Introduction

The repository is the code repository for the case study Finding peer stocks using business description of a company

Executing the code

There are three ways to execute the code.

Native Python

1. Step 1: [Optional] execute the code python py/etl.py --path-files "data/" --path-figs "doc/figs/"
2. Step 2: Step 1 will create a thematic.h5 file in the data directory (example data is given in data directory) python py/model.py --path-data "data/thematic.h5""

SnakeMake

Snakemake user can just type in snakemake --cores 1 from command shell. Please note Rscript and Python should be in path

Mlflow

Mlflow users can just type mlflow run .

Schema thematic.h5

key	data
stoxx50	Euro Stoxx50 Universe
desc	Yahoo finance data
analysis	Analysis data