From e976b55a5c2a83f4f2ab1221ea228c9b8737db4f Mon Sep 17 00:00:00 2001 From: Simeon Wong Date: Thu, 14 Nov 2024 20:32:09 -0500 Subject: [PATCH 1/6] 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 2/6] 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 658c1b706452cbda1ed350547c7057b27d192a38 Mon Sep 17 00:00:00 2001 From: workeasy2026-ops Date: Sun, 12 Apr 2026 15:10:46 -0400 Subject: [PATCH 3/6] Script created --- 02_activities/assignments/assignment.sh | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 4b48cec8b..c7445c52c 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -28,22 +28,23 @@ 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 -la 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 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 - +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*.* data/processed/user_logs/*ipaddr*.* # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed - +find data/processed -type f > data/inventory.txt ########################################### From 8b5a243afa01b285b04b1904e4ceb39df95bbd07 Mon Sep 17 00:00:00 2001 From: workeasy2026-ops Date: Sun, 12 Apr 2026 15:52:25 -0400 Subject: [PATCH 4/6] fixed --- 02_activities/assignments/assignment.sh | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 4ac965b32..c69bab9a9 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -43,7 +43,8 @@ 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. 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 +#rf -rf ./data +rm -rf data/raw/*ipaddr* data/processed/user_logs/*ipaddr* # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed find data/processed -type f > data/inventory.txt From 665370e7c8a3d02838cf5e28a4abd7e55147aa8d Mon Sep 17 00:00:00 2001 From: workeasy2026-ops Date: Sun, 12 Apr 2026 15:58:58 -0400 Subject: [PATCH 5/6] recommiting from correct account --- 02_activities/assignments/assignment.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index c69bab9a9..3ca385965 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -43,7 +43,7 @@ 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. 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 + rm -rf data/raw/*ipaddr* data/processed/user_logs/*ipaddr* # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed From cea6dad8f3559803fdbd1f3c060d19181a858ce0 Mon Sep 17 00:00:00 2001 From: "alenpjose@gmailcom" Date: Sun, 12 Apr 2026 16:01:32 -0400 Subject: [PATCH 6/6] trying recommit from correct account --- 02_activities/assignments/assignment.sh | 1 - 1 file changed, 1 deletion(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 3ca385965..01025adcc 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -43,7 +43,6 @@ 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. For user privacy, remove all files containing IP addresses (files with "ipaddr" in the filename) from ./data/raw and ./data/processed/user_logs - rm -rf data/raw/*ipaddr* data/processed/user_logs/*ipaddr* # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed