Basics of R Session 5.2 - Missing values

Dr Manohar Kapse

rm(list=ls())
# Missing Values
X<-c(1,2,NA,4,5)
str(X)

##  num [1:5] 1 2 NA 4 5

is.na(X)

## [1] FALSE FALSE  TRUE FALSE FALSE

sum(is.na(X))

## [1] 1

which(is.na(X))

## [1] 3

Step by Step

is.na(X)

## [1] FALSE FALSE  TRUE FALSE FALSE

X[is.na(X)]

## [1] NA

X[is.na(X)]<-999
X

## [1]   1   2 999   4   5

Change to some specific statement or string

X[is.na(X)]<-"missing values"
str(X) # converted all to string

##  chr [1:5] "1" "2" "999" "4" "5"

Imputig with mean

X<-c(1,2,NA,4,5)
X[is.na(X)]<-mean(X)
X  # no output, since missing value was there

## [1]  1  2 NA  4  5

X[is.na(X)]<-mean(X, na.rm = TRUE)
X

## [1] 1 2 3 4 5

Omiting the Missing values

X<-c(1,2,NA,4,5)
X<-na.omit(X)
X

## [1] 1 2 4 5
## attr(,"na.action")
## [1] 3
## attr(,"class")
## [1] "omit"

use hsurvey data set

data1<-read.csv("file:///C:/Users/LENOVO/Desktop/health Survey.csv")
# to check missing values in a file
summary(data1)

##       Case.Identification Current.age...respondent Age.in.5.year.groups
##      1  1   2  2:     1   Min.   :15.00            15-19:23955         
##      1  1   3  2:     1   1st Qu.:21.00            20-24:22807         
##      1  1   5  5:     1   Median :28.00            25-29:20653         
##      1  1   6  2:     1   Mean   :29.16            30-34:17867         
##      1  1   7  2:     1   3rd Qu.:37.00            35-39:16158         
##      1  1   7  3:     1   Max.   :49.00            40-44:13138         
##  (Other)        :124379                            45-49: 9807         
##                  State       Type.of.place.of.residence
##  [UP] Uttar Pradesh :12183   Rural:67424               
##  [MH] Maharashtra   : 9034   Urban:56961               
##  [AP] Andhra Pradesh: 7128                             
##  [WB] West Bengal   : 6794                             
##  [MP] Madhya Pradesh: 6427                             
##  [KA] Karnataka     : 6008                             
##  (Other)            :76811                             
##                 State.1      Type.of.place.of.residence.1
##  [UP] Uttar Pradesh :12183   Rural:67424                 
##  [MH] Maharashtra   : 9034   Urban:56961                 
##  [AP] Andhra Pradesh: 7128                               
##  [WB] West Bengal   : 6794                               
##  [MP] Madhya Pradesh: 6427                               
##  [KA] Karnataka     : 6008                               
##  (Other)            :76811                               
##  Highest.educational.level Highest.year.of.education
##  9           :   12        Min.   : 0.00            
##  Higher      :12966        1st Qu.: 3.00            
##  No education:39769        Median : 4.00            
##  Primary     :17756        Mean   : 3.95            
##  Secondary   :53882        3rd Qu.: 5.00            
##                            Max.   :11.00            
##                            NA's   :39781            
##          Household.has..electricity     Household.has..motorcycle.scooter
##  9                    :   23        9                    :   49          
##  No                   :23070        No                   :90934          
##  Not a dejure resident: 5528        Not a dejure resident: 5528          
##  Yes                  :95764        Yes                  :27874          
##                                                                          
##                                                                          
##                                                                          
##              Household.has..car                  Religion    
##  9                    :    55   Hindu                :89957  
##  No                   :112490   Muslim               :16742  
##  Not a dejure resident:  5528   Christian            :10977  
##  Yes                  :  6312   Sikh                 : 2772  
##                                 Buddhist/Neo-Buddhist: 1765  
##                                 other                : 1032  
##                                 (Other)              : 1140  
##  Number.of.household.members..listed.          Educational.attainment
##  Min.   : 1.000                       9                   :   12     
##  1st Qu.: 4.000                       Complete primary    : 8039     
##  Median : 5.000                       Complete secondary  : 7611     
##  Mean   : 6.007                       Higher              :12966     
##  3rd Qu.: 7.000                       Incomplete primary  : 9717     
##  Max.   :35.000                       Incomplete secondary:46271     
##                                       No education        :39769     
##               Has.telephone                                  Literacy    
##  9                   :   45   9                                  :  107  
##  No                  :93489   Able to read only parts of sentence: 6082  
##  Not de jure resident: 5528   Able to read whole sentence        :73628  
##  Yes                 :25323   Blind/visually impaired            :  130  
##                               Cannot read at all                 :43901  
##                               No card with required language     :  537  
##                                                                          
##   Wealth.index   Wealth.index.factor.score..5.decimals.
##  Middle :23682   Min.   :-175304                       
##  Poorer :17652   1st Qu.: -76482                       
##  Poorest:14077   Median :   1737                       
##  Richer :30136   Mean   :   7403                       
##  Richest:38838   3rd Qu.:  88900                       
##                  Max.   : 236620                       
##                                                        
##  Total.children.ever.born  Sons.at.home    Daughters.at.home
##  Min.   : 0.000           Min.   :0.0000   Min.   :0.0000   
##  1st Qu.: 0.000           1st Qu.:0.0000   1st Qu.:0.0000   
##  Median : 2.000           Median :1.0000   Median :0.0000   
##  Mean   : 2.064           Mean   :0.8668   Mean   :0.7289   
##  3rd Qu.: 3.000           3rd Qu.:1.0000   3rd Qu.:1.0000   
##  Max.   :16.000           Max.   :9.0000   Max.   :8.0000   
##                                                             
##  Sons.elsewhere    Daughters.elsewhere
##  Min.   :0.00000   Min.   :0.000      
##  1st Qu.:0.00000   1st Qu.:0.000      
##  Median :0.00000   Median :0.000      
##  Mean   :0.09649   Mean   :0.165      
##  3rd Qu.:0.00000   3rd Qu.:0.000      
##  Max.   :7.00000   Max.   :6.000      
##                                       
##                           Marital.status 
##  Currently married               :87925  
##  Deserted                        :  443  
##  Divorced                        :  504  
##  Married, but Gauna not performed:  470  
##  Never married                   :30191  
##  Separated                       :  931  
##  Widowed                         : 3921

descr::descr(data1)

## 
## Case.Identification
##     1  1   2  2     1  1   3  2     1  1   5  5     1  1   6  2 
##               1               1               1               1 
##     1  1   7  2     1  1   7  3     1  1   7  5     1  1   7  9 
##               1               1               1               1 
##     1  1   8  4     1  1   9  2     1  1  10  2     1  1  10  5 
##               1               1               1               1 
##     1  1  11  2     1  1  12  4     1  1  14  2     1  1  14  3 
##               1               1               1               1 
##     1  1  15  2     1  1  18  1     1  1  18  3     1  1  19  2 
##               1               1               1               1 
##     1  1  21  2     1  1  22  3     1  1  23  2     1  1  25  2 
##               1               1               1               1 
##     1  1  25  3     1  1  26  3     1  1  27  3     1  1  27  5 
##               1               1               1               1 
##     1  1  27  6     1  1  29  4     1  1  29 11     1  1  30  1 
##               1               1               1               1 
##     1  1  30  2     1  1  32  2     1  1  32  5     1  1  33  2 
##               1               1               1               1 
##     1  1  33  3     1  1  34  4     1  1  34  5     1  1  34  6 
##               1               1               1               1 
##     1  1  34  7     1  1  34  9     1  1  35  2     1  1  36  2 
##               1               1               1               1 
##     1  1  39  4     1  1  40  2     1  1  41  2     1  1  41  3 
##               1               1               1               1 
##     1  1  43  2     1  1  44  2     1  1  44  6     1  1  45  2 
##               1               1               1               1 
##     1  1  45  4     1  1  46  3     1  1  46  6     1  1  48  2 
##               1               1               1               1 
##     1  1  49  2     1  1  49  5     1  1  50  2     1  1  51  2 
##               1               1               1               1 
##     1  1  52  2     1  1  55  3     1  1  55  4     1  1  56  7 
##               1               1               1               1 
##     1  2   1  2     1  2   3  2     1  2   3  4     1  2   4  2 
##               1               1               1               1 
##     1  2   4  7     1  2   5  2     1  2   5  4     1  2   5  5 
##               1               1               1               1 
##     1  2   6  2     1  2   6  4     1  2   6  6     1  2   7  4 
##               1               1               1               1 
##     1  2   8  2     1  2   8  4     1  2   8  7     1  2   9  4 
##               1               1               1               1 
##     1  2   9  8     1  2  10  4     1  2  10  5     1  2  11  2 
##               1               1               1               1 
##     1  2  12  2     1  2  12  3     1  2  12  4     1  2  13  2 
##               1               1               1               1 
##     1  2  13  6     1  2  14  2     1  2  15  7     1  3   1  4 
##               1               1               1               1 
##     1  3   1  5     1  3   2  2     1  3   3  3     1  3   3  4 
##               1               1               1               1 
##     1  3   4  3     1  3   6  2     1  3   9  4         (Other) 
##               1               1               1          124286 
## 
## Current.age...respondent
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   15.00   21.00   28.00   29.16   37.00   49.00 
## 
## Age.in.5.year.groups
## 15-19 20-24 25-29 30-34 35-39 40-44 45-49 
## 23955 22807 20653 17867 16158 13138  9807 
## 
## State
##    [AP] Andhra Pradesh [AR] Arunachal Pradesh             [AS] Assam 
##                   7128                   1647                   3840 
##             [BH] Bihar      [CH] Chhattisgarh             [DL] Delhi 
##                   3818                   3810                   3349 
##           [GJ] Gujarat               [GO] Goa  [HP] Himachal Pradesh 
##                   3729                   3464                   3193 
##           [HR] Haryana         [JH] Jharkhand [JM] Jammu and Kashmir 
##                   2790                   2983                   3281 
##         [KA] Karnataka            [KE] Kerala         [MG] Meghalaya 
##                   6008                   3566                   2124 
##       [MH] Maharashtra           [MN] Manipur    [MP] Madhya Pradesh 
##                   9034                   4512                   6427 
##           [MZ] Mizoram          [NA] Nagaland            [OR] Orissa 
##                   1791                   3896                   4540 
##            [PJ] Punjab         [RJ] Rajasthan            [SK] Sikkim 
##                   3681                   3892                   2127 
##        [TN] Tamil Nadu           [TR] Tripura       [UC] Uttaranchal 
##                   5919                   1906                   2953 
##     [UP] Uttar Pradesh       [WB] West Bengal 
##                  12183                   6794 
## 
## Type.of.place.of.residence
## Rural Urban 
## 67424 56961 
## 
## State.1
##    [AP] Andhra Pradesh [AR] Arunachal Pradesh             [AS] Assam 
##                   7128                   1647                   3840 
##             [BH] Bihar       [CH] Chhatisgarh             [DL] Delhi 
##                   3818                   3810                   3349 
##           [GJ] Gujarat               [GO] Goa  [HP] Himachal Pradesh 
##                   3729                   3464                   3193 
##           [HR] Haryana         [JH] Jharkhand [JM] Jammu and Kashmir 
##                   2790                   2983                   3281 
##         [KA] Karnataka            [KE] Kerala         [MG] Meghalaya 
##                   6008                   3566                   2124 
##       [MH] Maharashtra           [MN] Manipur    [MP] Madhya Pradesh 
##                   9034                   4512                   6427 
##           [MZ] Mizoram          [NA] Nagaland            [OR] Orissa 
##                   1791                   3896                   4540 
##            [PJ] Punjab         [RJ] Rajasthan            [SK] Sikkim 
##                   3681                   3892                   2127 
##        [TN] Tamil Nadu           [TR] Tripura       [UC] Uttaranchal 
##                   5919                   1906                   2953 
##     [UP] Uttar Pradesh       [WB] West Bengal 
##                  12183                   6794 
## 
## Type.of.place.of.residence.1
## Rural Urban 
## 67424 56961 
## 
## Highest.educational.level
##            9       Higher No education      Primary    Secondary 
##           12        12966        39769        17756        53882 
## 
## Highest.year.of.education
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##    0.00    3.00    4.00    3.95    5.00   11.00   39781 
## 
## Household.has..electricity
##                     9                    No Not a dejure resident 
##                    23                 23070                  5528 
##                   Yes 
##                 95764 
## 
## Household.has..motorcycle.scooter
##                     9                    No Not a dejure resident 
##                    49                 90934                  5528 
##                   Yes 
##                 27874 
## 
## Household.has..car
##                     9                    No Not a dejure resident 
##                    55                112490                  5528 
##                   Yes 
##                  6312 
## 
## Religion
##                    99 Buddhist/Neo-Buddhist             Christian 
##                   158                  1765                 10977 
##            Donyi polo                 Hindu                  Jain 
##                   385                 89957                   539 
##                Jewish                Muslim           No religion 
##                    11                 16742                    44 
##                 other     Parsi/Zoroastrian                  Sikh 
##                  1032                     3                  2772 
## 
## Number.of.household.members..listed.
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   1.000   4.000   5.000   6.007   7.000  35.000 
## 
## Educational.attainment
##                    9     Complete primary   Complete secondary 
##                   12                 8039                 7611 
##               Higher   Incomplete primary Incomplete secondary 
##                12966                 9717                46271 
##         No education 
##                39769 
## 
## Has.telephone
##                    9                   No Not de jure resident 
##                   45                93489                 5528 
##                  Yes 
##                25323 
## 
## Literacy
##                                   9 Able to read only parts of sentence 
##                                 107                                6082 
##         Able to read whole sentence             Blind/visually impaired 
##                               73628                                 130 
##                  Cannot read at all      No card with required language 
##                               43901                                 537 
## 
## Wealth.index
##  Middle  Poorer Poorest  Richer Richest 
##   23682   17652   14077   30136   38838 
## 
## Wealth.index.factor.score..5.decimals.
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
## -175304  -76482    1737    7403   88900  236620 
## 
## Total.children.ever.born
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   0.000   0.000   2.000   2.064   3.000  16.000 
## 
## Sons.at.home
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##  0.0000  0.0000  1.0000  0.8668  1.0000  9.0000 
## 
## Daughters.at.home
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##  0.0000  0.0000  0.0000  0.7289  1.0000  8.0000 
## 
## Sons.elsewhere
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
## 0.00000 0.00000 0.00000 0.09649 0.00000 7.00000 
## 
## Daughters.elsewhere
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   0.000   0.000   0.000   0.165   0.000   6.000 
## 
## Marital.status
##                Currently married                         Deserted 
##                            87925                              443 
##                         Divorced Married, but Gauna not performed 
##                              504                              470 
##                    Never married                        Separated 
##                            30191                              931 
##                          Widowed 
##                             3921

#------------#

# is.na(data1)  # not so usefull

# is.na(data1$Current.age...respondent) # not so usefull

# if we find the total number of missing then use full

sum(is.na(data1))

## [1] 39781

sum(is.na(data1$Current.age...respondent))

## [1] 0

sum(is.na(data1$Type.of.place.of.residence))

## [1] 0

sum(is.na(data1$Highest.year.of.education))

## [1] 39781

location of the missing values

#which(is.na(data1$Highest.year.of.education))

# recode missing values string or number; in categorical data string is better, for scale number is better

table(data1$Educational.attainment)

## 
##                    9     Complete primary   Complete secondary 
##                   12                 8039                 7611 
##               Higher   Incomplete primary Incomplete secondary 
##                12966                 9717                46271 
##         No education 
##                39769

data1$Highest.year.of.education[is.na(data1$Highest.year.of.education)]<-"missing vales"

table(data1$Educational.attainment)

## 
##                    9     Complete primary   Complete secondary 
##                   12                 8039                 7611 
##               Higher   Incomplete primary Incomplete secondary 
##                12966                 9717                46271 
##         No education 
##                39769

# replace 9 which is coded as missing to NA
data1$Educational.attainment[data1$Educational.attainment==9]<-NA
table(data1$Educational.attainment)

## 
##                    9     Complete primary   Complete secondary 
##                    0                 8039                 7611 
##               Higher   Incomplete primary Incomplete secondary 
##                12966                 9717                46271 
##         No education 
##                39769

#fix(data1)
sum(is.na(data1$Educational.attainment))

## [1] 12

Basics of R Session 5.1 - Library(dplyr)

Dr Manohar Kapse

19 March 2019

library(dplyr)

## Warning: package 'dplyr' was built under R version 3.5.3

## 
## 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

# importthe data from the location C:/Users/LENOVO/Desktop/MBAdata.csv

mbaper<-read.csv("C:/Users/LENOVO/Desktop/MBAdata.csv")

#Equivalent of str in traditional approach. Gives the structure of data
str(mbaper)

## 'data.frame':    273 obs. of  19 variables:
##  $ Age_in_years_completed                                          : int  22 26 24 22 22 26 22 20 22 25 ...
##  $ Percentage_in_10_Class                                          : num  91.2 77 79.8 82 95 86.4 91.2 91.4 71 77.6 ...
##  $ Percentage_in_12_Class                                          : num  91.2 68 61.6 70 78.6 80.4 80 77 74.8 82.6 ...
##  $ Percentage_in_Under_Graduate                                    : num  70 72.7 60.3 76.5 75.4 ...
##  $ Gender                                                          : Factor w/ 2 levels "Female","Male": 1 1 1 2 2 2 2 1 2 2 ...
##  $ STATE                                                           : Factor w/ 9 levels "Central Zone",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ Previous_Degree                                                 : Factor w/ 6 levels "Arts","Commerce",..: 2 3 3 3 3 3 2 2 3 3 ...
##  $ Fathers_qualification                                           : Factor w/ 9 levels "CA/CS","DIPLOMA",..: 9 5 7 7 9 9 9 9 7 9 ...
##  $ Mothers_qualification                                           : Factor w/ 7 levels "DIPLOMA","HSC",..: 5 5 2 7 7 7 5 7 7 7 ...
##  $ Fathers_occupation                                              : Factor w/ 7 levels "Farming","Not Alive",..: 4 2 4 4 4 7 6 6 7 7 ...
##  $ Mothers_occupation                                              : Factor w/ 4 levels "House wife","Professional Job",..: 2 1 1 2 1 1 2 1 1 1 ...
##  $ Marital_status                                                  : Factor w/ 2 levels "Married","Single": 2 1 2 2 2 2 2 2 2 2 ...
##  $ Place_you_belong_to                                             : Factor w/ 3 levels "Rural","Semi Urban",..: 3 3 3 2 3 2 2 3 3 2 ...
##  $ Total_Family_Income_per_annum                                   : Factor w/ 6 levels "0-3 Lakh","10-15 lakh",..: 4 1 2 6 6 3 1 4 6 6 ...
##  $ Funding_for_the_MBA_Program                                     : Factor w/ 6 levels "Family","Loan",..: 3 1 2 3 1 1 4 1 2 3 ...
##  $ Work_Experience                                                 : Factor w/ 6 levels "1-2 year","2-3 year",..: 6 4 6 6 6 2 6 6 6 6 ...
##  $ Career_options_after_MBA                                        : Factor w/ 5 levels "Family Business",..: 3 3 3 3 3 3 3 3 3 3 ...
##  $ Alternate_Career_Option_after_MBA_if_not_selected_through_Instit: Factor w/ 5 levels "Family Business",..: 3 3 3 3 3 2 5 3 5 3 ...
##  $ perceivedscorecat                                               : Factor w/ 3 levels "desired skills",..: 3 2 2 2 2 1 2 2 2 2 ...

#fix(mbaper)
glimpse(mbaper)

## Observations: 273
## Variables: 19
## $ Age_in_years_completed                                           <int> ...
## $ Percentage_in_10_Class                                           <dbl> ...
## $ Percentage_in_12_Class                                           <dbl> ...
## $ Percentage_in_Under_Graduate                                     <dbl> ...
## $ Gender                                                           <fct> ...
## $ STATE                                                            <fct> ...
## $ Previous_Degree                                                  <fct> ...
## $ Fathers_qualification                                            <fct> ...
## $ Mothers_qualification                                            <fct> ...
## $ Fathers_occupation                                               <fct> ...
## $ Mothers_occupation                                               <fct> ...
## $ Marital_status                                                   <fct> ...
## $ Place_you_belong_to                                              <fct> ...
## $ Total_Family_Income_per_annum                                    <fct> ...
## $ Funding_for_the_MBA_Program                                      <fct> ...
## $ Work_Experience                                                  <fct> ...
## $ Career_options_after_MBA                                         <fct> ...
## $ Alternate_Career_Option_after_MBA_if_not_selected_through_Instit <fct> ...
## $ perceivedscorecat                                                <fct> ...

adding or removing variables from the file

mbaper_age<-select(mbaper, Age_in_years_completed)
str(mbaper_age)

## 'data.frame':    273 obs. of  1 variable:
##  $ Age_in_years_completed: int  22 26 24 22 22 26 22 20 22 25 ...

mbaper_age<-select(mbaper, -Age_in_years_completed)
str(mbaper_age)

## 'data.frame':    273 obs. of  18 variables:
##  $ Percentage_in_10_Class                                          : num  91.2 77 79.8 82 95 86.4 91.2 91.4 71 77.6 ...
##  $ Percentage_in_12_Class                                          : num  91.2 68 61.6 70 78.6 80.4 80 77 74.8 82.6 ...
##  $ Percentage_in_Under_Graduate                                    : num  70 72.7 60.3 76.5 75.4 ...
##  $ Gender                                                          : Factor w/ 2 levels "Female","Male": 1 1 1 2 2 2 2 1 2 2 ...
##  $ STATE                                                           : Factor w/ 9 levels "Central Zone",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ Previous_Degree                                                 : Factor w/ 6 levels "Arts","Commerce",..: 2 3 3 3 3 3 2 2 3 3 ...
##  $ Fathers_qualification                                           : Factor w/ 9 levels "CA/CS","DIPLOMA",..: 9 5 7 7 9 9 9 9 7 9 ...
##  $ Mothers_qualification                                           : Factor w/ 7 levels "DIPLOMA","HSC",..: 5 5 2 7 7 7 5 7 7 7 ...
##  $ Fathers_occupation                                              : Factor w/ 7 levels "Farming","Not Alive",..: 4 2 4 4 4 7 6 6 7 7 ...
##  $ Mothers_occupation                                              : Factor w/ 4 levels "House wife","Professional Job",..: 2 1 1 2 1 1 2 1 1 1 ...
##  $ Marital_status                                                  : Factor w/ 2 levels "Married","Single": 2 1 2 2 2 2 2 2 2 2 ...
##  $ Place_you_belong_to                                             : Factor w/ 3 levels "Rural","Semi Urban",..: 3 3 3 2 3 2 2 3 3 2 ...
##  $ Total_Family_Income_per_annum                                   : Factor w/ 6 levels "0-3 Lakh","10-15 lakh",..: 4 1 2 6 6 3 1 4 6 6 ...
##  $ Funding_for_the_MBA_Program                                     : Factor w/ 6 levels "Family","Loan",..: 3 1 2 3 1 1 4 1 2 3 ...
##  $ Work_Experience                                                 : Factor w/ 6 levels "1-2 year","2-3 year",..: 6 4 6 6 6 2 6 6 6 6 ...
##  $ Career_options_after_MBA                                        : Factor w/ 5 levels "Family Business",..: 3 3 3 3 3 3 3 3 3 3 ...
##  $ Alternate_Career_Option_after_MBA_if_not_selected_through_Instit: Factor w/ 5 levels "Family Business",..: 3 3 3 3 3 2 5 3 5 3 ...
##  $ perceivedscorecat                                               : Factor w/ 3 levels "desired skills",..: 3 2 2 2 2 1 2 2 2 2 ...

mbaper_age<-select(mbaper, Age_in_years_completed:Mothers_qualification)
str(mbaper_age)

## 'data.frame':    273 obs. of  9 variables:
##  $ Age_in_years_completed      : int  22 26 24 22 22 26 22 20 22 25 ...
##  $ Percentage_in_10_Class      : num  91.2 77 79.8 82 95 86.4 91.2 91.4 71 77.6 ...
##  $ Percentage_in_12_Class      : num  91.2 68 61.6 70 78.6 80.4 80 77 74.8 82.6 ...
##  $ Percentage_in_Under_Graduate: num  70 72.7 60.3 76.5 75.4 ...
##  $ Gender                      : Factor w/ 2 levels "Female","Male": 1 1 1 2 2 2 2 1 2 2 ...
##  $ STATE                       : Factor w/ 9 levels "Central Zone",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ Previous_Degree             : Factor w/ 6 levels "Arts","Commerce",..: 2 3 3 3 3 3 2 2 3 3 ...
##  $ Fathers_qualification       : Factor w/ 9 levels "CA/CS","DIPLOMA",..: 9 5 7 7 9 9 9 9 7 9 ...
##  $ Mothers_qualification       : Factor w/ 7 levels "DIPLOMA","HSC",..: 5 5 2 7 7 7 5 7 7 7 ...

To filter data based on some conditions we could use the filter function, the filter is associated with cases

filter(dataset, variable==value)

mbaper_age<-filter(mbaper, Percentage_in_10_Class==75)
str(mbaper_age$Percentage_in_10_Class)

##  num [1:4] 75 75 75 75

mbaper_age<-filter(mbaper, Percentage_in_10_Class<75)
str(mbaper_age$Percentage_in_10_Class)

##  num [1:43] 71 70 72.2 67 74 66.4 72 69.6 72 69.2 ...

mbaper_age<-filter(mbaper, Percentage_in_10_Class>75)
str(mbaper_age$Percentage_in_10_Class)

##  num [1:226] 91.2 77 79.8 82 95 86.4 91.2 91.4 77.6 87.4 ...

#-------------------------------------------------------#

specific category from a categorical variable

mbaper_zone<-filter(mbaper, STATE =="GOA")
str(mbaper_zone$STATE)

##  Factor w/ 9 levels "Central Zone",..: 3

dim(mbaper_zone$STATE)

## NULL

head(mbaper_zone$STATE)  # only one observation is there

## [1] GOA
## 9 Levels: Central Zone East Zone GOA GUJARAT Nepal ... west Zone

more than one category

, for and

mbaper_zone<-filter(mbaper, STATE=="North East Zone",STATE=="Central Zone")
str(mbaper_zone)

## 'data.frame':    0 obs. of  19 variables:
##  $ Age_in_years_completed                                          : int 
##  $ Percentage_in_10_Class                                          : num 
##  $ Percentage_in_12_Class                                          : num 
##  $ Percentage_in_Under_Graduate                                    : num 
##  $ Gender                                                          : Factor w/ 2 levels "Female","Male": 
##  $ STATE                                                           : Factor w/ 9 levels "Central Zone",..: 
##  $ Previous_Degree                                                 : Factor w/ 6 levels "Arts","Commerce",..: 
##  $ Fathers_qualification                                           : Factor w/ 9 levels "CA/CS","DIPLOMA",..: 
##  $ Mothers_qualification                                           : Factor w/ 7 levels "DIPLOMA","HSC",..: 
##  $ Fathers_occupation                                              : Factor w/ 7 levels "Farming","Not Alive",..: 
##  $ Mothers_occupation                                              : Factor w/ 4 levels "House wife","Professional Job",..: 
##  $ Marital_status                                                  : Factor w/ 2 levels "Married","Single": 
##  $ Place_you_belong_to                                             : Factor w/ 3 levels "Rural","Semi Urban",..: 
##  $ Total_Family_Income_per_annum                                   : Factor w/ 6 levels "0-3 Lakh","10-15 lakh",..: 
##  $ Funding_for_the_MBA_Program                                     : Factor w/ 6 levels "Family","Loan",..: 
##  $ Work_Experience                                                 : Factor w/ 6 levels "1-2 year","2-3 year",..: 
##  $ Career_options_after_MBA                                        : Factor w/ 5 levels "Family Business",..: 
##  $ Alternate_Career_Option_after_MBA_if_not_selected_through_Instit: Factor w/ 5 levels "Family Business",..: 
##  $ perceivedscorecat                                               : Factor w/ 3 levels "desired skills",..:

dim(mbaper_zone$STATE)

## NULL

head(mbaper_zone$STATE)

## factor(0)
## 9 Levels: Central Zone East Zone GOA GUJARAT Nepal ... west Zone

#   | for or

mbaper_zone<-filter(mbaper, STATE=="North East Zone" | STATE=="Central Zone")

str(mbaper_zone)

## 'data.frame':    24 obs. of  19 variables:
##  $ Age_in_years_completed                                          : int  22 26 24 22 22 26 22 20 22 25 ...
##  $ Percentage_in_10_Class                                          : num  91.2 77 79.8 82 95 86.4 91.2 91.4 71 77.6 ...
##  $ Percentage_in_12_Class                                          : num  91.2 68 61.6 70 78.6 80.4 80 77 74.8 82.6 ...
##  $ Percentage_in_Under_Graduate                                    : num  70 72.7 60.3 76.5 75.4 ...
##  $ Gender                                                          : Factor w/ 2 levels "Female","Male": 1 1 1 2 2 2 2 1 2 2 ...
##  $ STATE                                                           : Factor w/ 9 levels "Central Zone",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ Previous_Degree                                                 : Factor w/ 6 levels "Arts","Commerce",..: 2 3 3 3 3 3 2 2 3 3 ...
##  $ Fathers_qualification                                           : Factor w/ 9 levels "CA/CS","DIPLOMA",..: 9 5 7 7 9 9 9 9 7 9 ...
##  $ Mothers_qualification                                           : Factor w/ 7 levels "DIPLOMA","HSC",..: 5 5 2 7 7 7 5 7 7 7 ...
##  $ Fathers_occupation                                              : Factor w/ 7 levels "Farming","Not Alive",..: 4 2 4 4 4 7 6 6 7 7 ...
##  $ Mothers_occupation                                              : Factor w/ 4 levels "House wife","Professional Job",..: 2 1 1 2 1 1 2 1 1 1 ...
##  $ Marital_status                                                  : Factor w/ 2 levels "Married","Single": 2 1 2 2 2 2 2 2 2 2 ...
##  $ Place_you_belong_to                                             : Factor w/ 3 levels "Rural","Semi Urban",..: 3 3 3 2 3 2 2 3 3 2 ...
##  $ Total_Family_Income_per_annum                                   : Factor w/ 6 levels "0-3 Lakh","10-15 lakh",..: 4 1 2 6 6 3 1 4 6 6 ...
##  $ Funding_for_the_MBA_Program                                     : Factor w/ 6 levels "Family","Loan",..: 3 1 2 3 1 1 4 1 2 3 ...
##  $ Work_Experience                                                 : Factor w/ 6 levels "1-2 year","2-3 year",..: 6 4 6 6 6 2 6 6 6 6 ...
##  $ Career_options_after_MBA                                        : Factor w/ 5 levels "Family Business",..: 3 3 3 3 3 3 3 3 3 3 ...
##  $ Alternate_Career_Option_after_MBA_if_not_selected_through_Instit: Factor w/ 5 levels "Family Business",..: 3 3 3 3 3 2 5 3 5 3 ...
##  $ perceivedscorecat                                               : Factor w/ 3 levels "desired skills",..: 3 2 2 2 2 1 2 2 2 2 ...

dim(mbaper_zone$STATE)

## NULL

head(mbaper_zone$STATE)

## [1] Central Zone Central Zone Central Zone Central Zone Central Zone
## [6] Central Zone
## 9 Levels: Central Zone East Zone GOA GUJARAT Nepal ... west Zone

| for or ### exact word has to be used

mbaper_zone<-filter(mbaper, STATE=="North East Zone" | Previous_Degree=="Commerce")

str(mbaper_zone)

## 'data.frame':    102 obs. of  19 variables:
##  $ Age_in_years_completed                                          : int  22 22 20 23 22 22 22 22 21 21 ...
##  $ Percentage_in_10_Class                                          : num  91.2 91.2 91.4 67 74 85.5 83 76 85 92.4 ...
##  $ Percentage_in_12_Class                                          : num  91.2 80 77 62 61 84.6 82 75 88 89 ...
##  $ Percentage_in_Under_Graduate                                    : num  70 67 65 67 66 86.9 75.6 69 79 77 ...
##  $ Gender                                                          : Factor w/ 2 levels "Female","Male": 1 2 1 1 2 1 2 1 1 1 ...
##  $ STATE                                                           : Factor w/ 9 levels "Central Zone",..: 1 1 1 1 1 2 2 2 2 2 ...
##  $ Previous_Degree                                                 : Factor w/ 6 levels "Arts","Commerce",..: 2 2 2 2 2 2 2 2 2 2 ...
##  $ Fathers_qualification                                           : Factor w/ 9 levels "CA/CS","DIPLOMA",..: 9 9 9 7 9 9 9 9 9 9 ...
##  $ Mothers_qualification                                           : Factor w/ 7 levels "DIPLOMA","HSC",..: 5 5 7 5 7 5 6 7 7 7 ...
##  $ Fathers_occupation                                              : Factor w/ 7 levels "Farming","Not Alive",..: 4 6 6 6 6 6 6 6 6 6 ...
##  $ Mothers_occupation                                              : Factor w/ 4 levels "House wife","Professional Job",..: 2 2 1 1 2 2 1 1 1 1 ...
##  $ Marital_status                                                  : Factor w/ 2 levels "Married","Single": 2 2 2 2 2 2 2 2 2 2 ...
##  $ Place_you_belong_to                                             : Factor w/ 3 levels "Rural","Semi Urban",..: 3 2 3 3 3 1 3 2 3 3 ...
##  $ Total_Family_Income_per_annum                                   : Factor w/ 6 levels "0-3 Lakh","10-15 lakh",..: 4 1 4 1 6 6 5 5 1 4 ...
##  $ Funding_for_the_MBA_Program                                     : Factor w/ 6 levels "Family","Loan",..: 3 4 1 3 4 3 5 1 2 3 ...
##  $ Work_Experience                                                 : Factor w/ 6 levels "1-2 year","2-3 year",..: 6 6 6 1 6 5 1 6 6 6 ...
##  $ Career_options_after_MBA                                        : Factor w/ 5 levels "Family Business",..: 3 3 3 3 3 3 5 3 3 2 ...
##  $ Alternate_Career_Option_after_MBA_if_not_selected_through_Instit: Factor w/ 5 levels "Family Business",..: 3 5 3 3 5 5 2 5 3 2 ...
##  $ perceivedscorecat                                               : Factor w/ 3 levels "desired skills",..: 3 2 2 1 1 2 2 2 2 2 ...

dim(mbaper_zone$STATE)

## NULL

head(mbaper_zone$STATE)

## [1] Central Zone Central Zone Central Zone Central Zone Central Zone
## [6] East Zone   
## 9 Levels: Central Zone East Zone GOA GUJARAT Nepal ... west Zone

mbaper_zone<-filter(mbaper, STATE=="North East Zone" , Previous_Degree=="Commerce")

str(mbaper_zone)

## 'data.frame':    3 obs. of  19 variables:
##  $ Age_in_years_completed                                          : int  23 21 25
##  $ Percentage_in_10_Class                                          : num  75 68 71.7
##  $ Percentage_in_12_Class                                          : num  74 78 90
##  $ Percentage_in_Under_Graduate                                    : num  67 65 73
##  $ Gender                                                          : Factor w/ 2 levels "Female","Male": 2 1 1
##  $ STATE                                                           : Factor w/ 9 levels "Central Zone",..: 6 6 6
##  $ Previous_Degree                                                 : Factor w/ 6 levels "Arts","Commerce",..: 2 2 2
##  $ Fathers_qualification                                           : Factor w/ 9 levels "CA/CS","DIPLOMA",..: 2 9 9
##  $ Mothers_qualification                                           : Factor w/ 7 levels "DIPLOMA","HSC",..: 1 6 7
##  $ Fathers_occupation                                              : Factor w/ 7 levels "Farming","Not Alive",..: 4 6 7
##  $ Mothers_occupation                                              : Factor w/ 4 levels "House wife","Professional Job",..: 2 1 1
##  $ Marital_status                                                  : Factor w/ 2 levels "Married","Single": 2 2 2
##  $ Place_you_belong_to                                             : Factor w/ 3 levels "Rural","Semi Urban",..: 3 1 3
##  $ Total_Family_Income_per_annum                                   : Factor w/ 6 levels "0-3 Lakh","10-15 lakh",..: 6 2 2
##  $ Funding_for_the_MBA_Program                                     : Factor w/ 6 levels "Family","Loan",..: 4 1 1
##  $ Work_Experience                                                 : Factor w/ 6 levels "1-2 year","2-3 year",..: 6 6 2
##  $ Career_options_after_MBA                                        : Factor w/ 5 levels "Family Business",..: 3 4 3
##  $ Alternate_Career_Option_after_MBA_if_not_selected_through_Instit: Factor w/ 5 levels "Family Business",..: 3 4 3
##  $ perceivedscorecat                                               : Factor w/ 3 levels "desired skills",..: 2 2 1

dim(mbaper_zone$STATE)

we can use ==, >, >= &, |, !, xor(), between(), near()

head(mbaper_zone$STATE)

## [1] North East Zone North East Zone North East Zone
## 9 Levels: Central Zone East Zone GOA GUJARAT Nepal ... west Zone

#-------------------------------------#

Select columns and then subset data based on a condition, combination of rows and variables

mbaper_age<-select(mbaper, Age_in_years_completed)

str(mbaper_age)

## 'data.frame':    273 obs. of  1 variable:
##  $ Age_in_years_completed: int  22 26 24 22 22 26 22 20 22 25 ...

dim(mbaper_age)

## [1] 273   1

head(mbaper_age)

##   Age_in_years_completed
## 1                     22
## 2                     26
## 3                     24
## 4                     22
## 5                     22
## 6                     26

mbaper_age<-filter(select(mbaper, Age_in_years_completed),Age_in_years_completed==25)

str(mbaper_age)

## 'data.frame':    22 obs. of  1 variable:
##  $ Age_in_years_completed: int  25 25 25 25 25 25 25 25 25 25 ...

dim(mbaper_age)

## [1] 22  1

head(mbaper_age)

##   Age_in_years_completed
## 1                     25
## 2                     25
## 3                     25
## 4                     25
## 5                     25
## 6                     25

use of pipe function

1:8 %>% sum

## [1] 36

1:8 %>% sum %>% sqrt

## [1] 6

1:8 %>% sum %>% sqrt%>% sum*10

## [1] 60

#---------------------------------#

mbaper_age<-select(mbaper, Age_in_years_completed) %>%

  filter(Age_in_years_completed==22)

str(mbaper_age)

## 'data.frame':    70 obs. of  1 variable:
##  $ Age_in_years_completed: int  22 22 22 22 22 22 22 22 22 22 ...

dim(mbaper_age)

## [1] 70  1

head(mbaper_age)

##   Age_in_years_completed
## 1                     22
## 2                     22
## 3                     22
## 4                     22
## 5                     22
## 6                     22

mbaper_age<-select(mbaper, Age_in_years_completed) %>%

  arrange(Age_in_years_completed)



mbaper_age<-select(mbaper, Age_in_years_completed) %>%

  arrange(-Age_in_years_completed)

we can also use, starts_with(), ends_with(), contains() example select(mbaper,starts_with("percentage")