Choose a direction, build a skill, then put it into practice.
AI skills, workflows and projects →30 resources
Saved resourcesRead public teaching material about command-line tools and version control.
Next action: Work through the shell lesson and keep a short record of useful commands.
Source: missing.csail.mit.edu
Find public MIT lecture notes, exams and videos without registration.
Next action: Choose one finance or analytics course and work through its first problem set.
Source: ocw.mit.edu
Read browser-based SQL lessons covering queries, joins and aggregates.
Next action: Complete SELECT and JOIN lessons and explain your query decisions aloud.
Source: sqlbolt.com
Read the open handbook for reproducible, ethical and collaborative data science, from project design to communication.
Suitable for: Readers who meet the stated knowledge prerequisites and want a bounded original explanation of the selected concepts.
Learning goals: Identify OS,interpreter,dependencies/configuration and input/source/output hashes needed for repeatability.; Use a source-linked original small scenario to record two-copy equality,changed input and empty-input behaviour.; Explain why one runtime equality is not cross-platform reproducibility or learner mastery.
L2 · en · Source practice details on resource page
Next action: Open the actual Reproducible Environments chapter: Prerequisites, Summary, computational environment and Motivation. Use a small analysis you already control, record its environment and file fingerprints, repeat a clean copy, change one input and inspect the empty-input case.
Source: book.the-turing-way.org
A Data Carpentry lesson on preserving original measurement records, separating variables and observations, and recording table-cleaning steps.
Suitable for: 初次整理科学观察或测量表格、具备所列基础知识的读者
Learning goals: 把一次测量定义为一行，分开物种、性别、日期、地点及质量字段; 写明质量单位和未记录值含义，保留原始文件并记录整理步骤; 制作可追溯的整理表、字段字典与检查记录；区分数据格式检查和研究结论
L1 · en · Source practice details on resource page
Next action: 从章节 Keeping track of your analyses 和 Structuring data in spreadsheets 开始阅读，再查看 Exercise 提示和静态指导；用自己编写的虚构记录练习整理，不依赖未核实的外链数据文件。
Source: datacarpentry.github.io
Official pandas 3.0.6 documentation for missing-value reductions, merge keys and deduplication; reduction defaults do not fill missing cells.
Suitable for: Readers preparing to explain tabular-data behaviour who meet the stated prerequisites.
Learning goals: State what pandas returns for the sum and the product of an all-NA series, and say why that is dangerous for a revenue metric.; Distinguish count(), size and nunique() as candidate denominators and pick one for a stated metric.; Write, in one sentence, what the denominator of your own metric counts.
L2 · en · Source practice details on resource page
Next action: Open Calculations with missing data, then Series.sum skipna and min_count. State which values contribute to a known subtotal and what complete-total policy you intend.
Source: pandas.pydata.org
Historical invoice-line dataset with a source dictionary, sterling unit prices and cancellation coding. Read the source and define missingness, cohort and monetary scope before attempting customer segmentation.
Suitable for: Readers planning a bounded historical retail analysis who meet the stated knowledge prerequisites.
Learning goals: State invoice-line grain,sterling units,historical period and timestamp timezone unknown.; Define disjoint cohort exclusions and distinguish them from overlapping cancellation/negative/missing diagnostics.; Define recency/frequency/positive-sales monetary using a cutoff and tie-preserving quartile policy.; Explain why numeric CustomerID/history is not anonymity and why source no-missing metadata differs from CSV empty fields.; Write a bounded historical analytical proposal with denominator/assumption/limitation statements, without observed effectiveness claims.
L3 · en · Source practice details on resource page
Next action: Read the UCI Variables Table, License and Citation sections. If analysing the data, follow the original UCI download link and first write an invoice-line grain, cohort-exclusion, cutoff, duplicate and tie policy.
Source: archive.ics.uci.edu
Business Queensland explains profit, fixed and variable costs, turnover, a simplified break-even revenue formula and gross margin.
Suitable for: Readers who meet the stated knowledge prerequisites and want to explain the selected concepts.
Learning goals: Classify costs consistently for a fictional one-month single-product model.; Calculate break-even units and check that demand and serial capacity can supply them.; Explain the conditional profit/backlog effect of improving the binding station.
L2 · en · Source practice details on resource page
Next action: Read Profit basics, Expenses and costs, Break-even point and Gross profit margin; create your own fictional single-product scenario with explicit units and period.
Source: www.business.qld.gov.au
Selected GAO Green Book paragraphs explain preventive and detective control timing and the separation of authority, custody and recording roles.
Suitable for: Readers who meet the stated knowledge prerequisites and want to explain the selected concepts.
Learning goals: Classify proposed controls by the timing of the unintended payment event.; Identify incompatible authority/custody/recording roles in four self-written fictional payment records.; Specify population, time period, evidence request and residual risk for each flagged row.
L2 · en · Source practice details on resource page
Next action: Read Principle 10, printed pages 70–73 (PDF viewer pages 77–80), especially sections 10.10–10.13 and 10.21–10.23; then sketch your own fictional payment-control matrix.
Source: www.gao.gov
The historical Investor.gov bulletin explains fixed coupons, the rate/price relationship and maturity sensitivity, with two rate/price examples.
Suitable for: Readers who meet the stated knowledge prerequisites and want to explain the selected concepts.
Learning goals: Distinguish fixed coupon payment from discount yield and resale price in a dated fictional schedule.; Reprice unchanged fictional cash flows under a 100 basis-point nominal-yield shock.; Explain maturity/coupon sensitivity and the limited effect of cash weighting under a stated instantaneous-price scenario.
L2 · en · Source practice details on resource page
Next action: Read the rate/price examples, Coupon Rates and Maturity sections. For optional original practice, hold a fictional cash-flow schedule fixed while changing its discount yield.
Source: www.investor.gov
MIT Libraries explains AND, OR, NOT and search grouping with examples, while qualifying differences between database behavior.
Suitable for: Readers who meet the stated knowledge prerequisites and want to explain the selected concepts.
Learning goals: 把研究问题拆成概念块并选择同义词; 区分AND交集、OR并集和NOT排除; 用比较结果说明括号分组与排除可能遗漏相关记录
L2 · en · Source practice details on resource page
Next action: 阅读 Using AND、Using OR、Using NOT 和 Search order。先用自己编写的有限集合比较分组与排除，再为实际数据库另行核对语法和行为。
Source: libguides.mit.edu
OpenLearn section 1.6 presents explanation about supporting opinions with evidence, visible Activity 6 prompts and static Answer/Comment responses.
Suitable for: Readers who meet the stated knowledge prerequisites and want to explain the selected concepts.
Learning goals: 辨认主张、支持材料与隐含推论桥梁; 比较证据范围与主张范围; 提出反解释并将结论缩到证据可支持的范围
L2 · en · Source practice details on resource page
Next action: 在原站查看 §1.6 的可见 Activity 6 提示及静态 Answer/Comment；留意 Text 3 附件上下文未被本目录核实，再用自己编写的短段落练习比较主张和证据范围。
Source: www.open.edu