Continuous data

My broad definition of continuous data is data that is stored as a number, either an integer or a float. There is some gray area between categorical and continuous data. For example, the grade level could be represented as a number (ignoring Kindergarten, or using 0 to represent it). A grade column, in this case, could be both categorical and continuous, so the techniques in this section and the previous section could both apply to it.

We will examine a continuous column from the fuel economy dataset in this section. The city08 column lists the miles per gallon that are expected when driving a car at the lower speeds found in a city.

How to do it…

1. Pick out the columns that are numeric (typically int64 or float64):

   >>> fueleco.select_dtypes("number")
          barrels08  barrelsA08  ...  phevHwy  phevComb
   0      15.695714         0.0  ...        0         0
   1      29.964545         0.0  ...        0         0
   2     ...