library(readr)
cherryblossoms <- read_csv("cherry-blossoms.csv")
## Rows: 102 Columns: 2
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## dbl (2): Year, Peak_Bloom
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
cherryblossoms
## # A tibble: 102 × 2
## Year Peak_Bloom
## <dbl> <dbl>
## 1 1921 79
## 2 1922 97
## 3 1923 99
## 4 1924 104
## 5 1925 86
## 6 1926 101
## 7 1927 79
## 8 1928 99
## 9 1929 90
## 10 1930 91
## # ℹ 92 more rows
#The number in the Peak_Bloom column is the number of days from January 1.
paste("The mean number of days to reach peak bloom is", round(mean(cherryblossoms$Peak_Bloom), 1), "days from January 1.")
## [1] "The mean number of days to reach peak bloom is 93.5 days from January 1."
paste("The median number of days to reach peak bloom is", round(median(cherryblossoms$Peak_Bloom), 1),"days from January 1.")
## [1] "The median number of days to reach peak bloom is 94.5 days from January 1."
paste("The correlation between the year and the number of days to reach peak bloom is", round(cor(cherryblossoms$Year, cherryblossoms$Peak_Bloom), 1), ".")
## [1] "The correlation between the year and the number of days to reach peak bloom is -0.3 ."
paste("This means the number of days to reach peak bloom has decreased over the years.")
## [1] "This means the number of days to reach peak bloom has decreased over the years."
summary(cherryblossoms$Peak_Bloom)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 74.00 88.25 94.50 93.51 99.00 108.00
plot(x=cherryblossoms$Year, y=cherryblossoms$Peak_Bloom, type="p", xlab="Year", ylab="Days", main="Days to Reach Peak Bloom", frame.plot=FALSE)