From e976b55a5c2a83f4f2ab1221ea228c9b8737db4f Mon Sep 17 00:00:00 2001 From: Simeon Wong Date: Thu, 14 Nov 2024 20:32:09 -0500 Subject: [PATCH 1/4] delete ip logs... WARNING UNTESTED! --- 02_activities/assignments/assignment.sh | 1 + 1 file changed, 1 insertion(+) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index d81e9a77b..001291867 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -33,6 +33,7 @@ unzip rawdata.zip # 6. Repeat the above step for user logs and 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 +rf -rf ./data # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed From ea20676d33161a6f4d0fcd3c4f7aa5360f0f4309 Mon Sep 17 00:00:00 2001 From: Simeon Wong Date: Thu, 14 Nov 2024 20:55:44 -0500 Subject: [PATCH 2/4] initialize README file with company name --- 02_activities/assignments/assignment.sh | 1 + 1 file changed, 1 insertion(+) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 001291867..f2bfd22bd 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -11,6 +11,7 @@ set -x mkdir analysis output touch README.md +echo "# Project Name: DSI Consulting Inc." > README.md touch analysis/main.py # download client data From 0ce00a7f41f1f0508c95c2dfefd809bb5df85c74 Mon Sep 17 00:00:00 2001 From: Sydney Ma Date: Wed, 4 Mar 2026 14:05:08 -0800 Subject: [PATCH 3/4] first edition --- 02_activities/assignments/assignment.sh | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 4b48cec8b..af1d0264a 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -28,22 +28,31 @@ unzip -q rawdata.zip # Complete assignment here # 1. Create a directory named data +mkdir data # 2. Move the ./rawdata directory to ./data/raw (eg. move it into ./data and rename it to raw) +mv rawdata data/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 -p data/processed/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 - +cp data/raw/*server*.log data/processed/server_logs/ # 6. Repeat the above step for user logs and event logs +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 +rm data/raw/*ipaddr*.log +rm data/processed/user_logs/*ipaddr*.log # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed - +# ls data/processed > data/inventory.txt +find data/processed -type f > data/inventory.txt ########################################### From c3d27907a7d9c87ed7243a3a4ac3f9f41aa03557 Mon Sep 17 00:00:00 2001 From: Sydney Ma Date: Wed, 4 Mar 2026 21:26:20 -0800 Subject: [PATCH 4/4] second_edition --- 02_activities/assignments/assignment.sh | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index af1d0264a..62257e14d 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -38,17 +38,20 @@ 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 -p data/processed/server_logs/user_logs/event_logs +mkdir -p data/processed/server_logs +mkdir -p data/processed/user_logs +mkdir -p 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 cp data/raw/*server*.log data/processed/server_logs/ + # 6. Repeat the above step for user logs and event logs 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 -rm data/raw/*ipaddr*.log -rm data/processed/user_logs/*ipaddr*.log +rm data/raw/*ipaddr* +rm data/processed/user_logs/*ipaddr* # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed # ls data/processed > data/inventory.txt