 value 2135.898314
## final value 2135.893180
## converged
## # weights: 31
## initial value 2281.734981
## iter 10 value 2180.750524
## iter 20 value 2160.006932
## iter 30 value 2151.392423
## iter 40 value 2147.267518
## iter 50 value 2145.867535
## iter 60 value 2145.215317
## iter 70 value 2145.067814
## iter 80 value 2144.932361
## iter 90 value 2144.764608
## iter 100 value 2144.350027
## iter 110 value 2143.574014
## iter 120 value 2143.548780
## iter 130 value 2143.339127
## iter 140 value 2138.633924
## iter 150 value 2136.413898
## iter 160 value 2134.951535
## iter 170 value 2134.772207
## iter 180 value 2134.465205
## iter 190 value 2134.327608
## iter 200 value 2134.315959
## iter 210 value 2134.296641
## iter 220 value 2134.283882
## iter 230 value 2134.261302
## iter 240 value 2134.257208
## final value 2134.250240
## converged
## # weights: 31
## initial value 2280.244088
## iter 10 value 2165.166991
## iter 20 value 2149.621679
## iter 30 value 2145.336521
## iter 40 value 2143.916991
## iter 50 value 2143.078800
## iter 60 value 2141.794903
## iter 70 value 2141.715725
## iter 80 value 2141.583818
## iter 90 value 2141.529279
## iter 100 value 2141.519576
## iter 110 value 2141.500210
## iter 120 value 2141.487099
## final value 2141.480875
## converged
## # weights: 31
## initial value 2257.354519
## iter 10 value 2149.876454
## iter 20 value 2131.322345
## iter 30 value 2124.467122
## iter 40 value 2119.072533
## iter 50 value 2116.459419
## iter 60 value 2115.771989
## iter 70 value 2115.423731
## iter 80 value 2115.199658
## iter 90 value 2114.870401
## iter 100 value 2114.494821
## iter 110 value 2114.274300
## iter 120 value 2114.132268
## iter 130 value 2114.097836
## iter 140 value 2114.095590
## iter 150 value 2114.060601
## iter 160 value 2114.021052
## iter 170 value 2114.002194
## iter 180 value 2113.985262
## iter 190 value 2113.967010
## iter 200 value 2113.964569
## iter 200 value 2113.964555
## iter 200 value 2113.964549
## final value 2113.964549
## converged
## # weights: 31
## initial value 2456.699258
## iter 10 value 2184.031864
## iter 20 value 2139.881824
## iter 30 value 2133.917027
## iter 40 value 2131.399312
## iter 50 value 2130.742536
## iter 60 value 2129.823139
## iter 70 value 2129.463118
## iter 80 value 2129.245310
## iter 90 value 2128.340434
## iter 100 value 2127.595854
## iter 110 value 2127.439624
## iter 120 value 2127.372596
## iter 130 value 2127.193426
## iter 140 value 2127.111813
## iter 150 value 2126.520110
## iter 160 value 2125.927631
## iter 170 value 2125.674121
## iter 180 value 2125.463379
## iter 190 value 2125.370951
## iter 200 value 2125.359389
## iter 210 value 2125.338201
## iter 220 value 2125.243243
## iter 230 value 2125.178137
## iter 240 value 2125.167020
## iter 250 value 2125.090107
## iter 260 value 2124.010377
## iter 270 value 2122.219755
## iter 280 value 2117.874675
## iter 290 value 2116.089199
## iter 300 value 2115.787366
## iter 310 value 2115.668812
## iter 320 value 2115.646744
## final value 2115.646526
## converged
## # weights: 31
## initial value 2363.903356
## iter 10 value 2168.301157
## iter 20 value 2144.114487
## iter 30 value 2140.349198
## iter 40 value 2138.747061
## iter 50 value 2137.741220
## iter 60 value 2137.420556
## iter 70 value 2137.360717
## iter 80 value 2137.320505
## iter 90 value 2137.192651
## iter 100 value 2137.099441
## iter 110 value 2137.048302
## iter 120 value 2137.040546
## iter 130 value 2136.779294
## iter 140 value 2136.442337
## iter 150 value 2136.109250
## iter 160 value 2136.063878
## iter 170 value 2135.851682
## iter 180 value 2134.943255
## iter 190 value 2134.835553
## iter 200 value 2134.810292
## iter 210 value 2134.622482
## iter 220 value 2133.888503
## iter 230 value 2133.577702
## iter 240 value 2133.158045
## iter 250 value 2133.073768
## iter 260 value 2132.992510
## iter 270 value 2132.785483
## iter 280 value 2131.702972
## iter 290 value 2131.466759
## iter 300 value 2131.290285
## iter 310 value 2130.715218
## iter 320 value 2128.324997
## iter 330 value 2127.520096
## iter 340 value 2126.153057
## iter 350 value 2125.713398
## iter 360 value 2125.643549
## iter 370 value 2125.612636
## iter 380 value 2125.405197
## final value 2125.405040
## converged
## # weights: 31
## initial value 2372.472532
## iter 10 value 2153.220474
## iter 20 value 2131.452757
## iter 30 value 2124.473698
## iter 40 value 2122.196763
## iter 50 value 2119.721040
## iter 60 value 2118.376363
## iter 70 value 2116.818100
## iter 80 value 2115.376462
## iter 90 value 2113.822065
## iter 100 value 2113.058028
## iter 110 value 2112.097094
## iter 120 value 2111.834251
## iter 130 value 2111.753660
## iter 140 value 2111.745107
## iter 150 value 2111.734852
## iter 160 value 2111.695480
## iter 170 value 2111.677619
## iter 180 value 2111.605433
## iter 190 value 2111.421712
## iter 200 value 2111.373087
## iter 210 value 2111.343822
## iter 220 value 2111.334193
## iter 230 value 2111.331254
## iter 240 value 2111.325823
## iter 250 value 2111.324337
## final value 2111.322919
## converged
## # weights: 31
## initial value 2289.293022
## iter 10 value 2174.644527
## iter 20 value 2158.342483
## iter 30 value 2146.187762
## iter 40 value 2142.513538
## iter 50 value 2140.498543
## iter 60 value 2139.358905
## iter 70 value 2138.350367
## iter 80 value 2138.197232
## iter 90 value 2137.689080
## iter 100 value 2137.047834
## iter 110 value 2136.460263
## iter 120 value 2136.236968
## iter 130 value 2136.172065
## iter 140 value 2136.168837
## iter 140 value 2136.168816
## iter 150 value 2136.168175
## iter 150 value 2136.168171
## iter 150 value 2136.168154
## final value 2136.168154
## converged
## # weights: 31
## initial value 2412.626189
## iter 10 value 2161.667736
## iter 20 value 2142.266104
## iter 30 value 2136.558566
## iter 40 value 2134.664741
## iter 50 value 2134.064402
## iter 60 value 2133.932988
## iter 70 value 2133.856932
## iter 80 value 2133.835220
## iter 90 value 2133.811888
## iter 100 value 2133.773266
## iter 110 value 2133.748770
## iter 120 value 2133.728639
## iter 130 value 2133.679628
## iter 140 value 2133.677200
## iter 150 value 2133.658059
## iter 160 value 2133.622813
## iter 170 value 2133.610491
## iter 180 value 2133.606341
## iter 190 value 2133.602041
## final value 2133.601174
## converged
## # weights: 31
## initial value 2285.085495
## iter 10 value 2192.542793
## iter 20 value 2147.029027
## iter 30 value 2135.847216
## iter 40 value 2132.416484
## iter 50 value 2129.609658
## iter 60 value 2126.315936
## iter 70 value 2125.856716
## iter 80 value 2125.177433
## iter 90 value 2124.727883
## iter 100 value 2124.529585
## iter 110 value 2124.384794
## iter 120 value 2124.337411
## iter 130 value 2124.316019
## iter 140 value 2124.313116
## iter 150 value 2124.312443
## final value 2124.312378
## converged
## # weights: 31
## initial value 2334.594216
## iter 10 value 2174.946580
## iter 20 value 2158.300198
## iter 30 value 2152.059051
## iter 40 value 2146.482220
## iter 50 value 2144.636290
## iter 60 value 2144.413706
## iter 70 value 2144.335228
## iter 80 value 2144.029958
## iter 90 value 2143.552629
## iter 100 value 2143.065042
## iter 110 value 2142.744746
## iter 120 value 2142.666743
## iter 130 value 2142.591108
## iter 140 value 2142.504219
## iter 150 value 2142.140092
## iter 160 value 2141.985981
## iter 170 value 2141.895933
## iter 180 value 2141.877710
## iter 190 value 2141.862491
## iter 190 value 2141.862482
## final value 2141.862482
## converged
## # weights: 31
## initial value 2293.270068
## iter 10 value 2131.015355
## iter 20 value 2116.933976
## iter 30 value 2112.621196
## iter 40 value 2111.874822
## iter 50 value 2111.010869
## iter 60 value 2109.118981
## iter 70 value 2108.428657
## iter 80 value 2107.792914
## iter 90 value 2107.347797
## iter 100 value 2107.041521
## iter 110 value 2106.939878
## iter 120 value 2106.894117
## iter 130 value 2106.865066
## iter 140 value 2106.841530
## iter 150 value 2106.785388
## iter 160 value 2106.736641
## iter 170 value 2106.670727
## iter 180 value 2106.620030
## iter 190 value 2106.590415
## final value 2106.589855
## converged
## # weights: 31
## initial value 2303.303635
## iter 10 value 2170.663237
## iter 20 value 2151.406783
## iter 30 value 2143.000728
## iter 40 value 2140.920183
## iter 50 value 2139.511431
## iter 60 value 2138.642321
## iter 70 value 2138.384775
## iter 80 value 2138.078901
## iter 90 value 2137.840886
## iter 100 value 2137.737055
## iter 110 value 2137.048980
## iter 120 value 2136.288952
## iter 130 value 2136.105207
## iter 140 value 2136.070879
## iter 150 value 2135.981054
## iter 160 value 2135.789248
## iter 170 value 2135.537034
## iter 180 value 2135.504514
## iter 190 value 2135.344245
## iter 200 value 2135.248200
## iter 210 value 2135.219889
## iter 220 value 2135.181665
## iter 230 value 2135.128220
## iter 240 value 2135.125680
## iter 250 value 2135.121964
## iter 260 value 2135.116291
## iter 270 value 2135.100007
## final value 2135.094494
## converged
## # weights: 31
## initial value 2329.890216
## iter 10 value 2172.194960
## iter 20 value 2148.931370
## iter 30 value 2141.066632
## iter 40 value 2132.539734
## iter 50 value 2131.739318
## iter 60 value 2131.400166
## iter 70 value 2131.232492
## iter 80 value 2131.129242
## iter 90 value 2130.948502
## iter 100 value 2130.742674
## iter 110 value 2130.400125
## iter 120 value 2130.043305
## iter 130 value 2129.885188
## iter 140 value 2129.842737
## iter 150 value 2129.754549
## iter 160 value 2129.712466
## iter 170 value 2129.694351
## iter 180 value 2129.661969
## iter 190 value 2129.616477
## iter 200 value 2129.611826
## iter 210 value 2129.575288
## iter 220 value 2129.485557
## iter 230 value 2129.390288
## iter 240 value 2129.325381
## iter 250 value 2129.185052
## iter 260 value 2129.167811
## iter 270 value 2129.157854
## iter 280 value 2129.115447
## iter 290 value 2129.077214
## iter 300 value 2129.003213
## iter 310 value 2128.976796
## final value 2128.973766
## converged
## # weights: 31
## initial value 2796.469196
## iter 10 value 2264.054662
## iter 20 value 2193.990753
## iter 30 value 2172.930729
## iter 40 value 2161.693992
## iter 50 value 2152.988760
## iter 60 value 2150.276136
## iter 70 value 2148.468123
## iter 80 value 2148.261071
## iter 90 value 2148.068854
## iter 100 value 2143.518331
## iter 110 value 2137.331956
## iter 120 value 2136.988124
## iter 130 value 2136.906832
## iter 140 value 2136.846685
## iter 150 value 2136.840224
## iter 160 value 2136.837240
## iter 170 value 2136.827668
## iter 180 value 2136.805081
## iter 190 value 2136.772661
## iter 200 value 2136.723182
## final value 2136.712531
## converged
## # weights: 31
## initial value 2376.477677
## iter 10 value 2169.465139
## iter 20 value 2153.524117
## iter 30 value 2139.947031
## iter 40 value 2137.983454
## iter 50 value 2136.192095
## iter 60 value 2135.182106
## iter 70 value 2134.960517
## iter 80 value 2134.497349
## iter 90 value 2134.029023
## iter 100 value 2133.981631
## iter 110 value 2133.970805
## iter 120 value 2133.963516
## final value 2133.962515
## converged
## # weights: 31
## initial value 2313.025323
## iter 10 value 2179.651027
## iter 20 value 2150.379058
## iter 30 value 2141.352849
## iter 40 value 2140.093698
## iter 50 value 2138.620853
## iter 60 value 2136.968030
## iter 70 value 2136.793767
## iter 80 value 2136.535933
## iter 90 value 2135.846453
## iter 100 value 2135.546305
## iter 110 value 2135.041184
## iter 120 value 2133.742066
## iter 130 value 2131.799972
## iter 140 value 2131.139623
## iter 150 value 2130.659569
## iter 160 value 2130.350067
## iter 170 value 2130.243576
## iter 180 value 2130.197992
## iter 190 value 2130.011364
## iter 200 value 2129.896038
## iter 210 value 2129.734929
## iter 220 value 2129.693203
## iter 230 value 2129.598593
## iter 240 value 2129.582165
## iter 250 value 2129.552358
## iter 260 value 2129.540452
## iter 270 value 2129.465163
## iter 280 value 2129.345878
## iter 290 value 2128.282136
## iter 300 value 2128.161854
## iter 310 value 2128.141271
## iter 320 value 2128.118485
## iter 330 value 2128.080577
## final value 2128.076876
## converged
## # weights: 31
## initial value 2283.920504
## iter 10 value 2173.536874
## iter 20 value 2149.500855
## iter 30 value 2144.952341
## iter 40 value 2139.011224
## iter 50 value 2136.986885
## iter 60 value 2136.621709
## iter 70 value 2136.458221
## iter 80 value 2136.352435
## iter 90 value 2136.263087
## iter 100 value 2136.211905
## iter 110 value 2136.099219
## iter 120 value 2136.045277
## iter 130 value 2135.996780
## iter 140 value 2135.978682
## iter 150 value 2135.962623
## iter 160 value 2135.923166
## iter 170 value 2135.885167
## iter 180 value 2135.860054
## iter 190 value 2135.848067
## final value 2135.847742
## converged
## # weights: 31
## initial value 2530.848536
## iter 10 value 2160.432169
## iter 20 value 2138.269060
## iter 30 value 2130.647048
## iter 40 value 2127.338220
## iter 50 value 2125.075375
## iter 60 value 2124.335519
## iter 70 value 2123.995835
## iter 80 value 2123.721057
## iter 90 value 2123.259046
## iter 100 value 2123.024810
## iter 110 value 2122.962515
## iter 120 value 2122.930221
## iter 130 value 2122.907623
## iter 140 value 2122.890522
## iter 150 value 2122.852517
## iter 160 value 2122.838946
## iter 170 value 2122.827491
## iter 180 value 2122.825552
## final value 2122.825455
## converged
## # weights: 31
## initial value 2566.992688
## iter 10 value 2172.162510
## iter 20 value 2152.903259
## iter 30 value 2140.332151
## iter 40 value 2131.919504
## iter 50 value 2128.561691
## iter 60 value 2125.181990
## iter 70 value 2124.833679
## iter 80 value 2124.722028
## iter 90 value 2123.978155
## iter 100 value 2121.816651
## iter 110 value 2121.034441
## iter 120 value 2120.718110
## iter 130 value 2120.513832
## iter 140 value 2120.476091
## iter 150 value 2120.382238
## iter 160 value 2120.249359
## iter 170 value 2120.114727
## iter 180 value 2119.975913
## iter 190 value 2119.729726
## iter 200 value 2119.725561
## iter 210 value 2119.695502
## iter 220 value 2119.663458
## iter 230 value 2119.656241
## iter 240 value 2119.643504
## iter 250 value 2119.631615
## iter 260 value 2119.626110
## final value 2119.626058
## converged
## # weights: 31
## initial value 2458.837930
## iter 10 value 2188.165494
## iter 20 value 2168.280818
## iter 30 value 2163.133162
## iter 40 value 2159.764112
## iter 50 value 2158.959911
## iter 60 value 2158.451080
## iter 70 value 2158.326236
## iter 80 value 2158.274649
## iter 90 value 2158.106171
## iter 100 value 2157.922749
## iter 110 value 2157.778631
## iter 120 value 2157.702557
## final value 2157.685773
## converged
## # weights: 31
## initial value 2329.168146
## iter 10 value 2170.906477
## iter 20 value 2151.573017
## iter 30 value 2136.562326
## iter 40 value 2131.795865
## iter 50 value 2129.217007
## iter 60 value 2128.521955
## iter 70 value 2128.306807
## iter 80 value 2128.031642
## iter 90 value 2127.631295
## iter 100 value 2126.836004
## iter 110 value 2126.719538
## iter 120 value 2126.566102
## iter 130 value 2126.551568
## iter 140 value 2126.548172
## iter 150 value 2126.524675
## iter 160 value 2126.495008
## iter 170 value 2126.483271
## iter 180 value 2126.480882
## iter 190 value 2126.474416
## final value 2126.474220
## converged
## # weights: 31
## initial value 2458.523489
## iter 10 value 2176.580544
## iter 20 value 2152.027698
## iter 30 value 2147.794434
## iter 40 value 2146.929966
## iter 50 value 2146.475393
## iter 60 value 2146.412594
## iter 70 value 2146.369814
## iter 80 value 2145.313083
## iter 90 value 2144.706308
## iter 100 value 2144.453731
## iter 110 value 2144.319416
## iter 120 value 2144.142381
## iter 130 value 2143.924055
## iter 140 value 2143.820267
## iter 150 value 2143.686752
## iter 160 value 2143.475925
## iter 170 value 2143.102793
## iter 180 value 2142.715495
## iter 190 value 2142.649538
## final value 2142.649434
## converged
## # weights: 31
## initial value 2496.838433
## iter 10 value 2173.526821
## iter 20 value 2149.843613
## iter 30 value 2142.715016
## iter 40 value 2138.470273
## iter 50 value 2137.803349
## iter 60 value 2137.656311
## iter 70 value 2137.627863
## iter 80 value 2137.571883
## iter 90 value 2137.382764
## iter 100 value 2137.302617
## iter 110 value 2137.253773
## iter 120 value 2137.189509
## iter 130 value 2137.135237
## iter 140 value 2137.119528
## iter 150 value 2137.082394
## iter 160 value 2137.052837
## final value 2137.036040
## converged
## # weights: 31
## initial value 2599.195302
## iter 10 value 2180.230664
## iter 20 value 2155.820297
## iter 30 value 2150.249958
## iter 40 value 2145.372001
## iter 50 value 2138.394501
## iter 60 value 2135.991179
## iter 70 value 2134.598916
## iter 80 value 2134.203009
## iter 90 value 2134.108501
## iter 100 value 2133.782004
## iter 110 value 2133.600594
## iter 120 value 2133.355087
## iter 130 value 2132.608975
## iter 140 value 2132.326875
## iter 150 value 2132.096245
## iter 160 value 2131.623250
## iter 170 value 2130.908118
## iter 180 value 2130.572282
## iter 190 value 2130.473728
## iter 200 value 2130.333851
## iter 210 value 2130.303426
## iter 220 value 2130.284134
## iter 230 value 2130.248747
## iter 240 value 2130.235388
## iter 250 value 2130.215491
## iter 260 value 2130.197970
## iter 270 value 2129.889241
## iter 280 value 2129.400937
## iter 290 value 2129.077753
## iter 300 value 2128.859204
## iter 310 value 2128.765115
## iter 320 value 2128.665458
## iter 330 value 2128.626813
## iter 340 value 2128.624651
## iter 350 value 2128.618846
## iter 360 value 2128.562943
## iter 370 value 2128.492029
## iter 380 value 2128.424397
## iter 390 value 2128.367679
## iter 400 value 2128.361398
## iter 400 value 2128.361384
## iter 400 value 2128.361368
## final value 2128.361368
## converged
## # weights: 31
## initial value 2403.982107
## iter 10 value 2164.938525
## iter 20 value 2145.218259
## iter 30 value 2138.984719
## iter 40 value 2135.441686
## iter 50 value 2133.923438
## iter 60 value 2133.583981
## iter 70 value 2133.549931
## iter 80 value 2133.451368
## iter 90 value 2133.323782
## iter 100 value 2133.228447
## iter 110 value 2133.175887
## iter 120 value 2133.105502
## final value 2133.095593
## convergedhead(accuracyANN30,31)#Function accuracy values per different samples
accuracyNB<-function(trials){
acc <- data.frame(i = integer(),Accuracy= integer())
for(i in 450:trials) {
# random sample
smp_size <- floor(0.80 * nrow(mydata3))
## set the seed to make the partition reproducible
set.seed(i)
train_ind <- sample(seq_len(nrow(mydata3)), size = smp_size)
trainC <- mydata3[train_ind, ]
testC <- mydata3[-train_ind, ]
NaivemodelC<-naiveBayes(popularity~.,data=trainC, laplace=1)
laplace_prediction1C<-predict(NaivemodelC,testC,type="class")
confumatNaiveC<-data.frame(Actual=testC$popularity,Prediction=laplace_prediction1C)
accuracy<-nrow(subset(confumatNaiveC,Actual==Prediction))/nrow(confumatNaiveC)
trial=i
attempt <- data.frame(Trial = trial, Accuracy = accuracy)
acc <- rbind(acc,attempt)
}
return(acc)
}accuracyNB30<-accuracyNB(480)head(accuracyNB30,31)#Function accuracy values per different samples
accuracyRF<-function(trials){
acc <- data.frame(i = integer(),Accuracy= integer())
for(i in 450:trials) {
# random sample
smp_size <- floor(0.80 * nrow(mydata3))
## set the seed to make the partition reproducible
set.seed(i)
train_ind <- sample(seq_len(nrow(mydata3)), size = smp_size)
trainC <- mydata3[train_ind, ]
testC <- mydata3[-train_ind, ]
RFmodelC<-rpart(popularity~.,data=trainC, method="class")
RF_prediction1C<-predict(RFmodelC,testC,type="class")
confumatRF<-data.frame(Actual=testC$popularity,Prediction=RF_prediction1C)
accuracy<-nrow(subset(confumatRF,Actual==Prediction))/nrow(confumatRF)
trial=i
attempt <- data.frame(Trial = trial, Accuracy = accuracy)
acc <- rbind(acc,attempt)
}
return(acc)
}accuracyRF30<-accuracyRF(480)head(accuracyRF30,31)#Function accuracy values per different samples
accuracyGLM<-function(trials){
acc <- data.frame(i = integer(),Accuracy= integer())
for(i in 450:trials) {
# random sample
smp_size <- floor(0.80 * nrow(mydata3))
## set the seed to make the partition reproducible
set.seed(i)
train_ind <- sample(seq_len(nrow(mydata3)), size = smp_size)
trainC <- mydata3[train_ind, ]
testC <- mydata3[-train_ind, ]
glmModel <- glm(data = trainC, popularity ~ ., family = "binomial")
predGLM <- predict(glmModel, newdata = testC, type = "response")
predGLMClass<-ifelse(predGLM>0.5,"very popular","popular")
confumatLG<-data.frame(Actual=testC$popularity,Prediction=predGLMClass)
accuracy<-nrow(subset(confumatLG,Actual==Prediction))/nrow(confumatLG)
trial=i
attempt <- data.frame(Trial = trial, Accuracy = accuracy)
acc <- rbind(acc,attempt)
}
return(acc)
}accuracyGLM30<-accuracyGLM(480)head(accuracyGLM30,31)#Function accuracy values per different samples
accuracyRF1<-function(trials){
acc <- data.frame(i = integer(),Accuracy= integer())
for(i in 450:trials) {
# random sample
smp_size <- floor(0.80 * nrow(mydata3))
## set the seed to make the partition reproducible
set.seed(i)
train_ind <- sample(seq_len(nrow(mydata2)), size = smp_size)
trainC <- mydata3[train_ind, ]
testC <- mydata3[-train_ind, ]
RFmodelC<-randomForest(popularity~.,data=trainC, method="class")
RF_prediction1C2<-predict(RFmodelC,testC,type="class")
confumatRF<-data.frame(Actual=testC$popularity,Prediction=RF_prediction1C2)
accuracy<-nrow(subset(confumatRF,Actual==Prediction))/nrow(confumatRF)
trial=i
attempt <- data.frame(Trial = trial, Accuracy = accuracy)
acc <- rbind(acc,attempt)
}
return(acc)
}accuracyRF130<-accuracyRF1(480)head(accuracyRF130,31)library("dplyr")#Putting all the accuracy values together
accuracyANN30$model<-"ANN"
accuracyNB30$model<-"Naive Bayes"
accuracyRF30$model<-"Class. & Reg. Trees"
accuracyRF130$model<-"Random Forest"
accuracyGLM30$model<-"Logistic Reg."
bestAccuracy<-rbind(accuracyANN30,accuracyNB30,accuracyRF30,accuracyRF130,accuracyGLM30)
byModel<-group_by(bestAccuracy,model)
byModelAvg<-summarize(byModel,
Avg=mean(Accuracy))
byModelAvgp<-ggplot(byModelAvg, aes(model,Avg,fill=model))+geom_bar(position="dodge",stat="identity") + geom_text(aes(label = round(Avg,digits=2)),size = 3, hjust = 0.5, vjust = 3, position = "stack")+labs(title = "Comparison Avg Accuracy per Model (31 Trials)",x="Model", y="Avg Accuracy")+theme(axis.text.x = element_text(angle = 45,size=8))
p
#Running Anova for the variables using previous match
AnovaModel<-aov(bestAccuracy$Accuracy~bestAccuracy$model)
summary(AnovaModel)## Df Sum Sq Mean Sq F value Pr(>F)
## bestAccuracy$model 4 0.01549 0.003873 17.63 6.98e-12 ***
## Residuals 150 0.03294 0.000220
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1TUKEY <- TukeyHSD(AnovaModel)
TUKEY## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = bestAccuracy$Accuracy ~ bestAccuracy$model)
##
## $`bestAccuracy$model`
## diff lwr upr
## Class. & Reg. Trees-ANN -9.722641e-03 -0.020116487 0.0006712053
## Logistic Reg.-ANN -3.655412e-03 -0.014049258 0.0067384347
## Naive Bayes-ANN -2.897950e-02 -0.039373346 -0.0185856533
## Random Forest-ANN -9.760326e-03 -0.020154172 0.0006335207
## Logistic Reg.-Class. & Reg. Trees 6.067229e-03 -0.004326617 0.0164610757
## Naive Bayes-Class. & Reg. Trees -1.925686e-02 -0.029650705 -0.0088630124
## Random Forest-Class. & Reg. Trees -3.768465e-05 -0.010431531 0.0103561616
## Naive Bayes-Logistic Reg. -2.532409e-02 -0.035717934 -0.0149302418
## Random Forest-Logistic Reg. -6.104914e-03 -0.016498760 0.0042889322
## Random Forest-Naive Bayes 1.921917e-02 0.008825328 0.0296130202
## p adj
## Class. & Reg. Trees-ANN 0.0787050
## Logistic Reg.-ANN 0.8677724
## Naive Bayes-ANN 0.0000000
## Random Forest-ANN 0.0767941
## Logistic Reg.-Class. & Reg. Trees 0.4922134
## Naive Bayes-Class. & Reg. Trees 0.0000093
## Random Forest-Class. & Reg. Trees 1.0000000
## Naive Bayes-Logistic Reg. 0.0000000
## Random Forest-Logistic Reg. 0.4858618
## Random Forest-Naive Bayes 0.0000097RFmodelC<-randomForest(popularity~.,data=train1, method="class")varImpPlot(RFmodelC)
This model indicates that rap and trap have more importance in the random forest classifier.