Intermediate Predictive Analytics in Python

PodstawowyPoziom umiejętności

Zaktualizowano 08.2024

Learn how to prepare and organize your data for predictive analytics.

Utwórz bezpłatne konto

Lub

Kontynuując, akceptujesz nasze Warunki korzystania, naszą Politykę prywatności oraz fakt, że Twoje dane są przechowywane w USA.

Opis kursu

Building good models only succeeds if you have a decent base table to start with. In this course you will learn how to construct a good base table, create variables and prepare your data for modeling. We finish with advanced topics on the matter.

Wymagania wstępne

Introduction to Predictive Analytics in Python

Crucial base table concepts

In this chapter you will learn how to construct the foundations of your base table, namely the population and the target.

The basetable timeline

50 PD

Timeline violations

50 PD

Available data

100 PD

Timeline violation

100 PD

The population

50 PD

Select the relevant population

50 PD

A timeline compliant population

100 PD

Removing duplicate objects

100 PD

The target

50 PD

Calculate an event target

100 PD

Calculate an aggregated target

100 PD

Rozpocznij Rozdział

Creating variables

You will learn how to add variables to the base table that you can use to predict the target.

Adding fixed variables

50 PD

Selecting the right value

50 PD

Adding age

100 PD

Adding the donor segment

100 PD

Adding living place

100 PD

Adding aggregated variables

50 PD

Selecting the appropriate date

50 PD

Maximum value last year

100 PD

Recency of donations

100 PD

Adding evolutions

50 PD

Ratio of last month's and last year's average

100 PD

Absolute difference between two years

100 PD

Using evolution variables

50 PD

Performance of evolution variables

100 PD

Meaning of evolution

100 PD

Rozpocznij Rozdział

Data preparation

Once you derived variables from the raw data, it is time to clean the data and prepare it for modeling. In this Chapter we discuss the steps that need to be taken to make your data modeling-ready.

Creating dummies

50 PD

Creating a dummy from a two-category variable

100 PD

Creating dummies from a many-categories variable

100 PD

Missing values

50 PD

How to replace missing values

50 PD

Creating a missing value dummy

100 PD

Replace missing values with the median value

100 PD

Replace missing values with a fixed value

100 PD

Handling outliers

50 PD

Influence of outliers on predictive models

50 PD

Handle outliers with winsorization

100 PD

Handle outliers with standard deviation

100 PD

Transformations

50 PD

Interactions

50 PD

Square root transformation

100 PD

Adding interactions to the basetable

100 PD

Rozpocznij Rozdział

Advanced base table concepts

In some cases, the target or variables change heavily with the seasons. You will learn how you can deal with seasonality by adding different snapshots to the base table.

Seasonality

50 PD

Seasonality or not

50 PD

Detecting seasonality

100 PD

The effect of seasonality

100 PD

Using multiple snapshots

50 PD

Target values

50 PD