|
所在平台: Coursera |
课程主页: https://www.coursera.org/learn/data-science-methodology
课程评论：没有评论
课程名称：数据科学方法论 课程概述： 尽管近年来计算能力和数据获取的明显提升，我们在决策过程中有效利用数据的能力仍然常常未能被最大化。很多时候，我们对所提问题的理解不够深入，无法正确应用数据解决实际问题。本课程旨在分享一种数据科学的方法论，以确保在问题解决中所使用的数据是相关的，并且能够被合理操作以应对具体问题。 在本课程中，您将学习到： - 处理数据科学问题的主要步骤。 - 数据科学实践中的关键步骤，从明确的商业或研究问题到数据收集与分析，再到模型构建和模型部署后的反馈理解。 - 数据科学家的思考方式！ 课程大纲： 1. 从问题到方法与从需求到收集： 在本模块中，您将了解为何数据科学充满趣味，数据科学方法论的概念，以及数据科学家为何需要这种方法论。您将深入学习前两个阶段：商业理解和分析方法，并掌握定义决策树分类的数据需求的考虑因素和步骤。此外，您还将学习数据科学家在评估数据内容、质量及初步洞察中所使用的过程和技术。 2. 从理解到准备与从建模到评估： 在这一模块中，您将学习数据科学家在理解、准备和清理数据时所执行的任务和目标。您将探讨数据建模过程的目的、特征和目标，并了解如何处理缺失、不合法或误导性的数据。 3. 从部署到反馈与最终评估： 完成本模块后，您将能够描述数据科学方法论的部署及反馈阶段，评估数据模型的表现、影响和准备情况，识别通常参与模型优化的利益相关者，并解释为何部署与反馈应该是一个迭代过程。 4. 最终项目与评估： 在完成最终项目前，您将学习CRISP-DM数据科学方法论与John Rollins基础方法论的比较，并运用所学知识完成一个同行评分的作业。您将以客户端和数据科学家的角色，描述如何运用CRISP-DM方法论解决所定义的商业问题，并进行彼此作业的评分。 这个课程将为您在数据科学领域的实践提供扎实的方法论基础。
Name:From Problem to Approach and From Requirements to Collection
Description:In this module, you will discover what makes data science interesting, learn what a data science methodology is, and why data scientists need a data science methodology. Next, you’ll gain more in-depth knowledge of the first two data science methodology stages: Business Understanding and Analytic Approach. You’ll discover how to identify considerations and steps needed to define the data requirements for decision tree classification during the Data Requirements stage. Next, learn about the processes and techniques data scientists use to assess data content, quality, and initial insights and how data scientists manage data gaps. Round out this week with practical hands-on experience learning how to approach the Business Understanding and the Analytic Approach stage tasks and the Data Requirements and Collection stage tasks for any data science problem.
Name:From Understanding to Preparation and From Modeling to Evaluation
Description:In this module, you will learn what data scientists do when their tasks and goals are to understand, prepare, and clean the data. You’ll examine the purposes, characteristics, and goals of the data modeling process. You’ll also explore how to prepare a data set by handling missing, invalid, or misleading data. Then check out the hands-on labs where you can gain experience completing tasks relevant to the Data Understanding, Data Preparation, and Modeling and Evaluation stages. You’ll be able to apply the skills you learn to future data science problems.
Name:From Deployment to Feedback and Final Evaluation
Description:When you complete this module, you’ll be able to describe the deployment and feedback stages of the data science methodology. You’ll learn how to assess a data model’s performance, impact, and readiness. You’ll be able to identify the stakeholders who usually contribute to model refinement. You’ll also be able to explain why deployment and feedback should be an iterative process. To complete your hands-on lab experience, you’ll devise a business problem to solve using data related to email, hospitals, or credit cards. You’ll demonstrate your understanding of data science methodology by applying it to a given problem. You’ll construct responses that address each phase of the CRISP-DM based on a chosen business problem. After submitting your work, you’ll evaluate your peers’ final projects and provide constructive ideas and suggestions that fellow learners can apply right away.
Name:Final Project and Assessment
Description:Before completing your final project, learn how CRISP-DM data science methodology compares to John Rollins’ foundational data science methodology. Then, apply what you learned to complete a peer-graded assignment using CRISP-DM data science methodology to solve a business problem you define. You'll first take on both the client and data scientist role and describe how you would apply CRISP-DM data science methodology to solve the business problem. Then, take on the role of a data scientist and apply your knowledge of CRISP-DM data methodology stages to describe how you would solve the business problem. After you submit your assignment, you'll grade the assignment of one peer who is enrolled in this session. Let's get started!
Despite the recent increase in computing power and access to data over the last couple of decades, our ability to use the data within the decision making process is either lost or not maximized at all too often, we don't have a solid understanding of the questions being asked and how to apply the data correctly to the problem at hand. This course has one purpose, and that is to share a methodology that can be used within data science, to ensure that the data used in problem solving is relevant and properly manipulated to address the question at hand. Accordingly, in this course, you will learn: - The major steps involved in tackling a data science problem. - The major steps involved in practicing data science, from forming a concrete business or research problem, to collecting and analyzing data, to building a model, and understanding the feedback after model deployment. - How data scientists think!
