From e976b55a5c2a83f4f2ab1221ea228c9b8737db4f Mon Sep 17 00:00:00 2001 From: Simeon Wong Date: Thu, 14 Nov 2024 20:32:09 -0500 Subject: [PATCH 01/12] 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 02/12] 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 c1616caf76f4522f55602cd185fd405f08734e44 Mon Sep 17 00:00:00 2001 From: Awan Date: Fri, 7 Nov 2025 11:44:05 -0500 Subject: [PATCH 03/12] Answered Q-1 of assignment project --- 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 4b2baa7ae..810214873 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -28,6 +28,7 @@ unzip -q rawdata.zip # Complete assignment here # 1. Create a directory named data +mkdir data # 2. Move the ./rawdata directory to ./data/raw From 97ac55053fab5aaab535a790c8bd8afbce88da77 Mon Sep 17 00:00:00 2001 From: Awan Date: Fri, 7 Nov 2025 18:55:20 -0500 Subject: [PATCH 04/12] Answered Q-2 --- 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 810214873..4664ff4ab 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -31,6 +31,7 @@ unzip -q rawdata.zip mkdir data # 2. Move the ./rawdata directory to ./data/raw +mv ./rawdata ./data/raw # 3. List the contents of the ./data/raw directory From 80290860c0f65ebfb82ab4cefd60519b531a45f0 Mon Sep 17 00:00:00 2001 From: Awan Date: Fri, 7 Nov 2025 21:02:49 -0500 Subject: [PATCH 05/12] Answered Q 1-7 --- 02_activities/assignments/assignment.sh | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 4664ff4ab..38bba1afe 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -34,14 +34,24 @@ mkdir data mv ./rawdata ./data/raw # 3. List the contents of the ./data/raw directory +ls -al ./data/raw # 4. In ./data/processed, create the following directories: server_logs, user_logs, and event_logs +mkdir ./data/processed +mkdir ./data/processed/server_logs +mkdir ./data/processed/user_logs +mkdir ./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/*server*.log ./data/processed/user_logs/ +cp ./data/raw/*server*.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 +find ./data/raw ./data/processed/user_logs -type f -name '*ipaddr*' +find ./data/raw ./data/processed/user_logs -type f -name '*ipaddr*' -delete # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed From f473c6f8efcba8dd25af56cddf8772e927269c0e Mon Sep 17 00:00:00 2001 From: Awan Date: Fri, 7 Nov 2025 21:09:45 -0500 Subject: [PATCH 06/12] Answer Q 1-8 Revised --- 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 38bba1afe..e2e7a35b6 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -54,7 +54,7 @@ find ./data/raw ./data/processed/user_logs -type f -name '*ipaddr*' find ./data/raw ./data/processed/user_logs -type f -name '*ipaddr*' -delete # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed - +touch ./data/inventory.txt ########################################### From f655b2b6bddd471e54bece95f4c43c96fa407b5e Mon Sep 17 00:00:00 2001 From: Awan Date: Fri, 7 Nov 2025 21:15:08 -0500 Subject: [PATCH 07/12] Answered Q 1-8 with correction --- 02_activities/assignments/assignment.sh | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index e2e7a35b6..ac739caa3 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -43,11 +43,11 @@ mkdir ./data/processed/user_logs mkdir ./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/ +cp ./data/raw/*server*.log ./data/processed/server_logs # 6. Repeat the above step for user logs and event logs -cp ./data/raw/*server*.log ./data/processed/user_logs/ -cp ./data/raw/*server*.log ./data/processed/event_logs/ +cp ./data/raw/*server*.log ./data/processed/user_logs +cp ./data/raw/*server*.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 find ./data/raw ./data/processed/user_logs -type f -name '*ipaddr*' From 6ad8c207a8ee80c2c592463f661e723707defcc0 Mon Sep 17 00:00:00 2001 From: Awan Date: Fri, 7 Nov 2025 21:29:11 -0500 Subject: [PATCH 08/12] Answer Q 1-8 corrected --- 02_activities/assignments/assignment.sh | 2 ++ 1 file changed, 2 insertions(+) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index ac739caa3..353a651f3 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -55,6 +55,8 @@ find ./data/raw ./data/processed/user_logs -type f -name '*ipaddr*' -delete # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed touch ./data/inventory.txt +mv ./data/processed/* ./data/inventory.txt/ + ########################################### From 597311402a0b9fefbab0db33e92d43489e93bbfa Mon Sep 17 00:00:00 2001 From: Awan Date: Fri, 7 Nov 2025 22:08:14 -0500 Subject: [PATCH 09/12] Q-8 Correction --- 02_activities/assignments/assignment.sh | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 353a651f3..67726a025 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -54,9 +54,7 @@ find ./data/raw ./data/processed/user_logs -type f -name '*ipaddr*' find ./data/raw ./data/processed/user_logs -type f -name '*ipaddr*' -delete # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed -touch ./data/inventory.txt -mv ./data/processed/* ./data/inventory.txt/ - +data/processed/./data/inventory.txt ########################################### From 15531cf8472ba2b9b08fae743e1fc40f615ca985 Mon Sep 17 00:00:00 2001 From: Awan Date: Fri, 7 Nov 2025 22:17:25 -0500 Subject: [PATCH 10/12] Working on Q8 --- 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 67726a025..051a06e29 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -54,6 +54,7 @@ find ./data/raw ./data/processed/user_logs -type f -name '*ipaddr*' find ./data/raw ./data/processed/user_logs -type f -name '*ipaddr*' -delete # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed +touch data/inventory.txt data/processed/./data/inventory.txt ########################################### From efb8d718e999590d058479345d49c69c65b2d776 Mon Sep 17 00:00:00 2001 From: Awan Date: Fri, 7 Nov 2025 22:24:18 -0500 Subject: [PATCH 11/12] Still working on Q8 --- 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 051a06e29..141d4fb5c 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -55,7 +55,7 @@ find ./data/raw ./data/processed/user_logs -type f -name '*ipaddr*' -delete # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed touch data/inventory.txt -data/processed/./data/inventory.txt +ls -R ./data/processed/ > ./data/inventory.txt ########################################### From a45cd2add657afcb62c8be1044d7aa86ac94e209 Mon Sep 17 00:00:00 2001 From: Awan Date: Sat, 8 Nov 2025 10:45:27 -0500 Subject: [PATCH 12/12] Q6 corrected --- 02_activities/assignments/assignment.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 141d4fb5c..aac89e093 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -46,8 +46,8 @@ mkdir ./data/processed/event_logs cp ./data/raw/*server*.log ./data/processed/server_logs # 6. Repeat the above step for user logs and event logs -cp ./data/raw/*server*.log ./data/processed/user_logs -cp ./data/raw/*server*.log ./data/processed/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 find ./data/raw ./data/processed/user_logs -type f -name '*ipaddr*'