Follow the transformation
Measure the problem by column, row group and time/segment.
Investigate the data-generating process before choosing a fix.
Choose deletion, correction, imputation, transformation or retention with an explicit reason.
Python, NumPy & pandas · Lesson 10
Missing Data
Missing Data is a data-quality decision, not merely a cleaning command.
What Missing Data actually means
Missing Data is a data-quality decision, not merely a cleaning command. The correct treatment depends on how the issue arose, whether it carries information, and how the treatment changes the population or downstream model.
Missing Data matters because numerical arrays and labelled tables are the working representations for most data-science pipelines. Types, shape, alignment, missingness and reusable code determine whether later statistics and models receive the intended data.
Deeper walkthrough
Read Missing Data as a mechanism, not a recipe
Treat this as a sequence of observable decisions rather than one opaque command. Stage 1: Measure the problem by column, row group and time/segment. Stage 2: Investigate the data-generating process before choosing a fix. Stage 3: Choose deletion, correction, imputation, transformation or retention with an explicit reason. Final checkpoint: Record an indicator or audit trail when the fact that a value was missing/changed may itself matter.
Know what would convince you
- Compare row/column counts, dtypes and missing values before and after the operation.
- Trace a few representative rows or one group manually from source values to result.
Useful distinctionDeletion: Removes affected rows/columns; can bias the population.
Click a stage to inspect what happens, what changes, and what should be checked before moving on.
Stage 1
Measure the problem by column
Measure the problem by column, row group and time/segment. For Missing Data, identify the exact state before this stage, the operation or rule applied here, and the observable state afterwards so the mechanism remains inspectable.
State focus: identify exactly what changed at this stage and what observable evidence confirms that change.
Trace the mechanism step by step
- Measure the problem by column, row group and time/segment.
- Investigate the data-generating process before choosing a fix.
- Choose deletion, correction, imputation, transformation or retention with an explicit reason.
- Fit learned preprocessing only on training data when predictive modelling is involved.
- Record an indicator or audit trail when the fact that a value was missing/changed may itself matter.
Make the concept concrete
Demonstration
Python / pandas example
# Step 1 — Import the module so its functions/classes are available to the rest of this example.
import pandas as pd
# Step 2 — Construct `df` as a tabular object with named columns for inspectable analysis.
df=pd.DataFrame({"age":[25,None,40],"income":[50,60,None]})
# Step 3 — Display the current value explicitly so the result/state can be inspected during execution.
print(df.isna().sum())
# Step 4 — Display the current value explicitly so the result/state can be inspected during execution.
print(df.isna().mean())Expected / illustrative result
The table shows both missing counts and proportions; treatment should follow an investigation of why values are missing.
Interpret the result.
For Missing Data, trace representative source rows/columns into the result and reconcile row counts, dtypes, keys or missing values that the operation could change.
Know what this is — and what it is not
DeletionRemoves affected rows/columns; can bias the population.Simple imputationUses a fixed statistic/category; easy but shrinks variability.Model-based imputationUses relationships with other variables; more assumptions and leakage risk.Missing indicatorPreserves information about whether a value was missing.When it is appropriate
Use Missing Data when the data are naturally tabular and row grain, column meaning, keys and dtypes can be stated explicitly.
When to stop or reconsider
Reconsider the operation if row identity/grain is unclear, join keys are not validated, chained transformations hide state, or the task is better expressed with a simpler table operation.
Failure modes to recognise
- Changing row grain or row count without noticing it.
- Joining/grouping on keys whose uniqueness or missingness was never checked.
- Interpreting a derived column or aggregation without reconciling it to source rows and units.
How to check the result
- Compare row/column counts, dtypes and missing values before and after the operation.
- Trace a few representative rows or one group manually from source values to result.
- For joins/reshapes/grouping, verify key uniqueness/cardinality and reconcile totals where totals should be preserved.
Demonstrate understanding
Try this:
Build a tiny, inspectable example of Missing Data. First measure the problem by column, row group and time/segment. Then investigate the data-generating process before choosing a fix. Write the expected result before running it, and explain one condition that would make the result misleading or invalid.
Work with 4–8 rows that contain the exact key/category/missing-value pattern you want to understand. Trace one row or group all the way through.
Check reasoning, not memorisation
Before trusting a result from Missing Data, which check provides the strongest evidence that you understand and applied it correctly?
Keep the important distinctions visible
Step 1Measure the problem by column, row group and time/segment.Step 2Investigate the data-generating process before choosing a fix.Step 3Choose deletion, correction, imputation, transformation or retention with an explicit reason.Step 4Fit learned preprocessing only on training data when predictive modelling is involved.What to remember
- Missing Data is a data-quality decision, not merely a cleaning command. The correct treatment depends on how the issue arose, whether it carries information, and how the treatment changes the population or downstream model.
- Measure the problem by column, row group and time/segment.
- Changing row grain or row count without noticing it.
- Compare row/column counts, dtypes and missing values before and after the operation.