---
title: "Final Project for ANLY 512-51- R-2017/Fall - Data Visualization"
output:
flexdashboard::flex_dashboard:
orientation: columns
vertical_layout: fill
source_code: embed
---
```{r setup, include=FALSE}
library(flexdashboard)
library("ggplot2")
library(dplyr)
library(data.table)
data <- fread("JC-201709-citibike-tripdata.csv", header=TRUE, showProgress = FALSE, stringsAsFactors = FALSE, data.table = FALSE)
names(data)
names(data) <- make.names(names(data))
names(data)
class(data)
```
Page 1
==================================
Column {data-width=600}
-----------------------------------------------------------------------
### Data Preview
```{r}
head(data)
```
Column {data-width=400}
-----------------------------------------------------------------------
### Data Summary
```{r}
summary(data)
```
### Data Class
```{r}
attach(data)
sapply(data,class)
```
Page 2
==================================
Row {data-heigh=550}
-----------------------------------------------------------------------
### User Birth Year
```{r}
data$birth.year <- as.integer(data$birth.year)
ggplot(data) + geom_histogram(aes(birth.year),fill="red")
```
Row {data-heigh=350}
-----------------------------------------------------------------------
### User Type
```{r}
ggplot(data) + geom_bar(aes(usertype,fill=usertype), width=0.2)
```
Page 3
==================================
column
-----------------------------------------------------------------------
### Average Trip Duration by User Type
```{r}
ggplot(data, aes(x = usertype, y = tripduration)) + stat_summary(fun.y = "mean", geom = "bar") + ylab("Avg Trip Duration")
```
column
-----------------------------------------------------------------------
### Average Trip Duration by Gender
```{r}
data$gender <- as.factor(data$gender)
levels(data$gender) <- c("UNKNOWN", "MALE", "FEMALE")
ggplot(data, aes(x = gender, y = tripduration)) + stat_summary(fun.y = "mean", geom = "bar") + ylab("Avg Trip Duration")
```
Page 4
==================================
-----------------------------------------------------------------------
### Weekday Usage
```{r}
require(lubridate)
data$starttime <- ymd_hms(data$starttime)
data$stoptime <- ymd_hms(data$stoptime)
data$duration <-data$stoptime - data$starttime
data$myduration <- difftime(data$stoptime, data$starttime, units="secs")
data$weekday <- wday(data$starttime, label=TRUE)
data$hour <- as.factor(hour(data$starttime))
ggplot(data) + geom_bar(aes(x=weekday, y=(..count..)/sum(..count..), fill=weekday)) + theme_bw() + ylab("Proportion")
```
Page 5
==================================
-----------------------------------------------------------------------
Column {data-width=300}
-----------------------------------------------------------------------
### Chart 1
```{r}
ggplot(data) + geom_bar(aes(x=hour, y=(..count..)/sum(..count..)), fill="lightblue") + theme_light() + ylab("Proportion")
```
Page 6
==================================
-----------------------------------------------------------------------
### Hourly Weekday
```{r}
data %>% subset( (usertype == "Subscriber") & !(weekday %in% c("Sat","Sun"))) %>%
ggplot(.) + geom_bar(aes(x=hour, y=(..count..)/sum(..count..), fill=weekday), position = "dodge") + ylab("Proportion") + scale_fill_brewer(palette = "YlOrRd")
```
