使用 SAS Viya 进行机器学习

SAS

課程信息

46,648 次近期查看

This course covers the theoretical foundation for different techniques associated with supervised machine learning models. In addition, a business case study is defined to guide participants through all steps of the analytical life cycle, from problem understanding to model deployment, through data preparation, feature selection, model training and validation, and model assessment. A series of demonstrations and exercises is used to reinforce the concepts and the analytical approach to solving business problems. 
This course uses Model Studio, the pipeline flow interface in SAS Viya that enables you to prepare, develop, compare, and deploy advanced analytics models. You learn to train supervised machine learning models to make better decisions on big data. The SAS applications used in this course make machine learning possible without programming or coding.

可分享的證書

完成後獲得證書

100% 在線

立即開始，按照自己的計劃學習。

可靈活調整截止日期

根據您的日程表重置截止日期。

中級

完成時間大約為47 小時

英語（English）

字幕：英語（English）

講師

授課教師評分

4.44/5 （11 個評分）

Jeff Thompson

Senior Analytical Training Consultant

Education

4,476 個學生

1 門課程

Catherine Truxillo

Director, Analytical Education

Education

4,476 個學生

1 門課程

可分享的證書

完成後獲得證書

100% 在線

立即開始，按照自己的計劃學習。

可靈活調整截止日期

根據您的日程表重置截止日期。

中級

完成時間大約為47 小時

英語（English）

字幕：英語（English）

提供方

SAS

Through innovative software and services, SAS empowers and inspires customers around the world to transform data into intelligence. SAS is a trusted analytics powerhouse for organizations seeking immediate value from their data. A deep bench of analytics solutions and broad industry knowledge keep our customers coming back and feeling confident. With SAS®, you can discover insights from your data and make sense of it all. Identify what’s working and fix what isn’t. Make more intelligent decisions. And drive relevant change.

教學大綱 - 您將從這門課程中學到什麼

週

週 1

完成時間為 1 小時

Course Overview

In this module, you meet the instructor and learn about course logistics, such as how to access the software for this course.

完成時間為 1 小時

1 個視頻（總計 1 分鐘）, 3 個閱讀材料, 1 個測驗

1 個視頻

Welcome to the Course!1分鐘

3 個閱讀材料

Learner Prerequisites

Using SAS® Viya® for Learners with This Course (Required)10分鐘

Using Forums and Getting Help10分鐘

完成時間為 8 小時

Getting Started with Machine Learning using SAS® Viya®

In this module, you learn how you can meet today's business challenges with machine learning using SAS® Viya®. You start working on the project that runs throughout the course.

完成時間為 8 小時

15 個視頻（總計 40 分鐘）, 16 個閱讀材料, 10 個測驗

15 個視頻

Introduction16

Machine Learning in SAS Viya2分鐘

Analytics Life Cycle1分鐘

Case Study: Customer Churn2分鐘

SAS Viya Tools for SAS Visual Data Mining and Machine Learning1分鐘

Demo: Creating a Project4分鐘

Predictive Modeling5分鐘

Importance of Data Preparation55

Essential Data Tasks1分鐘

Dividing the Data3分鐘

Addressing Rare Events Using Event-Based Sampling3分鐘

Demo: Modifying the Data Partition4分鐘

Managing Missing Values3分鐘

Demo: Building a Pipeline from a Basic Template4分鐘

SAS Viya in the SAS Platform: Architecture1分鐘

16 個閱讀材料

Applications of Prediction-Based Decision Making10分鐘

Advantages of the SAS Platform10分鐘

Case Study: Data Dictionary10分鐘

SAS Drive and the Applications Menu10分鐘

Importing Data from a Local Source10分鐘

SAS Viya Tools for Data Preparation10分鐘

Cross Validation for Small Data Sets10分鐘

Global Metadata10分鐘

Managing Missing Values: Details10分鐘

Pipeline Templates in Model Studio10分鐘

Logistic Regression10分鐘

SAS Cloud Analytic Services10分鐘

SAS Viya: A Shift in Mindset10分鐘

Data Sources and CAS10分鐘

Interfaces and Products10分鐘

SAS Visual Data Mining and Machine Learning10分鐘

7 個練習

Question 1.0130分鐘

Question 1.0230分鐘

Question 1.0330分鐘

Question 1.0430分鐘

Question 1.0530分鐘

Question 1.0630分鐘

Getting Started with Machine Learning and SAS Viya30分鐘

週

週 2

完成時間為 9 小時

Data Preparation and Algorithm Selection

In this module, you learn to explore the data and finish preparing the data for analysis. You also learn some general considerations for selecting an algorithm.

完成時間為 9 小時

14 個視頻（總計 47 分鐘）, 11 個閱讀材料, 16 個測驗

14 個視頻

Introduction to Data Preparation and Algorithm Selection48

Exploring the Data1分鐘

Demo: Exploring the Data4分鐘

Replacing Incorrect Values1分鐘

Demo: Replacing Incorrect Values Starting on the Data Tab7分鐘

Feature Creation27

Text Mining1分鐘

Demo: Adding Text Mining Features7分鐘

Using Transformations to Handle Extreme or Unusual Values3分鐘

Demo: Transforming Inputs5分鐘

Selecting Useful Inputs4分鐘

Demo: Selecting Features6分鐘

Demo: Saving a Pipeline to the Exchange1分鐘

Essential Discovery Tasks and Selecting an Algorithm1分鐘

11 個閱讀材料

Data Mining Preprocessing Nodes in Model Studio10分鐘

Replacing Incorrect Values Starting with the Manage Variables Node10分鐘

Singular Value Decomposition10分鐘

Feature Extraction Node10分鐘

Finding the Best Transformation in Model Studio10分鐘

Feature Selection and the Variable Selection Node in Model Studio: Details10分鐘

Variable Clustering10分鐘

Best Practices for Common Data Preparation Challenges10分鐘

Automated Feature Engineering Pipeline Template10分鐘

Considerations for Selecting an Algorithm10分鐘

Comparison of Modeling Algorithms10分鐘

9 個練習

Question 2.0130分鐘

Question 2.0230分鐘

Question 2.0330分鐘

Question 2.0430分鐘

Question 2.0530分鐘

Question 2.0630分鐘

Question 2.0730分鐘

Question 2.085分鐘

Data Preparation and Algorithm Selection Quiz30分鐘

週

週 3

完成時間為 11 小時

Decision Trees and Ensembles of Trees

In this module, you learn to build decision tree models as well as models based on ensembles, or combinations, of decision trees.

完成時間為 11 小時

23 個視頻（總計 68 分鐘）, 12 個閱讀材料, 21 個測驗

23 個視頻

Introduction to Decision Trees and Ensembles of Trees41

Basics of Decision Trees2分鐘

Demo: Building a Decision Tree Model Using the Default Settings7分鐘

Decision Trees for Categorical Targets: Classification Trees3分鐘

Decision Trees for Interval Targets: Regression Trees2分鐘

Improving the Decision Tree Model25

Demo: Modifying the Structure Parameters1分鐘

Recursive Partitioning3分鐘

Splitting Criteria4分鐘

Split Search9分鐘

Demo: Modifying the Recursive Partitioning Parameters1分鐘

Optimizing the Complexity of a Decision Tree Model39

Pruning3分鐘

Demo: Modifying the Pruning Parameters2分鐘

Regularizing and Tuning the Hyperparameters of a Machine Learning Model2分鐘

Building Ensemble Models1分鐘

Perturb and Combine Methods5分鐘

Bagging2分鐘

Boosting1分鐘

Comparison of Tree-Based Models1分鐘

Demo: Building a Gradient Boosting Model3分鐘

Forest Models3分鐘

Demo: Building a Forest Model4分鐘

12 個閱讀材料

Impurity Reduction Measures for Categorical and Interval Targets10分鐘

Splitting Criteria in Model Studio10分鐘

Adjustments in a Split Search10分鐘

Missing Values in Decision Trees in Model Studio10分鐘

Surrogate Splits10分鐘

Calculating Variable Importance for Surrogate Splits10分鐘

Bottom-Up Pruning Requirements10分鐘

Pruning Options in Model Studio10分鐘

Autotuning Options for Decision Trees in Model Studio10分鐘

Gradient Boosting Models10分鐘

Autotuning Options for Gradient Boosting in Model Studio10分鐘

Autotuning Options for Forests in Model Studio10分鐘

11 個練習

Question 3.01

Question 3.0230分鐘

Question 3.0330分鐘

Question 3.0430分鐘

Question 3.0530分鐘

Think About It30分鐘

Question 3.0630分鐘

Question 3.0730分鐘

Question 3.08

Question 3.0930分鐘

Decision Trees and Ensembles of Trees Quiz30分鐘

週

週 4

完成時間為 8 小時

Neural Networks

In this module, you learn to build neural network models.

完成時間為 8 小時

18 個視頻（總計 37 分鐘）, 10 個閱讀材料, 13 個測驗

18 個視頻

Introduction to Neural Networks29

Beyond Traditional Regression: Neural Networks3分鐘

Limitations of Neural Networks2分鐘

Basics of Neural Networks3分鐘

Estimating Weights and Making Predictions3分鐘

Learning Process2分鐘

Essential Discovery Tasks for Neural Networks24

Demo: Building a Neural Network Using the Default Settings3分鐘

Improving the Neural Network Model22

Neural Network Architectures4分鐘

Activation Functions1分鐘

Shaping the Sigmoid2分鐘

Demo: Modifying the Neural Network Architecture1分鐘

Optimizing the Complexity of a Neural Network Model40

Weight Decay1分鐘

Early Stopping2分鐘

Regularizing and Tuning the Hyperparameters of a Neural Network Model32

Demo: Modifying the Learning and Optimization Parameters2分鐘

10 個閱讀材料

Standardization Methods10分鐘

Iterative Updating in Numerical Optimization10分鐘

Numerical Optimization Methods in Model Studio10分鐘

Deviance Measures in Model Studio10分鐘

Calculating the Number of Parameters10分鐘

Deep Learning10分鐘

Hidden Layer Activation Functions in Model Studio10分鐘

Target Layer Activation Functions and Error Functions in Model Studio10分鐘

Selected Hyperparameters Related to the Learning Process in Model Studio10分鐘

Autotuning Options for Neural Networks in Model Studio10分鐘

8 個練習

Question 4.0130分鐘

Question 4.0230分鐘

Question 4.0330分鐘

Question 4.0430分鐘

Question 4.0530分鐘

Question 4.0630分鐘

Question 4.0730分鐘

Neural Networks Quiz30分鐘

週

週 5

完成時間為 6 小時

Support Vector Machines

In this module, you learn to build support vector machine models.

完成時間為 6 小時

17 個視頻（總計 26 分鐘）, 5 個閱讀材料, 11 個測驗

17 個視頻

Introduction to Support Vector Machines46

Support Vector Machines as Classifier Models2分鐘

Mathematical Definition of a Support Vector Machine1分鐘

Maximum-Margin Hyperplane and Support Vectors1分鐘

Essential Discovery Tasks for Support Vector Machines23

Demo: Building a Support Vector Machine Using the Default Settings2分鐘

Improving the Support Vector Machine Model1分鐘

Optimization Problem1分鐘

Accounting for Errors with Nonlinearly Separable Data51

Demo: Modifying the Methods of Solution Parameters1分鐘

Optimizing the Complexity of the Support Vector Machine Model31

Feature Space Approach for Nonlinearly Separable Data1分鐘

Kernel Trick1分鐘

Demo: Increasing the Flexibility of the Support Vector Machine2分鐘

Model Interpretability1分鐘

Demo: Adding Model Interpretability4分鐘

Regularizing and Tuning the Hyperparameters of the Support Vector Machine Model22

5 個閱讀材料

Dot Products10分鐘

Constraints for Optimization10分鐘

Lagrange Approach for Estimation10分鐘

Model Interpretability Plots10分鐘

Autotuning Options for Support Vector Machines in Model Studio10分鐘

5 個練習

Question 5.0130分鐘

Question 5.0230分鐘

Question 5.0330分鐘

Question 5.0430分鐘

Support Vector Machines Quiz30分鐘

週

週 6

完成時間為 6 小時

Model Deployment

In this module, you learn how to select the model that best meets the requirements of your business challenge and put the model into production. You also learn about managing the model over time.

完成時間為 6 小時

14 個視頻（總計 27 分鐘）, 2 個閱讀材料, 11 個測驗

14 個視頻

Introduction to Model Deployment36

Essential Deployment Tasks41

Selecting a Model45

Numeric Measures of Model Performance1分鐘

Confusion Matrix for Decision Predictions1分鐘

ROC Charts and the C-Statistic3分鐘

Charts Based on Response Rate: CPH and Lift3分鐘

Ways of Comparing Models in Model Studio1分鐘

Demo: Comparing Models within a Pipeline2分鐘

Demo: Comparing Models across Pipelines2分鐘

Demo: Exploring the Settings for Model Comparison and Selection2分鐘

Scoring and Managing the Champion Model1分鐘

Demo: Exploring the Features for Scoring and Managing a Model in Model Manager2分鐘

Monitoring and Updating the Model1分鐘

2 個閱讀材料

Numeric Measures of Model Performance by Prediction Type10分鐘

Model Selection Statistics by Target Type10分鐘

6 個練習

Question 6.0130分鐘

Question 6.0230分鐘

Question 6.0330分鐘

Question 6.0430分鐘

Question 6.0530分鐘

Model Deployment Quiz30分鐘

常見問題

我什么时候能够访问课程视频和作业？
讲座和作业的访问权限取决于您的注册类型。如果您以旁听模式参加课程，则可以免费查看大多数课程资料。要访问评分作业并获得证书，您需要在旁听期间或之后购买证书体验。如果看不到旁听选项：
课程可能不提供旁听选项。您可以尝试免费试用，也可以申请助学金。
课程可能会改为提供'完整课程，没有证书'。通过此选项，您可以查看所有课程材料、提交所要求的作业，以及获得最终成绩。这也意味着您将无法购买证书体验。
我购买证书后会得到什么？
您购买证书后，将有权访问所有课程材料，包括评分作业。完成课程后，您的电子课程证书将添加到您的成就页中，您可以通过该页打印您的课程证书或将其添加到您的领英档案中。如果您只想阅读和查看课程内容，可以免费旁听课程。
Is financial aid available?
是的，Coursera 可以向无法承担学费的学生提供助学金。点击左侧‘注册’按钮下的‘助学金’链接即可申请助学金。您可以根据屏幕提示完成申请，申请获批后会收到通知。了解详情。
What browser is recommended for accessing software in this course?
We recommend Chrome, Firefox or Safari when accessing the software.
完成课程后，我会获得大学学分吗？
此课程不提供大学学分，但部分大学可能会选择接受课程证书作为学分。查看您的合作院校，了解详情。Coursera 上的在线学位和 Mastertrack™ 证书提供获得大学学分的机会。

還有其他問題嗎？請訪問學生幫助中心。

使用 SAS Viya 进行机器学习