data(cars)
median_speed <- median(cars$speed)
median_speed## [1] 15#install.packages("jsonlite")
library("jsonlite")
url <- "https://min-api.cryptocompare.com/data/v2/histoday?fsym=BTC&tsym=USD&limit=100"
response <- fromJSON(url)
btc_data <- response$Data$Data
str(btc_data)## 'data.frame': 101 obs. of 9 variables:
## $ time : int 1721520000 1721606400 1721692800 1721779200 1721865600 1721952000 1722038400 1722124800 1722211200 1722297600 ...
## $ high : num 68371 68491 67775 67121 66154 ...
## $ low : num 65841 66595 65466 65112 63429 ...
## $ open : num 67164 68177 67568 65940 65376 ...
## $ volumefrom : num 18123 26713 29466 21576 29473 ...
## $ volumeto : num 1.22e+09 1.81e+09 1.96e+09 1.43e+09 1.90e+09 ...
## $ close : num 68177 67568 65940 65376 65794 ...
## $ conversionType : chr "direct" "direct" "direct" "direct" ...
## $ conversionSymbol: chr "" "" "" "" ...max_close_price <- max(btc_data$close, na.rm = TRUE)
print(max_close_price)## [1] 72683.93# Maximum daily close price is $69,020.94Question 3
Identify a topic of interest and give your project a name/title. –> Remote Work & its Impact on Mental Health
Phrase 3-5 research questions you would like to explore. 1. How has the shift to remote work affected employee productivity across various industries? 2. What industries have the most impact on employee mental health? 3. Are there differences in productivity levels between full-time remote workers and hybrid workers?
List the data sources that your find that are relevant with your research questions. https://www.kaggle.com/datasets/waqi786/remote-work-and-mental-health
Describe your data extracted, statistically and/or visually. - Our dataset includes variables such as work location, industry, stress level, age, number of virtual meetings, and social isolation rating.
remote_work_mental_health <- read.csv("Impact_of_Remote_Work_on_Mental_Health.csv")
#View(remote_work_mental_health)
summary(remote_work_mental_health)## Employee_ID Age Gender Job_Role
## Length:5000 Min. :22 Length:5000 Length:5000
## Class :character 1st Qu.:31 Class :character Class :character
## Mode :character Median :41 Mode :character Mode :character
## Mean :41
## 3rd Qu.:51
## Max. :60
## Industry Years_of_Experience Work_Location
## Length:5000 Min. : 1.00 Length:5000
## Class :character 1st Qu.: 9.00 Class :character
## Mode :character Median :18.00 Mode :character
## Mean :17.81
## 3rd Qu.:26.00
## Max. :35.00
## Hours_Worked_Per_Week Number_of_Virtual_Meetings Work_Life_Balance_Rating
## Min. :20.00 Min. : 0.000 Min. :1.000
## 1st Qu.:29.00 1st Qu.: 4.000 1st Qu.:2.000
## Median :40.00 Median : 8.000 Median :3.000
## Mean :39.61 Mean : 7.559 Mean :2.984
## 3rd Qu.:50.00 3rd Qu.:12.000 3rd Qu.:4.000
## Max. :60.00 Max. :15.000 Max. :5.000
## Stress_Level Mental_Health_Condition Access_to_Mental_Health_Resources
## Length:5000 Length:5000 Length:5000
## Class :character Class :character Class :character
## Mode :character Mode :character Mode :character
##
##
##
## Productivity_Change Social_Isolation_Rating Satisfaction_with_Remote_Work
## Length:5000 Min. :1.000 Length:5000
## Class :character 1st Qu.:2.000 Class :character
## Mode :character Median :3.000 Mode :character
## Mean :2.994
## 3rd Qu.:4.000
## Max. :5.000
## Company_Support_for_Remote_Work Physical_Activity Sleep_Quality
## Min. :1.000 Length:5000 Length:5000
## 1st Qu.:2.000 Class :character Class :character
## Median :3.000 Mode :character Mode :character
## Mean :3.008
## 3rd Qu.:4.000
## Max. :5.000
## Region
## Length:5000
## Class :character
## Mode :character
##
##
## 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, unionlibrary(tidyr)
str(remote_work_mental_health)## 'data.frame': 5000 obs. of 20 variables:
## $ Employee_ID : chr "EMP0001" "EMP0002" "EMP0003" "EMP0004" ...
## $ Age : int 32 40 59 27 49 59 31 42 56 30 ...
## $ Gender : chr "Non-binary" "Female" "Non-binary" "Male" ...
## $ Job_Role : chr "HR" "Data Scientist" "Software Engineer" "Software Engineer" ...
## $ Industry : chr "Healthcare" "IT" "Education" "Finance" ...
## $ Years_of_Experience : int 13 3 22 20 32 31 24 6 9 28 ...
## $ Work_Location : chr "Hybrid" "Remote" "Hybrid" "Onsite" ...
## $ Hours_Worked_Per_Week : int 47 52 46 32 35 39 51 54 24 57 ...
## $ Number_of_Virtual_Meetings : int 7 4 11 8 12 3 7 7 4 6 ...
## $ Work_Life_Balance_Rating : int 2 1 5 4 2 4 3 3 2 1 ...
## $ Stress_Level : chr "Medium" "Medium" "Medium" "High" ...
## $ Mental_Health_Condition : chr "Depression" "Anxiety" "Anxiety" "Depression" ...
## $ Access_to_Mental_Health_Resources: chr "No" "No" "No" "Yes" ...
## $ Productivity_Change : chr "Decrease" "Increase" "No Change" "Increase" ...
## $ Social_Isolation_Rating : int 1 3 4 3 3 5 5 5 2 2 ...
## $ Satisfaction_with_Remote_Work : chr "Unsatisfied" "Satisfied" "Unsatisfied" "Unsatisfied" ...
## $ Company_Support_for_Remote_Work : int 1 2 5 3 3 1 3 4 4 1 ...
## $ Physical_Activity : chr "Weekly" "Weekly" "None" "None" ...
## $ Sleep_Quality : chr "Good" "Good" "Poor" "Poor" ...
## $ Region : chr "Europe" "Asia" "North America" "Europe" ...head(data)##
## 1 function (..., list = character(), package = NULL, lib.loc = NULL,
## 2 verbose = getOption("verbose"), envir = .GlobalEnv, overwrite = TRUE)
## 3 {
## 4 fileExt <- function(x) {
## 5 db <- grepl("\\\\.[^.]+\\\\.(gz|bz2|xz)$", x)
## 6 ans <- sub(".*\\\\.", "", x)sum(is.na(remote_work_mental_health$Work_Location))## [1] 0sum(is.na(remote_work_mental_health$Stress_Level))## [1] 0stress_summary <- remote_work_mental_health %>%
group_by(Work_Location) %>%
summarise(average_stress = mean(Stress_Level, na.rm = TRUE),
count = n()) %>%
arrange(desc(average_stress))## Warning: There were 3 warnings in `summarise()`.
## The first warning was:
## ℹ In argument: `average_stress = mean(Stress_Level, na.rm = TRUE)`.
## ℹ In group 1: `Work_Location = "Hybrid"`.
## Caused by warning in `mean.default()`:
## ! argument is not numeric or logical: returning NA
## ℹ Run `dplyr::last_dplyr_warnings()` to see the 2 remaining warnings.