|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/feature-engineering-for-machine-learning/
课程评论：没有评论
课程名称：机器学习特征工程 课程概述：欢迎参加《机器学习特征工程》课程，这是在线上最全面的特征工程课程。在本课程中，您将学习变量填补、变量编码、特征转换、离散化，并了解如何从数据中创建新特征。掌握特征工程和特征提取，您将学习多种特征工程方法，使您的数据能够准备好用于训练机器学习模型。 具体而言，您将学习： - 如何填补缺失数据 - 如何编码分类变量 - 如何转换数值变量并改变其分布 - 如何进行离散化 - 如何去除异常值 - 如何从日期和时间中提取特征 - 如何从现有特征中创建新特征 该课程强调数学、统计和领域知识在创建有用特征中的应用。特征工程是将现有特征转换或创建新变量以用于机器学习的过程。原始数据不适合训练机器学习算法，因此数据科学家花费大量时间进行数据预处理。课程内容涵盖了准备数据训练模型所需的所有知识。 课程将教授最常用的特征工程技术，如均值和中位数填补、独热编码、对数转换以及离散化，并探索更高级的方法，以提高机器学习模型的性能。您将学习金融中的证据权重法，以及如何创建变量与目标之间单调关系的技术，进一步增强线性模型的表现。 课程还将指导如何利用Python的开源库（如NumPy、Pandas、Scikit-learn等）实现这些特征工程方法，通过详细的讲解介绍每种技术的优缺点和处理流程。到课程结束时，您将能够根据变量特性和希望训练的模型，选择合适的特征工程技术，并测试各种转换方法。 课程内容全面，结合视频、演示文稿和Jupyter笔记本，提供了超过100个讲座和大约10小时的视频，所有主题均包含可供参考和练习的Python代码示例。这栋课程不设定 syllabus，内容不断更新以包括新的特征工程方法，并保证30天退款无风险。 如果您希望在数据科学领域事业上更上一层楼，并有效应对数据清理、缺失值以及变量类型和分布的问题，赶快报名参加这门课程，成为机器学习特征工程的专家！
Welcome to Feature Engineering for Machine Learning, the most comprehensive course on feature engineering available online. In this course, you will learn about variable imputation, variable encoding, feature transformation, discretization, and how to create new features from your data.Master Feature Engineering and Feature Extraction.In this course, you will learn multiple feature engineering methods that will allow you to transform your data and leave it ready to train machine learning models. Specifically, you will learn:How to impute missing dataHow to encode categorical variablesHow to transform numerical variables and change their distributionHow to perform discretizationHow to remove outliersHow to extract features from date and timeHow to create new features from existing onesCreate useful Features with Math, Statistics and Domain KnowledgeFeature engineering is the process of transforming existing features or creating new variables for use in machine learning. Raw data is not suitable to train machine learning algorithms. Instead, data scientists devote a lot of time to data preprocessing. This course teaches you everything you need to know to leave your data ready to train your models.While most online courses will teach you the very basics of feature engineering, like imputing variables with the mean or transforming categorical variables using one hot encoding, this course will teach you that, and much, much more.In this course, you will first learn the most popular and widely used techniques for variable engineering, like mean and median imputation, one-hot encoding, transformation with logarithm, and discretization. Then, you will discover more advanced methods that capture information while encoding or transforming your variables to improve the performance of machine learning models.You will learn methods like the weight of evidence, used in finance, and how to create monotonic relationships between variables and targets to boost the performance of linear models. You will also learn how to create features from date and time variables and how to handle categorical variables with a lot of categories.The methods that you will learn were described in scientific articles, are used in data science competitions, and are commonly utilized in organizations. And what's more, they can be easily implemented by utilizing Python's open-source libraries!Throughout the lectures, you'll find detailed explanations of each technique and a discussion about their advantages, limitations, and underlying assumptions, followed by the best programming practices to implement them in Python.By the end of the course, you will be able to decide which feature engineering technique you need based on the variable characteristics and the models you wish to train. And you will also be well placed to test various transformation methods and let your models decide which ones work best.Step-up your Career in Data ScienceYou've taken your first steps into data science. You know about the most commonly used prediction models. You've even trained a few linear regression or classification models. At this stage, you're probably starting to find some challenges: your data is dirty, lots of values are missing, some variables are not numerical, and others extremely skewed. You may also wonder whether your code is efficient and performant or if there is a better way to program. You search online, but you can't find consolidated resources on feature engineering. Maybe just blogs? So you may start to wonder: how are things really done in tech companies?In this course, you will find answers to those questions. Throughout the course, you will learn multiple techniques for the different aspects of variable transformation, and how to implement them in an elegant, efficient, and professional manner using Python. You will leverage the power of Python's open source ecosystem, including the libraries NumPy, Pandas, Scikit-learn, and special packages for feature engineering: Feature-engine and Category encoders.By the end of the course, you will be able to implement all your feature engineering steps into a single elegant pipeline, which will allow you to put your predictive models into production with maximum efficiency.Leverage the Power of Open SourceWe will perform all feature engineering methods utilizing Pandas and Numpy, and we will compare the implementation with Scikit-learn, Feature-engine, and Category encoders, highlighting the advantages and limitations of each library. As you progress in the course, you will be able to choose the library you like the most to carry out your projects.There is a dedicated Python notebook with code to implement each feature engineering method, which you can reuse in your projects to speed up the development of your machine learning models.The Most Comprehensive Online Course for Feature EngineeringThere is no one single place to go to learn about feature engineering. It involves hours of searching on the web to find out what people are doing to get the most out of their data.That is why, this course gathers plenty of techniques used worldwide for feature transformation, learnt from data competitions in Kaggle and the KDD, scientific articles, and from the instructor's experience as a data scientist. This course therefore provides a source of reference where you can learn new methods and also revisit the techniques and code needed to modify variables whenever you need to.This course is taught by a lead data scientist with experience in the use of machine learning in finance and insurance, who is also a book author and the lead developer of a Python open source library for feature engineering. And there is more:The course is constantly updated to include new feature engineering methods.Notebooks are regularly refreshed to ensure all methods are carried out with the latest releases of the Python libraries, so your code will never break.The course combines videos, presentations, and Jupyter notebooks to explain the methods and show their implementation in Python.The curriculum was developed over a period of four years with continuous research in the field of feature engineering to bring you the latest technologies, tools, and trends.Want to know more? Read on...This comprehensive feature engineering course contains over 100 lectures spread across approximately 10 hours of video, and ALL topics include hands-on Python code examples that you can use for reference, practice, and reuse in your own projects.REMEMBER, the course comes with a 30-day money-back guarantee, so you can sign up today with no risk.So what are you waiting for? Enrol today and join the world's most comprehensive course on feature engineering for machine learning.
