Data Screening

Dataset:

library(readr)
groupProjectDataset<-read_csv("C:/Users/anuraggupta/Desktop/HU/ALNY 506/executive 2/income.csv")

## Parsed with column specification:
## cols(
##   Occupation = col_character(),
##   Industry = col_character(),
##   All_workers = col_double(),
##   All_weekly = col_double(),
##   M_workers = col_double(),
##   M_weekly = col_double(),
##   F_workers = col_double(),
##   F_weekly = col_double()
## )

library(tidyverse)

## -- Attaching packages --------------------------------------------------------------------------------------- tidyverse 1.2.1 --

## v ggplot2 3.1.1       v purrr   0.3.2  
## v tibble  2.1.1       v dplyr   0.8.0.1
## v tidyr   0.8.3       v stringr 1.4.0  
## v ggplot2 3.1.1       v forcats 0.4.0

## -- Conflicts ------------------------------------------------------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

library(dplyr)

str(groupProjectDataset)

## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 535 obs. of  8 variables:
##  $ Occupation : chr  "Chief executives" "General and operations managers" "Legislators" "Advertising and promotions managers" ...
##  $ Industry   : chr  "Management" "Management" "Management" "Management" ...
##  $ All_workers: num  1046 823 8 55 948 ...
##  $ All_weekly : num  2041 1260 NA 1050 1462 ...
##  $ M_workers  : num  763 621 5 29 570 24 96 466 551 7 ...
##  $ M_weekly   : num  2251 1347 NA NA 1603 ...
##  $ F_workers  : num  283 202 4 26 378 35 73 169 573 16 ...
##  $ F_weekly   : num  1836 1002 NA NA 1258 ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   Occupation = col_character(),
##   ..   Industry = col_character(),
##   ..   All_workers = col_double(),
##   ..   All_weekly = col_double(),
##   ..   M_workers = col_double(),
##   ..   M_weekly = col_double(),
##   ..   F_workers = col_double(),
##   ..   F_weekly = col_double()
##   .. )

#hist(groupProjectDataset$All_weekly)

groupProjectDataset <- filter(groupProjectDataset, groupProjectDataset$All_weekly!='NA')

ggplot(data = groupProjectDataset, mapping = aes(x = groupProjectDataset$All_weekly)) + geom_histogram(binwidth =15)+
  xlab("expectability") +
  ylab("positive emotion")