# Depression Survey — Test Project Configuration
#
# Data size: 500 rows x 10 columns
# Download: python dev/test-datasets/download.py --dataset depression
#
# Project name:
depression-test

# Data path:
/home/mrichardson/Projects/Urika/dev/test-datasets/depression/data

# Description:
Synthetic cross-sectional survey data modeled after clinical depression screening studies.
Each row represents a participant who completed the Beck Depression Inventory (BDI) along
with self-report measures of lifestyle and psychosocial factors. Variables include age,
gender, BDI depression score (0-63), average nightly sleep hours, weekly exercise frequency,
perceived social support score (1-10), self-rated stress level (1-10), income bracket, and
a derived depression severity category (minimal, mild, moderate, severe) based on standard
BDI cutoffs. The data was generated to reflect realistic correlational structure: poor
sleep, low exercise, weak social support, and high stress are associated with higher BDI
scores. The research goal is to identify which modifiable lifestyle factors are the
strongest predictors of depression severity and to build a predictive model for BDI score.

# Research question:
Which modifiable lifestyle factors (sleep, exercise, social support, stress) are the
strongest predictors of depression severity, and can we build a reliable predictive model
for BDI score from these variables?

# Mode:
exploratory

# Web search:
no

# Venv:
no

# Knowledge suggestions:
Add the data-description.md from dev/test-datasets/depression/knowledge/. Optionally add
background on the Beck Depression Inventory scoring and clinical cutoffs.
