From 9fc59c1ea0a5fd60026ad38b2783d3ecf755e374 Mon Sep 17 00:00:00 2001 From: guillaume-millot <90203812+guillaume-millot@users.noreply.github.com> Date: Wed, 1 May 2024 11:11:01 +0200 Subject: [PATCH] Update README.md --- eval/README.md | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/eval/README.md b/eval/README.md index d291901..993563a 100644 --- a/eval/README.md +++ b/eval/README.md @@ -2,7 +2,7 @@ ## Setup -To run the evaluation scripts, we need some additional requirements that are not listed in the project dependencies. +To run the evaluation scripts, you need some additional requirements that are not listed in the project dependencies. ``` apt-get install wkhtmltopdf @@ -12,7 +12,7 @@ apt-get install wkhtmltopdf First, you need to generate evaluation data with the `eval_table_extraction.py` script. This script will iterate through several reports and apply the set of table extraction algorithms you provided in your yaml configuration. -As an example, you might select the pages in the report from their filename and then apply several table extraction algorithms. Check out `configs/eval_table_extraction.yaml` for a suitable evaluation script. +Check out `configs/eval_table_extraction.yaml` for a suitable yaml configuration. You can then call the script as : @@ -37,6 +37,6 @@ To run the application, it is as simple as : streamlit run eval/eval_app.py eval/data/data_step2_before-currency-unit_eval.csv ``` -`data_step2_before-currency-unit_eval.csv` is a cleaned up version of the `data_step2_before-currency-unit.csv` file which contains reference data extracted and manually cleaned up by the team. +`data_step2_before-currency-unit_eval.csv` is a cleaned up version of the `data_step2_before-currency-unit.csv` file which contains reference data extracted and manually cleaned up by the TaxObservatory team. -At launch, you will be requested to provide a pickle file with extracted data. You might select `eval_20240408_200249.plk` in the `eval/data/` directory. It contains extracted tables for multiple reports and extractions and is a great way to get started. +At launch, you will be requested to provide a pickle file with extracted data. You might select `eval_20240408_200249.plk` from the `eval/data/` directory. It contains extracted tables for multiple reports and extractions and is a great way to get started.