ium_444380/download_data.sh

10 lines
348 B
Bash
Executable File

#!/bin/bash
kaggle datasets download -d AnalyzeBoston/crimes-in-boston --force
unzip -o crimes-in-boston.zip
iconv -f "windows-1252" -t "UTF-8" crime.csv > crime_conv.csv
#shuf crime.csv | head -n $1 > 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