1. Construct simple barchart for orangeBoardings, purpleBoardings,greenBoardings, bannerBoardings
data1 <- read.csv("Charm_City_Circulator_Ridership.csv")
dim(data1)
## [1] 1146   15
names(data1)
##  [1] "day"              "date"             "orangeBoardings" 
##  [4] "orangeAlightings" "orangeAverage"    "purpleBoardings" 
##  [7] "purpleAlightings" "purpleAverage"    "greenBoardings"  
## [10] "greenAlightings"  "greenAverage"     "bannerBoardings" 
## [13] "bannerAlightings" "bannerAverage"    "daily"
head(data1[1:5])
##         day       date orangeBoardings orangeAlightings orangeAverage
## 1    Monday 01/11/2010             877             1027         952.0
## 2   Tuesday 01/12/2010             777              815         796.0
## 3 Wednesday 01/13/2010            1203             1220        1211.5
## 4  Thursday 01/14/2010            1194             1233        1213.5
## 5    Friday 01/15/2010            1645             1643        1644.0
## 6  Saturday 01/16/2010            1457             1524        1490.5
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, union
orange <- data1 %>% 
  filter(!is.na(orangeBoardings)) %>%
  select(orangeBoardings)
orange$boarding <- "orange"
head(orange)
##   orangeBoardings boarding
## 1             877   orange
## 2             777   orange
## 3            1203   orange
## 4            1194   orange
## 5            1645   orange
## 6            1457   orange
orange2 <- orange$boarding
orange2 <- as.data.frame(orange2)

library(dplyr)
orange2 <- rename(orange2, "boarding" = "orange2")
names(orange2)
## [1] "boarding"
head(orange2)
##   boarding
## 1   orange
## 2   orange
## 3   orange
## 4   orange
## 5   orange
## 6   orange
purple <- data1 %>% 
  filter(!is.na(purpleBoardings)) %>%
  select(purpleBoardings)      
purple$boarding <- "purple"
head(purple)
##   purpleBoardings boarding
## 1            1028   purple
## 2            1327   purple
## 3            1726   purple
## 4            2044   purple
## 5            2230   purple
## 6            1852   purple
purple2 <- purple$boarding
purple2 <- as.data.frame(purple2)

library(dplyr)
purple2 <- rename(purple2, "boarding" = "purple2")
names(purple2)
## [1] "boarding"
head(purple2)
##   boarding
## 1   purple
## 2   purple
## 3   purple
## 4   purple
## 5   purple
## 6   purple
green <- data1 %>% 
  filter(!is.na(greenBoardings)) %>%
  select(greenBoardings)
green$boarding <- "green"
head(green)
##   greenBoardings boarding
## 1            887    green
## 2           1057    green
## 3           1142    green
## 4           1357    green
## 5            760    green
## 6            654    green
green2 <- green$boarding
green2 <- as.data.frame(green2)

library(dplyr)
green2 <- rename(green2, "boarding" = "green2")
names(green2)
## [1] "boarding"
head(green2)
##   boarding
## 1    green
## 2    green
## 3    green
## 4    green
## 5    green
## 6    green
banner <- data1 %>% 
  filter(!is.na(bannerBoardings)) %>%
  select(bannerBoardings)
banner$boarding <- "banner"
head(banner)
##   bannerBoardings boarding
## 1             520   banner
## 2             574   banner
## 3             630   banner
## 4             670   banner
## 5             847   banner
## 6             987   banner
banner2 <- banner$boarding
banner2 <- as.data.frame(banner2)
library(dplyr)
banner2 <- rename(banner2, "boarding" = "banner2")
names(banner2)
## [1] "boarding"
head(banner2)
##   boarding
## 1   banner
## 2   banner
## 3   banner
## 4   banner
## 5   banner
## 6   banner
cc <- rbind(orange2,
            green2, 
            purple2,
            banner2)

barplot(table(cc$boarding),
        main = "Bar chart showing the frequency of Boarding", 
        xlab = " category of boarding", 
        ylab = "frequency of boarding", 
        border =  "brown", 
        col = c("orange", "green", "purple", "blue"))

2) construct boxplot by group of day for orangeBoardings, PurpleBoardings,greenBoardings, bannerBoardings.

library(dplyr)
new <- data1 %>% 
group_by(day) %>%
  summarise(orange = mean(orangeBoardings, na.rm=T), 
            purple = mean(purpleBoardings, na.rm= T), 
            green = mean(greenBoardings, na.rm=T), 
            banner = mean(bannerBoardings, na.rm=T))
new2 <- data1 %>% 
  group_by(day) %>%
  select(day, orangeBoardings)
orange$boarding <- "orange"
head(orange)
##   orangeBoardings boarding
## 1             877   orange
## 2             777   orange
## 3            1203   orange
## 4            1194   orange
## 5            1645   orange
## 6            1457   orange
orangebp <- orange$boarding
orangebp <- as.data.frame(orangebp)
library(dplyr)
orangebp <- rename(orangebp, "boarding" = "orangebp")
names(orangebp)
## [1] "boarding"
head(orangebp)
##   boarding
## 1   orange
## 2   orange
## 3   orange
## 4   orange
## 5   orange
## 6   orange
new3 <- data1 %>%
  group_by(day) %>%
  select(day, purpleBoardings)
purple$boarding <- "purple"
head(purple)
##   purpleBoardings boarding
## 1            1028   purple
## 2            1327   purple
## 3            1726   purple
## 4            2044   purple
## 5            2230   purple
## 6            1852   purple
purplebp <- orange$boarding
purplebp <- as.data.frame(purplebp)
library(dplyr)
purplebp <- rename(purplebp, "boarding" = "purplebp")
names(purplebp)
## [1] "boarding"
head(purplebp)
##   boarding
## 1   orange
## 2   orange
## 3   orange
## 4   orange
## 5   orange
## 6   orange
new4 <- data1 %>%
  group_by(day) %>%
  select(day, bannerBoardings)
banner$boarding <- "banner"
head(banner)
##   bannerBoardings boarding
## 1             520   banner
## 2             574   banner
## 3             630   banner
## 4             670   banner
## 5             847   banner
## 6             987   banner
bannerbp <- banner$boarding
bannerbp <- as.data.frame(bannerbp)
library(dplyr)
bannerbp <- rename(bannerbp, "boarding" = "bannerbp")
names(bannerbp)
## [1] "boarding"
head(bannerbp)
##   boarding
## 1   banner
## 2   banner
## 3   banner
## 4   banner
## 5   banner
## 6   banner
new5 <- data1 %>%
  group_by(day) %>%
  select(day, greenBoardings)
green$boarding <- "green"
head(green)
##   greenBoardings boarding
## 1            887    green
## 2           1057    green
## 3           1142    green
## 4           1357    green
## 5            760    green
## 6            654    green
greenbp <- green$boarding
greenbp <- as.data.frame(greenbp)
library(dplyr)
greenbp <- rename(greenbp, "boarding" = "greenbp")
names(greenbp)
## [1] "boarding"
head(greenbp)
##   boarding
## 1    green
## 2    green
## 3    green
## 4    green
## 5    green
## 6    green
cc <- rbind(orangebp,
            greenbp, 
            purplebp,
            bannerbp)
  1. Construct line chart for orangeBoardings, purpleBoardings,greenBoardings and BannerBoardings by date for month October 2010
new <- data1 %>% 
  group_by(date) %>%
  summarise(orange = mean(orangeBoardings, na.rm=T), 
            purple = mean(purpleBoardings, na.rm= T), 
            green = mean(greenBoardings, na.rm=T), 
            banner = mean(bannerBoardings, na.rm=T))
library(ggplot2)
qplot(new4$orangeBoardings)
## Warning: Unknown or uninitialised column: 'orangeBoardings'.

## Warning: Unknown or uninitialised column: 'orangeBoardings'.

## Warning: Unknown or uninitialised column: 'orangeBoardings'.