Lab

Same actigraphy table as the walkthrough. Setup and data load are filled in. Use the Data Science Agent, and write some of the code yourself.

Question

The walkthrough looks at condition versus control, and at weekdays versus weekends. This table also carries other columns on each person: gender, age range, education (edu), inpatient care, and the related score fields.

Do any of those relate to activity? Is the relationship different for controls and for people with depression?

# Setting up the Colab environment. DO NOT EDIT!
try:
  from applied_biostats import setup_environment
except ImportError:
  !pip -q install applied-biostats-helper
  from applied_biostats import setup_environment
finally:
  grader = setup_environment('Module12_lab')

import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import pingouin as pg

Load the staged actigraphy table

act = pd.read_csv('depresjon_minute.csv.gz', parse_dates=['timestamp'])

print('Unit of analysis reminder: person (or person-day), not minute')
print('n people:', act['person_id'].nunique())
print(act['group'].value_counts())
print('n minute rows:', len(act))
act.head()

Continue with the Data Science Agent

Explore those columns with the agent and with code you type yourself. Any hypothesis test should print n and the observational unit. Write a short conclusion you can tie to a figure or table.