From 64d25fe84035c78f8d4ff0e444d39f724baede5d Mon Sep 17 00:00:00 2001 From: Vibhu Jawa Date: Mon, 10 Feb 2025 15:03:08 -0800 Subject: [PATCH] Update tutorials/distributed_data_classification/fineweb-edu-ensebmle-classification.ipynb Co-authored-by: Sarah Yurick <53962159+sarahyurick@users.noreply.github.com> Signed-off-by: Vibhu Jawa --- .../fineweb-edu-ensebmle-classification.ipynb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tutorials/distributed_data_classification/fineweb-edu-ensebmle-classification.ipynb b/tutorials/distributed_data_classification/fineweb-edu-ensebmle-classification.ipynb index 47dffb00..140232b1 100644 --- a/tutorials/distributed_data_classification/fineweb-edu-ensebmle-classification.ipynb +++ b/tutorials/distributed_data_classification/fineweb-edu-ensebmle-classification.ipynb @@ -253,7 +253,7 @@ " output_dataset = classifier(dataset=output_dataset)\n", "\n", "# Dropping int columns\n", - "# As we add new based on a threshold (in the following columns0\n", + "# As we add new based on a threshold (in the following columns)\n", "output_dataset.df = output_dataset.df.drop(columns=[v[\"int_score\"] for v in classifier_scores.values()])\n", "output_dataset.to_parquet(output_path=OUTPUT_CLASSIFICATION_RESULTS)" ]