In violetacln/revaliew: advanced validation implementation: review of data content

knitr::opts_chunk$set(echo = FALSE, warning=FALSE)

Data-set and main information needed

about: time-variables, modeled - variables, imputed-variables

Assume a data-frame has been built.

Example for this run:

knitr::opts_chunk$set(echo = FALSE, warning=FALSE)

## main data set as a data.frame
#df <- 

##data sets which need to be compared (could be same data measured at different moments in time), as data.frames
#df1<- 
#df2<-

##time series we need to explore:
#tsuniv
#tsmultiv

Data view

knitr::opts_chunk$set(echo = FALSE, warning=FALSE)
view_data(df)

Section 2: Univariate analysis

knitr::opts_chunk$set(echo = FALSE, warning=FALSE)
view_univar(df)

Multivariate analysis

knitr::opts_chunk$set(echo = FALSE, warning=FALSE)
view_multivar(df)

Outliers' detection

knitr::opts_chunk$set(echo = FALSE, warning=FALSE)
view_outliers(df)

Variability in data

knitr::opts_chunk$set(echo = FALSE, warning=FALSE)
rev_variability(df)

Checking assumptions about data

knitr::opts_chunk$set(echo = FALSE, warning=FALSE)
check_assumptions(df1,df2)

Association rules discovery

knitr::opts_chunk$set(echo = FALSE, warning=FALSE)
view_assoc(df)

Clusters identification

knitr::opts_chunk$set(echo = FALSE, warning=FALSE)
view_clusters(df)

Reviewing models

knitr::opts_chunk$set(echo = FALSE, warning=FALSE)
# if a glm type of model, then
rev_model(model_a)
#if a time series model, then
#rev_model_ts(model_a)

Reviewing time series characteristics

knitr::opts_chunk$set(echo = FALSE, warning=FALSE)
#for all time series, univariate
rev_ts_univ(tsuniv)
#for any multivariate time series
rev_ts_multiv(tsmultiv)