From e976b55a5c2a83f4f2ab1221ea228c9b8737db4f Mon Sep 17 00:00:00 2001 From: Simeon Wong Date: Thu, 14 Nov 2024 20:32:09 -0500 Subject: [PATCH 1/8] 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 2/8] 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 e1993c9eccb6a0678db7e36bd37ab0212ece63c2 Mon Sep 17 00:00:00 2001 From: Aakash11bajaj Date: Thu, 6 Nov 2025 18:45:24 -0500 Subject: [PATCH 3/8] Added mkdir --- 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 d2e8de7c2d874b660c22f0247f295361780a7883 Mon Sep 17 00:00:00 2001 From: Aakash11bajaj Date: Sat, 8 Nov 2025 11:20:14 -0500 Subject: [PATCH 4/8] Completed assignment - check 1 if it runs online --- 02_activities/assignments/assignment.sh | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 810214873..4cac4d738 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -29,21 +29,23 @@ 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 +mkdir ./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 - +mv ./data/raw/server*.log processed/server_logs # 6. Repeat the above step for user logs and event logs - +mv ./data/raw/user*.log ./data/processed/user_logs +mv ./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/processed/user_logs/user_ipaddr* +rm .data/raw/ipaddr* # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed - +echo "Files in processed folder \n1) sever-logs\n2) user_logs\n3) event_logs" >> ./data/processed/inventory.txt ########################################### From f3664bc9f4e53af0c5a93cf792a7e875d2e07a69 Mon Sep 17 00:00:00 2001 From: Aakash11bajaj Date: Sat, 8 Nov 2025 11:37:57 -0500 Subject: [PATCH 5/8] modified --- 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 4cac4d738..0ca79d150 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -23,7 +23,7 @@ touch analysis/main.py # download client data curl -Lo rawdata.zip https://github.com/UofT-DSI/shell/raw/refs/heads/main/02_activities/assignments/rawdata.zip unzip -q rawdata.zip - +# ########################################### # Complete assignment here From cb0ed038dc69a664b50992c53dfd6f005f78a3d1 Mon Sep 17 00:00:00 2001 From: Aakash11bajaj Date: Sat, 8 Nov 2025 11:44:28 -0500 Subject: [PATCH 6/8] Modified check 2 --- 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 0ca79d150..be58be88f 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -35,17 +35,19 @@ mv ./rawdata ./data/raw/ 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 .data/processed/user_logs .data/processed/event_logs +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 -mv ./data/raw/server*.log processed/server_logs +mv ./data/raw/*server*.log processed/server_logs # 6. Repeat the above step for user logs and event logs -mv ./data/raw/user*.log ./data/processed/user_logs -mv ./data/raw/event*.log .data/processed/event_logs +mv ./data/raw/*user*.log ./data/processed/user_logs +mv ./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/processed/user_logs/user_ipaddr* -rm .data/raw/ipaddr* +rm ./data/processed/user_logs/*ipaddr* +rm ./data/raw/*ipaddr* # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed -echo "Files in processed folder \n1) sever-logs\n2) user_logs\n3) event_logs" >> ./data/processed/inventory.txt +find ./data/processed -type f > ./data/inventory.txt ########################################### From ac428bf6fd4c151786a0fdcea1700e3caaaa7e25 Mon Sep 17 00:00:00 2001 From: Aakash11bajaj Date: Sat, 8 Nov 2025 11:46:15 -0500 Subject: [PATCH 7/8] modified check 3 --- 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 be58be88f..2e00aa5e4 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -39,10 +39,10 @@ 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 -mv ./data/raw/*server*.log processed/server_logs +mv ./data/raw/*server*.log ./data/processed/server_logs # 6. Repeat the above step for user logs and event logs mv ./data/raw/*user*.log ./data/processed/user_logs -mv ./data/raw/*event*.log .data/processed/event_logs +mv ./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/processed/user_logs/*ipaddr* rm ./data/raw/*ipaddr* From a53bd3df66d134fa0fc2e1bec57291305510e0c4 Mon Sep 17 00:00:00 2001 From: Aakash11bajaj Date: Sat, 8 Nov 2025 11:47:57 -0500 Subject: [PATCH 8/8] modified check 4 --- 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 2e00aa5e4..2188a8759 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -39,10 +39,10 @@ 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 -mv ./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 -mv ./data/raw/*user*.log ./data/processed/user_logs -mv ./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/processed/user_logs/*ipaddr* rm ./data/raw/*ipaddr*