Data Science Desktop Survival Guide by Graham Williams
Desktop Survival Project Home Preface Data Science Introducing R R Constructs R Tasks R Strings R Read, Write, and Create Data Template Data Exploration Data Wrangling Data Visualisation Statistics ML Template ML Scenarios ML Activities ML Applications ML Algorithms Cluster Analysis Decision Trees Computer Vision Graph Data Privacy Literate Data Science Coding with Style Resources Bibliography Index

CLICK HERE TO VISIT THE UPDATED SURVIVAL GUIDE

Data Template

library(janitor)      # Cleanup: clean_names().
library(rattle)       # Dataset: weatherAUS.
library(magrittr)     # Pipelines: %<>%.
library(randomForest) # Imputation: na.roughfix().
library(dplyr)        # Wrangling: rename_all().


dsname <- "weatherAUS"
ds     <- get(dsname)
nobs   <- nrow(ds)

dim(ds)

vnames        <- names(ds)
ds           %<>% rename_all(normVarNames)
names(vnames) <- names(ds)

names(ds)

vars   <- names(ds)
target <- "rain_tomorrow"
vars   <- c(target, vars) %>% unique() %>% rev()

for (v in which(sapply(ds, is.factor))) levels(ds[[v]]) %<>% normVarNames()

risk   <- "risk_mm"
id     <- c("date", "location")
ignore <- c(risk, id)
vars   <- setdiff(vars, ignore)
inputs <- setdiff(vars, target)

form   <- formula(paste(target, "~ ."))

ds[vars] %<>% na.roughfix()

## Error in na.roughfix.data.frame(.): na.roughfix only works for numeric or factor

SPLIT <- c(0.7, 0.15, 0.15)

tr     <- sample(nobs, SPLIT[1]*nobs)
tu     <- nobs %>% seq_len() %>% setdiff(tr) %>% sample(SPLIT[2]*nobs)
te     <- nobs %>% seq_len() %>% setdiff(tr) %>% setdiff(tu)

target.tr <- ds %>% slice(tr) %>% pull(target)
target.tu <- ds %>% slice(tu) %>% pull(target)
target.te <- ds %>% slice(te) %>% pull(target)

if (!is.null(risk))
{
  risk.tr   <- ds %>% slice(tr) %>% pull(risk)
  risk.tu   <- ds %>% slice(tu) %>% pull(risk)
  risk.te   <- ds %>% slice(te) %>% pull(risk)
}