Pular para o conteúdo principal

Curso

Introdução à Análise Preditiva em Python

BásicoNível de habilidade

Atualizado 11/2022

Neste curso, você vai aprender a usar e apresentar modelos de regressão logística para fazer previsões.

Iniciar Curso Gratuitamente

PythonMachine Learning

4 h

14 vídeos

52 Exercícios

4,100 XP

22,554

Declaração de realização

Preferido por alunos de milhares de empresas

Treinando uma equipe?

Experimente para Empresas

Descrição do curso

Neste curso, você vai aprender a construir um modelo de regressão logística com variáveis relevantes. Você também vai aprender a usar esse modelo para fazer previsões e como apresentá-lo, junto com seu desempenho, para as partes interessadas de negócios.

Pré-requisitos

Intermediate Python

1

Building Logistic Regression Models

In this Chapter, you'll learn the basics of logistic regression: how can you predict a binary target with continuous variables and, how should you interpret this model and use it to make predictions for new examples?

Introduction and base table structure

Structure of the base table

Exploring the base table

Exploring the predictive variables

Logistic regression

Interpretation of coefficients

Building a logistic regression model

Showing the coefficients and intercept

Using the logistic regression model

Making predictions

Donor that is most likely to donate

Iniciar Capítulo

2

Forward stepwise variable selection for logistic regression

In this chapter you'll learn why variable selection is crucial for building a useful model. You'll also learn how to implement forward stepwise variable selection for logistic regression and how to decide on the number of variables to include in your final model.

Motivation for variable selection

Which model is best?

Calculating AUC

Using different sets of variables

Forward stepwise variable selection

Selecting the next best variable

Finding the order of variables

Correlated variables

Deciding on the number of variables

Partitioning

Evaluating a model on test and train

Building the AUC curves

Deciding the cut-off

Iniciar Capítulo

3

Explaining model performance to business

Now that you know how to build a good model, you should convince stakeholders to use it by creating appropriate graphs. You will learn how to construct and interpret the cumulative gains curve and lift graph.

The cumulative gains curve

Interpreting the cumulative gains curve

Constructing the cumulative gains curve

A random model

The lift curve

Interpreting the lift curve

Constructing the lift curve

A perfect model

Guiding business to better decisions

Targeting using cumulative gains curve

Business case using lift curve

Business case using cumulative gains curve

Iniciar Capítulo

4

Interpreting and explaining models

In a business context, it is often important to explain the intuition behind the model you built. Indeed, if the model and its variables do not make sense, the model might not be used. In this chapter you'll learn how to explain the relationship between the variables in the model and the target by means of predictor insight graphs.

Predictor insight graphs

Interpretation of predictor insight graphs

Retrieving information from the predictor insight table

Discretization of continuous variables

Discretization of a certain variable

Discretizing all variables

Making clean cuts

Preparing the predictor insight graph table

Calculating average incidences

Constructing the predictor insight graph table

Grouping all predictor insight graph tables

Plotting the predictor insight graph

Plotting the incidences

Plotting the group sizes

Putting it all together

Iniciar Capítulo

Introdução à Análise Preditiva em Python

Curso
concluído

Obtenha um certificado de conclusão

Adicione esta credencial ao seu perfil do LinkedIn, currículo ou CV
Compartilhe nas redes sociais e em sua avaliação de desempenhoInscreva-se Agora

Faça como mais de 19 milhões de alunos e comece Introdução à Análise Preditiva em Python hoje mesmo!

Desenvolva suas habilidades em dados com o app do DataCamp

Continue progredindo em qualquer lugar com nossos cursos para celular e desafios diários de programação de 5 minutos.