library(readxl)
activity <- read_excel("Fitabase Data 4.12.16-5.12.16/dailyActivity_merged.xlsx") #activity contains daily data on steps, distance, calories, and active minute
library(readr)
heartrate <- read_csv("Fitabase Data 4.12.16-5.12.16/heartrate_seconds_merged.csv")
## Rows: 2483658 Columns: 3
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (1): Time
## dbl (2): Id, Value
##
## 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.
weight <- read_csv("Fitabase Data 4.12.16-5.12.16/weightLogInfo_merged.csv") #weight contains data on weight in Kg or Pounds
## Rows: 67 Columns: 8
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (1): Date
## dbl (6): Id, WeightKg, WeightPounds, Fat, BMI, LogId
## lgl (1): IsManualReport
##
## 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.
sleep <- read_csv("Fitabase Data 4.12.16-5.12.16/sleepDay_merged.csv") #sleep contains data on the total time spent on bed and the total time asleep each day
## Rows: 413 Columns: 5
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (1): SleepDay
## dbl (4): Id, TotalSleepRecords, TotalMinutesAsleep, TotalTimeInBed
##
## 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.
METs <- read_csv("Fitabase Data 4.12.16-5.12.16/minuteMETsNarrow_merged.csv") #METs is the metabolic equivalent of task for every minute
## Rows: 1325580 Columns: 3
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (1): ActivityMinute
## dbl (2): Id, METs
##
## 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.
library(pacman) #package used for managing other packages
library(tidyverse) #package used for data cleaning and manipulation
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.2 ✔ purrr 1.0.1
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.2 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
glimpse(activity) #To see the entire columns in activity table created
## Rows: 940
## Columns: 15
## $ Id <dbl> 1503960366, 1503960366, 1503960366, 150396036…
## $ ActivityDate <dttm> 2016-04-12, 2016-04-13, 2016-04-14, 2016-04-…
## $ TotalSteps <dbl> 13162, 10735, 10460, 9762, 12669, 9705, 13019…
## $ TotalDistance <dbl> 8.50, 6.97, 6.74, 6.28, 8.16, 6.48, 8.59, 9.8…
## $ TrackerDistance <dbl> 8.50, 6.97, 6.74, 6.28, 8.16, 6.48, 8.59, 9.8…
## $ LoggedActivitiesDistance <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ VeryActiveDistance <dbl> 1.88, 1.57, 2.44, 2.14, 2.71, 3.19, 3.25, 3.5…
## $ ModeratelyActiveDistance <dbl> 0.55, 0.69, 0.40, 1.26, 0.41, 0.78, 0.64, 1.3…
## $ LightActiveDistance <dbl> 6.06, 4.71, 3.91, 2.83, 5.04, 2.51, 4.71, 5.0…
## $ SedentaryActiveDistance <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ VeryActiveMinutes <dbl> 25, 21, 30, 29, 36, 38, 42, 50, 28, 19, 66, 4…
## $ FairlyActiveMinutes <dbl> 13, 19, 11, 34, 10, 20, 16, 31, 12, 8, 27, 21…
## $ LightlyActiveMinutes <dbl> 328, 217, 181, 209, 221, 164, 233, 264, 205, …
## $ SedentaryMinutes <dbl> 728, 776, 1218, 726, 773, 539, 1149, 775, 818…
## $ Calories <dbl> 1985, 1797, 1776, 1745, 1863, 1728, 1921, 203…
## Filter and clean the activity data
#selecting only the possible columns the will be used for data visualization
activity_1 <- activity %>%
mutate(date = as_date(ActivityDate, "%Y-%m-%d")) %>%
mutate(month_year = format(date, "%b %Y")) %>%
select(Id, date, ActivityDate, TotalSteps, TotalDistance, VeryActiveMinutes, FairlyActiveMinutes, LightlyActiveMinutes, SedentaryMinutes, Calories, month_year) %>%
select(-ActivityDate) %>%
filter(!(Id %in% 4057192912))
## Warning: There was 1 warning in `mutate()`.
## ℹ In argument: `date = as_date(ActivityDate, "%Y-%m-%d")`.
## Caused by warning in `as.POSIXlt.POSIXct()`:
## ! unknown timezone '%Y-%m-%d'
head(activity_1)
## # A tibble: 6 × 10
## Id date TotalSteps TotalDistance VeryActiveMinutes
## <dbl> <date> <dbl> <dbl> <dbl>
## 1 1503960366 2016-04-12 13162 8.5 25
## 2 1503960366 2016-04-13 10735 6.97 21
## 3 1503960366 2016-04-14 10460 6.74 30
## 4 1503960366 2016-04-15 9762 6.28 29
## 5 1503960366 2016-04-16 12669 8.16 36
## 6 1503960366 2016-04-17 9705 6.48 38
## # ℹ 5 more variables: FairlyActiveMinutes <dbl>, LightlyActiveMinutes <dbl>,
## # SedentaryMinutes <dbl>, Calories <dbl>, month_year <chr>
glimpse(METs) #To see the entire columns in METs table created
## Rows: 1,325,580
## Columns: 3
## $ Id <dbl> 1503960366, 1503960366, 1503960366, 1503960366, 1503960…
## $ ActivityMinute <chr> "4/12/2016 12:00:00 AM", "4/12/2016 12:01:00 AM", "4/12…
## $ METs <dbl> 10, 10, 10, 10, 10, 12, 12, 12, 12, 12, 12, 12, 10, 10,…
METs_1 <- METs %>%
mutate(date_time = parse_date_time(ActivityMinute, "%m/%d/%Y %I:%M:%S %p")) %>%
select(-ActivityMinute)
head(METs_1)
## # A tibble: 6 × 3
## Id METs date_time
## <dbl> <dbl> <dttm>
## 1 1503960366 10 2016-04-12 00:00:00
## 2 1503960366 10 2016-04-12 00:01:00
## 3 1503960366 10 2016-04-12 00:02:00
## 4 1503960366 10 2016-04-12 00:03:00
## 5 1503960366 10 2016-04-12 00:04:00
## 6 1503960366 12 2016-04-12 00:05:00
glimpse(weight) #To see the entire columns in weight table created
## Rows: 67
## Columns: 8
## $ Id <dbl> 1503960366, 1503960366, 1927972279, 2873212765, 2873212…
## $ Date <chr> "5/2/2016 23:59", "5/3/2016 23:59", "4/13/2016 1:08", "…
## $ WeightKg <dbl> 52.6, 52.6, 133.5, 56.7, 57.3, 72.4, 72.3, 69.7, 70.3, …
## $ WeightPounds <dbl> 115.9631, 115.9631, 294.3171, 125.0021, 126.3249, 159.6…
## $ Fat <dbl> 22, NA, NA, NA, NA, 25, NA, NA, NA, NA, NA, NA, NA, NA,…
## $ BMI <dbl> 22.65, 22.65, 47.54, 21.45, 21.69, 27.45, 27.38, 27.25,…
## $ IsManualReport <lgl> TRUE, TRUE, FALSE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, …
## $ LogId <dbl> 1.46223e+12, 1.46232e+12, 1.46051e+12, 1.46128e+12, 1.4…
weight_1 <- weight %>%
mutate(ID = as.character(Id)) %>%
select(ID, WeightKg) %>%
group_by(ID) %>%
drop_na() %>%
summarise(avg_weight = mean(WeightKg))
head(weight_1)
## # A tibble: 6 × 2
## ID avg_weight
## <chr> <dbl>
## 1 1503960366 52.6
## 2 1927972279 134.
## 3 2873212765 57
## 4 4319703577 72.4
## 5 4558609924 69.6
## 6 5577150313 90.7
glimpse(sleep)
## Rows: 413
## Columns: 5
## $ Id <dbl> 1503960366, 1503960366, 1503960366, 1503960366, 150…
## $ SleepDay <chr> "4/12/2016 12:00:00 AM", "4/13/2016 12:00:00 AM", "…
## $ TotalSleepRecords <dbl> 1, 2, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
## $ TotalMinutesAsleep <dbl> 327, 384, 412, 340, 700, 304, 360, 325, 361, 430, 2…
## $ TotalTimeInBed <dbl> 346, 407, 442, 367, 712, 320, 377, 364, 384, 449, 3…
sleep_1 <- sleep %>%
mutate(Date_1 = as.character(SleepDay)) %>%
mutate(PST = TotalTimeInBed - TotalMinutesAsleep) %>%
separate(Date_1, c("date", "time"), sep = " ") %>%
mutate(Date = as.Date(date, "%m/%d/%Y", optional = FALSE)) %>%
select(-TotalSleepRecords, -SleepDay, -date, -time) %>%
drop_na() %>%
filter(!(Id %in% c(1644430081, 1844505072, 1927972279, 4020332650, 2320127002, 4558609924, 6775888955, 7007744171, 8053475328)))
## Warning: Expected 2 pieces. Additional pieces discarded in 413 rows [1, 2, 3, 4, 5, 6,
## 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, ...].
head(sleep_1)
## # A tibble: 6 × 5
## Id TotalMinutesAsleep TotalTimeInBed PST Date
## <dbl> <dbl> <dbl> <dbl> <date>
## 1 1503960366 327 346 19 2016-04-12
## 2 1503960366 384 407 23 2016-04-13
## 3 1503960366 412 442 30 2016-04-15
## 4 1503960366 340 367 27 2016-04-16
## 5 1503960366 700 712 12 2016-04-17
## 6 1503960366 304 320 16 2016-04-19
glimpse(heartrate)
## Rows: 2,483,658
## Columns: 3
## $ Id <dbl> 2022484408, 2022484408, 2022484408, 2022484408, 2022484408, 2022…
## $ Time <chr> "4/12/2016 7:21:00 AM", "4/12/2016 7:21:05 AM", "4/12/2016 7:21:…
## $ Value <dbl> 97, 102, 105, 103, 101, 95, 91, 93, 94, 93, 92, 89, 83, 61, 60, …
heartrate_1 <- heartrate %>%
mutate(date_time = parse_date_time(Time, "%m/%d/%Y %I:%M:%S %p")) %>%
select(-Time)
head(heartrate_1)
## # A tibble: 6 × 3
## Id Value date_time
## <dbl> <dbl> <dttm>
## 1 2022484408 97 2016-04-12 07:21:00
## 2 2022484408 102 2016-04-12 07:21:05
## 3 2022484408 105 2016-04-12 07:21:10
## 4 2022484408 103 2016-04-12 07:21:20
## 5 2022484408 101 2016-04-12 07:21:25
## 6 2022484408 95 2016-04-12 07:22:05
library(ggplot2)
ggplot(sleep_1,
mapping = aes(
x = Date,
y = TotalMinutesAsleep)
)+
geom_line()+
labs(x = "",
y = "DailySleep(mins)",
title = "Time Asleep per Day",
subtitle = "April & May")+
theme(axis.text.x = element_text(angle=45,
hjust=0.8,
size = 8)
)+
scale_x_date(date_breaks = "2 week")+
facet_wrap(~Id)
ggplot(sleep_1,
mapping = aes(
x = Date,
y = PST)
)+
geom_line()+
labs(x = "Date",
y = "Possible Stressed Time",
title = "Users on Bed without Sleeping",
subtitle = "April & May")+
theme(axis.text.x = element_text(angle=45,
hjust=0.8,
size = 8)
)+
scale_x_date(date_breaks = "2 week")+
facet_wrap(~Id)
ggplot(activity_1,
mapping = aes(
x = date,
y = TotalDistance,
colour = FairlyActiveMinutes)
) +
geom_line() +
scale_color_gradient(low = "#94E873", high = "#00441B") +
labs(x = "Date",
y = "Distances(Km)",
title = "User's Daily Activity",
subtitle = "April & May"
) +
scale_x_date(date_minor_breaks = "month")+
theme(axis.text.x = element_text(angle=45)
)+
theme(axis.text.y = element_text(size = 5))+
theme(axis.text.x = element_text(size = 5))+
facet_wrap(vars(Id))
ggplot(heartrate_1,
mapping = aes(
x = date_time,
y = Value,
colour = Id)
) +
geom_step() +
scale_color_gradient(low = "#132B43", high = "#2A77B2") +
labs(x = "Date_time",
y = "Pulse Value per second",
title = "Time Series of User's Heartbeat",
subtitle = "April & May"
) +
theme_light() +
theme(axis.text.y = element_text(size = 5))+
theme(axis.text.x = element_text(angle=45,
hjust=0.8,
size = 5)
)+
facet_wrap(vars(Id), scales = "free")
ggplot(activity_1,
mapping = aes(
x = date,
y = Calories,
colour = month_year)
) +
geom_line() +
scale_color_hue(direction = 1) +
labs(x = "Date",
y = "Calories (KJ)",
title = "Showing Calories Burnt by Users",
subtitle = "April & May"
) +
theme_bw() +
theme(axis.text.y = element_text(size = 5))+
theme(axis.text.x = element_text(angle=45,
size = 5)
)+
facet_wrap(vars(Id))
ggplot(weight_1,
mapping = aes(
x = ID,
y = avg_weight,
fill = avg_weight)
)+
geom_col() +
theme_minimal()+
labs(x = "ID",
y = "Average Weight",
title = "Average Weight of Users"
) +
scale_fill_gradient(low = "#1881EB", high = "#08243A")
print(mean(activity_1$TotalDistance))
## [1] 5.500929
print(sd(activity_1$TotalDistance))
## [1] 3.927566
print(mean(sleep_1$TotalMinutesAsleep)/60)
## [1] 7.143887
print(sd(sleep_1$TotalMinutesAsleep)/60)
## [1] 1.676945
print(mean(sleep_1$PST))
## [1] 38.38522
print(sd(sleep_1$PST))
## [1] 40.85727