——-Loading Data into R

#setwd("F:\\1_FreeMLVideo_R")
#change to your own working directory

setwd("C:\\Users\\joe\\Desktop\\RStudio")

## read in csv and tex files
resp1=read.csv("Resp1.csv",header=T)
head(resp1)
str(resp1)
## 'data.frame':    32 obs. of  2 variables:
##  $ fitness    : int  0 0 0 0 0 0 0 0 1 1 ...
##  $ respiration: num  3.94 4.26 4.16 3.76 4.07 3.57 4.11 4.18 4 4.16 ...
resp2=read.table("Resp2.txt",header=T)
head(resp2)
#read in the CSV data  UCL website:
#https://archive.ics.uci.edu/ml/datasets/Wine+Quality

winer1=read.csv("winequality-red.csv",header=T)
#header= T will read in column names as well
head(winer1)
summary(winer1)
##  fixed.acidity.volatile.acidity.citric.acid.residual.sugar.chlorides.free.sulfur.dioxide.total.sulfur.dioxide.density.pH.sulphates.alcohol.quality
##  6.7;0.46;0.24;1.7;0.077;18;34;0.9948;3.39;0.6;10.6;6  :   4                                                                                      
##  7.2;0.36;0.46;2.1;0.074;24;44;0.99534;3.4;0.85;11;7   :   4                                                                                      
##  7.2;0.695;0.13;2;0.076;12;20;0.99546;3.29;0.54;10.1;5 :   4                                                                                      
##  7.5;0.51;0.02;1.7;0.084;13;31;0.99538;3.36;0.54;10.5;6:   4                                                                                      
##  11.5;0.18;0.51;4;0.104;4;23;0.9996;3.28;0.97;10.1;6   :   3                                                                                      
##  6.4;0.64;0.21;1.8;0.081;14;31;0.99689;3.59;0.66;9.8;5 :   3                                                                                      
##  (Other)                                               :1577
winer1=read.csv("winequality-red.csv",header=T,sep=",")
#header= T will read in column names as well
head(winer1)
summary(winer1)
##  fixed.acidity.volatile.acidity.citric.acid.residual.sugar.chlorides.free.sulfur.dioxide.total.sulfur.dioxide.density.pH.sulphates.alcohol.quality
##  6.7;0.46;0.24;1.7;0.077;18;34;0.9948;3.39;0.6;10.6;6  :   4                                                                                      
##  7.2;0.36;0.46;2.1;0.074;24;44;0.99534;3.4;0.85;11;7   :   4                                                                                      
##  7.2;0.695;0.13;2;0.076;12;20;0.99546;3.29;0.54;10.1;5 :   4                                                                                      
##  7.5;0.51;0.02;1.7;0.084;13;31;0.99538;3.36;0.54;10.5;6:   4                                                                                      
##  11.5;0.18;0.51;4;0.104;4;23;0.9996;3.28;0.97;10.1;6   :   3                                                                                      
##  6.4;0.64;0.21;1.8;0.081;14;31;0.99689;3.59;0.66;9.8;5 :   3                                                                                      
##  (Other)                                               :1577
#specify the correct seperator
winer=read.table("winequality-red.csv",header=T,sep=";")
#header= T will read in column names as well
head(winer)
summary(winer)
##  fixed.acidity   volatile.acidity  citric.acid    residual.sugar  
##  Min.   : 4.60   Min.   :0.1200   Min.   :0.000   Min.   : 0.900  
##  1st Qu.: 7.10   1st Qu.:0.3900   1st Qu.:0.090   1st Qu.: 1.900  
##  Median : 7.90   Median :0.5200   Median :0.260   Median : 2.200  
##  Mean   : 8.32   Mean   :0.5278   Mean   :0.271   Mean   : 2.539  
##  3rd Qu.: 9.20   3rd Qu.:0.6400   3rd Qu.:0.420   3rd Qu.: 2.600  
##  Max.   :15.90   Max.   :1.5800   Max.   :1.000   Max.   :15.500  
##    chlorides       free.sulfur.dioxide total.sulfur.dioxide
##  Min.   :0.01200   Min.   : 1.00       Min.   :  6.00      
##  1st Qu.:0.07000   1st Qu.: 7.00       1st Qu.: 22.00      
##  Median :0.07900   Median :14.00       Median : 38.00      
##  Mean   :0.08747   Mean   :15.87       Mean   : 46.47      
##  3rd Qu.:0.09000   3rd Qu.:21.00       3rd Qu.: 62.00      
##  Max.   :0.61100   Max.   :72.00       Max.   :289.00      
##     density             pH          sulphates         alcohol     
##  Min.   :0.9901   Min.   :2.740   Min.   :0.3300   Min.   : 8.40  
##  1st Qu.:0.9956   1st Qu.:3.210   1st Qu.:0.5500   1st Qu.: 9.50  
##  Median :0.9968   Median :3.310   Median :0.6200   Median :10.20  
##  Mean   :0.9967   Mean   :3.311   Mean   :0.6581   Mean   :10.42  
##  3rd Qu.:0.9978   3rd Qu.:3.400   3rd Qu.:0.7300   3rd Qu.:11.10  
##  Max.   :1.0037   Max.   :4.010   Max.   :2.0000   Max.   :14.90  
##     quality     
##  Min.   :3.000  
##  1st Qu.:5.000  
##  Median :6.000  
##  Mean   :5.636  
##  3rd Qu.:6.000  
##  Max.   :8.000
##Read in excel data
#excel
#summary(boston1)
library(readxl)
dfb <- read_excel("boston1.xls")
## New names:
## * `` -> ...8
## * `` -> ...9
## * `` -> ...10
head(dfb)
summary(dfb)
##        MV            INDUS            NOX              RM       
##  Min.   : 5.00   Min.   : 0.46   Min.   :38.50   Min.   :3.561  
##  1st Qu.:17.02   1st Qu.: 5.19   1st Qu.:44.90   1st Qu.:5.886  
##  Median :21.20   Median : 9.69   Median :53.80   Median :6.208  
##  Mean   :22.53   Mean   :11.14   Mean   :55.47   Mean   :6.285  
##  3rd Qu.:25.00   3rd Qu.:18.10   3rd Qu.:62.40   3rd Qu.:6.623  
##  Max.   :50.00   Max.   :27.74   Max.   :87.10   Max.   :8.780  
##       TAX              PT            LSTAT         ...8        
##  Min.   :187.0   Min.   :12.60   Min.   : 1.73   Mode:logical  
##  1st Qu.:279.0   1st Qu.:17.40   1st Qu.: 6.95   NA's:506      
##  Median :330.0   Median :19.05   Median :11.36                 
##  Mean   :408.2   Mean   :18.46   Mean   :12.65                 
##  3rd Qu.:666.0   3rd Qu.:20.20   3rd Qu.:16.95                 
##  Max.   :711.0   Max.   :22.00   Max.   :37.97                 
##    ...9            ...10          
##  Mode:logical   Length:506        
##  NA's:506       Class :character  
##                 Mode  :character  
##                                   
##                                   
## 
#Using RCurl to read in csv data hosted online on github and other #sites
library(RCurl)
## Loading required package: bitops
data1= read.csv(text=getURL("https://raw.githubusercontent.com/sciruela/Happiness-Salaries/master/data.csv"))
head(data1)
summary(data1)
##       Country       Salary       Happiness           SP        
##  Australia: 1   Min.   : 453   Min.   :180.0   Min.   : 1.000  
##  Austria  : 1   1st Qu.:1268   1st Qu.:218.3   1st Qu.: 1.000  
##  Belgium  : 1   Median :1756   Median :241.7   Median : 2.500  
##  Brazil   : 1   Mean   :1643   Mean   :234.6   Mean   : 4.643  
##  Canada   : 1   3rd Qu.:2043   3rd Qu.:253.3   3rd Qu.: 7.250  
##  Cyprus   : 1   Max.   :2749   Max.   :273.5   Max.   :20.000  
##  (Other)  :22                                                  
##      Fitch            Moody       
##  Min.   : 1.000   Min.   : 1.000  
##  1st Qu.: 1.000   1st Qu.: 1.000  
##  Median : 2.000   Median : 1.000  
##  Mean   : 4.357   Mean   : 4.429  
##  3rd Qu.: 7.000   3rd Qu.: 6.000  
##  Max.   :17.000   Max.   :20.000  
## 
data2=read.csv(text=getURL("https://raw.githubusercontent.com/opetchey/RREEBES/master/Beninca_etal_2008_Nature/data/nutrients_original.csv"), skip=7, header=T)
head(data2)
summary(data2)
##        Date        Day.number          NO2             NO3        
##          :7815   Min.   :  69.0   Min.   : 0.04   Min.   : 0.000  
##  01/02/93:   1   1st Qu.: 710.2   1st Qu.: 0.29   1st Qu.: 0.850  
##  01/03/93:   1   Median :1373.5   Median : 0.50   Median : 1.640  
##  01/04/91:   1   Mean   :1364.4   Mean   : 2.23   Mean   : 3.941  
##  01/04/96:   1   3rd Qu.:2021.8   3rd Qu.: 1.12   3rd Qu.: 3.030  
##  01/04/97:   1   Max.   :2658.0   Max.   :45.90   Max.   :89.630  
##  (Other) : 343   NA's   :7815     NA's   :7816    NA's   :7816    
##       NH4          Total.dissolved.inorganic.nitrogen
##  Min.   :  0.070   Min.   :  1.26                    
##  1st Qu.:  2.737   1st Qu.:  5.44                    
##  Median :  4.700   Median :  8.59                    
##  Mean   :  7.288   Mean   : 13.50                    
##  3rd Qu.:  7.138   3rd Qu.: 13.48                    
##  Max.   :165.600   Max.   :194.66                    
##  NA's   :7819      NA's   :7820                      
##  Soluble.reactive.phosphorus    X          
##  Min.   : 0.000              Mode:logical  
##  1st Qu.: 0.520              NA's:8163     
##  Median : 1.320                            
##  Mean   : 4.629                            
##  3rd Qu.: 4.285                            
##  Max.   :46.500                            
##  NA's   :7815                              
##                                                                                                               X.1      
##                                                                                                                 :8158  
##  All nutrient concentrations are in micromol/L                                                                  :   1  
##  Empty spaces are missing data                                                                                  :   1  
##  N.B.                                                                                                           :   1  
##  The analysis in Beninc<U+0088> et al. (Nature 2008) included all nutrient data from 16/06/1991 until 20/10/1997:   1  
##  Zero values are nutrient concentrations under the detection limit.                                             :   1  
## 

———— Index and Subset of Data

data(iris)
??iris
## starting httpd help server ... done
str(iris)
## 'data.frame':    150 obs. of  5 variables:
##  $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
##  $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
##  $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
##  $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
##  $ Species     : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...
summary(iris$Species)
##     setosa versicolor  virginica 
##         50         50         50
head(iris, 10)
df6 = iris[1:6,]
df2 = iris[,1:2]


vars = c("Sepal.Length", "Petal.Width", "Species")
nd=iris[vars]
str(nd)
## 'data.frame':    150 obs. of  3 variables:
##  $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
##  $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
##  $ Species     : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...
head(nd)
vars = names (iris) %in% c("Species")
nd = iris[!vars]
str(nd)
## 'data.frame':    150 obs. of  4 variables:
##  $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
##  $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
##  $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
##  $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
head(nd)
#exclude column three and four
nd = iris[c(-3,-4)]
head(nd)
df_setosa=subset(iris,iris$Species=="setosa")
str(df_setosa)
## 'data.frame':    50 obs. of  5 variables:
##  $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
##  $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
##  $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
##  $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
##  $ Species     : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...
summary(df_setosa)
##   Sepal.Length    Sepal.Width     Petal.Length    Petal.Width   
##  Min.   :4.300   Min.   :2.300   Min.   :1.000   Min.   :0.100  
##  1st Qu.:4.800   1st Qu.:3.200   1st Qu.:1.400   1st Qu.:0.200  
##  Median :5.000   Median :3.400   Median :1.500   Median :0.200  
##  Mean   :5.006   Mean   :3.428   Mean   :1.462   Mean   :0.246  
##  3rd Qu.:5.200   3rd Qu.:3.675   3rd Qu.:1.575   3rd Qu.:0.300  
##  Max.   :5.800   Max.   :4.400   Max.   :1.900   Max.   :0.600  
##        Species  
##  setosa    :50  
##  versicolor: 0  
##  virginica : 0  
##                 
##                 
## 

———— Cleaning Up Data

library(MASS)
data()

##Randomly distributed NAs
data(airquality)
??airquality ##more info about these data
str(airquality)
## 'data.frame':    153 obs. of  6 variables:
##  $ Ozone  : int  41 36 12 18 NA 28 23 19 8 NA ...
##  $ Solar.R: int  190 118 149 313 NA NA 299 99 19 194 ...
##  $ Wind   : num  7.4 8 12.6 11.5 14.3 14.9 8.6 13.8 20.1 8.6 ...
##  $ Temp   : int  67 72 74 62 56 66 65 59 61 69 ...
##  $ Month  : int  5 5 5 5 5 5 5 5 5 5 ...
##  $ Day    : int  1 2 3 4 5 6 7 8 9 10 ...
head(airquality)
summary(airquality)
##      Ozone           Solar.R           Wind             Temp      
##  Min.   :  1.00   Min.   :  7.0   Min.   : 1.700   Min.   :56.00  
##  1st Qu.: 18.00   1st Qu.:115.8   1st Qu.: 7.400   1st Qu.:72.00  
##  Median : 31.50   Median :205.0   Median : 9.700   Median :79.00  
##  Mean   : 42.13   Mean   :185.9   Mean   : 9.958   Mean   :77.88  
##  3rd Qu.: 63.25   3rd Qu.:258.8   3rd Qu.:11.500   3rd Qu.:85.00  
##  Max.   :168.00   Max.   :334.0   Max.   :20.700   Max.   :97.00  
##  NA's   :37       NA's   :7                                       
##      Month            Day      
##  Min.   :5.000   Min.   : 1.0  
##  1st Qu.:6.000   1st Qu.: 8.0  
##  Median :7.000   Median :16.0  
##  Mean   :6.993   Mean   :15.8  
##  3rd Qu.:8.000   3rd Qu.:23.0  
##  Max.   :9.000   Max.   :31.0  
## 
aq=na.omit(airquality) #remove rows containing NAs
head(aq)
summary(aq)
##      Ozone          Solar.R           Wind            Temp      
##  Min.   :  1.0   Min.   :  7.0   Min.   : 2.30   Min.   :57.00  
##  1st Qu.: 18.0   1st Qu.:113.5   1st Qu.: 7.40   1st Qu.:71.00  
##  Median : 31.0   Median :207.0   Median : 9.70   Median :79.00  
##  Mean   : 42.1   Mean   :184.8   Mean   : 9.94   Mean   :77.79  
##  3rd Qu.: 62.0   3rd Qu.:255.5   3rd Qu.:11.50   3rd Qu.:84.50  
##  Max.   :168.0   Max.   :334.0   Max.   :20.70   Max.   :97.00  
##      Month            Day       
##  Min.   :5.000   Min.   : 1.00  
##  1st Qu.:6.000   1st Qu.: 9.00  
##  Median :7.000   Median :16.00  
##  Mean   :7.216   Mean   :15.95  
##  3rd Qu.:9.000   3rd Qu.:22.50  
##  Max.   :9.000   Max.   :31.00
str(aq)
## 'data.frame':    111 obs. of  6 variables:
##  $ Ozone  : int  41 36 12 18 23 19 8 16 11 14 ...
##  $ Solar.R: int  190 118 149 313 299 99 19 256 290 274 ...
##  $ Wind   : num  7.4 8 12.6 11.5 8.6 13.8 20.1 9.7 9.2 10.9 ...
##  $ Temp   : int  67 72 74 62 65 59 61 69 66 68 ...
##  $ Month  : int  5 5 5 5 5 5 5 5 5 5 ...
##  $ Day    : int  1 2 3 4 7 8 9 12 13 14 ...
##  - attr(*, "na.action")= 'omit' Named int  5 6 10 11 25 26 27 32 33 34 ...
##   ..- attr(*, "names")= chr  "5" "6" "10" "11" ...
aq2=airquality[complete.cases(airquality), ] #only retain non-NA rows
head(aq2)
summary(aq2)
##      Ozone          Solar.R           Wind            Temp      
##  Min.   :  1.0   Min.   :  7.0   Min.   : 2.30   Min.   :57.00  
##  1st Qu.: 18.0   1st Qu.:113.5   1st Qu.: 7.40   1st Qu.:71.00  
##  Median : 31.0   Median :207.0   Median : 9.70   Median :79.00  
##  Mean   : 42.1   Mean   :184.8   Mean   : 9.94   Mean   :77.79  
##  3rd Qu.: 62.0   3rd Qu.:255.5   3rd Qu.:11.50   3rd Qu.:84.50  
##  Max.   :168.0   Max.   :334.0   Max.   :20.70   Max.   :97.00  
##      Month            Day       
##  Min.   :5.000   Min.   : 1.00  
##  1st Qu.:6.000   1st Qu.: 9.00  
##  Median :7.000   Median :16.00  
##  Mean   :7.216   Mean   :15.95  
##  3rd Qu.:9.000   3rd Qu.:22.50  
##  Max.   :9.000   Max.   :31.00
## replace NAs with 0
aqty=airquality

aqty[is.na(aqty)]<-0
head(aqty)
summary(aqty)
##      Ozone           Solar.R           Wind             Temp      
##  Min.   :  0.00   Min.   :  0.0   Min.   : 1.700   Min.   :56.00  
##  1st Qu.:  4.00   1st Qu.: 95.0   1st Qu.: 7.400   1st Qu.:72.00  
##  Median : 21.00   Median :194.0   Median : 9.700   Median :79.00  
##  Mean   : 31.94   Mean   :177.4   Mean   : 9.958   Mean   :77.88  
##  3rd Qu.: 46.00   3rd Qu.:256.0   3rd Qu.:11.500   3rd Qu.:85.00  
##  Max.   :168.00   Max.   :334.0   Max.   :20.700   Max.   :97.00  
##      Month            Day      
##  Min.   :5.000   Min.   : 1.0  
##  1st Qu.:6.000   1st Qu.: 8.0  
##  Median :7.000   Median :16.0  
##  Mean   :6.993   Mean   :15.8  
##  3rd Qu.:8.000   3rd Qu.:23.0  
##  Max.   :9.000   Max.   :31.0
## replcae missing values with average values

meanOzone=mean(airquality$Ozone,na.rm=T)
# remove NAs while computing mean of Ozone
#with na mean value will be na

aqty.fix=ifelse(is.na(airquality$Ozone),meanOzone,airquality$Ozone)
summary(aqty.fix)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    1.00   21.00   42.13   42.13   46.00  168.00
1+1
## [1] 2
##visualize the patterns of NAs
library(mice)
## Loading required package: lattice
## 
## Attaching package: 'mice'
## The following object is masked from 'package:RCurl':
## 
##     complete
## The following objects are masked from 'package:base':
## 
##     cbind, rbind
aqty2=airquality
md.pattern(aqty2)

##     Wind Temp Month Day Solar.R Ozone   
## 111    1    1     1   1       1     1  0
## 35     1    1     1   1       1     0  1
## 5      1    1     1   1       0     1  1
## 2      1    1     1   1       0     0  2
##        0    0     0   0       7    37 44
#111 observations with no values

library(VIM) #visualize the pattern of NAs
## Loading required package: colorspace
## Loading required package: grid
## Loading required package: data.table
## VIM is ready to use. 
##  Since version 4.0.0 the GUI is in its own package VIMGUI.
## 
##           Please use the package to use the new (and old) GUI.
## Suggestions and bug-reports can be submitted at: https://github.com/alexkowa/VIM/issues
## 
## Attaching package: 'VIM'
## The following object is masked from 'package:datasets':
## 
##     sleep
mp <- aggr(aqty2, col=c('navyblue','yellow'),
                    numbers=TRUE, sortVars=TRUE,
                    labels=names(aqty2), cex.axis=.7,
                    gap=3, ylab=c("Missing data","Pattern"))

## 
##  Variables sorted by number of missings: 
##  Variable      Count
##     Ozone 0.24183007
##   Solar.R 0.04575163
##      Wind 0.00000000
##      Temp 0.00000000
##     Month 0.00000000
##       Day 0.00000000
#72.5% observations in the entire data have no missing values
#22.9% missing values in Ozone

#impute
#500 iterataions of predictive mean mapping for imputing
#5 datasets
im_aqty<- mice(aqty2, m=5, maxit = 50, method = 'pmm', seed = 500)
## 
##  iter imp variable
##   1   1  Ozone  Solar.R
##   1   2  Ozone  Solar.R
##   1   3  Ozone  Solar.R
##   1   4  Ozone  Solar.R
##   1   5  Ozone  Solar.R
##   2   1  Ozone  Solar.R
##   2   2  Ozone  Solar.R
##   2   3  Ozone  Solar.R
##   2   4  Ozone  Solar.R
##   2   5  Ozone  Solar.R
##   3   1  Ozone  Solar.R
##   3   2  Ozone  Solar.R
##   3   3  Ozone  Solar.R
##   3   4  Ozone  Solar.R
##   3   5  Ozone  Solar.R
##   4   1  Ozone  Solar.R
##   4   2  Ozone  Solar.R
##   4   3  Ozone  Solar.R
##   4   4  Ozone  Solar.R
##   4   5  Ozone  Solar.R
##   5   1  Ozone  Solar.R
##   5   2  Ozone  Solar.R
##   5   3  Ozone  Solar.R
##   5   4  Ozone  Solar.R
##   5   5  Ozone  Solar.R
##   6   1  Ozone  Solar.R
##   6   2  Ozone  Solar.R
##   6   3  Ozone  Solar.R
##   6   4  Ozone  Solar.R
##   6   5  Ozone  Solar.R
##   7   1  Ozone  Solar.R
##   7   2  Ozone  Solar.R
##   7   3  Ozone  Solar.R
##   7   4  Ozone  Solar.R
##   7   5  Ozone  Solar.R
##   8   1  Ozone  Solar.R
##   8   2  Ozone  Solar.R
##   8   3  Ozone  Solar.R
##   8   4  Ozone  Solar.R
##   8   5  Ozone  Solar.R
##   9   1  Ozone  Solar.R
##   9   2  Ozone  Solar.R
##   9   3  Ozone  Solar.R
##   9   4  Ozone  Solar.R
##   9   5  Ozone  Solar.R
##   10   1  Ozone  Solar.R
##   10   2  Ozone  Solar.R
##   10   3  Ozone  Solar.R
##   10   4  Ozone  Solar.R
##   10   5  Ozone  Solar.R
##   11   1  Ozone  Solar.R
##   11   2  Ozone  Solar.R
##   11   3  Ozone  Solar.R
##   11   4  Ozone  Solar.R
##   11   5  Ozone  Solar.R
##   12   1  Ozone  Solar.R
##   12   2  Ozone  Solar.R
##   12   3  Ozone  Solar.R
##   12   4  Ozone  Solar.R
##   12   5  Ozone  Solar.R
##   13   1  Ozone  Solar.R
##   13   2  Ozone  Solar.R
##   13   3  Ozone  Solar.R
##   13   4  Ozone  Solar.R
##   13   5  Ozone  Solar.R
##   14   1  Ozone  Solar.R
##   14   2  Ozone  Solar.R
##   14   3  Ozone  Solar.R
##   14   4  Ozone  Solar.R
##   14   5  Ozone  Solar.R
##   15   1  Ozone  Solar.R
##   15   2  Ozone  Solar.R
##   15   3  Ozone  Solar.R
##   15   4  Ozone  Solar.R
##   15   5  Ozone  Solar.R
##   16   1  Ozone  Solar.R
##   16   2  Ozone  Solar.R
##   16   3  Ozone  Solar.R
##   16   4  Ozone  Solar.R
##   16   5  Ozone  Solar.R
##   17   1  Ozone  Solar.R
##   17   2  Ozone  Solar.R
##   17   3  Ozone  Solar.R
##   17   4  Ozone  Solar.R
##   17   5  Ozone  Solar.R
##   18   1  Ozone  Solar.R
##   18   2  Ozone  Solar.R
##   18   3  Ozone  Solar.R
##   18   4  Ozone  Solar.R
##   18   5  Ozone  Solar.R
##   19   1  Ozone  Solar.R
##   19   2  Ozone  Solar.R
##   19   3  Ozone  Solar.R
##   19   4  Ozone  Solar.R
##   19   5  Ozone  Solar.R
##   20   1  Ozone  Solar.R
##   20   2  Ozone  Solar.R
##   20   3  Ozone  Solar.R
##   20   4  Ozone  Solar.R
##   20   5  Ozone  Solar.R
##   21   1  Ozone  Solar.R
##   21   2  Ozone  Solar.R
##   21   3  Ozone  Solar.R
##   21   4  Ozone  Solar.R
##   21   5  Ozone  Solar.R
##   22   1  Ozone  Solar.R
##   22   2  Ozone  Solar.R
##   22   3  Ozone  Solar.R
##   22   4  Ozone  Solar.R
##   22   5  Ozone  Solar.R
##   23   1  Ozone  Solar.R
##   23   2  Ozone  Solar.R
##   23   3  Ozone  Solar.R
##   23   4  Ozone  Solar.R
##   23   5  Ozone  Solar.R
##   24   1  Ozone  Solar.R
##   24   2  Ozone  Solar.R
##   24   3  Ozone  Solar.R
##   24   4  Ozone  Solar.R
##   24   5  Ozone  Solar.R
##   25   1  Ozone  Solar.R
##   25   2  Ozone  Solar.R
##   25   3  Ozone  Solar.R
##   25   4  Ozone  Solar.R
##   25   5  Ozone  Solar.R
##   26   1  Ozone  Solar.R
##   26   2  Ozone  Solar.R
##   26   3  Ozone  Solar.R
##   26   4  Ozone  Solar.R
##   26   5  Ozone  Solar.R
##   27   1  Ozone  Solar.R
##   27   2  Ozone  Solar.R
##   27   3  Ozone  Solar.R
##   27   4  Ozone  Solar.R
##   27   5  Ozone  Solar.R
##   28   1  Ozone  Solar.R
##   28   2  Ozone  Solar.R
##   28   3  Ozone  Solar.R
##   28   4  Ozone  Solar.R
##   28   5  Ozone  Solar.R
##   29   1  Ozone  Solar.R
##   29   2  Ozone  Solar.R
##   29   3  Ozone  Solar.R
##   29   4  Ozone  Solar.R
##   29   5  Ozone  Solar.R
##   30   1  Ozone  Solar.R
##   30   2  Ozone  Solar.R
##   30   3  Ozone  Solar.R
##   30   4  Ozone  Solar.R
##   30   5  Ozone  Solar.R
##   31   1  Ozone  Solar.R
##   31   2  Ozone  Solar.R
##   31   3  Ozone  Solar.R
##   31   4  Ozone  Solar.R
##   31   5  Ozone  Solar.R
##   32   1  Ozone  Solar.R
##   32   2  Ozone  Solar.R
##   32   3  Ozone  Solar.R
##   32   4  Ozone  Solar.R
##   32   5  Ozone  Solar.R
##   33   1  Ozone  Solar.R
##   33   2  Ozone  Solar.R
##   33   3  Ozone  Solar.R
##   33   4  Ozone  Solar.R
##   33   5  Ozone  Solar.R
##   34   1  Ozone  Solar.R
##   34   2  Ozone  Solar.R
##   34   3  Ozone  Solar.R
##   34   4  Ozone  Solar.R
##   34   5  Ozone  Solar.R
##   35   1  Ozone  Solar.R
##   35   2  Ozone  Solar.R
##   35   3  Ozone  Solar.R
##   35   4  Ozone  Solar.R
##   35   5  Ozone  Solar.R
##   36   1  Ozone  Solar.R
##   36   2  Ozone  Solar.R
##   36   3  Ozone  Solar.R
##   36   4  Ozone  Solar.R
##   36   5  Ozone  Solar.R
##   37   1  Ozone  Solar.R
##   37   2  Ozone  Solar.R
##   37   3  Ozone  Solar.R
##   37   4  Ozone  Solar.R
##   37   5  Ozone  Solar.R
##   38   1  Ozone  Solar.R
##   38   2  Ozone  Solar.R
##   38   3  Ozone  Solar.R
##   38   4  Ozone  Solar.R
##   38   5  Ozone  Solar.R
##   39   1  Ozone  Solar.R
##   39   2  Ozone  Solar.R
##   39   3  Ozone  Solar.R
##   39   4  Ozone  Solar.R
##   39   5  Ozone  Solar.R
##   40   1  Ozone  Solar.R
##   40   2  Ozone  Solar.R
##   40   3  Ozone  Solar.R
##   40   4  Ozone  Solar.R
##   40   5  Ozone  Solar.R
##   41   1  Ozone  Solar.R
##   41   2  Ozone  Solar.R
##   41   3  Ozone  Solar.R
##   41   4  Ozone  Solar.R
##   41   5  Ozone  Solar.R
##   42   1  Ozone  Solar.R
##   42   2  Ozone  Solar.R
##   42   3  Ozone  Solar.R
##   42   4  Ozone  Solar.R
##   42   5  Ozone  Solar.R
##   43   1  Ozone  Solar.R
##   43   2  Ozone  Solar.R
##   43   3  Ozone  Solar.R
##   43   4  Ozone  Solar.R
##   43   5  Ozone  Solar.R
##   44   1  Ozone  Solar.R
##   44   2  Ozone  Solar.R
##   44   3  Ozone  Solar.R
##   44   4  Ozone  Solar.R
##   44   5  Ozone  Solar.R
##   45   1  Ozone  Solar.R
##   45   2  Ozone  Solar.R
##   45   3  Ozone  Solar.R
##   45   4  Ozone  Solar.R
##   45   5  Ozone  Solar.R
##   46   1  Ozone  Solar.R
##   46   2  Ozone  Solar.R
##   46   3  Ozone  Solar.R
##   46   4  Ozone  Solar.R
##   46   5  Ozone  Solar.R
##   47   1  Ozone  Solar.R
##   47   2  Ozone  Solar.R
##   47   3  Ozone  Solar.R
##   47   4  Ozone  Solar.R
##   47   5  Ozone  Solar.R
##   48   1  Ozone  Solar.R
##   48   2  Ozone  Solar.R
##   48   3  Ozone  Solar.R
##   48   4  Ozone  Solar.R
##   48   5  Ozone  Solar.R
##   49   1  Ozone  Solar.R
##   49   2  Ozone  Solar.R
##   49   3  Ozone  Solar.R
##   49   4  Ozone  Solar.R
##   49   5  Ozone  Solar.R
##   50   1  Ozone  Solar.R
##   50   2  Ozone  Solar.R
##   50   3  Ozone  Solar.R
##   50   4  Ozone  Solar.R
##   50   5  Ozone  Solar.R
#50 iterataions of predictive mean mapping for imputing

summary(im_aqty)
## Class: mids
## Number of multiple imputations:  5 
## Imputation methods:
##   Ozone Solar.R    Wind    Temp   Month     Day 
##   "pmm"   "pmm"      ""      ""      ""      "" 
## PredictorMatrix:
##         Ozone Solar.R Wind Temp Month Day
## Ozone       0       1    1    1     1   1
## Solar.R     1       0    1    1     1   1
## Wind        1       1    0    1     1   1
## Temp        1       1    1    0     1   1
## Month       1       1    1    1     0   1
## Day         1       1    1    1     1   0
im_aqty$imp$Ozone #values imputed in ozone
#get back the completed dataset u
completedData <- complete(im_aqty,1)
head(completedData)