|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/applied-statistics-and-data-preparation-with-python/
课程评论：没有评论
Coursera 课程《Applied Statistics and Data Preparation with Python》旨在教授学员数据分析和数据科学的实用技能。 **学习数据分析和数据科学的五大理由：** 1. **提升解决问题的能力：** 培养分析性思维，以正确方式解决问题的能力，这在职业生涯和日常生活中都非常有益。 2. **高需求：** 数据分析师和数据科学家是当前和未来非常热门的职业，随着各行各业对数据依赖的增加，其价值将持续增长。 3. **分析无处不在：** 数据广泛存在于各类公司中，帮助企业从数据中获取洞察、优化流程。这为进入分析领域提供了绝佳机会。 4. **日益重要的价值：** 随着数据的爆炸式增长，企业从数据中发现价值、辅助决策的需求前所未有，数据分析师的职业前景广阔。 5. **多样化的相关技能：** 该领域融合了计算机科学、商业和数学等多学科知识。数据分析师还需要具备清晰沟通复杂信息的能力。 **课程内容概述：** 本课程将主要聚焦于 Python 编程在应用统计和数据准备中的作用，尤其是在 CRISP-DM 数据挖掘过程中的“数据理解”和“数据准备”阶段。 **核心教学内容包括：** * **数据挖掘流程介绍：** 包含数据挖掘的整体过程。 * **应用统计学：** * 数据获取与读取 * 描述性统计：均值、中位数、众数、方差、标准差、范围、分位数、偏度、峰度等。 * 数据分布可视化：直方图（Histogram）、QQ图（QQPlot）。 * 统计检验：Shapiro-Wilk 检验（Shapiro Test）、t 检验（One Sample T Test, Two Sample T Test）、卡方检验（Chi-Square Test）、单因素方差分析（One Way ANOVA）。 * 回归分析：简单线性回归（Simple Linear Regression）、多元线性回归（Multiple Linear Regression）。 * 相关性分析：协方差（Covariance）、相关系数（Correlation）。 * **数据处理：** * DataFrame 的基本操作：查看头部（DF.head()）、尾部（DF.tail()）、描述性统计（DF.describe()）。 * 数据筛选与选择：选择变量、选择行、同时选择变量和行。 * 数据变换：删除变量、添加行（Append Rows）、排序变量（Sort Variables）、重命名变量（Rename Variables）。 * 数据聚合：分组（GroupBY）。 * 缺失值处理：检查缺失值（Is THere Missing Values）、删除缺失值（Remove Missing Values）、替换缺失值（Replace Missing Values）。 * 重复值处理：删除重复值（Remove Duplicates）。 **先修要求：** 课程建议学员具备一定的 Python 编程基础，可以通过讲师的其他课程《Create Your Calculator: Learn Python Programming Basics Fast》来学习 Python 基础。 **认证：** 学员完成课程并通过 EMHAcademy 的考试，有机会获得 SVBook Certified Data Miner using Python 认证。
Why learn Data Analysis and Data Science?According to SAS, the five reasons are1. Gain problem solving skillsThe ability to think analytically and approach problems in the right way is a skill that is very useful in the professional world and everyday life. 2. High demandData Analysts and Data Scientists are valuable. With a looming skill shortage as more and more businesses and sectors work on data, the value is going to increase. 3. Analytics is everywhereData is everywhere. All company has data and need to get insights from the data. Many organizations want to capitalize on data to improve their processes. It's a hugely exciting time to start a career in analytics.4. It's only becoming more importantWith the abundance of data available for all of us today, the opportunity to find and get insights from data for companies to make decisions has never been greater. The value of data analysts will go up, creating even better job opportunities. 5. A range of related skillsThe great thing about being an analyst is that the field encompasses many fields such as computer science, business, and maths. Data analysts and Data Scientists also need to know how to communicate complex information to those without expertise.The Internet of Things is Data Science + Engineering. By learning data science, you can also go into the Internet of Things and Smart Cities. This is the bite-size course to learn Python Programming for Applied Statistics. In CRISP-DM data mining process, Applied Statistics is at the Data Understanding stage. This course also covers Data processing, which is at the Data Preparation Stage. You will need to know some Python programming, and you can learn Python programming from my "Create Your Calculator: Learn Python Programming Basics Fast" course. You will learn Python Programming for applied statistics. You can take the course as follows, and you can take an exam at EMHAcademy to get SVBook Certified Data Miner using Python certificate: - Create Your Calculator: Learn Python Programming Basics Fast (R Basics)- Applied Statistics using Python with Data Processing (Data Understanding and Data Preparation)- Advanced Data Visualizations using Python with Data Processing (Data Understanding and Data Preparation, in the future)- Machine Learning with Python (Modeling and Evaluation)ContentGetting StartedGetting Started 2Getting Started 3Data Mining ProcessDownload Data setRead Data setModeMedianMeanRangeRange One ColumnQuantileVarianceStandard DeviationHistogramQQPLotShapiro TestSkewness and KurtosisDescribe()CorrelationCovarianceOne Sample T TestTwo Sample TTestChi-Square TestOne Way ANOVASimple Linear RegressionMultiple Linear RegressionData Processing: DF.head()Data Processing: DF.tail()Data Processing: DF.describe()Data Processing: Select VariablesData Processing: Select RowsData Processing: Select Variables and RowsData Processing: Remove VariablesData Processing: Append RowsData Processing: Sort VariablesData Processing: Rename VariablesData Processing: GroupBYData Processing: Remove Missing ValuesData Processing: Is THere Missing ValuesData Processing: Replace Missing ValuesData Processing: Remove Duplicates
