prepare_data_bigtools

wget https://www.dropbox.com/s/lwj2ksz5jwh875l/data.zip?dl=0 -O data.zip
wget https://www.dropbox.com/s/gby06nhftx7jify/mapreduce.zip?dl=0 -O mapreduce.zip

unzip data.zip
unzip mapreduce.zip

hdfs dfs -rm -r /user/admin/*
rm ~/cdr_from_hdfs.csv

sudo -u hdfs hdfs dfs -mkdir /user/admin
sudo -u hdfs hdfs dfs -chown admin:admin /user/admin

hdfs dfs -mkdir -p /user/admin/output

hdfs dfs -put ~/data /user/admin
hdfs dfs -ls data
hdfs dfs -ls /user/admin/data

sudo -u hdfs hdfs fsck /

sudo -u hdfs hdfs dfs -chmod -R 777 /user/admin

cd ~
chmod +x ~/mapreduce/ex0/mapper.py
chmod +x ~/mapreduce/ex0/reducer.py
chmod +x ~/mapreduce/ex1/mapper.py
chmod +x ~/mapreduce/ex1/reducer.py
chmod +x ~/mapreduce/ex2/mapper.py
chmod +x ~/mapreduce/ex2/reducer.py
chmod +x ~/mapreduce/ex3/mapper.py
chmod +x ~/mapreduce/ex3/reducer.py
chmod +x ~/mapreduce/ex4_student/mapper_student.py
chmod +x ~/mapreduce/ex4_student/reducer_student.py
chmod +x ~/mapreduce/word_count/mapper.py
chmod +x ~/mapreduce/word_count/reducer.py

hdfs dfs -rm -r -f /user/admin/output*

hdfs dfs -get /user/admin/data/cdr.csv ~/cdr_from_hdfs.csv
ls ~
head ~/cdr_from_hdfs.csv