diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 4b48cec8b..99e5e4a82 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -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 @@ -27,24 +28,30 @@ unzip -q rawdata.zip ########################################### # Complete assignment here -# 1. Create a directory named data +# 1. +mkdir data -# 2. Move the ./rawdata directory to ./data/raw (eg. move it into ./data and rename it to raw) +# 2. +mv rawdata data/raw -# 3. List the contents of the ./data/raw directory +# 3. +ls data/raw -# 4. Create the directory ./data/processed, -# then create the following sub-directories within it: server_logs, user_logs, and event_logs +# 4. +mkdir -p data/processed/server_logs data/processed/user_logs data/processed/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 +# 5. +cp data/raw/*server*.log data/processed/server_logs/ -# 6. Repeat the above step for user logs and event logs +# 6. +cp data/raw/*user*.log data/processed/user_logs/ +cp data/raw/*event*.log data/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 +# 7. +rm -f data/raw/*ipaddr* +rm -f data/processed/user_logs/*ipaddr* -# 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed +# 8. +find data/processed -type f | sort > data/inventory.txt - -########################################### - -echo "Project setup is complete!" +echo "Project steps complete" \ No newline at end of file diff --git a/newproject/assignment.sh b/newproject/assignment.sh new file mode 100644 index 000000000..775a16fab --- /dev/null +++ b/newproject/assignment.sh @@ -0,0 +1,27 @@ +#!/bin/bash + +# 1. Create the data directory +mkdir -p data + +# 2. Move rawdata into data/raw +mv rawdata data/raw + +# 3. List contents to verify +ls data/raw + +# 4. Create the sub-directories +mkdir -p data/processed/server_logs data/processed/user_logs data/processed/event_logs + +# 5 & 6. Copy the specific logs +cp data/raw/*server*.log data/processed/server_logs/ +cp data/raw/*user*.log data/processed/user_logs/ +cp data/raw/*event*.log data/processed/event_logs/ + +# 7. Privacy: Force-remove IP address files +rm -f data/raw/*ipaddr* +rm -f data/processed/user_logs/*ipaddr* + +# 8. Create the inventory list +ls -R data/processed > data/inventory.txt + +echo "Assignment steps completed." \ No newline at end of file