From e976b55a5c2a83f4f2ab1221ea228c9b8737db4f Mon Sep 17 00:00:00 2001 From: Simeon Wong Date: Thu, 14 Nov 2024 20:32:09 -0500 Subject: [PATCH 1/7] 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 2/7] 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 f04ce9f14e09d2cf0d4814932063f473d40b4694 Mon Sep 17 00:00:00 2001 From: Liza Igoshina Date: Fri, 6 Mar 2026 14:18:42 -0500 Subject: [PATCH 3/7] updated assignment.sh to the correct branch --- 02_activities/assignments/assignment.sh | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 4b48cec8b..d6c6a1ddf 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -28,22 +28,37 @@ unzip -q rawdata.zip # Complete assignment here # 1. Create a directory named data +mkdir data # 2. Move the ./rawdata directory to ./data/raw (eg. move it into ./data and rename it to raw) +mv ./rawdata ./data/raw # 3. List the contents of the ./data/raw directory +cd ./data/raw +ls # 4. Create the directory ./data/processed, # then create the following sub-directories within it: server_logs, user_logs, and event_logs +mkdir ./data/processed # 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 processed +mkdir ./data/processed/server_logs +cp ./data/raw/*server*.log ./data/processed/server_logs/ # 6. Repeat the above step for user logs and event logs +mkdir ./data/processed/user_logs +mkdir ./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*.log +rm ./data/processed/user_logs/*ipaddr*.txt # 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 ########################################### From 7fd8997c21e2f741b0fb6394c7bea52bc00efca2 Mon Sep 17 00:00:00 2001 From: Liza Igoshina Date: Fri, 6 Mar 2026 14:31:41 -0500 Subject: [PATCH 4/7] removed cd commands, made paths general --- 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 d6c6a1ddf..1987992d2 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -34,15 +34,13 @@ mkdir data mv ./rawdata ./data/raw # 3. List the contents of the ./data/raw directory -cd ./data/raw -ls +ls ./data/raw # 4. Create the directory ./data/processed, # then create the following sub-directories within it: server_logs, user_logs, and event_logs mkdir ./data/processed # 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 processed mkdir ./data/processed/server_logs cp ./data/raw/*server*.log ./data/processed/server_logs/ From 3887c5274afeddeccb236616ef3f4a59839c9411 Mon Sep 17 00:00:00 2001 From: Liza Igoshina Date: Fri, 6 Mar 2026 14:40:10 -0500 Subject: [PATCH 5/7] made the ipaddr files not specific to .txt or .log --- 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 1987992d2..f2a5791cb 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -52,8 +52,8 @@ 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*.log -rm ./data/processed/user_logs/*ipaddr*.txt +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 From c4e27683e874d9ec096ed5d44af596f290f61e52 Mon Sep 17 00:00:00 2001 From: Liza Igoshina Date: Fri, 6 Mar 2026 14:46:37 -0500 Subject: [PATCH 6/7] resolved coworker comment --- 02_activities/assignments/assignment.sh | 3 --- 1 file changed, 3 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 9d3f827d7..5f35eec84 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -56,9 +56,6 @@ cp ./data/raw/*event*.log ./data/processed/event_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 ./data/processed/* > ./data/inventory.txt From 4bd7ddcce5b8a4ed037caa79a6f04da77862dd65 Mon Sep 17 00:00:00 2001 From: Liza Igoshina Date: Fri, 6 Mar 2026 14:49:42 -0500 Subject: [PATCH 7/7] forgot to remove HEAD so showed as conflict? --- 02_activities/assignments/assignment.sh | 1 - 1 file changed, 1 deletion(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 5f35eec84..1171c32f4 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -53,7 +53,6 @@ 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*