Skills Drill 1
Anika
3/3/2021
Step 1
library(ggplot2)
library(gapminder)
library(readr)
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, unionStep 2
drug_data<-read.csv("/Volumes/NO NAME/Data 333/SkillsDrill1Data.csv")Step 3
head(drug_data)## marij_ever marij_month marij_year cocaine_ever
## 1 1 Used Marijuana Past 30 days 1 1
## 2 0 Did not use Marijuana Past 30 days 0 0
## 3 1 Did not use Marijuana Past 30 days 0 0
## 4 0 Did not use Marijuana Past 30 days 0 0
## 5 0 Did not use Marijuana Past 30 days 0 0
## 6 0 Did not use Marijuana Past 30 days 0 0
## cocaine_month cocaine_year crack_ever crack_month
## 1 Did not use Cocaine Past 30 days 0 1 0
## 2 Did not use Cocaine Past 30 days 0 0 0
## 3 Did not use Cocaine Past 30 days 0 0 0
## 4 Did not use Cocaine Past 30 days 0 0 0
## 5 Did not use Cocaine Past 30 days 0 0 0
## 6 Did not use Cocaine Past 30 days 0 0 0
## crack_year heroin_ever heroin_month heroin_year hallucinogen_ever
## 1 0 0 0 0 1
## 2 0 0 0 0 0
## 3 0 0 0 0 0
## 4 0 0 0 0 0
## 5 0 0 0 0 0
## 6 0 0 0 0 0
## hallucinogen_month hallucinogen_year inhalant_ever inhalant_month
## 1 0 1 0 0
## 2 0 0 0 0
## 3 0 0 0 0
## 4 0 0 0 0
## 5 0 0 0 0
## 6 0 0 0 0
## inhalant_year meth_ever meth_month meth_year painrelieve_ever
## 1 0 0 0 0 0
## 2 0 0 0 0 0
## 3 0 0 0 0 0
## 4 0 0 0 0 0
## 5 0 0 0 0 0
## 6 0 0 0 0 0
## painrelieve_month painrelieve_year tranq_ever tranq_month tranq_year
## 1 0 0 0 0 0
## 2 0 0 0 0 0
## 3 0 0 0 0 0
## 4 0 0 0 0 0
## 5 0 0 0 0 0
## 6 0 0 0 0 0
## stimulant_ever stimulant_month stimulant_year sedative_ever sedative_month
## 1 0 0 0 0 0
## 2 0 0 0 0 0
## 3 0 0 0 0 0
## 4 0 0 0 0 0
## 5 0 0 0 0 0
## 6 0 0 0 0 0
## sedative_year anydrugever pharmamonth
## 1 0 1 Did not use Pharmaceutical Narcotics Past 30 days
## 2 0 0 Did not use Pharmaceutical Narcotics Past 30 days
## 3 0 1 Did not use Pharmaceutical Narcotics Past 30 days
## 4 0 0 Did not use Pharmaceutical Narcotics Past 30 days
## 5 0 0 Did not use Pharmaceutical Narcotics Past 30 days
## 6 0 0 Did not use Pharmaceutical Narcotics Past 30 days
## nonpharmamonth nonpharmamonth_nomj anydrugmonth anydrugyear anydrugever_nomj
## 1 1 0 1 1 1
## 2 0 0 0 0 0
## 3 0 0 0 0 0
## 4 0 0 0 0 0
## 5 0 0 0 0 0
## 6 0 0 0 0 0
## anydrugmonth_nomj anydrugyear_nomj countofdrugs_ever countofdrugs_month
## 1 0 1 4 1
## 2 0 0 0 0
## 3 0 0 1 0
## 4 0 0 0 0
## 5 0 0 0 0
## 6 0 0 0 0
## countofdrugs_year SelectiveLeave SkipSick
## 1 2 0 0
## 2 0 0 0
## 3 0 0 0
## 4 0 0 0
## 5 0 2 2
## 6 0 0 0Step 4
drug_data %>%
select(cocaine_month,SelectiveLeave) %>%
rename(DaysSkippedWork = SelectiveLeave) %>%
filter(DaysSkippedWork<31) %>%
summarize(meanDaysSkippedWork=mean(DaysSkippedWork))## meanDaysSkippedWork
## 1 0.3272463Step 5
drug_data %>%
select(cocaine_month,SelectiveLeave) %>%
rename(DaysSkippedWork = SelectiveLeave) %>%
filter(DaysSkippedWork<31) %>%
group_by((cocaine_month)) %>%
summarize(meanDaysSkippedWork=mean(DaysSkippedWork))## # A tibble: 2 x 2
## `(cocaine_month)` meanDaysSkippedWork
## * <chr> <dbl>
## 1 Did not use Cocaine Past 30 days 0.322
## 2 Used Cocaine Past 30 days 0.85Step 6
- Employees that used cocaine within the last 30 days skipped almost 3x as many days of work (2.65 is more accurate) when compared to employees that did not use it.
Step 7
drug_data %>%
select(cocaine_month,SelectiveLeave) %>%
rename(DaysSkippedWork = SelectiveLeave) %>%
filter(DaysSkippedWork<31) %>%
group_by(cocaine_month) %>%
summarize(meanDaysSkippedWork=mean(DaysSkippedWork)) %>%
ggplot() +
geom_col(aes(x=cocaine_month, y=meanDaysSkippedWork, fill=(meanDaysSkippedWork)))
Extra credit
drug_data %>%
select(marij_month,SelectiveLeave) %>%
rename(DaysSkippedWork = SelectiveLeave) %>%
filter(DaysSkippedWork<31) %>%
group_by(marij_month) %>%
summarize(meanDaysSkippedWork=mean(DaysSkippedWork)) %>%
ggplot() +
geom_col(aes(x=marij_month, y=meanDaysSkippedWork, fill=(meanDaysSkippedWork)))
Interpretation
- Employees that used marijuana were more likely to skip work when compared to workers that did not use it.