...
Code Block |
---|
language | bash |
---|
title | Build your login dataframe |
---|
|
> ds.table1D(x="Dwide2$female")
$counts
Dwide2$female
0 1324
1 1368
Total 2692
$percentages
Dwide2$female
0 49.18
1 50.82
Total 100.00
$validity
[1] "All tables are valid!"
|
Code Block |
---|
|
> ds.dataFrameSubset(df.name="Dwide2", V1="Dwide2$female", V2="1", Boolean.operator="==", newobj="Dwide2_females")
$is.object.created
[1] "A data object <Dwide2_females> has been created in all specified data sources"
$validity.check
[1] "<Dwide2_females> appears valid in all sources"
> ds.dim("Dwide2")
$`dimensions of Dwide2 in study1`
[1] 886 16
$`dimensions of Dwide2 in study2`
[1] 659 16
$`dimensions of Dwide2 in study3`
[1] 1167 16
$`dimensions of Dwide2 in combined studies`
[1] 2712 16
> ds.dim("Dwide2_females")
$`dimensions of Dwide2_females in study1`
[1] 441 16
$`dimensions of Dwide2_females in study2`
[1] 344 16
$`dimensions of Dwide2_females in study3`
[1] 583 16
$`dimensions of Dwide2_females in combined studies`
[1] 1368 16
|
Data visualisations
The new ds.scatterPlot function uses two anonymization techniques that produce non-disclosive coordinates that can be displayed in a scatter plot. The anonymization technique is specified by the user in the argument method where there are two possible choices; the "deterministic" and the "probabilistic". If the 'deteministic' method is selected (the default option), then the generated scatter plot shows the scaled centroids of each k nearest neighbours of the original variables where the value of k is set by the user. If the 'probabilistic' method is selected, then the generated scatter plot shows the original data disturbed by the addition of random stochastic noise. The added noise follows a normal distribution with zero mean and variance equal to a percentage of the initial variance of each variable. This percentage is specified by the user in the argument noise.
...