ium_487197/download_dataset.sh
Wojciech Lidwin d001f55a09 Test
2023-03-26 18:42:53 +02:00

12 lines
402 B
Bash

#!/bin/bash
kaggle datasets download -d sohier/crime-in-baltimore
unzip crime-in-baltimore.zip
echo 'Split'
wc -l BPD_Part_1_Victim_Based_Crime_Data.csv
head -n 8000 BPD_Part_1_Victim_Based_Crime_Data.csv > baltimore_train.csv
tail -n 2000 BPD_Part_1_Victim_Based_Crime_Data.csv > baltimore_test.csv
head -n 2000 baltimore_train.csv > baltimore_dev.csv
echo 'End'
wc -l baltimore_train.csv