Added script downloading and splitting data

2022-03-27 11:29:22 +02:00 · 2022-03-27 11:29:22 +02:00 · 98939fc551
commit 98939fc551
parent 22a0d94899
1 changed files with 8 additions and 0 deletions
--- a/download_data.sh
+++ b/download_data.sh
@ -0,0 +1,8 @@
+#!/bin/bash
+
+kaggle datasets download -d AnalyzeBoston/crimes-in-boston
+unzip crimes-in-boston.zip
+shuf crime.csv > crime.shuf
+head -n 30000 crime.shuf > crime.test
+head -n 60000 crime.shuf | tail -n 30000 > crime.dev
+tail -n +60001 crime.shuf > crime.train