Compare two measurements · Data Playground

The question

Describe current-week activity in steps and minutes; do not mix in the previous week.

df Measurement profile

Your inputs

`df`

steps is a count; minutes is duration. Missing measurements are unknown, not zero.

Field meanings and units

record_id: Activity-observation identifier.
group: Comparison group.
date: Calendar date supplied as YYYY-MM-DD text unless the task states it is invalid.
steps: Recorded step count, additive across observations.
minutes: Elapsed duration in minutes; unknown is not zero.
week: Current or Previous reporting week.

`df` · first 5 of 16 rows
`record_id`	`group`	`date`	`steps`	`minutes`	`week`
A001	Morning	2026-04-01	2500	20	Previous
A002	Evening	2026-04-09	3070	27	Current
A003	Morning	2026-04-10	3640	34	Current
A004	Evening	2026-04-04	4210	41	Previous
A005	Morning	2026-04-12	4780	None	Current

View all 16 rows

`df` · complete input
`record_id`	`group`	`date`	`steps`	`minutes`	`week`
A001	Morning	2026-04-01	2500	20	Previous
A002	Evening	2026-04-09	3070	27	Current
A003	Morning	2026-04-10	3640	34	Current
A004	Evening	2026-04-04	4210	41	Previous
A005	Morning	2026-04-12	4780	None	Current
A006	Evening	2026-04-13	5350	55	Current
A007	Morning	2026-04-07	5920	21	Previous
A008	Evening	2026-04-08	2640	28	Current
A009	Morning	2026-04-09	3210	35	Current
A010	Evening	2026-04-03	3780	42	Previous
A011	Morning	2026-04-11	4350	49	Current
A012	Evening	2026-04-12	4920	56	Current
A013	Morning	2026-04-06	5490	22	Previous
A014	Evening	2026-04-14	6060	29	Current
A015	Morning	2026-04-08	2780	36	Current
A016	Evening	2026-04-02	3350	43	Previous

The editable setup in Your Python creates these inputs when you run it.

Your task · Compare two measurements

Describe current-week activity in steps and minutes; do not mix in the previous week.

summaryDataFrameknownSeries

Deliverables

Make the outputs listed below. Use each name exactly as shown. Then choose Check answer.

Python name key

Teal outlines name table columns. Violet left rules name Python objects. Dotted rules mark syntax, functions and parameters. Use each name exactly as shown.

Words in this task

missing: no value was supplied

Current-week summaryOutputsummaryDataFrame
1. Use the Current-week steps and minutes columns to create summary with their standard descriptive statistics (describe()).
2. Each column should ignore its own missing values.
Known measurementsOutputknownSeries
1. Store the count of known values for steps and minutes in known.

Data policy Keep all supplied source tables unchanged. Work on separate outputs.

Help Hints & explained solution

Choose the amount of help you need. Opening one hint does not reveal the others.

Hint 1 — Think

A row may have one measurement without the other. How should that appear in a summary?

Hint 2 — Tools

describe(), count() and selection

Revisit: Describe numeric columns · Find missing values · Combine conditions · Answer one numerical question

Hint 3 — Approach

Select current-week measurements, summarise each numeric column and count the observations available for each.

Explained solution

Add these lines below # Your work in the editor. The supplied input setup is already there.

current = df.loc[df.week == 'Current', ['steps', 'minutes']]
summary = current.describe()
known = current.count()
summary

View supplied setup

This code is already at the top of the editor.

import pandas as pd

# Supplied input: df (16 rows)
df = pd.DataFrame(
    [
        ('A001', 'Morning', '2026-04-01', 2500, 20, 'Previous'),
        ('A002', 'Evening', '2026-04-09', 3070, 27, 'Current'),
        ('A003', 'Morning', '2026-04-10', 3640, 34, 'Current'),
        ('A004', 'Evening', '2026-04-04', 4210, 41, 'Previous'),
        ('A005', 'Morning', '2026-04-12', 4780, None, 'Current'),
        ('A006', 'Evening', '2026-04-13', 5350, 55, 'Current'),
        ('A007', 'Morning', '2026-04-07', 5920, 21, 'Previous'),
        ('A008', 'Evening', '2026-04-08', 2640, 28, 'Current'),
        ('A009', 'Morning', '2026-04-09', 3210, 35, 'Current'),
        ('A010', 'Evening', '2026-04-03', 3780, 42, 'Previous'),
        ('A011', 'Morning', '2026-04-11', 4350, 49, 'Current'),
        ('A012', 'Evening', '2026-04-12', 4920, 56, 'Current'),
        ('A013', 'Morning', '2026-04-06', 5490, 22, 'Previous'),
        ('A014', 'Evening', '2026-04-14', 6060, 29, 'Current'),
        ('A015', 'Morning', '2026-04-08', 2780, 36, 'Current'),
        ('A016', 'Evening', '2026-04-02', 3350, 43, 'Previous'),
    ],
    columns=['record_id', 'group', 'date', 'steps', 'minutes', 'week'],
)

Why these steps exist

Each column has its own observed count; an unknown duration does not invalidate a known step count.
The 50% row is the median. The standard deviation summarises variation in the observed sample.

Another valid approach

Selecting columns before or after the population filter is equivalent here. Keep the summary limited to the requested measures.