From ba6133548beb092a60da3c93395bbde72b6dca8b Mon Sep 17 00:00:00 2001
From: Thomas Wood <thomas@fastdatascience.com>
Date: Wed, 7 Feb 2024 22:07:51 +0000
Subject: [PATCH] Update kaggle.md

---
 content/en/blog/kaggle.md | 24 ++++++++++++++++++++++--
 1 file changed, 22 insertions(+), 2 deletions(-)

diff --git a/content/en/blog/kaggle.md b/content/en/blog/kaggle.md
index d09504aa..4a2f7940 100644
--- a/content/en/blog/kaggle.md
+++ b/content/en/blog/kaggle.md
@@ -38,9 +38,29 @@ kaggle competitions download -c harmony-pdf-and-word-questionnaires-extract
 unzip harmony-pdf-and-word-questionnaires-extract.zip 
 ```
 
-5. Run [create_sample_submission.py](https://github.com/harmonydata/pdf-questionnaire-extraction/blob/main/data/create_sample_submission.py) in the folder containing your data. It will create a CSV file `submission.csv`.
+5. Run [create_sample_submission.py](https://github.com/harmonydata/pdf-questionnaire-extraction/blob/main/data/create_sample_submission.py) in the folder containing your data to create your train and test predictions:
 
-6. Submit your CSV file to Kaggle
+To generate predictions for the training data and write to train_predictions.csv:
+
+```
+python create_sample_submission.py train
+```
+
+To evaluate the train predictions:
+
+```
+python evaluate_train_results.py
+```
+
+6. To modify the prediction logic or inject your own model, you can edit the function `dummy_extract_questions`.
+
+7. To generate predictions for the test data and write to submission.csv:
+
+```
+python create_sample_submission.py test
+```
+
+8. Submit your CSV file to Kaggle
 
 ```
 kaggle competitions submit -c harmony-pdf-and-word-questionnaires-extract -f submission.csv -m "Message"