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

Ordered Factor

20180723 Given our knowledge that compass directions have an obvious order, we convert the direction variables into an ordered factor. We do so using ordered=TRUE with base::factor().

# Note the names of the wind direction variables.

ds %>%
  select(contains("_dir")) %>%
  names() %T>%
  print() ->
vnames

## [1] "wind_gust_dir" "wind_dir_9am"  "wind_dir_3pm"

# Convert these variables from character to factor.

ds[vnames] %<>%
  lapply(factor, levels=compass, ordered=TRUE) %>%
  data.frame() %>%
  as_tibble()
# Confirm they are now factors.

ds[vnames] %>% sapply(class)

##      wind_gust_dir wind_dir_9am wind_dir_3pm
## [1,] "ordered"     "ordered"    "ordered"   
## [2,] "factor"      "factor"     "factor"

We can again obtain a distribution of the variables to confirm that all we have changed is the data type.

# Verify the distribution has not changed.

ds %>%
  select(contains("_dir")) %>%
  sapply(table)

##     wind_gust_dir wind_dir_9am wind_dir_3pm
## N           10989        13978        10475
## NNE          7937         9782         8002
## NE           8715         9335        10092
## ENE          9965         9592         9605
## E           11071        11237        10123
## ESE          9055         9536        10290
## SE          11331        11398        12919
## SSE         10946        10954        11089
## S           11043        10519        11788
## SSW         10809         9272         9902
## SW          10793        10135        11166
....