00_Data_Prep (R) - Data Cleaning & Assumptions Setup

This step is now implemented in Code/01_Data_Prep.R (no longer in a Python notebook).

Expected Input

data/raw/macro_data.csv
data/raw/wmt_financials.csv
data/raw/wmt_segments.csv
data/raw/peers_comps.csv

Process

Load raw data.
Align fiscal year (adjustment when year-end is in January).
Clean non-recurring items from EBIT and EBITDA:

restructuring charges
opioid settlements
gain on sale of assets

Estimate macro assumptions and calculate WACC.
Build master dataset for the models.

Outputs

data/processed/master_model_input.csv
data/processed/macro_data_clean.csv (if input exists)
data/processed/wmt_segments_clean.csv (if input exists)
data/processed/peers_comps_clean.csv (if input exists)
config/assumptions.csv
config/assumptions.yaml (if yaml package is installed)

Execution

From the project root:

Rscript Code/01_Data_Prep.R

Notes

If columns or files are missing, the script uses conservative defaults and issues warnings.
This step feeds Code/02_DCF.R and the rest of the models.