Tables and other media
Table structure, units, blanks, and cleaning
Prepare tabular data without changing what its rows and missing values mean.
Lesson 4 of 6 in the recommended order · About 25 min (estimate)
On this page
Practical AI glossary — terms and common confusions
- Model
- A learned component used to produce a result.
A drafting model is one part of a letter app; it is not the whole app.
- Application
- The software experience around components and services.
A letter app adds accounts, storage, and a Send button.
- Prompt
- Instructions and input supplied for a task.
“Summarize this notice in two bullets” specifies a task and shape, not a truth guarantee.
- Token
- A unit a model processes; it need not be a whole word.
A tokenizer can split a name into pieces; count using the actual system.
- Context
- Information available for the current request.
An earlier attachment may be absent even when its filename is visible.
- Training
- Adjusting a model using examples.
A training log differs from a conversation correction.
- Inference
- Using a trained model to produce a result.
Drafting another sentence does not by itself prove retraining.
- Retrieval
- Selecting material to supply to a task.
A retrieved notice still needs a relevance and date check.
- Embedding
- A numerical representation used to compare or organize items.
A similar search match is a candidate, not proof of the same meaning.
- Tool
- A function an application can call.
A calendar lookup can be read-only; finding an event is different from creating one.
- Agent
- Software that can choose and carry out steps toward a goal.
An agent still needs bounded permissions and checked action receipts.
- Hallucination
- Plausible generated content that is unsupported or false.
An invented opening time needs evidence or removal, even when phrased confidently.
- Evaluation
- Checking results against stated criteria.
Twenty checked examples establish a bounded result, not universal reliability.
- Multimodal
- Working with more than one kind of input or output.
A photo plus text does not prove every small label in the photo was read correctly.
Outcome
Check cleaning decisions for preserved identifiers, units, missingness, and duplicate rules.
Why it matters
Prepare tabular data without changing what its rows and missing values mean.
Concept
Define what one row represents and what each column measures before calculating. Keep identifiers as identifiers: leading zeros may matter, and similar names may refer to different people. Blanks, zero, and not applicable describe different states unless a documented rule equates them.
Cleaning should leave an audit trail. Preserve the original data, document each rule, and flag ambiguous duplicates for review. Standardizing “morning” and “Morning” can be safe under an explicit category rule; guessing missing preferences cannot. Unit conversion requires a known unit and a recorded conversion, not a guess from the number’s size.
Worked example
Cedar’s preference sheet uses an empty cell for “no response.” Replacing all empty cells with evening changes the result. Keep missingness separate. If the documented categories say AM and Morning both mean morning, normalizing those labels preserves meaning while making counts easier.
Cedar continuity note: these lessons use separate snapshots—room selection, booking pending, booking confirmed, and later attendance review. Survey responses are preferences, not attendance. Each supplied packet identifies the facts for its own task; do not import a later snapshot into an earlier decision.
Cedar preference cells: normalize labels, preserve missingness
Illustrative preference cells
| Original preference cell | Safe interpretation |
|---|---|
| AM | Morning preference recorded |
| Morning | Morning preference recorded |
| (blank: no stored value) | Preference remains unknown |
The parenthesized label is display notation, not text stored in the source cell. Keep that original preference cell empty rather than guessing evening.
Record the cleaning decision
Category labels- Normalize AM to Morning only under the documented equivalence.
Missing value- Leave the preference cell empty; record no response separately if the sheet needs a status field.
Audit trail- Keep the original value and the rule used for each change.
A recorded category and an empty cell support different claims.
Before you check
Write a data dictionary for three columns and a cleaning log with Original value, Rule, Result, and Unresolved question. Keep the supplied original rows unchanged.
Practice and fresh transfer
The packets below are fictional and contain the facts needed for these cases. External references are optional background. Judge each response independently: it may be supported, contradicted, or unresolved. Select the passages needed to justify your judgment and write why the distinction matters before revealing feedback.
Assess the response
Use Accept when all material claims are supported. Use Revise when a supplied fact or requirement is contradicted. Use Evidence is insufficient when a key fact cannot be established either way. If a response contains both an unknown and a direct contradiction, choose Revise and explain both problems. Conflicting claims with no established authority remain insufficient; a claim does not become a governing fact merely because a source asserts it.
Some responses are fully supported. Others need correction or more evidence. Judge each on its sources; do not edit a correct answer just to change it.
Your written notes stay in this page and disappear when you leave. Only a self-reviewed completion can be saved to your learning account. These practice checks do not establish independent proficiency.
Practice
Case 1
Consider the proposed response for this fictional Cedar work task. Use the supplied packet and stated requirements.
Source packet
- Source 1
- Dictionary: AM and Morning are equivalent morning-preference labels. Blank means no response.
- Source 2
- Rows: V01 AM; V02 Morning; V03 blank.
Response to assess
Normalize V01 and V02 to Morning; keep V03 as no response.
Practice
Case 2
Consider the proposed response for this fictional Cedar work task. Use the supplied packet and stated requirements.
Source packet
- Source 1
- Dictionary: Member IDs are four-character strings; leading zeros are significant.
- Source 2
- Row: Member ID 0042.
Response to assess
Convert 0042 to the number 42 and use that as the member ID.
Fresh transfer
Case 3
Consider a fictional missing-value interpretation.
Source packet
- Source 1
- Dictionary: Donations are recorded in dollars. A blank means amount not recorded; 0 means a recorded zero.
- Source 2
- Rows: A has 0; B is blank.
Response to assess
A has a recorded zero donation; B’s amount is unknown.
Fresh transfer
Case 4
Consider whether fictional duplicate-looking records can be merged.
Source packet
- Source 1
- Rows: Alex Kim, ID 102; Alex Kim, ID 209.
- Source 2
- Dictionary: Different IDs identify different member records; names are not unique.
Response to assess
Merge these into one member because the names match.
Save your self-review
Completion records that you reviewed the cases. Your explanation and transfer performance need a facilitator to establish independent learning.
Sign in with your learning-center account to save completion.
Review the explanation for every case before saving.
Summary and next step
Apply the checklist to a new task. Preserve supported content, explain any change with evidence, and name what remains unresolved. Saving records self-review, not independently demonstrated proficiency. A facilitator must assess the explanation and fresh transfer for human learning evidence.