AI Activity 1: Data Importing and Hidden Assumptions

NYC Airbnb Open Data 2019 listings dataset

AI activity
Modified

March 31, 2026

Importing data is not a neutral step. Import tools make assumptions about missing values, data types, dates, text encoding, and formatting. When assumptions are wrong, the dataset can be changed silently before analysis begins.

You will use an AI tool as a learning partner to investigate a core data science reality:

You are graded on how you think, critique, and explain, not on whether AI gives perfect answers.

To Do
  1. Download the dataset from the Dataset section below.
  2. Write your investigation question (2 to 3 sentences). Step 1 in Tasks.
  3. Run 3 to 5 AI prompts that cover missing values, types, dates, and validation. Step 2 in Tasks.
  4. Import the data and complete checklist items 1 to 4 first. Step 4
  5. Draft your synthesis, then build slides using the required 5 slide structure. Step 5 and Step 6

Assigned Roles (3 students)

[NOTE:] Each student has a designated role for accountability. However, teammates are encouraged to collaborate, support one another, and learn together in order to produce high-quality, cohesive work.

Prompt Engineer

Responsibilities

  • Create 3 to 5 purposeful AI prompts
  • Save AI responses and build the AI Interaction Log
  • Write annotations for each prompt and response pair

Data Science Auditor

Responsibilities

  • Identify hidden assumptions in AI guidance
  • Design and run post import validation checks
  • Provide evidence for at least two hidden assumptions

Synthesizer

Responsibilities

  • Write the Human Authored Synthesis in clear course language
  • Build slides using the required structure
  • Ensure the final work is consistent and concise

Dataset

Required file

Dataset notes

What you will submit

  • Group submissions
    • AI Interaction Log
    • Human Authored Synthesis
    • Slides for a 12 to 15 minute presentation
  • Individual submission
    • Individual Reflection (150 to 200 words)

Step by step tasks

Step 1 Define your investigation question (before using AI)

Write 2 to 3 sentences answering:

  • What import problem are we investigating
  • Why this problem matters in real data science

You must focus on hidden assumptions, for example assumptions about missing values, types, dates, or text encoding.

Step 2 Use AI strategically (3 to 5 prompts)

[Note:] You may run several prompts, but keep 5 most useful and meaningful prompts for reporting.

Your prompts must be purposeful and iterative.

Prompt requirements

  • At least 1 prompt about missing values and missing value representations
  • At least 1 prompt about type guessing and type coercion risks
  • At least 1 prompt about date parsing and mixed date formats
  • At least 1 prompt about validation steps after import

Suggested prompt starters (you may adapt)

  • “I am importing a CSV where missing values appear as blank cells, a period, the word unknown, and an em dash. What should I do in R or Python to import correctly and verify it”

  • “The column last_review mixes formats like 2019-06-23, 06/24/2019, and 06/20/19. What is a safe parsing strategy and how do I report failures”

  • “price contains values like $70, 70, and 60 dollars. What is a safe way to convert to numeric and validate the conversion”

  • “minimum_nights includes values like 2 nights and availability_365 includes values like 0/365 or 96 days. How should I clean these and what checks should I run”

  • “room_type and neighbourhood_group have inconsistent capitalization and whitespace. What cleaning steps are reasonable and how do I validate categories after cleaning”

Step 3 Create the AI Interaction Log

For each prompt, include:

  • Prompt goal
  • The AI response excerpt you used
  • Your annotation:
    • What AI got right
    • What AI assumed
    • What was missing, misleading, or incorrect

Important rule

  • You may not paste AI text into your final synthesis verbatim.

Step 4 Import the dataset and run required validation checks

Import the required file, then complete the validation checklist below. Your evidence can be screenshots, printed outputs, or short summaries of what you observed. A short summary without numbers or outputs does not count as evidence.

1. Rows and columns

  • Confirm the dataset has 600 rows and 16 columns after import.

2. Missing value representations

  • Identify at least three different missing value representations present in the file (examples include blank cells, a period, unknown, an em dash).
  • Choose two columns (recommended: last_review and reviews_per_month).
  • Report how many missing values you see in each column, and explain how you defined missingness.

3. Date column with mixed formats

  • Check last_review.
  • Show evidence that more than one date format exists in the raw data.
  • State whether your import tool parsed it as a date or left it as text.
  • If you parsed it, report how many non missing entries became missing after parsing.

4. Numeric values stored as text

  • Choose two columns from this list: price, minimum_nights, availability_365, reviews_per_month.
  • Show the raw formats you observe (for example $70, 60 dollars, 2 nights, 0/365, 0.03 per mo).
  • State what type your import tool assigned and what conversion would be required.

5. Currency stored as text

  • Check price.
  • Show at least three raw examples that are not purely numeric.
  • State what conversion you would use and one validation check you would run after conversion.

6. Categorical values with inconsistent formatting

  • Choose neighbourhood_group or room_type.
  • List the unique values you observe before cleaning (include at least 8 examples).
  • Propose a cleaning rule (for example trim whitespace, standardize case, replace underscores).
  • Show evidence of how categories change after cleaning (for example fewer unique levels or merged categories).

7. Text encoding and non ASCII or invisible characters

  • Find at least one host_name that contains a non ASCII character or an invisible character.
  • Show evidence that the character displays correctly after import.
  • State what could go wrong if encoding or invisible characters are not handled properly.

8. Silent coercion risk

  • Identify one column where a reasonable but incorrect conversion could silently create wrong values or missing values.
  • Explain the mistake, why it could be hard to notice, and how you would detect it using evidence.

Step 5 Write the Human Authored Synthesis (group)

Length target: 400 to 600 words.

Your synthesis must include:

  • Your investigation question
  • At least two hidden assumptions with evidence from your validation checks
  • A clear explanation of why the assumptions matter for later analysis
  • A short recommended import and validation routine for this dataset type

Your synthesis must be written in your own words.

Step 6 Presentation slides (group)

Use this exact slide structure:

  • Our question
  • What AI suggested
  • Where AI fell short
  • Our corrected understanding, with evidence
  • One takeaway for future data science work

Time: 12 to 15 minutes.

Individual Reflection (each student)

Write 150 to 200 words answering:

  • What did AI help you learn
  • What did AI miss or oversimplify
  • What did you contribute as a human thinker
  • How will you change your AI use in future data work

Your reflection must match your assigned role.

Participation (non-presenting students)

Please scan the QR code, or go to https://forms.office.com/r/eAKU9th9X5 to share what you learned from this activity.