Dockerfile.tar.gz

Numerical Variables

Default Job

In this course, you will learn how to apply basic and more advanced feature engineering to tabular data with python, during this course,  we will see a range of different techniques and methods to handle many common cases within the data set, so in result, you will create great features so that your machine learning models can predict good results.

Feature Engineering with Python

## Discretization with decision trees
Discretization with Decision Trees uses a decision tree to identify the optimal splitting points that determine the bins or contiguous intervals.

## Steps
1. Step 1: First, it trains a decision tree of limited depth (2, 3, or 4) using the variable we want to discretize to predict the target.
2. Step 2: The probability returned by the tree then replaces the original variable values. The probability is the same for all the observations within a single bin, thus replacing by the probability is equivalent to grouping the observations within the cut-off decided by the decision tree.

## Points to consider
When using decision trees for discretization, we have to consider these points: 
- It creates a monotonic relationship.
- Trees are known for being robust to outliers, so this method handles outliers.
- The observations in each bin are very much alike.
- This method does not help improve the values spread.
- It is vulnerable to over-fitting.
- It is a bit time-consuming to adjust the parameters effectively (e.g., tree depth, the minimum number of samples in one partition, minimum information gain)

## Demo

We will learn how to implement discretization with decision trees working with the Titanic dataset, just un the code snippet below:

# Discretization with decision trees
Discretization with Decision Trees uses a decision tree to identify the optimal splitting points that determine the bins or contiguous intervals.

# Steps
1. Step 1: First, it trains a decision tree of limited depth (2, 3, or 4) using the variable we want to discretize to predict the target.
2. Step 2: The probability returned by the tree then replaces the original variable values. The probability is the same for all the observations within a single bin, thus replacing by the probability is equivalent to grouping the observations within the cut-off decided by the decision tree.

# Points to consider
When using decision trees for discretization, we have to consider these points: 
- It creates a monotonic relationship.
- Trees are known for being robust to outliers, so this method handles outliers.
- The observations in each bin are very much alike.
- This method does not help improve the values spread.
- It is vulnerable to over-fitting.
- It is a bit time-consuming to adjust the parameters effectively (e.g., tree depth, the minimum number of samples in one partition, minimum information gain)

# Demo

We will learn how to implement discretization with decision trees working with the Titanic dataset, just un the code snippet below:

The discretization process can be achieved using decision trees as well. How does it work? What should we take into consideration? Furthermore, how to use this method in our code? We will see all that in this lesson.


Discretization with decision trees

The discretization process can be achieved using decision trees as well. How does it work? What should we take into consideration? Furthermore, how to use this method in our code? We will see all that in this lesson.

Introduction

Variable Types

Common Concerns in Datasets

Handling & Imputing Missing Values

Encoding Categorical Variables

Transforming Variables

Variable Discretization

Handling Outliers

Feature Scaling

Engineering Geospatial Data

Handling Date-Time and Mixed Variables

Resampling Imbalanced Data

Advanced Feature Engineering Techniques

Conclusion

Discretization with decision trees

Discretization with decision trees

Steps