Update README.md

Added reproduction instruction for the ELN data.

Author: daenuprobst

README.md

@@ -72,6 +72,20 @@ The library contains the class `DrfpEncoder` with one public method `encode`.
 # Reproduce
 Want to reproduce the results in our paper? You can find all the data in the `data` folder and encoding and training scripts in the `scripts` folder.
 
+## Electronic Laboratory Notebook (ELN) Experiment
+To reproduce the experiments on the electronic laboratory notebook (ELN) data:
+
+1. Encode the data using the script `encode_az_reactions.py`. This will write the files `az-2048-3-true.pkl` and `az-2048-3-true.pkl.gz` to the folder `data/az`.
+```bash
+cd scripts
+python encoding/encode_az_reactions.py
+```
+2. Train and test the xgboost model using the script `yield_prediction_az.py` (or `yield_prediction_az_rf.py` for the random forest model):
+```bash
+python training/yield_prediction_az.py
+python training/yield_prediction_az_rf.py
+```
+
 # Cite Us
 ```
 @article{probst2022reaction,