|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/master-python-data-analysis-and-modelling-essentials/
课程评论：没有评论
课程名称：掌握Python数据分析与建模基础 课程概述：在这个数据爆炸的时代，数据无处不在，因此建立数据分析和建模技能尤为重要。根据TIOBE指数，自2021年10月以来，Python已超过Java和C，成为当今最受欢迎的编程语言。Python在KDnuggets民调中也位居数据科学和机器学习平台的首位。本课程以真实世界的项目和数据集为基础，结合著名的Python库，教授如何探索数据、发现并解决问题，以及逐步开发经典的统计回归模型和机器学习回归模型。该课程特别适合初学者和中级学习者，但许多方法对于高级学习者也非常有帮助。 完成本课程后，您将掌握以下技能： 1. 使用Python Pandas库进行数据探索 2. 用不同方法重命名数据列 3. 通过各种方法检测数据集中的缺失值和异常值 4. 使用不同方法填补缺失值并处理异常值 5. 进行相关性分析并根据分析结果选择特征 6. 用不同方法对分类变量进行编码 7. 将数据集划分为模型训练和测试集 8. 使用缩放方法对数据进行归一化 9. 开发经典的统计回归模型和机器学习回归模型 10. 拟合模型、改进模型、评估模型并可视化建模结果等等 课程内容丰富，将为您在数据分析与建模领域奠定坚实的基础。
We are living in a data explosive world where data is ubiquitous, and thus it is essential to build data analysis and modelling skills. Based on TIOBE Index, Python has overpassed Java and C and become the most popular programming language of today since October 2021. Python leads the top Data Science and Machine Learning platforms based on KDnuggets poll. This course uses a real world project and dataset and well known Python libraries to show you how to explore data, find the problems and fix them, and how to develop classic statistical regression models and machine learning regression step by step in an easily understand way. This course is especially suitable for beginner and intermediate levels, but many of the methods are also very helpful for the advanced learners. After this course, you will own the skills to:(1) to explore data using Python Pandas library (2) to rename the data column using different methods(3) to detect the missing values and outliers in dataset through different methods(4) to use different methods to fill in the missings and treat the outliers(5) to make correlation analysis and select the features based on the analysis(6) to encode the categorical variables with different methods(7) to split dataset for model training and testing(8) to normalize data with scaling methods(9) to develop classic statistical regression models and machine learning regression models(10) to fit the model, improve the model, evaluate the model and visualize the modelling results, and many more
