Want to share your content on R-bloggers? click here if you have a blog, or here if you don’t.
Just writing this one quickly as it’s been hanging around my browser tabs for weeks…
I wrote Taking steps (in XML) almost 7 years ago and once in a while, I still grab Apple Health data from my phone and play around with it in R for a few minutes. Sometimes, curve fitting to a cloud of points generates a surprise.
library(tidyverse)
library(xml2)
theme_set(theme_bw())
health_data <- read_xml("~/Documents/apple_health_export/export.xml")
ws <- xml_find_all(health_data, ".//Record[@type='HKQuantityTypeIdentifierWalkingSpeed']") %>%
map(xml_attrs) %>%
map_df(as.list)
ws %>%
mutate(Date = ymd_hms(creationDate),
value = as.numeric(value)) %>%
ggplot(aes(Date, value)) +
geom_point(size = 1, alpha = 0.2, color = "grey70", fill = "grey70") +
geom_smooth() +
labs(y = "Walking speed (km/h)",
title = "Walking speed data",
subtitle = "Apple Health 2020 - 2023")
Result:
Huh. Looks seasonal. Looks faster in the (southern) winter. Has that been reported before? Sure has.
It didn’t impress everyone but I thought it was interesting.
R-bloggers.com offers daily e-mail updates about R news and tutorials about learning R and many other topics. Click here if you’re looking to post or find an R/data-science job.
Want to share your content on R-bloggers? click here if you have a blog, or here if you don’t.
Continue reading: Data discovery: seasonal speed
Key Points and Conclusions
The text discusses a personal experiment of tracking walking speed data over time through Apple Health and analyzing it with R programming for pattern observation. The core findings indicate that walking speed may have a correlation with seasons, perhaps implying a faster walking speed during the cold (winter) season.
Long-Term Implications
The finding of this experiment introduces many possibilities for future health and wellness studies. This is especially relevant when considering how lifestyle, environment, climate, and changing seasons can affect personal health indicators such as physical activity levels, in this case, walking speed.
“Looks seasonal. Looks faster in the (southern) winter. Has that been reported before?”
This observation can lead to more extensive research on seasonal variations in activity levels and performance. More granular data could potentially reveal insightful patterns and correlations between different health metrics and seasons.
Possible Future Developments
In theory, the implications of this find could prompt the development of new fitness technologies or app features. For instance, tracking software could be upgraded to consider seasonal factors when providing health predictions or personalized workout strategies. Similarly, users may receive health advice or guidance tailored to the current season.
Actionable Advice
For those involved in wellness research, health tech development, or even personal health enthusiasts, here are some advised courses of action:
- Combine Data: Use multiple, diverse data points for comprehensive health analysis. This approach will yield more in-depth insights and help explore possible correlations.
- Expand Research: Upon observing intriguing patterns like seasonal variations, delve further into research to validate or explore them.
- Enhanced Personalization: Leverage these insights to provide tailored health, fitness advice, or coaching to individuals taking seasonal variations into account.
- Continuous Learning: Regularly update and learn from a vast range of analysis sources like R-Bloggers.
Remember, these are suggestions based on a single observation. It would be advisable to conduct further research before making any significant changes to existing health regimes or development plans.