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 Glimpse

20200317 Another useful tool to quickly review the dataset is dplyr::glimpse(). Data from all columns is presented, including the first observations of the individual columns.

glimpse(ds)

## Rows: 3,984
## Columns: 24
## $ Date          <dttm> 2008-02-01, 2008-02-02, 2008-02-03, 2008-02-04, 2...
## $ Location      <chr> "Sydney", "Sydney", "Sydney", "Sydney", "Sydney", ...
## $ MinTemp       <dbl> 19.5, 19.5, 21.6, 20.2, 19.7, 20.2, 18.6, 17.2, 16...
## $ MaxTemp       <dbl> 22.4, 25.6, 24.5, 22.8, 25.7, 27.2, 26.3, 22.3, 20...
## $ Rainfall      <dbl> 15.6, 6.0, 6.6, 18.8, 77.4, 1.6, 6.2, 27.6, 12.6, ...
## $ Evaporation   <dbl> 6.2, 3.4, 2.4, 2.2, NA, 2.6, 5.2, 5.8, 4.8, 4.4, 6...
## $ Sunshine      <dbl> 0.0, 2.7, 0.1, 0.0, 0.0, 8.6, 5.2, 2.1, 3.0, 10.1,...
## $ WindGustDir   <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ WindGustSpeed <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA...
## $ WindDir9am    <chr> "S", "W", "ESE", "NNE", "NNE", "W", "W", "S", "SSW...
## $ WindDir3pm    <chr> "SSW", "E", "ESE", "E", "W", "ENE", "S", "SE", "W"...
## $ WindSpeed9am  <dbl> 17, 9, 17, 22, 11, 9, 15, 7, 19, 11, 9, 7, 24, 15,...
## $ WindSpeed3pm  <dbl> 20, 13, 2, 20, 6, 22, 15, 15, 9, 20, 26, 24, 30, 1...
## $ Humidity9am   <dbl> 92, 83, 88, 83, 88, 69, 75, 77, 92, 80, 78, 68, 87...
## $ Humidity3pm   <dbl> 84, 73, 86, 90, 74, 62, 80, 61, 91, 53, 53, 67, 70...
## $ Pressure9am   <dbl> 1017.6, 1017.9, 1016.7, 1014.2, 1008.3, 1002.7, 99...
## $ Pressure3pm   <dbl> 1017.4, 1016.4, 1015.6, 1011.8, 1004.8, 998.6, 100...
## $ Cloud9am      <dbl> 8, 7, 7, 8, 8, 6, 4, 7, 7, 4, 7, 7, 8, 7, 7, 7, 7,...
## $ Cloud3pm      <dbl> 8, 7, 8, 8, 8, 6, 7, 8, 7, 2, 8, 7, 7, 1, 3, 6, 7,...
## $ Temp9am       <dbl> 20.7, 22.4, 23.5, 21.4, 22.5, 23.8, 21.7, 18.9, 17...
## $ Temp3pm       <dbl> 20.9, 24.8, 23.0, 20.9, 25.5, 26.0, 22.3, 21.1, 16...
## $ RainToday     <chr> "Yes", "Yes", "Yes", "Yes", "Yes", "Yes", "Yes", "...
## $ RISK_MM       <dbl> 6.0, 6.6, 18.8, 77.4, 1.6, 6.2, 27.6, 12.6, 8.8, 0...
## $ RainTomorrow  <chr> "Yes", "Yes", "Yes", "Yes", "Yes", "Yes", "Yes", "...

Notice the style used for variable names here. Different datasets will use different styles. It is useful to convert the variable names (and the levels of a factor) to a canonical form across all of the dataset that we deal with and so avoid having to remember particular naming schemes. We do this next.