From 4da4b2deedb0f5649df9a5a6987b606b642a729d Mon Sep 17 00:00:00 2001 From: Szymon Bartanowicz Date: Tue, 14 May 2024 22:44:38 +0200 Subject: [PATCH] changed script --- script1.sh | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/script1.sh b/script1.sh index 1a60f4c..398f133 100644 --- a/script1.sh +++ b/script1.sh @@ -3,9 +3,10 @@ pip install kaggle kaggle datasets download -d open-powerlifting/powerlifting-database unzip -o powerlifting-database.zip DATASET_FILE="openpowerlifting.csv" -echo "Obcięte wiersze: ${1}" +column_names=$(head -n 1 $DATASET_FILE) +echo "Truncated rows: ${1}" head -n $1 $DATASET_FILE > cutoff_$DATASET_FILE -echo "Podział i wymieszanie" +echo "$column_names" > temp && cat cutoff_$DATASET_FILE >> temp && mv temp cutoff_$DATASET_FILE total_lines=$(tail -n +2 cutoff_$DATASET_FILE | wc -l) train_lines=$((total_lines * 90 / 100)) dev_lines=$((total_lines * 10 / 100)) @@ -15,4 +16,7 @@ head -n $train_lines shuffled.csv > train.csv tail -n $((dev_lines + test_lines)) shuffled.csv | head -n $dev_lines > dev.csv tail -n $test_lines shuffled.csv > test.csv mkdir -p data -mv train.csv dev.csv test.csv data/ \ No newline at end of file +echo "$column_names" | cat - train.csv > temp && mv temp train.csv +echo "$column_names" | cat - dev.csv > temp && mv temp dev.csv +echo "$column_names" | cat - test.csv > temp && mv temp test.csv +mv train.csv dev.csv test.csv data/