|
所在平台: Coursera |
课程主页: https://www.coursera.org/learn/statistics-for-data-science-python
课程评论：没有评论
课程名称：用Python进行数据科学统计分析 课程概述： 本课程旨在向学员介绍用于数据分析的基本统计方法和程序。完成课程后，学员将掌握统计学的关键主题，包括数据收集、描述性统计的应用、数据展示与可视化、变量之间关系的分析、概率分布、期望值、假设检验、方差分析（ANOVA）简介，以及回归与相关分析。课程采用实践导向，使用Python和Jupyter Notebooks进行统计分析，这也是数据科学家和数据分析师的常用工具。 在课程结束时，学员将完成一个项目，利用课程中的不同概念解决一个真实生活场景中的数据科学问题，展示对基础统计思维和推理的理解。课程重点在于发展清晰的不同数据类型的处理方法、直观理解、合理评估所提出的方法、使用Python分析数据并准确解读输出结果。 适合对象： 本课程适合希望进入数据和统计驱动角色的各类专业人士和学生，如数据科学家、数据分析师、商业分析师、统计学家和研究人员。课程不要求具备计算机科学或统计学背景。强烈建议在学习本课程之前先修习《数据科学的Python基础》课程，以便熟悉Python编程语言、Jupyter Notebooks及相关库。此外，课程还提供了Python的自学资料。 课程学习目标： ✔ 计算并应用集中趋势和离散程度的度量，应用于分组和未分组数据。 ✔ 清晰、简明地总结、展示和可视化数据，为非统计人员提供实际洞察。 ✔ 确定适合常见数据集的假设检验方法。 ✔ 进行假设检验、相关性检验和回归分析。 ✔ 在Python和Jupyter Notebooks中展示统计分析的熟练度。 课程大纲： 1. 课程简介与Python基础 - 欢迎参加课程！ 2. 介绍与描述性统计 - 本模块将介绍描述性统计的基本概念，包括均值、中位数、众数、方差和标准差，以及集中趋势和离散程度测量的使用价值。 3. 数据可视化 - 本模块将探讨根据数据类型和信息需求的不同，选择不同的数据可视化方法。学员将学习如何计算和解读这些测量指标和图表。 4. 概率分布简介 - 本模块将介绍概率和概率分布的基本概念及应用。 5. 假设检验 - 本模块将讲解处理数据时使用的适当检验，并解释各检验的假设及解释假设检验结果时的适当语言。 6. 回归分析 - 本模块将直接使用Python进行回归分析，测试样本和总体均值的关系与差异，而非经典的假设检验，并学习如何解读结果。 7. 项目案例：波士顿住房数据 - 在课程的最后一周，学员将获得一个数据集和一个场景利用描述性统计和假设检验提供数据的洞察。学员将使用Watson Studio进行分析，并提交其Notebook与同伴进行评审。 8. 期末考试 9. 其他资源 - Python统计的备忘单。 通过本课程学习，学员能够对统计学中的重要概念有一个全面的理解，并在数据科学的实际应用中熟练运用。
Name:Course Introduction and Python Basics
Description:Welcome!
Name:Introduction & Descriptive Statistics
Description:This module will focus on introducing the basics of descriptive statistics - mean, median, mode, variance, and standard deviation. It will explain the usefulness of the measures of central tendency and dispersion for different levels of measurement.
Name:Data Visualization
Description:This module will focus on different types of visualization depending on the type of data and information we are trying to communicate. You will learn to calculate and interpret these measures and graphs.
Name:Introduction to Probability Distributions
Description:This module will introduce the basic concepts and application of probability and probability distributions.
Name:Hypothesis testing
Description:This module will focus on teaching the appropriate test to use when dealing with data and relationships between them. It will explain the assumptions of each test and the appropriate language when interpreting the results of a hypothesis test.
Name:Regression Analysis
Description:This module will dive straight into using python to run regression analysis for testing relationships and differences in sample and population means rather than the classical hypothesis testing and how to interpret them.
Name:Project Case: Boston Housing Data
Description:In the final week of the course, you will be given a dataset and a scenario where you will use descriptive statistics and hypothesis testing to give some insights about the data you were provided. You will use Watson studio for your analysis and upload your notebook for a peer review and will also review a peer's project. The readings in this module contain the complete information you need.
Name:Final Exam
Description:
Name:Other Resources
Description:Cheat sheet for Statistics in Python
This Statistics for Data Science course is designed to introduce you to the basic principles of statistical methods and procedures used for data analysis. After completing this course you will have practical knowledge of crucial topics in statistics including - data gathering, summarizing data using descriptive statistics, displaying and visualizing data, examining relationships between variables, probability distributions, expected values, hypothesis testing, introduction to ANOVA (analysis of variance), regression and correlation analysis. You will take a hands-on approach to statistical analysis using Python and Jupyter Notebooks – the tools of choice for Data Scientists and Data Analysts. At the end of the course, you will complete a project to apply various concepts in the course to a Data Science problem involving a real-life inspired scenario and demonstrate an understanding of the foundational statistical thinking and reasoning. The focus is on developing a clear understanding of the different approaches for different data types, developing an intuitive understanding, making appropriate assessments of the proposed methods, using Python to analyze our data, and interpreting the output accurately. This course is suitable for a variety of professionals and students intending to start their journey in data and statistics-driven roles such as Data Scientists, Data Analysts, Business Analysts, Statisticians, and Researchers. It does not require any computer science or statistics background. We strongly recommend taking the Python for Data Science course before starting this course to get familiar with the Python programming language, Jupyter notebooks, and libraries. An optional refresher on Python is also provided. After completing this course, a learner will be able to: ✔Calculate and apply measures of central tendency and measures of dispersion to grouped and ungrouped data. ✔Summarize, present, and visualize data in a way that is clear, concise, and provides a practical insight for non-statisticians needing the results. ✔Identify appropriate hypothesis tests to use for common data sets. ✔Conduct hypothesis tests, correlation tests, and regression analysis. ✔Demonstrate proficiency in statistical analysis using Python and Jupyter Notebooks.
