#call datasets from dslabs and list them
data(package="dslabs")
list.files(system.file("script", package = "dslabs"))
## [1] "make-admissions.R"
## [2] "make-brca.R"
## [3] "make-brexit_polls.R"
## [4] "make-death_prob.R"
## [5] "make-divorce_margarine.R"
## [6] "make-gapminder-rdas.R"
## [7] "make-greenhouse_gases.R"
## [8] "make-historic_co2.R"
## [9] "make-mnist_27.R"
## [10] "make-movielens.R"
## [11] "make-murders-rda.R"
## [12] "make-na_example-rda.R"
## [13] "make-nyc_regents_scores.R"
## [14] "make-olive.R"
## [15] "make-outlier_example.R"
## [16] "make-polls_2008.R"
## [17] "make-polls_us_election_2016.R"
## [18] "make-reported_heights-rda.R"
## [19] "make-research_funding_rates.R"
## [20] "make-stars.R"
## [21] "make-temp_carbon.R"
## [22] "make-tissue-gene-expression.R"
## [23] "make-trump_tweets.R"
## [24] "make-weekly_us_contagious_diseases.R"
## [25] "save-gapminder-example-csv.R"
#call death probability dataframe from dslabs
data("death_prob")
#create csv file from death probability dataframe
write_csv(death_prob, "death_prob", na="")
#split dataframe into male and female
male <- death_prob %>% filter(sex == "Male")
female <- death_prob %>% filter(sex == "Female")
#create average probability between genders
unisex <- (male + female) / 2
## Warning in Ops.factor(left, right): '+' not meaningful for factors
#merge dataframes
death_prob <- rbind(unisex, death_prob)
#rename variable:
colnames(death_prob) <- c("Age", "Sex", "Probability")
#select non NA values:
death_prob <- death_prob %>% filter(Sex == "Male" | Sex == "Female")
#create plot
a <- ggplot(death_prob, aes(x = Age, y = Probability, colour = Sex)) + geom_line() + geom_point() +
xlab("Age") +
ylab("Probability of Death") +
ggtitle("Death Probability by Age") +
theme_minimal()
#display plot
a
