Hi everybody,
I'am new to R and trying to deal with missing values NA by imputation, but got stucked.
The data is something like this:
| id |
1111 |
0019 |
2059 |
6000 |
| 1 |
NA |
NA |
NA |
NA |
| 2 |
NA |
NA |
NA |
NA |
| 3 |
NA |
NA |
NA |
NA |
| 4 |
NA |
NA |
NA |
NA |
| 5 |
17621 |
8520 |
8273 |
828 |
| 6 |
77525 |
33805 |
40138 |
3582 |
| 7 |
69884 |
25737 |
38496 |
5651 |
| 8 |
NA |
NA |
NA |
NA |
| 9 |
NA |
NA |
NA |
NA |
| 10 |
NA |
NA |
NA |
NA |
| 11 |
NA |
NA |
NA |
NA |
| 12 |
42365 |
14853 |
23338 |
4174 |
| 13 |
22188 |
8707 |
12032 |
1449 |
| 14 |
54738 |
21094 |
29265 |
4379 |
| 15 |
44200 |
17345 |
23968 |
2887 |
| 16 |
7685 |
2520 |
4380 |
785 |
| 17 |
9612 |
3174 |
5358 |
1080 |
| 18 |
8669 |
2999 |
4868 |
802 |
| 19 |
NA |
NA |
NA |
NA |
| 20 |
NA |
NA |
NA |
NA |
| 21 |
NA |
NA |
NA |
NA |
| 22 |
NA |
NA |
NA |
NA |
| 23 |
NA |
NA |
NA |
NA |
| 24 |
NA |
NA |
NA |
NA |
| 25 |
11465 |
5127 |
5430 |
908 |
tried to do it with missForest
imp <- missForest(dfmis)
and
imp <- missForest(dfmis, xtrue = dfa)
But got error: Error in randomForest.default(x = obsX, y = obsY, ntree = ntree, mtry = mtry, :
length of response must be the same as predictors...
Also tried mice
imp <- mice(dfpmis, m=5, maxit = 50, method = 'pmm', seed = 500)
And got also error: Error in terms.formula(tmp, simplify = TRUE) :
invalid term in model formula.
I'll appreciate any thought on this.
Thank you in advance,
DR
Hi there,
See the example below based on the iris dataset. You will see that in the one instance we feed the original iris into xtrue to see the quality of the imputation but you are able to simple run without that dataset as well as demonstrated in iris.imp2.
library(missForest)
#> Loading required package: randomForest
#> randomForest 4.6-14
#> Type rfNews() to see new features/changes/bug fixes.
#> Loading required package: foreach
#> Loading required package: itertools
#> Loading required package: iterators
## Nonparametric missing value imputation on mixed-type data:
data(iris)
summary(iris)
#> Sepal.Length Sepal.Width Petal.Length Petal.Width
#> Min. :4.300 Min. :2.000 Min. :1.000 Min. :0.100
#> 1st Qu.:5.100 1st Qu.:2.800 1st Qu.:1.600 1st Qu.:0.300
#> Median :5.800 Median :3.000 Median :4.350 Median :1.300
#> Mean :5.843 Mean :3.057 Mean :3.758 Mean :1.199
#> 3rd Qu.:6.400 3rd Qu.:3.300 3rd Qu.:5.100 3rd Qu.:1.800
#> Max. :7.900 Max. :4.400 Max. :6.900 Max. :2.500
#> Species
#> setosa :50
#> versicolor:50
#> virginica :50
#>
#>
#>
## The data contains four continuous and one categorical variable.
## Artificially produce missing values using the 'prodNA' function:
set.seed(81)
iris.mis <- prodNA(iris, noNA = 0.2)
summary(iris.mis)
#> Sepal.Length Sepal.Width Petal.Length Petal.Width
#> Min. :4.300 Min. :2.000 Min. :1.000 Min. :0.100
#> 1st Qu.:5.100 1st Qu.:2.800 1st Qu.:1.600 1st Qu.:0.300
#> Median :5.750 Median :3.000 Median :4.400 Median :1.300
#> Mean :5.828 Mean :3.070 Mean :3.855 Mean :1.169
#> 3rd Qu.:6.400 3rd Qu.:3.375 3rd Qu.:5.100 3rd Qu.:1.800
#> Max. :7.900 Max. :4.400 Max. :6.900 Max. :2.500
#> NA's :24 NA's :32 NA's :33 NA's :32
#> Species
#> setosa :42
#> versicolor:40
#> virginica :39
#> NA's :29
#>
#>
#>
## Impute missing values providing the complete matrix for
## illustration. Use 'verbose' to see what happens between iterations:
iris.imp <- missForest(iris.mis, xtrue = iris, verbose = TRUE)
#> missForest iteration 1 in progress...done!
#> error(s): 0.206485 0.03448276
#> estimated error(s): 0.160313 0.05785124
#> difference(s): 0.01225256 0.1466667
#> time: 0.07 seconds
#>
#> missForest iteration 2 in progress...done!
#> error(s): 0.2115068 0.03448276
#> estimated error(s): 0.1439782 0.04132231
#> difference(s): 0.0001759815 0
#> time: 0.04 seconds
#>
#> missForest iteration 3 in progress...done!
#> error(s): 0.2164123 0.03448276
#> estimated error(s): 0.142713 0.04958678
#> difference(s): 4.654903e-05 0
#> time: 0.07 seconds
#>
#> missForest iteration 4 in progress...done!
#> error(s): 0.2204607 0.03448276
#> estimated error(s): 0.1429416 0.04958678
#> difference(s): 2.832941e-05 0
#> time: 0.04 seconds
#>
#> missForest iteration 5 in progress...done!
#> error(s): 0.2186308 0.03448276
#> estimated error(s): 0.1432276 0.04958678
#> difference(s): 3.899112e-05 0
#> time: 0.05 seconds
## The imputation is finished after five iterations having a final
## true NRMSE of 0.143 and a PFC of 0.036. The estimated final NRMSE
## is 0.157 and the PFC is 0.025 (see Details for the reason taking
## iteration 4 instead of iteration 5 as final value).
## The final results can be accessed directly. The estimated error:
iris.imp$OOBerror
#> NRMSE PFC
#> 0.14294158 0.04958678
## The true imputation error (if available):
iris.imp$error
#> NRMSE PFC
#> 0.22046067 0.03448276
## And of course the imputed data matrix (do not run this):
## iris.imp$Ximp
iris.imp$ximp
#> Sepal.Length Sepal.Width Petal.Length Petal.Width Species
#> 1 5.100000 3.500000 1.483978 0.2000000 setosa
#> 2 4.596743 3.000000 1.400000 0.2000000 setosa
#> 3 4.700000 3.200000 1.571645 0.2000000 setosa
#> 4 4.600000 3.308491 1.343283 0.2000000 setosa
#> 5 4.946217 3.600000 1.400000 0.2000000 setosa
#> 6 5.400000 3.900000 1.700000 0.3246167 setosa
#> 7 4.600000 3.400000 1.400000 0.3000000 setosa
#> 8 5.000000 3.400000 1.500000 0.2000000 setosa
#> 9 4.400000 3.015152 1.306128 0.1997000 setosa
#> 10 4.900000 3.100000 1.500000 0.1000000 setosa
#> 11 5.400000 3.700000 1.500000 0.2000000 setosa
#> 12 4.800000 3.175219 1.600000 0.2105000 setosa
#> 13 4.800000 3.247726 1.515808 0.1000000 setosa
#> 14 4.300000 3.000000 1.100000 0.1000000 setosa
#> 15 5.800000 3.793967 1.200000 0.2000000 setosa
#> 16 5.700000 4.400000 1.500000 0.4000000 setosa
#> 17 5.400000 3.900000 1.300000 0.4000000 setosa
#> 18 5.100000 3.500000 1.400000 0.3000000 setosa
#> 19 5.700000 3.800000 1.700000 0.3000000 setosa
#> 20 5.100000 3.800000 1.500000 0.3000000 setosa
#> 21 5.400000 3.400000 1.700000 0.2000000 setosa
#> 22 5.100000 3.760617 1.500000 0.4000000 setosa
#> 23 4.600000 3.600000 1.000000 0.2000000 setosa
#> 24 5.181750 3.300000 1.700000 0.3401667 setosa
#> 25 4.800000 3.400000 1.486224 0.2000000 setosa
#> 26 5.000000 3.000000 1.600000 0.3348667 setosa
#> 27 5.000000 3.400000 1.564650 0.4000000 setosa
#> 28 5.200000 3.500000 1.500000 0.2000000 setosa
#> 29 5.200000 3.400000 1.526502 0.2000000 setosa
#> 30 4.700000 3.200000 1.600000 0.2000000 setosa
#> 31 4.800000 3.100000 1.600000 0.2000000 setosa
#> 32 5.400000 3.992488 1.435600 0.4000000 setosa
#> 33 5.328964 4.100000 1.500000 0.2876667 setosa
#> 34 5.369470 4.200000 1.400000 0.2000000 setosa
#> 35 4.900000 3.100000 1.500000 0.2000000 setosa
#> 36 5.519200 2.487667 3.947292 1.1112500 versicolor
#> 37 5.121666 3.500000 1.483978 0.2000000 setosa
#> 38 4.900000 3.600000 1.410960 0.1000000 setosa
#> 39 4.400000 3.000000 1.300000 0.2000000 setosa
#> 40 5.100000 3.569493 1.500000 0.2301500 setosa
#> 41 5.000000 3.500000 1.300000 0.3000000 setosa
#> 42 4.500000 2.300000 1.300000 0.3000000 setosa
#> 43 4.400000 3.200000 1.372094 0.2000000 setosa
#> 44 5.000000 3.381917 1.600000 0.6000000 setosa
#> 45 5.100000 3.800000 1.900000 0.4000000 setosa
#> 46 4.800000 3.355694 1.400000 0.3000000 setosa
#> 47 5.100000 3.800000 1.600000 0.2000000 setosa
#> 48 4.600000 3.323424 1.400000 0.2000000 setosa
#> 49 5.300000 3.700000 1.500000 0.2000000 setosa
#> 50 5.000000 3.300000 1.400000 0.2000000 setosa
#> 51 7.000000 3.200000 4.992667 1.6422976 versicolor
#> 52 6.400000 2.839933 4.500000 1.5000000 versicolor
#> 53 6.900000 3.114000 4.900000 1.5000000 versicolor
#> 54 5.500000 2.300000 4.000000 1.0555000 versicolor
#> 55 6.121617 2.845333 4.600000 1.5000000 versicolor
#> 56 5.700000 2.800000 4.500000 1.3000000 versicolor
#> 57 6.300000 3.300000 4.836333 1.5734643 versicolor
#> 58 4.900000 2.203024 3.300000 1.0000000 versicolor
#> 59 6.600000 2.900000 4.600000 1.3000000 versicolor
#> 60 5.200000 2.700000 3.900000 1.4000000 versicolor
#> 61 5.000000 2.000000 3.463500 1.0000000 versicolor
#> 62 5.900000 3.000000 4.574878 1.5000000 versicolor
#> 63 6.000000 2.200000 4.000000 1.0000000 versicolor
#> 64 6.100000 2.900000 4.700000 1.4630000 versicolor
#> 65 5.600000 2.900000 3.600000 1.3000000 versicolor
#> 66 6.700000 3.100000 4.777488 1.4000000 versicolor
#> 67 5.600000 3.000000 4.500000 1.5000000 versicolor
#> 68 5.800000 2.454271 4.100000 1.0000000 versicolor
#> 69 6.200000 2.200000 4.500000 1.5000000 versicolor
#> 70 5.600000 2.500000 3.900000 1.1000000 versicolor
#> 71 5.900000 3.200000 4.800000 1.5193976 versicolor
#> 72 6.100000 2.610833 4.000000 1.2076000 versicolor
#> 73 6.048646 2.840600 4.541544 1.5000000 versicolor
#> 74 6.100000 2.800000 4.238548 1.2000000 versicolor
#> 75 6.400000 2.900000 4.300000 1.3000000 versicolor
#> 76 6.600000 3.000000 4.400000 1.4000000 versicolor
#> 77 6.800000 3.081000 4.800000 1.4000000 versicolor
#> 78 6.700000 3.135000 5.000000 1.6385476 versicolor
#> 79 6.000000 2.900000 4.500000 1.5000000 versicolor
#> 80 5.700000 2.600000 3.500000 1.1507500 versicolor
#> 81 5.500000 2.400000 3.904458 1.0555000 versicolor
#> 82 5.500000 2.400000 3.700000 1.0000000 versicolor
#> 83 5.800000 2.683000 3.900000 1.2000000 versicolor
#> 84 6.262917 2.700000 5.100000 1.5118333 versicolor
#> 85 5.400000 3.000000 4.270735 1.5000000 versicolor
#> 86 6.000000 3.400000 4.500000 1.6000000 versicolor
#> 87 6.700000 3.100000 4.866000 1.5000000 versicolor
#> 88 5.818619 2.300000 4.400000 1.3000000 versicolor
#> 89 5.600000 3.000000 4.100000 1.3000000 versicolor
#> 90 5.500000 2.500000 4.000000 1.1102500 versicolor
#> 91 5.500000 2.667500 4.400000 1.2000000 versicolor
#> 92 6.100000 2.873333 4.600000 1.4460000 versicolor
#> 93 5.800000 2.600000 3.814233 1.1432500 versicolor
#> 94 5.193333 2.300000 3.300000 1.0000000 versicolor
#> 95 5.600000 2.700000 4.200000 1.3000000 versicolor
#> 96 5.700000 2.732714 4.200000 1.2000000 versicolor
#> 97 5.929452 2.900000 4.200000 1.3000000 versicolor
#> 98 6.200000 2.900000 4.300000 1.3000000 versicolor
#> 99 5.100000 2.500000 3.660000 1.1000000 versicolor
#> 100 5.881819 2.800000 4.331931 1.3000000 versicolor
#> 101 6.300000 3.300000 6.000000 2.5000000 virginica
#> 102 6.213000 2.700000 5.100000 1.6864667 virginica
#> 103 7.100000 3.000000 5.900000 2.1000000 virginica
#> 104 6.300000 2.900000 4.959917 1.8000000 virginica
#> 105 6.500000 3.000000 5.800000 2.2000000 virginica
#> 106 7.600000 3.000000 6.600000 2.1000000 virginica
#> 107 4.900000 2.500000 4.500000 1.7000000 virginica
#> 108 7.300000 2.900000 6.300000 2.0173333 virginica
#> 109 6.700000 2.500000 5.221300 1.8000000 virginica
#> 110 7.340917 3.600000 6.100000 2.1470000 virginica
#> 111 6.500000 3.200000 5.100000 2.0000000 virginica
#> 112 5.930833 2.700000 4.995500 1.9000000 virginica
#> 113 6.800000 3.000000 5.500000 2.1000000 virginica
#> 114 5.700000 2.500000 5.000000 2.0000000 virginica
#> 115 5.800000 2.821250 5.100000 2.4000000 virginica
#> 116 6.400000 3.014500 5.300000 2.3000000 virginica
#> 117 6.500000 3.000000 5.500000 2.0942667 virginica
#> 118 7.700000 3.800000 6.700000 2.1200000 virginica
#> 119 7.700000 2.600000 6.900000 2.3000000 virginica
#> 120 6.000000 2.771500 5.000000 1.5000000 virginica
#> 121 6.900000 3.200000 5.700000 2.3000000 virginica
#> 122 5.600000 2.800000 4.900000 2.0000000 virginica
#> 123 7.700000 2.800000 6.700000 2.0000000 virginica
#> 124 6.300000 2.700000 4.900000 1.8000000 virginica
#> 125 6.700000 3.300000 5.700000 2.4345000 virginica
#> 126 7.200000 3.200000 6.000000 1.8000000 virginica
#> 127 6.200000 2.800000 4.800000 1.8000000 virginica
#> 128 6.100000 3.000000 4.900000 1.8340000 virginica
#> 129 6.451750 2.800000 5.600000 2.1000000 virginica
#> 130 7.200000 3.000000 5.800000 2.0546667 virginica
#> 131 5.912533 2.800000 4.984433 1.9000000 virginica
#> 132 7.900000 3.800000 6.400000 2.0000000 virginica
#> 133 6.400000 3.012000 5.600000 2.2000000 virginica
#> 134 6.300000 2.800000 5.100000 1.5000000 virginica
#> 135 6.100000 2.600000 5.600000 1.4000000 virginica
#> 136 7.700000 3.341500 6.100000 2.3000000 virginica
#> 137 6.300000 3.400000 5.600000 2.4000000 virginica
#> 138 6.668000 3.100000 5.500000 1.8000000 virginica
#> 139 6.234233 3.000000 4.800000 1.8000000 virginica
#> 140 6.900000 3.100000 5.516067 2.1000000 virginica
#> 141 6.700000 3.100000 5.363058 2.4000000 virginica
#> 142 6.900000 3.100000 5.100000 2.3000000 virginica
#> 143 5.800000 2.700000 5.039067 1.9570000 virginica
#> 144 6.800000 3.200000 5.900000 2.3000000 virginica
#> 145 6.700000 3.300000 5.700000 2.5000000 virginica
#> 146 6.503533 3.000000 5.200000 2.3000000 virginica
#> 147 5.894533 2.745250 5.000000 1.9000000 virginica
#> 148 6.500000 3.000000 5.200000 2.1320667 virginica
#> 149 6.200000 2.760083 5.400000 1.8063500 virginica
#> 150 6.419900 3.000000 5.100000 1.8000000 virginica
iris.imp2 <- missForest(iris.mis, verbose = TRUE)
#> missForest iteration 1 in progress...done!
#> estimated error(s): 0.1585091 0.0661157
#> difference(s): 0.01217872 0.1466667
#> time: 0.04 seconds
#>
#> missForest iteration 2 in progress...done!
#> estimated error(s): 0.1450789 0.03305785
#> difference(s): 0.0001785337 0
#> time: 0.06 seconds
#>
#> missForest iteration 3 in progress...done!
#> estimated error(s): 0.1417088 0.03305785
#> difference(s): 4.808566e-05 0
#> time: 0.05 seconds
#>
#> missForest iteration 4 in progress...done!
#> estimated error(s): 0.1402569 0.04958678
#> difference(s): 4.275054e-05 0
#> time: 0.05 seconds
#>
#> missForest iteration 5 in progress...done!
#> estimated error(s): 0.1453971 0.04132231
#> difference(s): 4.293823e-05 0
#> time: 0.06 seconds
iris.imp2
#> $ximp
#> Sepal.Length Sepal.Width Petal.Length Petal.Width Species
#> 1 5.100000 3.500000 1.492399 0.2000000 setosa
#> 2 4.634083 3.000000 1.400000 0.2000000 setosa
#> 3 4.700000 3.200000 1.563350 0.2000000 setosa
#> 4 4.600000 3.262682 1.355167 0.2000000 setosa
#> 5 4.960381 3.600000 1.400000 0.2000000 setosa
#> 6 5.400000 3.900000 1.700000 0.3121667 setosa
#> 7 4.600000 3.400000 1.400000 0.3000000 setosa
#> 8 5.000000 3.400000 1.500000 0.2000000 setosa
#> 9 4.400000 2.993748 1.286250 0.2023333 setosa
#> 10 4.900000 3.100000 1.500000 0.1000000 setosa
#> 11 5.400000 3.700000 1.500000 0.2000000 setosa
#> 12 4.800000 3.174998 1.600000 0.1998500 setosa
#> 13 4.800000 3.288842 1.490500 0.1000000 setosa
#> 14 4.300000 3.000000 1.100000 0.1000000 setosa
#> 15 5.800000 3.748451 1.200000 0.2000000 setosa
#> 16 5.700000 4.400000 1.500000 0.4000000 setosa
#> 17 5.400000 3.900000 1.300000 0.4000000 setosa
#> 18 5.100000 3.500000 1.400000 0.3000000 setosa
#> 19 5.700000 3.800000 1.700000 0.3000000 setosa
#> 20 5.100000 3.800000 1.500000 0.3000000 setosa
#> 21 5.400000 3.400000 1.700000 0.2000000 setosa
#> 22 5.100000 3.793417 1.500000 0.4000000 setosa
#> 23 4.600000 3.600000 1.000000 0.2000000 setosa
#> 24 5.129813 3.300000 1.700000 0.3025833 setosa
#> 25 4.800000 3.400000 1.506307 0.2000000 setosa
#> 26 5.000000 3.000000 1.600000 0.3373667 setosa
#> 27 5.000000 3.400000 1.575833 0.4000000 setosa
#> 28 5.200000 3.500000 1.500000 0.2000000 setosa
#> 29 5.200000 3.400000 1.529307 0.2000000 setosa
#> 30 4.700000 3.200000 1.600000 0.2000000 setosa
#> 31 4.800000 3.100000 1.600000 0.2000000 setosa
#> 32 5.400000 3.928617 1.506381 0.4000000 setosa
#> 33 5.288242 4.100000 1.500000 0.2885000 setosa
#> 34 5.299246 4.200000 1.400000 0.2000000 setosa
#> 35 4.900000 3.100000 1.500000 0.2000000 setosa
#> 36 5.517917 2.463967 3.946750 1.0655000 versicolor
#> 37 5.116759 3.500000 1.504399 0.2000000 setosa
#> 38 4.900000 3.600000 1.446333 0.1000000 setosa
#> 39 4.400000 3.000000 1.300000 0.2000000 setosa
#> 40 5.100000 3.571953 1.500000 0.2245278 setosa
#> 41 5.000000 3.500000 1.300000 0.3000000 setosa
#> 42 4.500000 2.300000 1.300000 0.3000000 setosa
#> 43 4.400000 3.200000 1.315833 0.2000000 setosa
#> 44 5.000000 3.327383 1.600000 0.6000000 setosa
#> 45 5.100000 3.800000 1.900000 0.4000000 setosa
#> 46 4.800000 3.319933 1.400000 0.3000000 setosa
#> 47 5.100000 3.800000 1.600000 0.2000000 setosa
#> 48 4.600000 3.253515 1.400000 0.2000000 setosa
#> 49 5.300000 3.700000 1.500000 0.2000000 setosa
#> 50 5.000000 3.300000 1.400000 0.2000000 setosa
#> 51 7.000000 3.200000 4.980000 1.6047500 versicolor
#> 52 6.400000 2.860452 4.500000 1.5000000 versicolor
#> 53 6.900000 3.104333 4.900000 1.5000000 versicolor
#> 54 5.500000 2.300000 4.000000 1.0635000 versicolor
#> 55 6.163576 2.674667 4.600000 1.5000000 versicolor
#> 56 5.700000 2.800000 4.500000 1.3000000 versicolor
#> 57 6.300000 3.300000 4.822000 1.5511667 versicolor
#> 58 4.900000 2.170533 3.300000 1.0000000 versicolor
#> 59 6.600000 2.900000 4.600000 1.3000000 versicolor
#> 60 5.200000 2.700000 3.900000 1.4000000 versicolor
#> 61 5.000000 2.000000 3.423410 1.0000000 versicolor
#> 62 5.900000 3.000000 4.570083 1.5000000 versicolor
#> 63 6.000000 2.200000 4.000000 1.0000000 versicolor
#> 64 6.100000 2.900000 4.700000 1.4675667 versicolor
#> 65 5.600000 2.900000 3.600000 1.3000000 versicolor
#> 66 6.700000 3.100000 4.769500 1.4000000 versicolor
#> 67 5.600000 3.000000 4.500000 1.5000000 versicolor
#> 68 5.800000 2.433817 4.100000 1.0000000 versicolor
#> 69 6.200000 2.200000 4.500000 1.5000000 versicolor
#> 70 5.600000 2.500000 3.900000 1.1000000 versicolor
#> 71 5.900000 3.200000 4.800000 1.5248333 versicolor
#> 72 6.100000 2.640183 4.000000 1.2080000 versicolor
#> 73 6.074643 2.903500 4.595483 1.5000000 versicolor
#> 74 6.100000 2.800000 4.291000 1.2000000 versicolor
#> 75 6.400000 2.900000 4.300000 1.3000000 versicolor
#> 76 6.600000 3.000000 4.400000 1.4000000 versicolor
#> 77 6.800000 3.078750 4.800000 1.4000000 versicolor
#> 78 6.700000 3.091000 5.000000 1.5900833 versicolor
#> 79 6.000000 2.900000 4.500000 1.5000000 versicolor
#> 80 5.700000 2.600000 3.500000 1.1715000 versicolor
#> 81 5.500000 2.400000 3.913850 1.0645000 versicolor
#> 82 5.500000 2.400000 3.700000 1.0000000 versicolor
#> 83 5.800000 2.658233 3.900000 1.2000000 versicolor
#> 84 6.149167 2.700000 5.100000 1.5301167 versicolor
#> 85 5.400000 3.000000 4.179583 1.5000000 versicolor
#> 86 6.000000 3.400000 4.500000 1.6000000 versicolor
#> 87 6.700000 3.100000 4.864000 1.5000000 versicolor
#> 88 5.843600 2.300000 4.400000 1.3000000 versicolor
#> 89 5.600000 3.000000 4.100000 1.3000000 versicolor
#> 90 5.500000 2.500000 4.000000 1.1090000 versicolor
#> 91 5.500000 2.683283 4.400000 1.2000000 versicolor
#> 92 6.100000 2.870667 4.600000 1.4639000 versicolor
#> 93 5.800000 2.600000 3.945000 1.2050000 versicolor
#> 94 5.167250 2.300000 3.300000 1.0000000 versicolor
#> 95 5.600000 2.700000 4.200000 1.3000000 versicolor
#> 96 5.700000 2.762633 4.200000 1.2000000 versicolor
#> 97 5.760267 2.900000 4.200000 1.3000000 versicolor
#> 98 6.200000 2.900000 4.300000 1.3000000 versicolor
#> 99 5.100000 2.500000 3.711750 1.1000000 versicolor
#> 100 6.016350 2.800000 4.399438 1.3000000 versicolor
#> 101 6.300000 3.300000 6.000000 2.5000000 virginica
#> 102 6.151167 2.700000 5.100000 1.6791167 virginica
#> 103 7.100000 3.000000 5.900000 2.1000000 virginica
#> 104 6.300000 2.900000 4.962833 1.8000000 virginica
#> 105 6.500000 3.000000 5.800000 2.2000000 virginica
#> 106 7.600000 3.000000 6.600000 2.1000000 virginica
#> 107 4.900000 2.500000 4.500000 1.7000000 virginica
#> 108 7.300000 2.900000 6.300000 2.0360000 virginica
#> 109 6.700000 2.500000 5.306533 1.8000000 virginica
#> 110 7.487500 3.600000 6.100000 2.1880000 virginica
#> 111 6.500000 3.200000 5.100000 2.0000000 virginica
#> 112 5.940250 2.700000 5.045000 1.9000000 virginica
#> 113 6.800000 3.000000 5.500000 2.1000000 virginica
#> 114 5.700000 2.500000 5.000000 2.0000000 virginica
#> 115 5.800000 2.884750 5.100000 2.4000000 virginica
#> 116 6.400000 3.033333 5.300000 2.3000000 virginica
#> 117 6.500000 3.000000 5.500000 2.1378333 virginica
#> 118 7.700000 3.800000 6.700000 2.1310000 virginica
#> 119 7.700000 2.600000 6.900000 2.3000000 virginica
#> 120 6.000000 2.780000 5.000000 1.5000000 virginica
#> 121 6.900000 3.200000 5.700000 2.3000000 virginica
#> 122 5.600000 2.800000 4.900000 2.0000000 virginica
#> 123 7.700000 2.800000 6.700000 2.0000000 virginica
#> 124 6.300000 2.700000 4.900000 1.8000000 virginica
#> 125 6.700000 3.300000 5.700000 2.4376667 virginica
#> 126 7.200000 3.200000 6.000000 1.8000000 virginica
#> 127 6.200000 2.800000 4.800000 1.8000000 virginica
#> 128 6.100000 3.000000 4.900000 1.8030000 virginica
#> 129 6.359500 2.800000 5.600000 2.1000000 virginica
#> 130 7.200000 3.000000 5.800000 2.0935000 virginica
#> 131 5.975000 2.800000 5.028000 1.9000000 virginica
#> 132 7.900000 3.800000 6.400000 2.0000000 virginica
#> 133 6.400000 3.053500 5.600000 2.2000000 virginica
#> 134 6.300000 2.800000 5.100000 1.5000000 virginica
#> 135 6.100000 2.600000 5.600000 1.4000000 virginica
#> 136 7.700000 3.261500 6.100000 2.3000000 virginica
#> 137 6.300000 3.400000 5.600000 2.4000000 virginica
#> 138 6.663450 3.100000 5.500000 1.8000000 virginica
#> 139 6.243000 3.000000 4.800000 1.8000000 virginica
#> 140 6.900000 3.100000 5.481000 2.1000000 virginica
#> 141 6.700000 3.100000 5.387250 2.4000000 virginica
#> 142 6.900000 3.100000 5.100000 2.3000000 virginica
#> 143 5.800000 2.700000 5.089250 1.9789167 virginica
#> 144 6.800000 3.200000 5.900000 2.3000000 virginica
#> 145 6.700000 3.300000 5.700000 2.5000000 virginica
#> 146 6.522100 3.000000 5.200000 2.3000000 virginica
#> 147 5.962750 2.760333 5.000000 1.9000000 virginica
#> 148 6.500000 3.000000 5.200000 2.1580000 virginica
#> 149 6.200000 2.771000 5.400000 1.8061667 virginica
#> 150 6.429000 3.000000 5.100000 1.8000000 virginica
#>
#> $OOBerror
#> NRMSE PFC
#> 0.14025694 0.04958678
#>
#> attr(,"class")
#> [1] "missForest"
Created on 2022-01-17 by the reprex package (v2.0.0)
Since I don't have a reprex from you I can't be sure if your data is in the correct format etc so compare with the example above.
Also just to add, if you have rows with full missing it won't be able to impute. That is literally impossible. It will need some information at least to be able to perform an impute.
Hi GM, thank you for the reply, reading it and making the reprex I realized some code errors.
This is the data:
|
id |
c0011 |
c0019 |
c2059 |
c6000 |
c4444 |
c4419 |
c4459 |
c4460 |
date |
| 1 |
1 |
NA |
NA |
NA |
NA |
NA |
NA |
NA |
NA |
2020 |
| 2 |
1 |
NA |
NA |
NA |
NA |
NA |
NA |
NA |
NA |
2020 |
| 3 |
1 |
NA |
NA |
NA |
NA |
NA |
NA |
NA |
NA |
2020 |
| 4 |
1 |
NA |
NA |
NA |
NA |
NA |
NA |
NA |
NA |
2020 |
| 5 |
1 |
33989 |
NA |
NA |
NA |
NA |
NA |
NA |
NA |
2021 |
| 6 |
1 |
1653 |
NA |
NA |
NA |
NA |
NA |
NA |
NA |
2021 |
| 7 |
1 |
799 |
NA |
NA |
NA |
NA |
NA |
NA |
NA |
2021 |
| 8 |
1 |
22383 |
NA |
NA |
NA |
NA |
NA |
NA |
NA |
2021 |
| 9 |
2 |
4011 |
2139 |
1639 |
233 |
991470 |
746901 |
217421 |
27148 |
2020 |
| 10 |
2 |
17621 |
8520 |
8273 |
828 |
991470 |
746901 |
217421 |
27148 |
2020 |
| 11 |
2 |
77525 |
33805 |
40138 |
3582 |
991470 |
746901 |
217421 |
27148 |
2020 |
| 12 |
2 |
69884 |
25737 |
38496 |
5651 |
991470 |
746901 |
217421 |
27148 |
2020 |
| 13 |
2 |
NA |
NA |
NA |
NA |
906534 |
679373 |
202449 |
24712 |
2021 |
| 14 |
2 |
NA |
NA |
NA |
NA |
906534 |
679373 |
202449 |
24712 |
2021 |
| 15 |
2 |
NA |
NA |
NA |
NA |
906534 |
679373 |
202449 |
24712 |
2021 |
| 16 |
2 |
NA |
NA |
NA |
NA |
906534 |
679373 |
202449 |
24712 |
2021 |
| 17 |
3 |
42365 |
14853 |
23338 |
4174 |
1012683 |
339358 |
563151 |
110174 |
2020 |
| 18 |
3 |
22188 |
8707 |
12032 |
1449 |
1012683 |
339358 |
563151 |
110174 |
2020 |
| 19 |
3 |
54738 |
21094 |
29265 |
4379 |
1012683 |
339358 |
563151 |
110174 |
2020 |
| 20 |
3 |
44200 |
17345 |
23968 |
2887 |
1012683 |
339358 |
563151 |
110174 |
2020 |
| 21 |
3 |
7685 |
2520 |
4380 |
785 |
1012683 |
339358 |
563151 |
110174 |
2020 |
| 22 |
3 |
9612 |
3174 |
5358 |
1080 |
1012683 |
339358 |
563151 |
110174 |
2020 |
| 23 |
3 |
8669 |
2999 |
4868 |
802 |
1012683 |
339358 |
563151 |
110174 |
2020 |
| 24 |
3 |
NA |
NA |
NA |
NA |
375736 |
124121 |
209384 |
42231 |
2021 |
| 25 |
3 |
NA |
NA |
NA |
NA |
375736 |
124121 |
209384 |
42231 |
2021 |
| 26 |
3 |
NA |
NA |
NA |
NA |
375736 |
124121 |
209384 |
42231 |
2021 |
| 27 |
3 |
NA |
NA |
NA |
NA |
375736 |
124121 |
209384 |
42231 |
2021 |
| 28 |
3 |
NA |
NA |
NA |
NA |
375736 |
124121 |
209384 |
42231 |
2021 |
| 29 |
3 |
NA |
NA |
NA |
NA |
375736 |
124121 |
209384 |
42231 |
2021 |
| 30 |
3 |
11465 |
5127 |
5430 |
908 |
375736 |
124121 |
209384 |
42231 |
2021 |
and the code:
# import from xlsx a data set with number of clients per category
df <-
# relabel
names(df) <- c('id', 'c0011', 'c0019', 'c0059', 'c0060',
'c4444', 'c4419', 'c4459', 'c4460', 'date')
#> Error in names(df) <- c("id", "c0011", "c0019", "c0059", "c0060", "c4444", : names() applied to a non-vector
# convert id and date to factor and others to integer with lapply
df[c(1, 10)] <- lapply(df[c(1, 10)], as.factor)
#> Error in df[c(1, 10)]: object of type 'closure' is not subsettable
df[c(2:9)] <- lapply(df[c(2:9)], as.integer)
#> Error in df[c(2:9)]: object of type 'closure' is not subsettable
# drop missing rows and factor vars
dfmis <- df[-c(1:4), -c(1, 10)]
#> Error in df[-c(1:4), -c(1, 10)]: object of type 'closure' is not subsettable
# check
sapply(dfmis, class)
#> Error in lapply(X = X, FUN = FUN, ...): object 'dfmis' not found
# impute
imp <- missForest(dfmis, xtrue = df)
#> Error in missForest(dfmis, xtrue = df): could not find function "missForest"
You have errors here on errors. You need to solve these first before presenting it.
df <- data.frame(first = c(1, 1, 1,1, 1, 1),
second = c(1,1,1,1,1,1),
thirth = c(1,1,NA,NA, 1, 1),
fourth = c(1,1,1,1,1, NA))
df
#Option 1:
Replace to zeros:
df$thirth[(3:4)] <- 0
df$fourth[6] <- 0
df
#Option 2:
Replace by the arithmetic mean:
df$thirth[(3:4)] <- mean(df$thirth)
df$fourth[6] <- mean(df$fourt)
df
Indeed there is much to learn, I'll work on that.
By the way after exporting the modified data frame to *.txt and importing, the imputation works like a charm. (Just to to calm my curiosity lol).
Thank you GM for the recommendations!
Hi Miguel,
A much simpler workarround, many thanks.