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 f8a41f5f77d6098a550193bdc83efb5d4b8c56ae Mon Sep 17 00:00:00 2001 From: Syed Ali Date: Tue, 15 Apr 2025 19:14:54 -0400 Subject: [PATCH 03/10] Finished Question 1 on Assignment --- 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 2fbb9c81d..8f5507ddf 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -21,6 +21,7 @@ unzip -q rawdata.zip # Complete assignment here # 1. Create a directory named data +mkdir data # 2. Move the ./rawdata directory to ./data/raw From a5fd28343c167b66ef272ec5ac33558034bdcebd Mon Sep 17 00:00:00 2001 From: Syed Ali Date: Sat, 19 Apr 2025 15:47:46 -0400 Subject: [PATCH 04/10] Finished Q2 and Q3 --- 02_activities/assignments/assignment.sh | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 8f5507ddf..270d0145b 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -24,10 +24,14 @@ 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 - +ls # 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 From 9dceb3c8f085e34436574d89a9dea181f108e40e Mon Sep 17 00:00:00 2001 From: Syed Ali Date: Sat, 19 Apr 2025 16:33:46 -0400 Subject: [PATCH 05/10] All Questions of the Assignment are completed --- 02_activities/assignments/assignment.sh | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 270d0145b..f315fedd1 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -26,7 +26,7 @@ mkdir data # 2. Move the ./rawdata directory to ./data/raw mv ./rawdata ./data/raw # 3. List the contents of the ./data/raw directory -ls +ls ./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 @@ -34,13 +34,16 @@ 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/user*.log ./data/processed/server_logs +cp ./data/raw/event*.log ./data/processed/server_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/*ipadder* +rm ./data/processed/*ipadder* # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed - +cd ./data/processed +ls > ./data/inventory.txt ########################################### From 22764078116c9b1e1950f9261c8cbfbd4a116aae Mon Sep 17 00:00:00 2001 From: Syed Ali Date: Sat, 19 Apr 2025 16:48:16 -0400 Subject: [PATCH 06/10] Correction done --- 02_activities/assignments/assignment.sh | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index f315fedd1..adf3804f8 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -36,11 +36,11 @@ 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/user*.log ./data/processed/server_logs -cp ./data/raw/event*.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 ./data/raw/*ipadder* -rm ./data/processed/*ipadder* +rm ./data/raw/*ipaddr* +rm ./data/processed/*ipaddr* # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed cd ./data/processed ls > ./data/inventory.txt From c73fde909c0c0c506b55e4cd48289f964f106bf4 Mon Sep 17 00:00:00 2001 From: Syed Ali Date: Sat, 19 Apr 2025 17:27:37 -0400 Subject: [PATCH 07/10] Corrections made --- 02_activities/assignments/assignment.sh | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index adf3804f8..23455b0e5 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -34,16 +34,20 @@ 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/ser*.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/*ipaddr* +rm ./data/processed/*logs/*ipaddr* # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed -cd ./data/processed +cd ./data/processed/user_logs ls > ./data/inventory.txt +cd ./data/processed/server_logs +ls >>./data/inventory.txt +cd ./data/processed/event_logs +ls >> ./data/inventory.txt ########################################### From 7a97e7bdae4efcb84113d9fa9a6bd256677686f1 Mon Sep 17 00:00:00 2001 From: Syed Ali Date: Sat, 19 Apr 2025 17:42:42 -0400 Subject: [PATCH 08/10] Correction made in Q8 --- 02_activities/assignments/assignment.sh | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 23455b0e5..93ddce803 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -42,11 +42,7 @@ cp ./data/raw/event*.log ./data/processed/event_logs rm ./data/raw/*ipaddr* rm ./data/processed/*logs/*ipaddr* # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed -cd ./data/processed/user_logs -ls > ./data/inventory.txt -cd ./data/processed/server_logs -ls >>./data/inventory.txt -cd ./data/processed/event_logs +touch ./data/inventory.txt ls >> ./data/inventory.txt ########################################### From 55ed2c0f73a8a64ac9289ff3d0f05d5cffcb9664 Mon Sep 17 00:00:00 2001 From: Syed Ali Date: Sat, 19 Apr 2025 17:49:29 -0400 Subject: [PATCH 09/10] Update --- 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 93ddce803..468c4576d 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -43,7 +43,9 @@ rm ./data/raw/*ipaddr* rm ./data/processed/*logs/*ipaddr* # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed touch ./data/inventory.txt -ls >> ./data/inventory.txt +ls > ./data/processed/server_logs/inventory.txt +ls >> ./data/processed/user_logs/inventory.txt +ls >> ./data/processed/event_logs/inventory.txt ########################################### From 8743acbb5228dfd265e3e7fe3d0b5227c3d4555c Mon Sep 17 00:00:00 2001 From: Syed Ali Date: Sat, 19 Apr 2025 18:26:52 -0400 Subject: [PATCH 10/10] Question 08 of Part 1 is also completed --- 02_activities/assignments/assignment.sh | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 468c4576d..8b0344ae4 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -42,10 +42,14 @@ cp ./data/raw/event*.log ./data/processed/event_logs rm ./data/raw/*ipaddr* rm ./data/processed/*logs/*ipaddr* # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed -touch ./data/inventory.txt -ls > ./data/processed/server_logs/inventory.txt -ls >> ./data/processed/user_logs/inventory.txt -ls >> ./data/processed/event_logs/inventory.txt +cd ./data/processed/user_logs +ls > ../../inventory.txt + +cd ../server_logs +ls >> ../../inventory.txt + +cd ../event_logs +ls >> ../../inventory.txt ###########################################