Justin Kaplan
Workshop 5
Load packages + Data
library(readr)
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(Hmisc)
##
## Attaching package: 'Hmisc'
## The following objects are masked from 'package:dplyr':
##
## src, summarize
## The following objects are masked from 'package:base':
##
## format.pval, units
library(VIM)
## Loading required package: colorspace
## Loading required package: grid
## VIM is ready to use.
## Suggestions and bug-reports can be submitted at: https://github.com/statistikat/VIM/issues
##
## Attaching package: 'VIM'
## The following object is masked from 'package:datasets':
##
## sleep
dirty_iris <- read.csv("https://raw.githubusercontent.com/edwindj/datacleaning/master/data/dirty_iris.csv")
Question 1
summary(dirty_iris$Petal.Length)
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 0.00 1.60 4.50 4.45 5.10 63.00 19
There are 19 Missing Data points
Question 2
sum(complete.cases(dirty_iris))
## [1] 96
Question 3
summary(dirty_iris)
## Sepal.Length Sepal.Width Petal.Length Petal.Width
## Min. : 0.000 Min. :-3.000 Min. : 0.00 Min. :0.1
## 1st Qu.: 5.100 1st Qu.: 2.800 1st Qu.: 1.60 1st Qu.:0.3
## Median : 5.750 Median : 3.000 Median : 4.50 Median :1.3
## Mean : 6.559 Mean : 3.391 Mean : 4.45 Mean :Inf
## 3rd Qu.: 6.400 3rd Qu.: 3.300 3rd Qu.: 5.10 3rd Qu.:1.8
## Max. :73.000 Max. :30.000 Max. :63.00 Max. :Inf
## NA's :10 NA's :17 NA's :19 NA's :12
## Species
## Length:150
## Class :character
## Mode :character
##
##
##
##
Question 4
dirty_iris[which(dirty_iris$Petal.Width=="Inf"),"Petal.Width"] <- NA
Question 5
filter(dirty_iris, Sepal.Width < 0 | Sepal.Length > 30)
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 5 -3 3.5 1 versicolor
## 2 73 29 63.0 NA virginica
## 3 49 30 14.0 2 setosa
Question 6
dirty_iris[which(dirty_iris$Sepal.Width=="-3"),"Sepal.Width"] <- 3
There are now only 2 exceptions for the rules
Question 7.1
mean(dirty_iris$Sepal.Width, na.rm=TRUE)
## [1] 3.43609
Mean_Width <- impute(dirty_iris$Sepal.Width, fun=mean)
print(Mean_Width)
## 1 2 3 4 5 6 7 8
## 3.20000 3.30000 3.43609* 3.40000 2.60000 3.43609* 2.70000 3.00000
## 9 10 11 12 13 14 15 16
## 2.70000 3.10000 3.50000 2.70000 3.00000 2.80000 3.90000 3.00000
## 17 18 19 20 21 22 23 24
## 3.43609* 3.20000 4.00000 3.43609* 3.60000 3.43609* 2.80000 3.30000
## 25 26 27 28 29 30 31 32
## 3.00000 3.20000 3.10000 29.00000 3.20000 2.80000 3.20000 3.20000
## 33 34 35 36 37 38 39 40
## 2.80000 2.90000 2.90000 3.00000 3.00000 2.20000 2.50000 3.00000
## 41 42 43 44 45 46 47 48
## 3.43609* 2.70000 3.43609* 2.70000 4.20000 2.80000 3.43609* 3.20000
## 49 50 51 52 53 54 55 56
## 3.00000 3.40000 2.60000 3.10000 2.70000 3.40000 3.30000 3.80000
## 57 58 59 60 61 62 63 64
## 3.80000 2.90000 2.80000 2.80000 2.30000 2.80000 3.00000 3.30000
## 65 66 67 68 69 70 71 72
## 3.00000 2.50000 2.50000 3.20000 3.50000 3.50000 3.00000 3.10000
## 73 74 75 76 77 78 79 80
## 3.50000 3.43609* 2.80000 2.50000 3.50000 3.00000 3.80000 3.80000
## 81 82 83 84 85 86 87 88
## 2.60000 3.40000 2.90000 3.70000 3.00000 3.80000 2.90000 2.90000
## 89 90 91 92 93 94 95 96
## 2.90000 2.50000 3.20000 3.43609* 3.40000 2.70000 2.20000 3.10000
## 97 98 99 100 101 102 103 104
## 2.30000 3.43609* 3.00000 2.80000 3.40000 3.60000 2.70000 3.00000
## 105 106 107 108 109 110 111 112
## 3.70000 3.43609* 3.00000 3.00000 2.80000 3.40000 3.40000 3.40000
## 113 114 115 116 117 118 119 120
## 3.40000 3.30000 3.10000 2.60000 3.43609* 3.10000 3.00000 2.80000
## 121 122 123 124 125 126 127 128
## 3.00000 2.30000 3.20000 4.10000 30.00000 2.90000 3.20000 3.43609*
## 129 130 131 132 133 134 135 136
## 3.60000 0.00000 2.50000 3.10000 3.43609* 3.30000 3.00000 3.00000
## 137 138 139 140 141 142 143 144
## 3.20000 3.00000 3.10000 2.20000 3.43609* 3.43609* 3.00000 2.90000
## 145 146 147 148 149 150
## 2.50000 3.10000 3.00000 3.50000 3.10000 2.60000
There are no longer any NA values and all of the NAs have been
replaced by 3.43609
Question 7.2
median(dirty_iris$Petal.Length, na.rm=TRUE)
## [1] 4.5
Median_Length <- impute(dirty_iris$Petal.Length, fun=median)
print(Median_Length)
## 1 2 3 4 5 6 7 8 9 10
## 4.500 6.000 5.400 1.600 3.500 4.500* 5.300 5.100 4.100 1.600
## 11 12 13 14 15 16 17 18 19 20
## 1.600 5.100 4.800 4.800 1.700 3.500 4.000 1.300 4.500* 4.200
## 21 22 23 24 25 26 27 28 29 30
## 4.500* 4.500 4.500* 5.700 5.900 1.400 1.500 63.000 5.100 0.820
## 31 32 33 34 35 36 37 38 39 40
## 4.500* 4.800 4.500 4.500* 23.000 1.400 5.500 4.500 5.800 1.600
## 41 42 43 44 45 46 47 48 49 50
## 1.200 3.900 1.300 5.100 1.400 6.700 4.500* 4.700 5.800 4.500
## 51 52 53 54 55 56 57 58 59 60
## 4.400 4.500* 3.900 1.600 4.700 6.700 1.500 4.500 5.600 5.600
## 61 62 63 64 65 66 67 68 69 70
## 3.300 6.100 1.100 1.400 5.800 4.900 4.500* 5.700 4.500* 1.300
## 71 72 73 74 75 76 77 78 79 80
## 4.600 5.100 1.400 4.600 4.900 4.500 1.300 6.600 0.000 6.400
## 81 82 83 84 85 86 87 88 89 90
## 5.600 1.700 4.700 1.500 5.200 1.900 4.300 4.200 1.400 5.000
## 91 92 93 94 95 96 97 98 99 100
## 6.000 3.300 1.400 5.100 5.000 4.500* 4.000 5.000 4.200 5.100
## 101 102 103 104 105 106 107 108 109 110
## 1.500 4.500* 4.900 4.100 4.500* 0.925 5.200 1.400 4.500* 1.400
## 111 112 113 114 115 116 117 118 119 120
## 4.500* 1.500 1.500 5.700 4.700 6.900 4.400 1.500 5.500 4.700
## 121 122 123 124 125 126 127 128 129 130
## 4.500* 1.300 5.300 1.500 14.000 3.600 5.900 5.100 4.500* 1.700
## 131 132 133 134 135 136 137 138 139 140
## 3.900 4.400 1.900 1.700 1.300 4.500* 1.600 4.900 5.400 4.000
## 141 142 143 144 145 146 147 148 149 150
## 1.400 3.800 4.400 5.600 5.000 5.600 4.500 1.500 4.500* 4.000
There are no NA values and all of the NAs have been replaced with
4.500
Question 7.3
model <- lm(Sepal.Length ~ Sepal.Width + Petal.Length,
data = dirty_iris)
I <- is.na(dirty_iris$Sepal.Length)
dirty_iris$Sepal.Length[I] <- predict(model, newdata = dirty_iris[I,])
head(model,10)
## $coefficients
## (Intercept) Sepal.Width Petal.Length
## -0.3441298 1.4718007 0.4500996
##
## $residuals
## 1 2 4 5 7 8
## 0.008919242 -0.913410218 -0.380152092 0.642099276 0.384739938 -0.466780365
## 9 10 11 12 13 14
## 0.324859447 -0.138611870 -0.527332165 0.074759857 -0.231750487 0.862609660
## 16 18 24 26 27 28
## -0.646621019 -0.250762067 -0.378380340 -0.395772026 0.006398089 2.305634158
## 29 32 33 35 36 37
## -0.161140512 -0.626110635 -0.102360463 -7.676382967 0.098588121 -0.046820201
## 38 39 40 42 44 45
## 1.280719980 0.754050290 0.208568203 0.414879366 -0.125240143 -0.967572763
## 46 48 49 50 51 53
## 0.907420438 0.518899324 -0.181850078 -0.685440905 0.037009644 -0.185120634
## 54 55 56 57 59 60
## -0.580152092 -0.328280749 -0.564380300 -0.823862427 0.102529987 0.102529987
## 61 62 63 64 65 66
## 0.473659415 0.877480192 -0.266382001 -0.142952100 0.518149922 0.759139922
## 70 71 72 73 75 76
## -0.392302288 -0.041730569 0.386039562 -0.337312247 -0.382400299 -0.460820241
## 77 78 79 80 81 82
## 0.107697712 0.558070249 -0.148713041 -0.229350422 0.096890135 -0.025162051
## 83 84 85 86 87 88
## 0.060439545 -0.376682354 0.288209676 -1.003902264 0.540479382 -0.114510659
## 89 90 91 93 94 95
## -0.154231805 0.714129963 0.133769856 -0.090132173 -0.125240143 0.855670184
## 97 99 100 101 103 104
## 0.658589701 -0.261690733 0.227579783 0.064857867 0.464779775 -0.316680774
## 107 108 110 112 113 115
## 0.088209676 0.098588121 -0.690132173 -0.335142133 -0.235142133 0.366079398
## 116 118 122 123 124 125
## 1.111760667 -0.293601911 0.873858597 -0.351160430 -1.165402649 -1.111286629
## 126 127 130 131 132 134
## 0.055549095 -0.221220185 5.278960456 0.509239513 0.501109275 -0.177981977
## 135 137 139 140 143 144
## -0.256401919 -0.385791944 0.251009684 1.305769775 0.548289349 -0.144650086
## 145 146 147 148 150
## 0.114129963 -0.039010234 -0.496720610 -0.282322206 0.517049480
##
## $effects
## (Intercept) Sepal.Width Petal.Length
## -71.113136134 76.114741287 20.509012864 0.662846838 0.389916093
##
## -0.464509454 0.339423240 -0.110450298 -0.505130393 0.081500617
##
## -0.227132667 0.870207380 -0.631833257 -0.221743535 -0.385273100
##
## -0.367535797 0.035341965 1.467564471 -0.161849502 -0.624472715
##
## -0.092415833 -7.812654381 0.129804251 -0.047678503 1.299604311
##
## 0.758294829 0.238219726 0.431007765 -0.118499383 -0.954236036
##
## 0.900154397 0.521319547 -0.185055290 -0.684435976 0.050716477
##
## -0.168992235 -0.556460369 -0.327350477 -0.586545842 -0.805348203
##
## 0.103869282 0.103869282 0.500441434 0.874907971 -0.232818962
##
## -0.116205821 0.514944710 0.770425190 -0.367753606 -0.035548143
##
## 0.386820522 -0.313545869 -0.375584882 -0.446405761 0.132246394
##
## 0.548606611 -0.118464268 -0.249169055 0.101209330 -0.002252632
##
## 0.067329619 -0.356678179 0.289698284 -0.988517252 0.550498668
##
## -0.103709070 -0.121525725 0.724632927 0.126020137 -0.064875845
##
## -0.118499383 0.870642999 0.679895598 -0.252379094 0.232830594
##
## 0.089331893 0.473085142 -0.306586831 0.089698284 0.129804251
##
## -0.664875845 -0.310668107 -0.210668107 0.369989571 1.105909920
##
## -0.264658035 0.916286680 -0.353434027 -1.151358274 -1.580927243
##
## 0.071044504 -0.228187600 5.352528180 0.528347813 0.507366358
##
## -0.153582608 -0.224403487 -0.359120322 0.249443735 1.328565622
##
## 0.556036382 -0.144800742 0.124632927 -0.042140790 -0.489755880
##
## -0.259338131 0.533885527
##
## $rank
## [1] 3
##
## $fitted.values
## 1 2 4 5 7 8 9
## 6.3910808 7.2134102 5.3801521 5.0579007 6.0152601 6.3667804 5.4751406
## 10 11 12 13 14 16 18
## 4.9386119 5.5273322 5.9252401 6.2317505 5.9373903 5.6466210 4.9507621
## 24 26 27 28 29 32 33
## 7.0783803 4.9957720 4.8936019 70.6943658 6.6611405 6.5261106 5.8023605
## 35 36 37 38 39 40 42
## 14.2763830 4.7014119 6.5468202 4.9192800 5.9459497 4.7914318 5.3851206
## 44 45 46 48 49 50 51
## 5.9252401 6.4675728 6.7925796 6.4811007 6.6818501 6.6854409 5.4629904
## 53 54 55 56 57 59 60
## 5.3851206 5.3801521 6.6282807 8.2643803 5.9238624 6.2974700 6.2974700
## 61 62 63 64 65 66 70
## 4.5263406 6.5225198 4.5663820 5.1429521 6.6818501 5.5408601 5.3923023
## 71 72 73 75 76 77 78
## 6.1417306 6.5139604 5.4373122 5.9824003 5.3608202 5.3923023 7.0419298
## 79 80 81 82 83 84 85
## 5.2487130 8.1293504 6.0031099 5.4251621 6.0395605 5.7766824 6.4117903
## 86 87 88 89 90 91 93
## 6.1039023 5.8595206 5.8145107 4.5542318 5.5858700 7.0662301 5.2901322
## 94 95 97 99 100 101 103
## 5.9252401 5.1443298 4.8414103 5.9616907 6.0724202 5.3351421 5.8352202
## 104 107 108 110 112 113 115
## 5.9166808 6.4117903 4.7014119 5.2901322 5.3351421 5.3351421 6.3339206
## 116 118 122 123 124 125 126
## 6.5882393 4.8936019 3.6261414 6.7511604 6.3654026 50.1112866 5.5444509
## 127 130 131 132 134 135 137
## 7.0212202 0.4210395 5.0907605 6.1988907 5.2779820 4.6564019 5.0857919
## 139 140 143 144 145 146 147
## 6.6489903 4.6942302 6.0517107 6.4446501 5.5858700 6.7390102 6.0967206
## 148 150
## 5.4823222 5.2829505
##
## $assign
## [1] 0 1 2
##
## $qr
## $qr
## (Intercept) Sepal.Width Petal.Length
## 1 -10.34408043 -3.617528e+01 -4.761177e+01
## 2 0.09667365 3.747411e+01 4.656817e+01
## 4 0.09667365 1.894585e-03 4.556550e+01
## 5 0.09667365 2.324266e-02 1.071572e-03
## 7 0.09667365 2.057415e-02 -3.579914e-02
## 8 0.09667365 1.256862e-02 -2.351128e-02
## 9 0.09667365 2.057415e-02 -9.463426e-03
## 10 0.09667365 9.900112e-03 5.593408e-02
## 11 0.09667365 -7.739234e-04 6.646552e-02
## 12 0.09667365 2.057415e-02 -3.140985e-02
## 13 0.09667365 1.256862e-02 -1.692735e-02
## 14 0.09667365 1.790564e-02 -2.219307e-02
## 16 0.09667365 1.256862e-02 1.160301e-02
## 18 0.09667365 7.231603e-03 6.515087e-02
## 24 0.09667365 4.563094e-03 -2.878056e-02
## 26 0.09667365 7.231603e-03 6.295623e-02
## 27 0.09667365 9.900112e-03 5.812872e-02
## 28 0.09667365 -6.812437e-01 -6.096662e-01
## 29 0.09667365 7.231603e-03 -1.824556e-02
## 32 0.09667365 7.231603e-03 -1.166163e-02
## 33 0.09667365 1.790564e-02 -1.560914e-02
## 35 0.09667365 1.523713e-02 -4.189852e-01
## 36 0.09667365 1.256862e-02 5.769051e-02
## 37 0.09667365 1.256862e-02 -3.228985e-02
## 38 0.09667365 3.391669e-02 -3.140629e-02
## 39 0.09667365 2.591116e-02 -5.203807e-02
## 40 0.09667365 1.256862e-02 5.330122e-02
## 42 0.09667365 2.057415e-02 -5.074140e-03
## 44 0.09667365 2.057415e-02 -3.140985e-02
## 45 0.09667365 -1.945348e-02 8.928482e-02
## 46 0.09667365 1.790564e-02 -6.389128e-02
## 48 0.09667365 7.231603e-03 -9.466989e-03
## 49 0.09667365 1.256862e-02 -3.887378e-02
## 50 0.09667365 1.894585e-03 1.880146e-04
## 51 0.09667365 2.324266e-02 -1.868021e-02
## 53 0.09667365 2.057415e-02 -5.074140e-03
## 54 0.09667365 1.894585e-03 6.383266e-02
## 55 0.09667365 4.563094e-03 -6.834130e-03
## 56 0.09667365 -8.779450e-03 -3.756269e-02
## 57 0.09667365 -8.779450e-03 7.655874e-02
## 59 0.09667365 1.790564e-02 -3.975021e-02
## 60 0.09667365 1.790564e-02 -3.975021e-02
## 61 0.09667365 3.124818e-02 -2.437719e-03
## 62 0.09667365 1.790564e-02 -5.072342e-02
## 63 0.09667365 1.256862e-02 6.427444e-02
## 64 0.09667365 4.563094e-03 6.558909e-02
## 65 0.09667365 1.256862e-02 -3.887378e-02
## 66 0.09667365 2.591116e-02 -3.228629e-02
## 70 0.09667365 -7.739234e-04 7.304945e-02
## 71 0.09667365 1.256862e-02 -1.253806e-02
## 72 0.09667365 9.900112e-03 -2.087842e-02
## 73 0.09667365 -7.739234e-04 7.085480e-02
## 75 0.09667365 1.790564e-02 -2.438771e-02
## 76 0.09667365 2.591116e-02 -2.350772e-02
## 77 0.09667365 -7.739234e-04 7.304945e-02
## 78 0.09667365 1.256862e-02 -5.643092e-02
## 79 0.09667365 -8.779450e-03 1.094784e-01
## 80 0.09667365 -8.779450e-03 -3.097876e-02
## 81 0.09667365 2.324266e-02 -4.501593e-02
## 82 0.09667365 1.894585e-03 6.163802e-02
## 83 0.09667365 1.523713e-02 -1.736557e-02
## 84 0.09667365 -6.110941e-03 7.392588e-02
## 85 0.09667365 1.256862e-02 -2.570592e-02
## 86 0.09667365 -8.779450e-03 6.778017e-02
## 87 0.09667365 1.523713e-02 -8.586994e-03
## 88 0.09667365 1.523713e-02 -6.392351e-03
## 89 0.09667365 1.523713e-02 5.505765e-02
## 90 0.09667365 2.591116e-02 -3.448093e-02
## 91 0.09667365 7.231603e-03 -3.799735e-02
## 93 0.09667365 1.894585e-03 6.822194e-02
## 94 0.09667365 2.057415e-02 -3.140985e-02
## 95 0.09667365 3.391669e-02 -4.237951e-02
## 97 0.09667365 3.124818e-02 -1.780022e-02
## 99 0.09667365 1.256862e-02 -3.759492e-03
## 100 0.09667365 1.790564e-02 -2.877700e-02
## 101 0.09667365 1.894585e-03 6.602730e-02
## 103 0.09667365 2.057415e-02 -2.702057e-02
## 104 0.09667365 1.256862e-02 -1.564849e-03
## 107 0.09667365 1.256862e-02 -2.570592e-02
## 108 0.09667365 1.256862e-02 5.769051e-02
## 110 0.09667365 1.894585e-03 6.822194e-02
## 112 0.09667365 1.894585e-03 6.602730e-02
## 113 0.09667365 1.894585e-03 6.602730e-02
## 115 0.09667365 9.900112e-03 -1.209985e-02
## 116 0.09667365 2.324266e-02 -7.354629e-02
## 118 0.09667365 9.900112e-03 5.812872e-02
## 122 0.09667365 3.124818e-02 4.145514e-02
## 123 0.09667365 7.231603e-03 -2.263485e-02
## 124 0.09667365 -1.678498e-02 8.445731e-02
## 125 0.09667365 -7.079287e-01 4.920374e-01
## 126 0.09667365 1.523713e-02 6.775506e-03
## 127 0.09667365 7.231603e-03 -3.580270e-02
## 130 0.09667365 9.262388e-02 -2.787919e-02
## 131 0.09667365 2.591116e-02 -1.033986e-02
## 132 0.09667365 9.900112e-03 -5.515919e-03
## 134 0.09667365 4.563094e-03 5.900516e-02
## 135 0.09667365 1.256862e-02 5.988515e-02
## 137 0.09667365 7.231603e-03 5.856694e-02
## 139 0.09667365 9.900112e-03 -2.746235e-02
## 140 0.09667365 3.391669e-02 -2.043308e-02
## 143 0.09667365 1.256862e-02 -8.148778e-03
## 144 0.09667365 1.523713e-02 -3.711735e-02
## 145 0.09667365 2.591116e-02 -3.448093e-02
## 146 0.09667365 9.900112e-03 -3.185163e-02
## 147 0.09667365 1.256862e-02 -1.034342e-02
## 148 0.09667365 -7.739234e-04 6.866016e-02
## 150 0.09667365 2.324266e-02 -9.901642e-03
## attr(,"assign")
## [1] 0 1 2
##
## $qraux
## [1] 1.096674 1.004563 1.063833
##
## $pivot
## [1] 1 2 3
##
## $tol
## [1] 1e-07
##
## $rank
## [1] 3
##
## attr(,"class")
## [1] "qr"
##
## $df.residual
## [1] 104
##
## $na.action
## 3 6 15 17 19 20 21 22 23 25 30 31 34 41 43 47 52 58 67 68
## 3 6 15 17 19 20 21 22 23 25 30 31 34 41 43 47 52 58 67 68
## 69 74 92 96 98 102 105 106 109 111 114 117 119 120 121 128 129 133 136 138
## 69 74 92 96 98 102 105 106 109 111 114 117 119 120 121 128 129 133 136 138
## 141 142 149
## 141 142 149
## attr(,"class")
## [1] "omit"
##
## $xlevels
## named list()
Question 7.4
for (i in 1:ncol(dirty_iris)){
dirty_iris[sample(1:nrow(dirty_iris), 10, replace=FALSE), i] <- NA
}
iris2 <- kNN(dirty_iris)
summary(iris2)
## Sepal.Length Sepal.Width Petal.Length Petal.Width
## Min. : 0.000 Min. : 0.000 Min. : 0.000 Min. :0.100
## 1st Qu.: 5.100 1st Qu.: 2.800 1st Qu.: 1.500 1st Qu.:0.300
## Median : 5.800 Median : 3.000 Median : 4.400 Median :1.300
## Mean : 6.076 Mean : 3.383 Mean : 4.303 Mean :1.207
## 3rd Qu.: 6.400 3rd Qu.: 3.300 3rd Qu.: 5.100 3rd Qu.:1.800
## Max. :49.000 Max. :30.000 Max. :63.000 Max. :2.500
## Species Sepal.Length_imp Sepal.Width_imp Petal.Length_imp
## Length:150 Mode :logical Mode :logical Mode :logical
## Class :character FALSE:139 FALSE:124 FALSE:122
## Mode :character TRUE :11 TRUE :26 TRUE :28
##
##
##
## Petal.Width_imp Species_imp
## Mode :logical Mode :logical
## FALSE:128 FALSE:140
## TRUE :22 TRUE :10
##
##
##
print(iris2)
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 6.400000 3.2 4.50 1.5 versicolor
## 2 6.300000 3.3 6.00 2.2 virginica
## 3 6.200000 3.0 5.40 2.3 virginica
## 4 5.000000 3.4 1.60 0.4 setosa
## 5 5.700000 2.6 3.50 1.0 versicolor
## 6 5.300000 3.2 1.50 0.2 setosa
## 7 6.400000 2.7 5.60 1.8 virginica
## 8 5.900000 3.0 5.10 1.8 virginica
## 9 5.800000 2.7 4.10 1.0 versicolor
## 10 4.800000 3.1 1.60 0.2 setosa
## 11 5.000000 3.5 1.60 0.6 setosa
## 12 6.000000 2.9 5.10 1.6 versicolor
## 13 6.000000 3.0 4.80 2.0 virginica
## 14 6.800000 2.8 4.80 1.4 versicolor
## 15 6.161062 3.9 1.40 0.2 setosa
## 16 5.000000 3.0 3.50 1.0 versicolor
## 17 5.500000 3.0 4.00 1.3 versicolor
## 18 4.700000 3.2 1.30 0.2 setosa
## 19 4.500000 4.0 1.40 0.2 setosa
## 20 5.600000 2.9 4.20 1.3 versicolor
## 21 4.900000 3.6 1.40 0.3 setosa
## 22 5.400000 2.9 4.50 1.5 versicolor
## 23 6.200000 2.8 5.50 1.8 virginica
## 24 6.700000 3.3 5.70 2.5 virginica
## 25 6.726860 3.0 5.90 2.1 virginica
## 26 4.600000 3.2 1.40 0.2 setosa
## 27 4.900000 3.1 1.50 0.1 setosa
## 28 6.300000 29.0 63.00 2.4 virginica
## 29 6.500000 3.2 5.10 2.0 virginica
## 30 4.145994 2.8 0.82 1.3 versicolor
## 31 4.400000 3.2 1.40 0.2 setosa
## 32 6.300000 3.2 4.80 1.4 versicolor
## 33 5.700000 2.8 4.50 1.3 versicolor
## 34 6.200000 3.0 4.20 1.3 versicolor
## 35 6.600000 2.9 23.00 1.3 versicolor
## 36 4.800000 3.0 1.40 0.2 setosa
## 37 6.500000 3.0 5.50 1.8 virginica
## 38 6.300000 2.2 4.50 1.5 versicolor
## 39 6.700000 2.5 5.80 1.8 virginica
## 40 5.000000 3.4 1.60 0.2 setosa
## 41 5.000000 3.4 1.20 0.2 setosa
## 42 5.800000 2.7 3.90 1.2 versicolor
## 43 0.000000 3.0 1.30 0.4 setosa
## 44 5.800000 2.7 5.10 1.9 virginica
## 45 5.500000 4.2 1.40 0.2 setosa
## 46 7.700000 2.8 6.70 2.0 virginica
## 47 5.700000 3.2 1.40 0.4 setosa
## 48 7.000000 3.2 4.60 1.4 versicolor
## 49 6.500000 3.0 5.80 2.2 virginica
## 50 6.000000 3.4 4.50 1.6 versicolor
## 51 5.500000 2.6 4.40 1.2 versicolor
## 52 4.900000 3.1 1.40 0.2 setosa
## 53 5.200000 2.7 3.90 1.4 versicolor
## 54 4.800000 3.4 1.60 0.2 setosa
## 55 6.300000 3.3 4.70 1.6 versicolor
## 56 7.700000 3.0 6.70 2.2 virginica
## 57 5.100000 3.8 1.50 0.3 setosa
## 58 5.949541 2.9 4.50 1.5 versicolor
## 59 6.400000 2.8 5.60 1.8 virginica
## 60 6.400000 2.8 5.60 1.8 virginica
## 61 5.000000 2.3 3.30 1.1 versicolor
## 62 7.400000 2.8 6.10 1.9 virginica
## 63 4.300000 3.0 1.50 0.1 setosa
## 64 5.000000 3.3 1.40 0.2 setosa
## 65 7.200000 3.0 5.10 1.6 virginica
## 66 6.300000 2.5 4.90 1.5 versicolor
## 67 5.100000 2.5 3.80 1.1 versicolor
## 68 6.931200 3.2 5.70 2.3 virginica
## 69 5.100000 3.5 1.40 0.3 setosa
## 70 5.000000 3.5 1.30 0.3 setosa
## 71 6.600000 3.0 4.60 1.4 versicolor
## 72 6.900000 3.1 5.10 2.3 virginica
## 73 5.100000 3.5 1.40 0.3 setosa
## 74 6.500000 2.9 4.60 1.5 versicolor
## 75 5.600000 2.8 4.90 2.0 virginica
## 76 4.900000 2.5 4.50 1.9 virginica
## 77 5.500000 3.5 1.30 0.2 setosa
## 78 7.600000 3.0 6.60 2.1 virginica
## 79 5.100000 3.8 0.00 0.2 setosa
## 80 7.900000 3.8 6.40 2.0 virginica
## 81 6.100000 2.6 5.10 1.4 virginica
## 82 5.400000 3.4 1.70 0.2 setosa
## 83 6.100000 2.9 4.70 1.4 versicolor
## 84 5.400000 3.7 1.50 0.2 setosa
## 85 6.700000 3.0 5.20 2.3 virginica
## 86 5.100000 3.8 1.90 0.3 setosa
## 87 6.400000 2.9 4.30 1.3 versicolor
## 88 5.700000 2.9 4.20 1.3 versicolor
## 89 4.400000 2.9 1.40 0.2 setosa
## 90 6.300000 2.5 5.00 1.9 virginica
## 91 6.300000 3.2 6.00 1.8 virginica
## 92 4.900000 2.7 3.30 1.0 versicolor
## 93 5.200000 3.4 1.40 0.2 setosa
## 94 5.800000 2.7 5.10 1.9 virginica
## 95 6.000000 2.2 5.00 1.5 virginica
## 96 6.900000 3.1 4.50 1.5 versicolor
## 97 5.500000 2.3 4.00 1.3 versicolor
## 98 6.700000 3.0 5.00 1.7 virginica
## 99 5.700000 3.0 4.20 1.2 versicolor
## 100 6.300000 2.8 5.10 1.5 virginica
## 101 5.400000 3.4 1.50 0.2 setosa
## 102 7.200000 3.6 5.70 2.5 virginica
## 103 6.300000 2.7 4.90 1.8 virginica
## 104 5.600000 3.0 4.10 1.3 versicolor
## 105 5.100000 3.7 1.40 0.3 setosa
## 106 5.500000 3.0 3.50 1.0 versicolor
## 107 6.500000 3.0 5.20 2.0 virginica
## 108 4.800000 3.0 1.40 0.2 setosa
## 109 6.100000 2.8 4.80 1.4 versicolor
## 110 4.600000 3.4 1.40 0.3 setosa
## 111 6.300000 3.4 5.60 2.4 virginica
## 112 5.000000 3.4 1.50 0.2 setosa
## 113 5.100000 3.4 1.50 0.2 setosa
## 114 7.078380 3.3 5.70 2.1 virginica
## 115 6.700000 2.9 4.70 1.5 versicolor
## 116 7.700000 2.6 5.40 2.3 virginica
## 117 6.300000 2.9 4.40 1.3 versicolor
## 118 4.700000 3.1 1.50 0.2 setosa
## 119 6.546820 3.0 5.50 2.1 virginica
## 120 5.892380 2.8 4.70 1.2 versicolor
## 121 5.900000 3.0 4.50 1.5 versicolor
## 122 4.500000 2.3 1.40 0.3 setosa
## 123 6.400000 3.0 5.30 2.3 virginica
## 124 5.200000 4.1 1.50 0.1 setosa
## 125 49.000000 30.0 14.00 2.0 setosa
## 126 5.600000 2.9 3.60 1.3 versicolor
## 127 6.800000 3.0 5.90 2.3 virginica
## 128 5.800000 3.0 5.10 2.4 virginica
## 129 4.600000 3.6 1.50 0.2 setosa
## 130 5.000000 0.0 1.70 0.3 setosa
## 131 5.600000 2.5 3.90 1.1 versicolor
## 132 6.700000 3.1 4.40 1.4 versicolor
## 133 5.000000 3.4 1.90 0.2 setosa
## 134 5.000000 3.3 1.70 0.5 setosa
## 135 4.400000 3.0 1.30 0.2 setosa
## 136 7.700000 3.0 5.40 2.3 virginica
## 137 4.700000 3.2 1.60 0.2 setosa
## 138 6.276760 3.0 4.90 1.8 virginica
## 139 6.900000 3.1 5.40 2.1 virginica
## 140 6.000000 2.2 4.00 1.0 versicolor
## 141 5.000000 3.0 1.40 0.2 setosa
## 142 5.500000 2.6 3.80 1.1 versicolor
## 143 6.600000 3.0 4.40 1.4 versicolor
## 144 6.300000 2.9 5.60 1.8 virginica
## 145 5.700000 2.5 5.00 2.0 virginica
## 146 6.700000 3.1 5.60 2.4 virginica
## 147 5.600000 3.0 4.50 1.5 versicolor
## 148 5.200000 3.5 1.50 0.2 setosa
## 149 6.400000 3.1 5.50 1.8 virginica
## 150 5.800000 2.7 4.00 1.1 versicolor
## Sepal.Length_imp Sepal.Width_imp Petal.Length_imp Petal.Width_imp
## 1 FALSE FALSE FALSE FALSE
## 2 FALSE FALSE FALSE TRUE
## 3 FALSE TRUE FALSE FALSE
## 4 FALSE FALSE FALSE FALSE
## 5 FALSE FALSE FALSE FALSE
## 6 FALSE TRUE TRUE FALSE
## 7 FALSE FALSE TRUE TRUE
## 8 FALSE FALSE FALSE FALSE
## 9 FALSE FALSE FALSE FALSE
## 10 FALSE FALSE FALSE FALSE
## 11 FALSE FALSE FALSE FALSE
## 12 FALSE TRUE FALSE FALSE
## 13 FALSE FALSE FALSE TRUE
## 14 FALSE FALSE FALSE FALSE
## 15 FALSE FALSE TRUE TRUE
## 16 FALSE FALSE FALSE FALSE
## 17 FALSE TRUE FALSE FALSE
## 18 FALSE FALSE FALSE FALSE
## 19 TRUE FALSE TRUE FALSE
## 20 FALSE TRUE FALSE FALSE
## 21 FALSE FALSE TRUE TRUE
## 22 FALSE TRUE FALSE FALSE
## 23 FALSE FALSE TRUE FALSE
## 24 TRUE FALSE FALSE FALSE
## 25 FALSE FALSE FALSE FALSE
## 26 FALSE FALSE FALSE FALSE
## 27 FALSE FALSE FALSE FALSE
## 28 TRUE FALSE FALSE TRUE
## 29 FALSE FALSE FALSE FALSE
## 30 FALSE FALSE FALSE FALSE
## 31 FALSE FALSE TRUE FALSE
## 32 TRUE FALSE FALSE TRUE
## 33 FALSE FALSE FALSE FALSE
## 34 FALSE TRUE TRUE FALSE
## 35 FALSE FALSE FALSE FALSE
## 36 FALSE FALSE FALSE TRUE
## 37 FALSE FALSE FALSE FALSE
## 38 TRUE FALSE FALSE FALSE
## 39 FALSE FALSE FALSE FALSE
## 40 FALSE TRUE FALSE FALSE
## 41 FALSE TRUE FALSE FALSE
## 42 FALSE FALSE FALSE FALSE
## 43 FALSE TRUE FALSE FALSE
## 44 FALSE FALSE FALSE FALSE
## 45 FALSE FALSE FALSE FALSE
## 46 FALSE FALSE FALSE FALSE
## 47 FALSE TRUE TRUE FALSE
## 48 FALSE FALSE TRUE FALSE
## 49 FALSE FALSE FALSE FALSE
## 50 FALSE FALSE FALSE FALSE
## 51 FALSE FALSE FALSE FALSE
## 52 FALSE FALSE TRUE FALSE
## 53 FALSE FALSE FALSE FALSE
## 54 FALSE FALSE FALSE FALSE
## 55 FALSE FALSE FALSE FALSE
## 56 FALSE TRUE FALSE FALSE
## 57 FALSE FALSE FALSE FALSE
## 58 FALSE FALSE FALSE FALSE
## 59 FALSE FALSE FALSE TRUE
## 60 FALSE FALSE FALSE TRUE
## 61 FALSE FALSE FALSE TRUE
## 62 FALSE FALSE FALSE FALSE
## 63 FALSE FALSE TRUE FALSE
## 64 FALSE FALSE FALSE FALSE
## 65 FALSE FALSE TRUE FALSE
## 66 FALSE FALSE FALSE FALSE
## 67 FALSE FALSE TRUE FALSE
## 68 FALSE FALSE FALSE FALSE
## 69 FALSE FALSE TRUE TRUE
## 70 FALSE FALSE FALSE FALSE
## 71 TRUE FALSE FALSE FALSE
## 72 FALSE FALSE FALSE FALSE
## 73 FALSE FALSE FALSE FALSE
## 74 FALSE TRUE FALSE FALSE
## 75 FALSE FALSE FALSE FALSE
## 76 FALSE FALSE FALSE TRUE
## 77 FALSE FALSE FALSE FALSE
## 78 FALSE FALSE FALSE FALSE
## 79 FALSE FALSE FALSE FALSE
## 80 FALSE FALSE FALSE FALSE
## 81 FALSE FALSE TRUE FALSE
## 82 FALSE FALSE FALSE FALSE
## 83 FALSE FALSE FALSE FALSE
## 84 FALSE FALSE FALSE FALSE
## 85 FALSE FALSE FALSE FALSE
## 86 FALSE FALSE FALSE TRUE
## 87 FALSE FALSE FALSE FALSE
## 88 FALSE FALSE FALSE FALSE
## 89 FALSE FALSE FALSE FALSE
## 90 FALSE FALSE FALSE FALSE
## 91 TRUE FALSE FALSE FALSE
## 92 FALSE TRUE FALSE FALSE
## 93 FALSE FALSE FALSE FALSE
## 94 FALSE FALSE FALSE FALSE
## 95 FALSE FALSE FALSE FALSE
## 96 FALSE FALSE TRUE FALSE
## 97 FALSE FALSE FALSE FALSE
## 98 FALSE TRUE FALSE FALSE
## 99 FALSE FALSE FALSE FALSE
## 100 FALSE FALSE FALSE FALSE
## 101 FALSE FALSE FALSE TRUE
## 102 FALSE FALSE TRUE FALSE
## 103 FALSE FALSE FALSE TRUE
## 104 FALSE FALSE FALSE FALSE
## 105 FALSE FALSE TRUE TRUE
## 106 FALSE TRUE TRUE FALSE
## 107 FALSE FALSE FALSE FALSE
## 108 FALSE FALSE FALSE TRUE
## 109 FALSE FALSE TRUE TRUE
## 110 FALSE FALSE FALSE FALSE
## 111 FALSE FALSE TRUE FALSE
## 112 FALSE FALSE FALSE FALSE
## 113 FALSE FALSE FALSE FALSE
## 114 FALSE FALSE FALSE FALSE
## 115 FALSE TRUE FALSE FALSE
## 116 FALSE FALSE TRUE FALSE
## 117 FALSE TRUE FALSE FALSE
## 118 TRUE FALSE FALSE FALSE
## 119 FALSE FALSE FALSE FALSE
## 120 FALSE TRUE FALSE FALSE
## 121 FALSE FALSE TRUE FALSE
## 122 FALSE FALSE TRUE FALSE
## 123 FALSE TRUE FALSE FALSE
## 124 FALSE FALSE FALSE FALSE
## 125 FALSE FALSE FALSE FALSE
## 126 FALSE FALSE FALSE FALSE
## 127 FALSE TRUE FALSE FALSE
## 128 FALSE TRUE FALSE FALSE
## 129 FALSE FALSE TRUE FALSE
## 130 TRUE FALSE FALSE FALSE
## 131 FALSE FALSE FALSE FALSE
## 132 FALSE FALSE FALSE FALSE
## 133 TRUE TRUE FALSE FALSE
## 134 TRUE FALSE FALSE FALSE
## 135 FALSE FALSE FALSE TRUE
## 136 FALSE FALSE TRUE FALSE
## 137 FALSE FALSE FALSE FALSE
## 138 FALSE FALSE FALSE FALSE
## 139 FALSE FALSE FALSE FALSE
## 140 FALSE FALSE FALSE FALSE
## 141 FALSE TRUE FALSE TRUE
## 142 FALSE TRUE FALSE FALSE
## 143 FALSE FALSE FALSE FALSE
## 144 FALSE FALSE FALSE FALSE
## 145 FALSE FALSE FALSE FALSE
## 146 FALSE FALSE FALSE FALSE
## 147 FALSE FALSE FALSE FALSE
## 148 FALSE FALSE FALSE FALSE
## 149 FALSE FALSE TRUE FALSE
## 150 FALSE TRUE FALSE TRUE
## Species_imp
## 1 FALSE
## 2 FALSE
## 3 FALSE
## 4 FALSE
## 5 FALSE
## 6 FALSE
## 7 FALSE
## 8 FALSE
## 9 FALSE
## 10 TRUE
## 11 FALSE
## 12 FALSE
## 13 FALSE
## 14 FALSE
## 15 FALSE
## 16 FALSE
## 17 TRUE
## 18 FALSE
## 19 FALSE
## 20 FALSE
## 21 FALSE
## 22 FALSE
## 23 FALSE
## 24 FALSE
## 25 FALSE
## 26 FALSE
## 27 FALSE
## 28 FALSE
## 29 FALSE
## 30 FALSE
## 31 FALSE
## 32 FALSE
## 33 FALSE
## 34 FALSE
## 35 FALSE
## 36 FALSE
## 37 FALSE
## 38 FALSE
## 39 FALSE
## 40 FALSE
## 41 FALSE
## 42 FALSE
## 43 TRUE
## 44 FALSE
## 45 FALSE
## 46 FALSE
## 47 FALSE
## 48 FALSE
## 49 FALSE
## 50 TRUE
## 51 FALSE
## 52 FALSE
## 53 FALSE
## 54 FALSE
## 55 FALSE
## 56 FALSE
## 57 FALSE
## 58 FALSE
## 59 FALSE
## 60 FALSE
## 61 FALSE
## 62 FALSE
## 63 FALSE
## 64 FALSE
## 65 FALSE
## 66 FALSE
## 67 FALSE
## 68 FALSE
## 69 FALSE
## 70 FALSE
## 71 FALSE
## 72 TRUE
## 73 FALSE
## 74 FALSE
## 75 FALSE
## 76 FALSE
## 77 FALSE
## 78 FALSE
## 79 FALSE
## 80 FALSE
## 81 FALSE
## 82 FALSE
## 83 FALSE
## 84 FALSE
## 85 FALSE
## 86 FALSE
## 87 TRUE
## 88 FALSE
## 89 FALSE
## 90 FALSE
## 91 FALSE
## 92 FALSE
## 93 FALSE
## 94 FALSE
## 95 FALSE
## 96 FALSE
## 97 FALSE
## 98 TRUE
## 99 TRUE
## 100 FALSE
## 101 FALSE
## 102 FALSE
## 103 FALSE
## 104 FALSE
## 105 FALSE
## 106 FALSE
## 107 FALSE
## 108 FALSE
## 109 FALSE
## 110 FALSE
## 111 FALSE
## 112 FALSE
## 113 FALSE
## 114 FALSE
## 115 FALSE
## 116 FALSE
## 117 FALSE
## 118 FALSE
## 119 FALSE
## 120 FALSE
## 121 FALSE
## 122 FALSE
## 123 FALSE
## 124 FALSE
## 125 FALSE
## 126 FALSE
## 127 FALSE
## 128 TRUE
## 129 FALSE
## 130 FALSE
## 131 FALSE
## 132 FALSE
## 133 FALSE
## 134 FALSE
## 135 FALSE
## 136 FALSE
## 137 FALSE
## 138 FALSE
## 139 FALSE
## 140 TRUE
## 141 FALSE
## 142 FALSE
## 143 FALSE
## 144 FALSE
## 145 FALSE
## 146 FALSE
## 147 FALSE
## 148 FALSE
## 149 FALSE
## 150 FALSE