Changes

|Total amount of time spent using apps classified as "very productive"

|Total amount of time spent using apps classified as "very productive"

|}

|}

The data was exported from the respective sources through the [[Open Humans]] integrations. A Jupyter notebook to export all this data in a unified spreadsheet will be made available soon.

The data was exported from the respective sources through the [[Open Humans]] integrations. A Jupyter notebook to export all this data in a unified spreadsheet is available<ref>https://exploratory.openhumans.org/notebook/169/</ref>.  

=== Processing the data ===

=== Processing the data ===

== Running a PCA ==

== Running a PCA ==

With the full data table prepared for this time period, I ended up with 280 observations (aka days) that had full data for these 37 variables that I could use to run the PCA. For this I used the [[R]] package <code>FactoMineR</code> as it not only provides the basic functions for running the analysis, but also a wide set of visualization options. Roughly speaking, PCAs are a way to reduce the dimensionality of data by 'rotating' the data in a way that it can be represented in fewer dimensions, ideally no more than 2-3 as this would allow visualizing it in a human-readable space. In this case, we have 37 different dimensions as given by the 37 variables and would like to boil it down to fewer dimensions without losing any information.   

With the full data table prepared for this time period, I ended up with 280 observations (aka days) that had full data for these 37 variables that I could use to run the PCA. For this I used the [[R]] package <code>FactoMineR</code> as it not only provides the basic functions for running the analysis, but also a wide set of visualization options<ref>A good tutorial can be found here: http://www.sthda.com/english/articles/31-principal-component-methods-in-r-practical-guide/112-pca-principal-component-analysis-essentials/</ref>. The code for running this analysis is online as well<ref>The R code is at the end of this notebook here: https://exploratory.openhumans.org/notebook/169/ (It won't run in the Open Humans notebook infrastructure due to some R-version issue. You will need to copy and paste it into your own R/RStudio environment). </ref>. Roughly speaking, PCAs are a way to reduce the dimensionality of data by 'rotating' the data in a way that it can be represented in fewer dimensions, ideally no more than 2-3 as this would allow visualizing it in a human-readable space. In this case, we have 37 different dimensions as given by the 37 variables and would like to boil it down to fewer dimensions without losing any information.   

===How do the different metrics correlate?===

===How do the different metrics correlate?===

I tried to account for this big signal by filtering out all days which fall on weekends, but the results didn't really change overall. Coming to think of it now this seems to partially be due to the impact of homeoffice/holidays/sickness that makes a weekday filtering only a rough proxy for the routines that took place. A potential approach to account for this might be to add my [[Overland]] GPS data into the mix to see whether I went to the office or not. Generally, adding GPS data might be able to provide a strong signal beyond showing presence/absence in the office, e.g. by summing up the total distance traveled on that day or other movement metrics that go beyond walking/biking as measured by my Apple Watch/Oura Ring.  

I tried to account for this big signal by filtering out all days which fall on weekends, but the results didn't really change overall. Coming to think of it now this seems to partially be due to the impact of homeoffice/holidays/sickness that makes a weekday filtering only a rough proxy for the routines that took place. A potential approach to account for this might be to add my [[Overland]] GPS data into the mix to see whether I went to the office or not. Generally, adding GPS data might be able to provide a strong signal beyond showing presence/absence in the office, e.g. by summing up the total distance traveled on that day or other movement metrics that go beyond walking/biking as measured by my Apple Watch/Oura Ring.  

Lastly, the very strong correlation of the variables into three main clusters in the PCA is quite interesting in itself as well as how they are or aren't correlated to each other. In particular the negative correlation between the various sleep metrics and the productivity & inactivity metrics is quite interesting to see. Not only does it make some intuitive sense to me, but it is equally interesting that the medium-high physical activity variables are nearly 90º rotated away from either of them, indicating a lack of correlation between those and any other of the metrics. I'm not fully sure how to interpret it, but given the labeling of the data points it might be a sign that whether I go to work or not doesn't have too much of an effect on higher levels of physical activity, rather workdays might only influence how much ''inactive/low-activity'' time I accumulate? {{Project Queries}}

Lastly, the very strong correlation of the variables into three main clusters in the PCA is quite interesting in itself as well as how they are or aren't correlated to each other. In particular the negative correlation between the various sleep metrics and the productivity & inactivity metrics is quite interesting to see. Not only does it make some intuitive sense to me, but it is equally interesting that the medium-high physical activity variables are nearly 90º rotated away from either of them, indicating a lack of correlation between those and any other of the metrics. I'm not fully sure how to interpret it, but given the labeling of the data points it might be a sign that whether I go to work or not doesn't have too much of an effect on higher levels of physical activity, rather workdays might only influence how much ''inactive/low-activity'' time I accumulate?  

[[Category:Projects]]

 

 

[[Category:Projects]][[Category:Productivity projects]][[Category:Sleep projects]][[Category:Diet, digestion and weight loss projects]]