Numeric variables

Feature Engineering per il Machine Learning in Python

Robert O'Callaghan

Director of Data Science, Ordergroove

Types of numeric features

  • Age
  • Price
  • Counts
  • Geospatial data
Feature Engineering per il Machine Learning in Python

Does size matter?

Feature Engineering per il Machine Learning in Python

Binarizing numeric variables

df['Binary_Violation'] = 0

df.loc[df['Number_of_Violations'] > 0, 
       'Binary_Violation'] = 1
Feature Engineering per il Machine Learning in Python

Binarizing numeric variables

Feature Engineering per il Machine Learning in Python

Binning numeric variables

import numpy as np
df['Binned_Group'] = pd.cut(
    df['Number_of_Violations'], 
    bins=[-np.inf, 0, 2, np.inf],
    labels=[1, 2, 3]
)
Feature Engineering per il Machine Learning in Python

Binning numeric variables

Feature Engineering per il Machine Learning in Python

Lets start practicing!

Feature Engineering per il Machine Learning in Python

Preparing Video For Download...