518 date & time exercise

Exercise1

library(lubridate)

## 
## Attaching package: 'lubridate'

## The following object is masked from 'package:base':
## 
##     date

startDate <- dmy("10-September-2019")
endDate <- dmy("18-May-2020")
endDate - startDate

## Time difference of 251 days

Exercise2

dta2 <- read.table("/Users/fightk/Downloads/calls_nyc (1).csv",sep=",", header = T)
str(dta2)

## 'data.frame':    24 obs. of  2 variables:
##  $ Hour : num  0.5 1.5 2.5 3.5 4.5 5.5 6.5 7.5 8.5 9.5 ...
##  $ Calls: int  1080 910 770 780 380 390 200 300 275 395 ...

library(knitr)
knitr::kable(head(dta2))

library(ggplot2)
dta2$Hour <- as.integer((dta2$Hour))
ggplot(data= dta2, aes(x= Hour, y= Calls))+
  geom_bar(stat = "identity", fill="cyan", color="gray", alpha=.2)+
  geom_abline(intercept = mean(dta2$Calls), slope=0, color="pink")+
  scale_x_time(breaks = 0:23 - .5,
               labels = c(0,  rep('', 4), 5, rep('', 4), 10, rep('', 4),
               15, rep('', 4), 20, rep('', 3)))+
  coord_polar(theta = 'x', start = -pi/24)+
  theme_bw()+
  theme(panel.grid.minor.x = element_blank(), 
        panel.grid.major.x = element_blank())

Exercise3

db_liu <- as.Date("1994/10/20")
dd_liu <- as.Date("2094/10/20")

bDays <- seq(from=db_liu, to=dd_liu, by="years")

data <-data.frame(table(weekdays(bDays)))
library(tidyverse)

## ─ Attaching packages ────── tidyverse 1.3.0 ─

## ✓ tibble  2.1.3     ✓ dplyr   0.8.5
## ✓ tidyr   1.0.2     ✓ stringr 1.4.0
## ✓ readr   1.3.1     ✓ forcats 0.5.0
## ✓ purrr   0.3.3

## ─ Conflicts ─────── tidyverse_conflicts() ─
## x lubridate::as.difftime() masks base::as.difftime()
## x lubridate::date()        masks base::date()
## x dplyr::filter()          masks stats::filter()
## x lubridate::intersect()   masks base::intersect()
## x dplyr::lag()             masks stats::lag()
## x lubridate::setdiff()     masks base::setdiff()
## x lubridate::union()       masks base::union()

names(data) <- c("weekdays", "Freq")
ggplot(data, aes(x=weekdays, y=Freq)) +
  geom_segment( aes(x=weekdays, xend=weekdays, y=0, yend=Freq)) +
  geom_point( size=5, color="yellow", fill=alpha("black", 0.3), alpha=0.7, shape=21, stroke=2) 

Erxercise4

dta4 <- read.table("/Users/fightk/Desktop/birth_college.txt", header = T)
str(dta4)

## 'data.frame':    29 obs. of  2 variables:
##  $ Birth   : num  23 22.1 20.6 19.6 18 15.9 16 17.2 15.7 16.6 ...
##  $ Entrance: int  NA NA NA NA NA NA NA NA NA NA ...

summary(dta4)

##      Birth          Entrance    
##  Min.   : 8.30   Min.   :44.00  
##  1st Qu.:11.00   1st Qu.:59.50  
##  Median :15.30   Median :70.50  
##  Mean   :14.41   Mean   :72.25  
##  3rd Qu.:16.00   3rd Qu.:89.50  
##  Max.   :23.00   Max.   :97.00  
##                  NA's   :13

colnames(dta4) <- c("Birth","College")
head(dta4)

dta4$Year <- c(1981:2009)
dta4 <- as.data.frame(dta4)
tail(dta4)

library(ggplot2)
ggplot(data=dta4)+
  geom_point(data=dta4, aes(x=Year, y=Birth),pch=1)  +
  scale_x_continuous(name="Year",  breaks=seq(1980, 2010, 5))+
  scale_y_continuous(name= "Birth rate(0.1%)", limits=c(0, 60), breaks=seq(0, 60, 10), 
sec.axis=sec_axis(~.+40, breaks = seq(40, 100, 10), name="Acceptance rate(%)")) +
  geom_point(data=dta4, aes(x=Year, y= College),pch=19) +
  guides(fill=T)

## Warning: Removed 22 rows containing missing values (geom_point).