---
title: "ANLY512_final_project_storyboard"
output:
flexdashboard::flex_dashboard:
orientation: rows
social: menu
source: embed
storyboard: true
---
```{r setup, include=FALSE}
library(flexdashboard)
```
### Steps Taken for the Past 3 Months
```{r}
steps<- read.csv("/Users/yh101251/Desktop/HU/512/final_project_files/steps.csv")
steps <- steps[,-3]
steps$date <- as.Date(steps$date)
```
```{r}
#install.packages("dygraphs")
library(dygraphs)
library(xts)
steps <- steps[3:94,]
ts_obj <- xts(steps[,2],order.by=as.Date(steps$date,"%Y/%m/%d"))
names(ts_obj) <- c("steps")
dygraph(ts_obj, main = "Steps Taken") %>% dyRangeSelector(dateWindow = c("2018-05-01", "2018-07-31")) %>%
dyAxis("y", label = "Number of Steps", valueRange = c(0, 12000))
```
***
Most steps taken: May 5, 2018, 11,936
Least steps taken: July 22, 2018, 86
### Phone Use in July
```{r}
moment<- read.csv("/Users/yh101251/Desktop/HU/512/final_project_files/moment.csv")
moment$date <- gsub("\\T.*","",moment$date)
moment$date <- as.Date(moment$date)
moment <- moment[order(as.Date(moment$date, format="%Y/%m/%d"), decreasing = FALSE),]
moment[8,1] <- moment[8,1] - 7.750000 * 60
moment[9,1] <- moment[9,1] - 6.316667 * 60
moment[10,1] <- moment[10,1] - 6.416667 * 60
library(xts)
moment_ts_obj <- xts(moment[,1:2], order.by = as.Date(moment$date,"%Y/%m/%d"))
dygraph(moment_ts_obj, main = "Phone Use") %>% dyRangeSelector(dateWindow = c("2018-07-05", "2018-08-02")) %>%
dyOptions(colors = RColorBrewer::brewer.pal(2, "Set2"))
```
***
Excluding the first few days with zero for both data - minutes on phone and times I pick up the phone:
the least number of pick-ups: 9 times, July 21;
the most number of pick-ups: 69 times, July 13;
most time spent: 399 minutes on July 25;
least time spent: 80 minutes on August 1.
Data caveat:ss
Because on 2018-07-11, 2018-07-12, 2018-07-13, running of sleep cycle on backend was counted as phone use minute count, the numbers of minuteCount should be deducted by the sleep time for these three dates.
### Phone Use on Each Day of Week
```{r}
library(dplyr)
library(lubridate)
library(scales)
library(ggplot2)
moment %>%
mutate(
day_of_week = as.Date(date) %>% wday(label = TRUE),
what_day = ifelse(grepl("Sat|Sun", day_of_week),"Weekend","Weekday") %>%
as.factor()
) %>%
ggplot() +
geom_boxplot(aes(x = day_of_week, y = minuteCount, color = what_day)) +
scale_y_continuous(breaks = pretty_breaks(5), labels = percent_format()) +
# scale_fill_manual(values = cols) +
ggtitle("Distribution of Time Spent on Phone", subtitle = "Source: iPhone Momemnt data (2018/07/05 - 2018/08/02)") +
labs(x = "Day of week", y = "Minutes") +
theme_bw() +
theme(legend.position = "none",
axis.text.x = element_text(size = 11, face = "bold"),
axis.text.y = element_text(size = 11, face = "bold"))
```
***
I tended to spend more time on my phone on Sunday and Friday on average.
### Hours of Sleep
```{r message=FALSE}
#install.packages("readr")
library(readr)
library(tidyverse)
library(lubridate)
df <- read_delim("/Users/yh101251/Desktop/HU/512/final_project_files/sleepdata.csv", delim = ";") %>%
rename(sleep_quality = `Sleep quality`,
time_in_bed = `Time in bed`,
steps = `Activity (steps)`) %>%
mutate(sleep_quality = str_replace(sleep_quality, "\\%", "") %>% as.numeric,
day_of_week = as.Date(Start) %>% wday(label = TRUE),
what_day = ifelse(grepl("Sat|Sun", day_of_week),"Weekend","Weekday") %>%
as.factor(),
sleep_hour = ymd_hms(Start) %>% hour(),
sleep_min = ymd_hms(Start) %>% minute()/60,
sleep_time = sleep_hour + sleep_min,
time_hr = period_to_seconds(hms(time_in_bed))/3600,
date = ymd_hms(Start),
day = day(date),
month = month(date),
year = year(date)) %>%
select(date, year, month, day, day_of_week,what_day,sleep_time, Start:time_in_bed, time_hr,steps) %>%
mutate_at(vars(year:day),as.factor)
## turn date into 2018-07-12 to match with steps data frame
df$date <- gsub("\\ .*","",df$date)
##turn steps$date into character to match with df
steps$date <- as.character(steps$date)
## change colume name of step into step_2 to avoid contradiction with the step column in df
colnames(steps) <- c("date","steps_2")
## sort the steps data from by date for easier join: d[order(as.Date(d$V3, format="%d/%m/%Y")),]
steps <- steps[order(as.Date(steps$date, format="%Y/%m/%d"), decreasing = FALSE),]
## merge the two datasets
df <- merge(df, steps)
## use the steps_2 column
```
```{r}
#install.packages("viridis")
library(viridis)
df %>% filter(time_hr > 0) %>%
ggplot(aes(x = Start, y = time_hr, color = sleep_quality)) +
geom_point(alpha = 0.6) +
# geom_smooth() +
scale_color_viridis() +
geom_hline(yintercept=mean(df$time_hr), linetype="dashed", color = "red") +
labs(title = "Hours of Sleep",
subtitle = "Source: iPhone sleep cycle data (2018/07/12 - 2018/07/31)",
x = "Date",
y = "Hours of Sleep",
color = "Sleep Quality\n") +
theme_bw()
```
***
To avoid the wrong data skewing the relationship, for this chart and those charts after this, I excluded one data point where sleep duration was zero, which I think was an error due to app glitch.
On average, I sleep for a little less than 6 hours everyday.
### Bedtime
```{r}
df %>%
ggplot(aes(x = Start, y = sleep_time, color = what_day)) +
geom_point(alpha = 0.6) +
scale_y_continuous(expand = c(0,0),
breaks = seq(0,24,4),
limits = c(0,24.1),
labels = c("12 AM","4 AM","8 AM", "12 PM", "4 PM","8 PM","11:59 PM")) +
labs(title = "Bedtime",
subtitle = "Source: iPhone sleep cycle data (2018/07/12 - 2018/07/31)",
x = "Date",
y = "Bedtime",
color = "") +
theme_bw() +
geom_hline(yintercept=2, linetype="dashed", color = "red")
```
***
I went to bed later than 2 am for 7 days out of the 19 days with data recorded.
### Sleep Quality vs Hours of Sleep
```{r}
df %>%
filter(time_hr > 0) %>%
ggplot(aes(x = time_hr, y = sleep_quality, color = what_day)) +
geom_point(size = 2, alpha = 0.3) +
geom_smooth(aes(group = 1), method = "lm") +
scale_x_continuous(breaks = seq(0,12,2)) +
labs(title = "Sleep Quality vs. Hours of Sleep",
subtitle = "Source: iPhone sleep cycle data (2018/07/12 - 2018/07/31)",
x = "Hours of Sleep",
y = "Sleep Quality",
color = "") +
theme_bw()
```
***
The longer the sleep, the higher the sleep quality. The hours of sleep seems to have a moderate positive correlation with sleep quality.
### Duration of Sleep Each Day of the Week
```{r}
#install.packages("ggridges")
library(ggridges)
library(ggplot2)
df %>% filter(time_hr > 0) %>%
ggplot(aes(x = time_hr, y = day_of_week, fill = ..x..)) +
geom_density_ridges_gradient(scale = 3) +
scale_x_continuous(expand = c(0.01, 0),
breaks= seq(0,12,4)) +
scale_y_discrete(expand = c(0.01, 0)) +
scale_fill_viridis(name = "Hours", option = "C") +
labs(title = "Duration of Sleep",
subtitle = "Source: iPhone sleep cycle data (2018/07/12 - 2018/07/31)",
x = "Time spent sleeping (hr)") +
theme_ridges(font_size = 13, grid = TRUE) + theme(axis.title.y = element_blank())
```
***
There was one Thursday and one Wednesday without data entry. Without Thursday and Wednesday, Sunday is the day when I sleep the longest
### Quality of Sleep Each Day of the Week
```{r}
library(ggridges)
library(ggplot2)
df %>%
filter(time_hr > 0) %>%
ggplot(aes(x = sleep_quality, y = day_of_week, fill = ..x..)) +
geom_density_ridges_gradient(scale = 3) +
scale_x_continuous(expand = c(0.01, 0)) +
scale_y_discrete(expand = c(0.01, 0)) +
scale_fill_viridis(name = "Quality of Sleep", option = "C") +
labs(title = 'Quality of Sleep Each Day of the Week',
subtitle = "Source: iPhone sleep cycle data (2018/07/12 - 2018/07/31)") +
theme_ridges(font_size = 13, grid = TRUE) + theme(axis.title.y = element_blank())
```
***
Without Thursday and Wednesday, I have higher sleep quality on Saturdays and Sundays.
### Sleep Duration vs Daily Steps
```{r}
df %>%
filter(steps > 0,
steps < 15000) %>%
filter(time_hr > 0) %>%
ggplot(aes(x = steps_2, y = time_hr, color = sleep_quality)) +
geom_point(alpha = 0.9) +
geom_smooth(color = "Purple", fill = "White", method = "lm") +
scale_color_viridis() +
scale_y_continuous(breaks = seq(0,12,2)) +
labs(title = "Sleep Duration vs Daily Steps",
subtitle = "Source: iPhone sleep cycle data (2018/07/12 - 2018/07/31)",
x = "Number of Steps",
y = "Sleep Duration (hr)",
color = "Sleep Quality\n") +
theme_dark()
```
***
I mostly take between 2000 and 3000 steps a day, and on these days I sleep between 4 and 7 hours.
When I have really low number of steps, my sleep hour tends to be longer, I think that's because those days are weekends, when I stay at home, and sleep earlier.
Although the linear regression line suggests weak to moderate negative correlation between number of steps and sleep duration, I don't think there are enough data points to say.
### Sleep Duration vs Minite on Phone
```{r}
## select the first 3 columns
moment <- moment[,1:3]
## turn moment$date to match sleep data df
moment$date <- as.character(moment$date)
## sort the steps data from by date for easier join: d[order(as.Date(d$V3, format="%d/%m/%Y")),]
moment <- moment[order(as.Date(moment$date, format="%Y/%m/%d"), decreasing = FALSE),]
## merge the two datasets
df <- merge(df, moment)
```
```{r}
df %>%
filter(steps > 0,
steps < 15000) %>%
filter(time_hr > 0) %>%
ggplot(aes(x = minuteCount, y = time_hr, color = sleep_quality)) +
geom_point(alpha = 0.9) +
geom_smooth(color = "Purple", fill = "White", method = "lm") +
scale_color_viridis() +
scale_y_continuous(breaks = seq(0,12,2)) +
labs(title = "Sleep Duration vs Minite on Phone",
subtitle = "Source: iPhone sleep cycle data (2018/07/12 - 2018/07/31)",
x = "Minite Count on Phone",
y = "Sleep Duration (hr)",
color = "Sleep Quality\n") +
theme_dark()
```
***
There seems to be weak positive correlation between the time I spend on phone and sleep duration. But it could again be because I haven't collected enough data.
### Sleep Quality vs. Minutes on Phone
```{r}
df %>% filter(time_hr > 0) %>%
ggplot(aes(x = minuteCount, y = sleep_quality, color = what_day)) +
geom_point(size = 2, alpha = 0.3) +
geom_smooth(aes(group = 1), method = "lm") +
scale_x_continuous(breaks = seq(0,12,2)) +
labs(title = "Sleep Quality vs. Minutes on Phone",
subtitle = "Source: iPhone sleep cycle data (2018/07/12 - 2018/07/31)",
x = "Minites on Phone",
y = "Sleep Quality",
color = "") +
theme_bw()
```
***
There seems to be weak positive correlation between the time I spend and sleep quality.
