From e976b55a5c2a83f4f2ab1221ea228c9b8737db4f Mon Sep 17 00:00:00 2001 From: Simeon Wong Date: Thu, 14 Nov 2024 20:32:09 -0500 Subject: [PATCH 01/10] 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 02/10] 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 9507592f017043f119b3e8543095c4076f208241 Mon Sep 17 00:00:00 2001 From: Alexandre T Date: Sat, 2 Aug 2025 07:42:16 -0400 Subject: [PATCH 03/10] Make data directory for the assignement1 DSI --- 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 8af8dc092..14e939eb1 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -28,7 +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 # 3. List the contents of the ./data/raw directory From e2b3e29f5b1df43a362c7a4e16f5faf63522bdda Mon Sep 17 00:00:00 2001 From: Alexandre T Date: Sat, 2 Aug 2025 10:25:17 -0400 Subject: [PATCH 04/10] Modification for assignment 1 --- 02_activities/assignments/assignment.sh | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 14e939eb1..8ff3b6ed6 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -30,19 +30,21 @@ unzip -q rawdata.zip # 1. Create a directory named data mkdir data # 2. Move the ./rawdata directory to ./data/raw - +mv rawdata data/raw # 3. List the contents of the ./data/raw directory - +ls data/raw # 4. In ./data/processed, create the following directories: server_logs, user_logs, and event_logs - +mkdir data/processed server_logs user_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* +rm ./data/processed/user_logs/*ipadrr* # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed - +touch data/inventory/inventory.txt ########################################### From 31a5658253984ee3d7ee247ea06a90f795bf63fb Mon Sep 17 00:00:00 2001 From: Alexandre T Date: Sat, 2 Aug 2025 11:54:32 -0400 Subject: [PATCH 05/10] Trigger GitHub Actions From 284b03d08230a661b9a96e64548ac897e561e229 Mon Sep 17 00:00:00 2001 From: Alexandre T Date: Sat, 2 Aug 2025 12:25:41 -0400 Subject: [PATCH 06/10] Changes on Assignment1 part1 --- 02_activities/assignments/assignment.sh | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 8ff3b6ed6..d59b60e09 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -34,12 +34,14 @@ mv rawdata data/raw # 3. List the contents of the ./data/raw directory ls data/raw # 4. In ./data/processed, create the following directories: server_logs, user_logs, and event_logs -mkdir data/processed server_logs user_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/ +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/ +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* rm ./data/processed/user_logs/*ipadrr* From 1b1d40d6127a36bdcc33f7ed10d1ffb82408ca49 Mon Sep 17 00:00:00 2001 From: Alexandre T Date: Sat, 2 Aug 2025 14:31:36 -0400 Subject: [PATCH 07/10] Changes on assignement 1 --- 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 d59b60e09..42f28a9de 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -44,9 +44,9 @@ 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* -rm ./data/processed/user_logs/*ipadrr* +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 -touch data/inventory/inventory.txt + ls ./data/processed > ./data/inventory.txt ########################################### From ac09d5c4c147fdf5ea58db83b1abf972604654e4 Mon Sep 17 00:00:00 2001 From: Alexandre T Date: Sat, 2 Aug 2025 15:03:26 -0400 Subject: [PATCH 08/10] changes on assignment 1 --- 02_activities/assignments/assignment.sh | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 42f28a9de..62b02cb97 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -46,7 +46,9 @@ cp data/raw/*event*.log data/processed/event_logs 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 +cd data/processed +touch data/inventory.txt + ########################################### From 08412036070c4e1c10e9605be1e0a82e020f1fb0 Mon Sep 17 00:00:00 2001 From: Alexandre T Date: Sat, 2 Aug 2025 15:09:50 -0400 Subject: [PATCH 09/10] changes on assignement 1 --- 02_activities/assignments/assignment.sh | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 62b02cb97..e1265533a 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -46,8 +46,7 @@ cp data/raw/*event*.log data/processed/event_logs 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 -cd data/processed -touch data/inventory.txt +ls -R ./data/processed >./data/inventory.txt ########################################### From 0530fa897005f8b7fbccfbb9603549c4a3bce9fd Mon Sep 17 00:00:00 2001 From: Alexandre T Date: Sat, 2 Aug 2025 15:42:01 -0400 Subject: [PATCH 10/10] changes on assignment1 --- 02_activities/assignments/assignment.sh | 5 ----- 1 file changed, 5 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index b304b7d55..caf0bde03 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -44,13 +44,8 @@ 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 -<<<<<<< HEAD rm ./data/raw/*ipaddr* rm ./data/processed/user_logs/*ipaddr* -======= -rf -rf ./data - ->>>>>>> ea20676d33161a6f4d0fcd3c4f7aa5360f0f4309 # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed ls -R ./data/processed >./data/inventory.txt