Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
30 changes: 22 additions & 8 deletions 02_activities/assignments/assignment.sh
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@ cd newproject

mkdir analysis output
touch README.md
echo "# Project Name: DSI Consulting Inc." > README.md
touch analysis/main.py

# download client data
Expand All @@ -27,24 +28,37 @@ unzip -q rawdata.zip
###########################################
# Complete assignment here

# 1. Create a directory named data

# 1. Create a directory named datacd data
mkdir data
# 2. Move the ./rawdata directory to ./data/raw (eg. move it into ./data and rename it to raw)

mv ./rawdata ./data
cd data
mv rawdata raw
# 3. List the contents of the ./data/raw directory

ls data/raw
# 4. Create the directory ./data/processed,
# then create the following sub-directories within it: server_logs, user_logs, and event_logs

mkdir processed
cd processed
mkdir server_logs user_logs event_logs
# 5. Copy all server log files (files with "server" in the name AND a .log extension) from ./data/raw to ./data/processed/server_logs

cd ..
cd raw
cp *server*.log ../processed/server_logs
# 6. Repeat the above step for user logs and event logs

cp *user*.log ../processed/user_logs
cp *event*.log ../processed/event_logs
# 7. For user privacy, remove all files containing IP addresses (files with "ipaddr" in the filename) from ./data/raw and ./data/processed/user_logs
rm *ipaddr*
cd ../processed/user_logs
rm *ipaddr*

# 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed


cd ../..
touch inventory.txt
cd processed
echo $(ls user_logs server_logs event_logs) >> ../inventory.txt
###########################################

echo "Project setup is complete!"