library(dplyr)
##
## 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
library(ggvis)
# get cleaned up data (removed some rows for duplicates, nonsense reponses, etc.)
df <- read.delim("~/Downloads/Copy of Salaries (Responses) - Form Responses 1 (2).tsv")
df %>%
ggvis(~Years.Experience, ~Monthly.Base.Pay) %>%
layer_points() %>%
layer_model_predictions(model = "lm", se = TRUE)
## Guessing formula = Monthly.Base.Pay ~ Years.Experience
df %>%
ggvis(~Years.Company, ~Monthly.Base.Pay) %>%
layer_points() %>%
layer_model_predictions(model = "lm", se = TRUE)
## Guessing formula = Monthly.Base.Pay ~ Years.Company
# Some descriptive stats
df %>%
group_by(Location) %>%
summarise(count = n()) %>%
arrange(desc(count))
## Source: local data frame [45 x 2]
##
## Location count
## (fctr) (int)
## 1 Makati 22
## 2 19
## 3 Quezon City 10
## 4 Manila 9
## 5 Ortigas 6
## 6 Pasig 6
## 7 Cebu 4
## 8 Metro Manila 4
## 9 Philippines 4
## 10 BGC 3
## .. ... ...
desc.count <- df %>%
mutate(Developer = grepl('developer', Job.Title, ignore.case = TRUE)) %>%
mutate(Engineer = grepl('engineer', Job.Title, ignore.case = TRUE)) %>%
mutate(Manager = grepl('manager', Job.Title, ignore.case = TRUE)) %>%
mutate(Artist = grepl('artist', Job.Title, ignore.case = TRUE)) %>%
mutate(Frontend = grepl('frontend', Job.Title, ignore.case = TRUE))
summary(desc.count[,12:16])
## Developer Engineer Manager Artist
## Mode :logical Mode :logical Mode :logical Mode :logical
## FALSE:62 FALSE:105 FALSE:125 FALSE:125
## TRUE :66 TRUE :23 TRUE :3 TRUE :3
## NA's :0 NA's :0 NA's :0 NA's :0
## Frontend
## Mode :logical
## FALSE:127
## TRUE :1
## NA's :0