Skip to content
Open
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
22 changes: 19 additions & 3 deletions 02_activities/assignments/assignment.sh
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,8 @@ set -x

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

# download client data
Expand All @@ -21,22 +23,36 @@ unzip -q rawdata.zip
# Complete assignment here

# 1. Create a directory named data
mkdir data #creates directory named data

# 2. Move the ./rawdata directory to ./data/raw
mv ./rawdata ./data/raw #move rawdata directory to raw directory

# 3. List the contents of the ./data/raw directory
ls ./data/raw #list contents of subdirectory

# 4. In ./data/processed, create the following directories: server_logs, user_logs, and event_logs
cd data #move to data directory
mkdir processed #creates processed subdirectory in data directory
cd ./processed #move into processed directory
mkdir server_logs user_logs event_logs #creates server_logs, user_logs, and event_logs directory

# 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 .. #move back to data directory
cp ./raw/*server*.log ./processed/server_logs/ #copies all files with "server" in the name, and carry a .log extension, to the .data/processed/server_logs destination folder

# 6. Repeat the above step for user logs and event logs
cp ./raw/*user*.log ./processed/user_logs/
cp ./raw/*event*.log ./processed/event_logs/ #like line 44, except it copies files to 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 ./raw/*ipaddr*.log #removes log files with "ipaddr"
rm ./raw/*ipaddr*.txt #removes txt files with "ipaddr"
rm ./processed/user_logs/*ipaddr*.log #removes log files with "ipaddr"
rm ./processed/user_logs/*ipaddr*.txt #removes txt files with "ipaddr"
# 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed

ls processed/* > inventory.txt

###########################################

echo "Project setup is complete!"
echo "Project setup is complete!"