From e976b55a5c2a83f4f2ab1221ea228c9b8737db4f Mon Sep 17 00:00:00 2001 From: Simeon Wong Date: Thu, 14 Nov 2024 20:32:09 -0500 Subject: [PATCH 01/13] 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 02/13] 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 71961bfc5057e3ace0f9878108d193d7db59652d Mon Sep 17 00:00:00 2001 From: Ceci Date: Sun, 12 Oct 2025 09:10:44 -0400 Subject: [PATCH 03/13] Create data directory --- 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 8af8dc092..db7ba57b4 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 c5689bc73f42fb6d47954d42c0c5df29b682d9fc Mon Sep 17 00:00:00 2001 From: Ceci Date: Sun, 12 Oct 2025 09:29:40 -0400 Subject: [PATCH 04/13] Move ./rawdata to ./data/raw --- 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 db7ba57b4..7a09ad023 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 ad44f58bc843a15eed3e92d7ae24f3dd2b960bca Mon Sep 17 00:00:00 2001 From: Ceci Date: Sun, 12 Oct 2025 09:34:06 -0400 Subject: [PATCH 05/13] List ./data/raw contents --- 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 7a09ad023..27e420ec8 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -34,6 +34,7 @@ mkdir data 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 From b036ccc7b15f365d2d17e7175bdbc81bfa98463f Mon Sep 17 00:00:00 2001 From: Ceci Date: Sun, 12 Oct 2025 09:38:12 -0400 Subject: [PATCH 06/13] Create three ./data/processed directories --- 02_activities/assignments/assignment.sh | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 27e420ec8..f754dbebf 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -37,6 +37,10 @@ mv rawdata data/raw ls data/raw # 4. In ./data/processed, create the following directories: server_logs, user_logs, and event_logs +cd data +mkdir processed +cd processed +mkdir 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 From 272061f67b86d27fad5905651aee6839495ac672 Mon Sep 17 00:00:00 2001 From: Ceci Date: Sun, 12 Oct 2025 09:41:36 -0400 Subject: [PATCH 07/13] Copy server log files --- 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 f754dbebf..559f2670a 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -43,6 +43,8 @@ cd processed mkdir 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 +cd .. +cp raw/server_*.log processed/server_logs # 6. Repeat the above step for user logs and event logs From bf6069c5c5b4535aa20314224887875b3e33befe Mon Sep 17 00:00:00 2001 From: Ceci Date: Sun, 12 Oct 2025 09:44:11 -0400 Subject: [PATCH 08/13] Add user and event logs --- 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 559f2670a..b9f157f22 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -47,6 +47,8 @@ cd .. cp raw/server_*.log processed/server_logs # 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 # 7. For user privacy, remove all files containing IP addresses (files with "ipaddr" in the filename) from ./data/raw and ./data/processed/user_logs From f9eafa8531bdae9f7406127615625be081bc39a2 Mon Sep 17 00:00:00 2001 From: Ceci Date: Sun, 12 Oct 2025 09:47:29 -0400 Subject: [PATCH 09/13] Remove IP address files --- 02_activities/assignments/assignment.sh | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index b9f157f22..a8f156c17 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -51,6 +51,11 @@ cp raw/user_*.log processed/user_logs cp raw/event_*.log 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 +cd raw +rm -i ipaddr* +cd .. +cd processed/user_logs +rm -i user_ipaddr* # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed From e92167488dec5f40d3e2d0a96d7b5e5afbc8528c Mon Sep 17 00:00:00 2001 From: Ceci Date: Sun, 12 Oct 2025 09:51:57 -0400 Subject: [PATCH 10/13] List ./data/processed subfolder files in inventory.txt --- 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 a8f156c17..a21a00b83 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -58,7 +58,9 @@ cd processed/user_logs rm -i user_ipaddr* # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed - +cd .. +ls server_logs user_logs event_logs >> inventory.txt +cat inventory.txt ########################################### From abde4e86d87c2b0ffbe19082e68fa2ca3a3fda21 Mon Sep 17 00:00:00 2001 From: Ceci Date: Sun, 12 Oct 2025 11:46:19 -0400 Subject: [PATCH 11/13] Modified Step 7 code and saved to assignment --- 02_activities/assignments/assignment.sh | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index a21a00b83..18f76a80f 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -51,11 +51,12 @@ cp raw/user_*.log processed/user_logs cp raw/event_*.log 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 +cd .. cd raw -rm -i ipaddr* +rm -i ipaddr_*.txt cd .. cd processed/user_logs -rm -i user_ipaddr* +rm -i user_ipaddr_*.log # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed cd .. From df6ff2eb88ba6c77b5d436bb49117d7fe4c5fa33 Mon Sep 17 00:00:00 2001 From: Ceci Date: Sun, 12 Oct 2025 12:43:39 -0400 Subject: [PATCH 12/13] Recoded Q7 --- 02_activities/assignments/assignment.sh | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 18f76a80f..d008c2e9e 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -41,22 +41,24 @@ cd data mkdir processed cd processed mkdir server_logs user_logs event_logs +pwd # 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 .. cp raw/server_*.log processed/server_logs +pwd # 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 +pwd # 7. For user privacy, remove all files containing IP addresses (files with "ipaddr" in the filename) from ./data/raw and ./data/processed/user_logs -cd .. cd raw -rm -i ipaddr_*.txt +rm -if *ipaddr* cd .. cd processed/user_logs -rm -i user_ipaddr_*.log +rm -if *ipaddr* # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed cd .. From 59d80e62cc5930337e3c909b0290fb7e4b410836 Mon Sep 17 00:00:00 2001 From: Ceci Date: Sun, 12 Oct 2025 12:59:51 -0400 Subject: [PATCH 13/13] Recoded 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 d008c2e9e..60c520aba 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -64,6 +64,7 @@ rm -if *ipaddr* cd .. ls server_logs user_logs event_logs >> inventory.txt cat inventory.txt +mv inventory.txt .. ###########################################