Basics of R- Session 6- Data Visualization -1 library ggplot2

Dr Manohar Kapse

19 March 2019

Use Libraries graphics and ggplot

library(graphics)
library(ggplot2)

#Import the file- MBAdata.csv and save as an R object mbaper
# import the file from the location-

mbaper<-read.csv("D:/1 Teaching Material/R/importfile/MBAdata.csv")

# study the data which is imported
str(mbaper)

## 'data.frame':    273 obs. of  19 variables:
##  $ Age_in_years_completed                                          : int  23 21 23 25 22 26 24 22 22 26 ...
##  $ Percentage_in_10_Class                                          : num  75 68 89.3 71.7 91.2 ...
##  $ Percentage_in_12_Class                                          : num  74 78 84.6 90 91.2 ...
##  $ Percentage_in_Under_Graduate                                    : num  67 65 66.4 73 70 ...
##  $ Gender                                                          : Factor w/ 2 levels "Female","Male": 2 1 2 1 1 1 1 2 2 2 ...
##  $ STATE                                                           : Factor w/ 10 levels "Central Zone",..: 6 6 6 6 1 1 1 1 1 1 ...
##  $ Previous_Degree                                                 : Factor w/ 6 levels "Arts","Commerce",..: 2 2 3 2 2 3 3 3 3 3 ...
##  $ Fathers_qualification                                           : Factor w/ 9 levels "CA/CS","DIPLOMA",..: 2 9 9 9 9 5 7 7 9 9 ...
##  $ Mothers_qualification                                           : Factor w/ 7 levels "DIPLOMA","HSC",..: 1 6 2 7 5 5 2 7 7 7 ...
##  $ Fathers_occupation                                              : Factor w/ 7 levels "Farming","Not Alive",..: 4 6 5 7 4 2 4 4 4 7 ...
##  $ Mothers_occupation                                              : Factor w/ 4 levels "House wife","Professional Job",..: 2 1 1 1 2 1 1 2 1 1 ...
##  $ Marital_status                                                  : Factor w/ 2 levels "Married","Single": 2 2 2 2 2 1 2 2 2 2 ...
##  $ Place_you_belong_to                                             : Factor w/ 3 levels "Rural","Semi Urban",..: 3 1 2 3 3 3 3 2 3 2 ...
##  $ Total_Family_Income_per_annum                                   : Factor w/ 6 levels "0-3 Lakh","10-15 lakh",..: 6 2 4 2 4 1 2 6 6 3 ...
##  $ Funding_for_the_MBA_Program                                     : Factor w/ 6 levels "Family","Loan",..: 4 1 1 1 3 1 2 3 1 1 ...
##  $ Work_Experience                                                 : Factor w/ 6 levels "1-2 year","2-3 year",..: 6 6 6 2 6 4 6 6 6 2 ...
##  $ Career_options_after_MBA                                        : Factor w/ 5 levels "Family Business",..: 3 4 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 4 3 3 3 3 3 3 3 2 ...
##  $ perceivedscorecat                                               : Factor w/ 3 levels "desired skills",..: 2 2 2 1 3 2 2 2 2 1 ...

# fix(mbaper)
dim(mbaper)

## [1] 273  19

summary(mbaper)

##  Age_in_years_completed Percentage_in_10_Class Percentage_in_12_Class
##  Min.   :19.00          Min.   :56.00          Min.   :57.00         
##  1st Qu.:21.00          1st Qu.:77.90          1st Qu.:73.60         
##  Median :22.00          Median :84.50          Median :82.00         
##  Mean   :22.41          Mean   :83.32          Mean   :80.57         
##  3rd Qu.:24.00          3rd Qu.:89.76          3rd Qu.:88.00         
##  Max.   :28.00          Max.   :97.20          Max.   :97.17         
##                                                                      
##  Percentage_in_Under_Graduate    Gender                STATE    
##  Min.   :58.00                Female:120   south zone     :140  
##  1st Qu.:67.10                Male  :153   North Zone     : 55  
##  Median :72.83                             East Zone      : 39  
##  Mean   :73.35                             Central Zone   : 20  
##  3rd Qu.:78.60                             west Zone      :  9  
##  Max.   :94.00                             North East Zone:  4  
##                                            (Other)        :  6  
##     Previous_Degree               Fathers_qualification
##  Arts       :  4    Under Graduate           :156      
##  Commerce   :101    Post Graduation          : 60      
##  Engineering:108    HSC                      : 20      
##  Journalism :  1    no formal Education      : 12      
##  Management : 36    DIPLOMA                  : 10      
##  Science    : 23    PhD or higher qualificati:  5      
##                     (Other)                  : 10      
##                Mothers_qualification        Fathers_occupation
##  DIPLOMA                  :  4       Farming         : 12     
##  HSC                      : 29       Not Alive       :  4     
##  no formal Education      : 15       others          :  3     
##  PhD or higher qualificati:  4       Professional Job:101     
##  Post Graduation          : 61       RETIRED         :  9     
##  SSC                      : 21       Self employed   :118     
##  Under Graduate           :139       Technical Job   : 26     
##         Mothers_occupation Marital_status Place_you_belong_to
##  House wife      :176      Married:  7    Rural     : 24     
##  Professional Job: 74      Single :266    Semi Urban: 62     
##  Self employed   : 16                     Urban     :187     
##  Technical Job   :  7                                        
##                                                              
##                                                              
##                                                              
##    Total_Family_Income_per_annum  Funding_for_the_MBA_Program
##  0-3 Lakh         :50            Family         :118         
##  10-15 lakh       :30            Loan           : 49         
##  15 lakh and above:24            Loan and family: 44         
##  3-5 Lakh         :56            Loan and self  : 22         
##  5-7 Lakh         :56            Self           : 35         
##  7- 10 Lakh       :57            Self and Family:  5         
##                                                              
##          Work_Experience              Career_options_after_MBA
##  1-2 year        : 45    Family Business          :  2        
##  2-3 year        : 33    Higher Studies           :  2        
##  3-4 year        :  6    Job                      :252        
##  4-5 year        :  2    Not yet decided          :  4        
##  less than 1 year: 25    Self-employed/ entreprene: 13        
##  no experience   :162                                         
##                                                               
##  Alternate_Career_Option_after_MBA_if_not_selected_through_Instit
##  Family Business          : 12                                   
##  Higher Studies           : 30                                   
##  Job                      :135                                   
##  Not yet decided          : 24                                   
##  Self-employed/ entreprene: 72                                   
##                                                                  
##                                                                  
##        perceivedscorecat
##  desired skills : 93    
##  prefered skills:172    
##  required skills:  8    
##                         
##                         
##                         
## 

descr::descr(mbaper)

## 
## Age_in_years_completed
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   19.00   21.00   22.00   22.41   24.00   28.00 
## 
## Percentage_in_10_Class
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   56.00   77.90   84.50   83.32   89.76   97.20 
## 
## Percentage_in_12_Class
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   57.00   73.60   82.00   80.57   88.00   97.17 
## 
## Percentage_in_Under_Graduate
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   58.00   67.10   72.83   73.35   78.60   94.00 
## 
## Gender
## Female   Male 
##    120    153 
## 
## STATE
##    Central Zone       East Zone             GOA         GUJARAT 
##              20              39               1               2 
##           Nepal North East Zone      North Zone      North ZOne 
##               1               4              55               2 
##      south zone       west Zone 
##             140               9 
## 
## Previous_Degree
##        Arts    Commerce Engineering  Journalism  Management     Science 
##           4         101         108           1          36          23 
## 
## Fathers_qualification
##                     CA/CS                   DIPLOMA 
##                         3                        10 
##                       HSC       no formal Education 
##                        20                        12 
##                 Not Alive PhD or higher qualificati 
##                         3                         5 
##           Post Graduation                       SSC 
##                        60                         4 
##            Under Graduate 
##                       156 
## 
## Mothers_qualification
##                   DIPLOMA                       HSC 
##                         4                        29 
##       no formal Education PhD or higher qualificati 
##                        15                         4 
##           Post Graduation                       SSC 
##                        61                        21 
##            Under Graduate 
##                       139 
## 
## Fathers_occupation
##          Farming        Not Alive           others Professional Job 
##               12                4                3              101 
##          RETIRED    Self employed    Technical Job 
##                9              118               26 
## 
## Mothers_occupation
##       House wife Professional Job    Self employed    Technical Job 
##              176               74               16                7 
## 
## Marital_status
## Married  Single 
##       7     266 
## 
## Place_you_belong_to
##      Rural Semi Urban      Urban 
##         24         62        187 
## 
## Total_Family_Income_per_annum
##          0-3 Lakh        10-15 lakh 15 lakh and above          3-5 Lakh 
##                50                30                24                56 
##          5-7 Lakh        7- 10 Lakh 
##                56                57 
## 
## Funding_for_the_MBA_Program
##          Family            Loan Loan and family   Loan and self 
##             118              49              44              22 
##            Self Self and Family 
##              35               5 
## 
## Work_Experience
##         1-2 year         2-3 year         3-4 year         4-5 year 
##               45               33                6                2 
## less than 1 year    no experience 
##               25              162 
## 
## Career_options_after_MBA
##           Family Business            Higher Studies 
##                         2                         2 
##                       Job           Not yet decided 
##                       252                         4 
## Self-employed/ entreprene 
##                        13 
## 
## Alternate_Career_Option_after_MBA_if_not_selected_through_Instit
##           Family Business            Higher Studies 
##                        12                        30 
##                       Job           Not yet decided 
##                       135                        24 
## Self-employed/ entreprene 
##                        72 
## 
## perceivedscorecat
##  desired skills prefered skills required skills 
##              93             172               8

for missing observations we will use an.omit so that all the observations with missing values will be omitted. If there are missing observation there will be a problem in using the commands

mbaper<-na.omit(mbaper)

# check the number of omitted observations

dim(mbaper)

## [1] 273  19

#convert all the categorical variables into factor

# first remove the missing values then convert to factor, as na may be converted to factor/ categories

mbaper$Gender<-as.factor(mbaper$Gender)

mbaper$STATE<-as.factor(mbaper$STATE)

mbaper$Previous_Degree<-as.factor(mbaper$Previous_Degree)

mbaper$perceivedscorecat<-as.factor(mbaper$perceivedscorecat)

mbaper$Marital_status<-as.factor(mbaper$Marital_status)

mbaper$Place_you_belong_to<-as.factor(mbaper$Place_you_belong_to)

#Study the data using graphs and charts

code for ggplot

args(ggplot)

ggplot(df, aes(x, y, ))

#single scale variable-

# 10th percentage of student

library(ggplot2)
ggplot(mbaper, aes(mbaper$Percentage_in_10_Class))+geom_dotplot()

## `stat_bindot()` using `bins = 30`. Pick better value with `binwidth`.

ggplot(mbaper, aes(mbaper$Percentage_in_10_Class))+geom_histogram()

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

ggplot(mbaper, aes(mbaper$Percentage_in_10_Class))+geom_freqpoly()

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

ggplot(mbaper, aes(mbaper$Percentage_in_10_Class))+geom_density()

# density plot is an alternative of Histogram

12th percentage of student

ggplot(mbaper, aes(mbaper$Percentage_in_12_Class))+geom_histogram()

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

ggplot(mbaper, aes(mbaper$Percentage_in_12_Class))+geom_freqpoly()

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

ggplot(mbaper, aes(mbaper$Percentage_in_12_Class))+geom_density()

# density plot is an alternative of Histogram

#two scale variables

ggplot(mbaper, aes(mbaper$Percentage_in_12_Class, mbaper$Percentage_in_10_Class))+ geom_point()

ggplot(mbaper, aes(mbaper$Percentage_in_12_Class, mbaper$Percentage_in_10_Class))+ geom_jitter()

ggplot(mbaper, aes(mbaper$Percentage_in_12_Class, mbaper$Percentage_in_10_Class))+ geom_line()

ggplot(mbaper, aes(mbaper$Percentage_in_12_Class, mbaper$Percentage_in_10_Class))+geom_smooth()

## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

ggplot(mbaper, aes(mbaper$Percentage_in_12_Class, mbaper$Percentage_in_10_Class))+ geom_bin2d()

single categorical data

ggplot(mbaper, aes(mbaper$Gender))+geom_bar()

ggplot(mbaper, aes(mbaper$Previous_Degree))+ geom_bar()

ggplot(mbaper, aes(mbaper$STATE))+ geom_bar()

two categorical variable

adding one more categorical variable- use fill

ggplot(mbaper, aes(mbaper$Gender, fill=mbaper$Marital_status))+ geom_bar()

ggplot(mbaper, aes(mbaper$Gender, fill=mbaper$Place_you_belong_to))+ geom_bar()

in geom_bar use position for different types of bar graph

ggplot(mbaper, aes(mbaper$Gender, fill= mbaper$Place_you_belong_to))+ geom_bar(position = "dodge")

ggplot(mbaper, aes(mbaper$Gender, fill= mbaper$Place_you_belong_to))+ geom_bar(position = "stack")

ggplot(mbaper, aes(mbaper$Gender, fill= mbaper$Place_you_belong_to))+ geom_bar(position = "fill")

Instead of Bar graphs we can use mosaic

ggplot(mbaper, aes(mbaper$Gender, mbaper$Previous_Degree))+ geom_bin2d()

use facet to add layer

ggplot(mbaper, aes(mbaper$Gender, fill=mbaper$Place_you_belong_to))+ geom_bar()+facet_grid(~mbaper$Previous_Degree)

ggplot(mbaper, aes(mbaper$Gender, fill=mbaper$Place_you_belong_to))+ geom_bar()+facet_wrap(~mbaper$Previous_Degree)

can add multiple layears

ggplot(mbaper, aes(mbaper$Gender, fill=mbaper$Place_you_belong_to))+ geom_bar()+facet_grid(~mbaper$Previous_Degree+mbaper$Marital_status)

Note: In the Code we dont have to write the name of the data file again and again

Example:-

ggplot(mbaper, aes(Gender, fill=Place_you_belong_to))+ geom_bar()+facet_grid(~Previous_Degree+Marital_status)