Walkthrough

Skeletal notebook for agent-assisted exploration. Setup and data load are filled in. Continue with the Data Science Agent.

Question

Is activity lower in the condition group than in controls, and does weekday versus weekend change the comparison?

The study reported lower daytime activity in depression, and a larger gap on weekends than on weekdays.

# 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_walkthrough')

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

Prompt the agent with the person-level question. Require that any hypothesis test print n and the observational unit. Canvas prompts from the recorded session will be added after class.