From e976b55a5c2a83f4f2ab1221ea228c9b8737db4f Mon Sep 17 00:00:00 2001 From: Simeon Wong Date: Thu, 14 Nov 2024 20:32:09 -0500 Subject: [PATCH 01/15] 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 02/15] 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 c6682c2dc42b376ab63dfc4186c4a54399f306b2 Mon Sep 17 00:00:00 2001 From: Jacqueline Brillantes Date: Mon, 2 Mar 2026 21:04:21 -0500 Subject: [PATCH 03/15] first question done --- 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 4b48cec8b..de5e5873b 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 (eg. move it into ./data and rename it to raw) # 3. List the contents of the ./data/raw directory From 804363764eaeaa7864c7c73f1fecd9dc34468a1c Mon Sep 17 00:00:00 2001 From: Jackie Brillantes Date: Mon, 2 Mar 2026 21:20:44 -0500 Subject: [PATCH 04/15] Second question is done --- 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 de5e5873b..5c7eda723 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -30,7 +30,7 @@ unzip -q rawdata.zip # 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) - +jackie # 3. List the contents of the ./data/raw directory # 4. Create the directory ./data/processed, From 00c32141ebd2e6e1e9036fe1d2267fc39d1d8521 Mon Sep 17 00:00:00 2001 From: Jackie Brillantes Date: Mon, 2 Mar 2026 22:17:04 -0500 Subject: [PATCH 05/15] questions 1 - 4 completed --- 02_activities/assignments/assignment.sh | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 5c7eda723..f5d067942 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -29,12 +29,26 @@ unzip -q rawdata.zip # 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) -jackie +mkdir rawdata +mv rawdata data +mv data raw +## double check to avoid accidental overwriting +mv -i data raw + # 3. List the contents of the ./data/raw directory +ls raw +## more detailed look of the contents of the directory +ls -l raw # 4. Create the directory ./data/processed, +## create parent directory +mkdir -p data/processed # then create the following sub-directories within it: server_logs, user_logs, and 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 From 27b7ac27087c64ce3362a71e27e8170182ad3aef Mon Sep 17 00:00:00 2001 From: Jackie Brillantes Date: Mon, 2 Mar 2026 22:39:15 -0500 Subject: [PATCH 06/15] changed some answers --- 02_activities/assignments/assignment.sh | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index f5d067942..f61c4d2db 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -32,10 +32,8 @@ mkdir data # 2. Move the ./rawdata directory to ./data/raw (eg. move it into ./data and rename it to raw) mkdir rawdata -mv rawdata data -mv data raw -## double check to avoid accidental overwriting -mv -i data raw +mkdir -p data +mv rawdata data/raw # 3. List the contents of the ./data/raw directory ls raw From 491c24be97882be7fcf10cd9d975b110f67b0a3f Mon Sep 17 00:00:00 2001 From: Jackie Brillantes Date: Tue, 3 Mar 2026 10:43:53 -0500 Subject: [PATCH 07/15] changed #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 f61c4d2db..80adb50b7 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -36,9 +36,9 @@ mkdir -p data mv rawdata data/raw # 3. List the contents of the ./data/raw directory -ls raw +ls ./data/raw ## more detailed look of the contents of the directory -ls -l raw +ls -l ./data/raw # 4. Create the directory ./data/processed, ## create parent directory From b8930de26a4d01408bb5d95f50ef8ee80cf3dbe3 Mon Sep 17 00:00:00 2001 From: Jackie Brillantes Date: Tue, 3 Mar 2026 11:23:00 -0500 Subject: [PATCH 08/15] #5 --- 02_activities/assignments/assignment.sh | 2 -- 1 file changed, 2 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 80adb50b7..a0c05e4a4 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -37,8 +37,6 @@ mv rawdata data/raw # 3. List the contents of the ./data/raw directory ls ./data/raw -## more detailed look of the contents of the directory -ls -l ./data/raw # 4. Create the directory ./data/processed, ## create parent directory From 89999d480e4fab1b660a586ae64a27bd9178b2fe Mon Sep 17 00:00:00 2001 From: Jackie Brillantes Date: Tue, 3 Mar 2026 15:48:44 -0500 Subject: [PATCH 09/15] completed assignment --- 02_activities/assignments/assignment.sh | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index a0c05e4a4..4d0ab71de 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -47,14 +47,21 @@ 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* ./data/processed/server_logs +cp ./data/raw/*.log ./data/processed/server_logs # 6. Repeat the above step for user logs and event logs +cp ./data/raw/*user* ./data/processed/user_logs +cp ./data/raw/*event* ./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/*ipaddr* # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed + ########################################### echo "Project setup is complete!" From 6dd0c75093c35f4361242fd9d2d18c75691d3a4b Mon Sep 17 00:00:00 2001 From: Jackie Brillantes Date: Tue, 3 Mar 2026 16:22:16 -0500 Subject: [PATCH 10/15] added question 8 --- 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 4d0ab71de..6028bf0a2 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -59,8 +59,7 @@ 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 - - +find ./data/processed -mindepth 2 -type f > ./data/inventory.txt ########################################### From 91a1b553c8244951ae2086fde7c25199843f7820 Mon Sep 17 00:00:00 2001 From: jbrillantes Date: Tue, 3 Mar 2026 19:41:46 -0500 Subject: [PATCH 11/15] Generate inventory.txt from processed data files Create inventory.txt file listing all files in processed subfolders --- 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 c7271f36d..bf93a749d 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -64,6 +64,7 @@ rf -rf ./data >>>>>>> ea20676d33161a6f4d0fcd3c4f7aa5360f0f4309 # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed +mkdir -p data/inventory.txt find ./data/processed -mindepth 2 -type f > ./data/inventory.txt ########################################### From 7e1391fd1022bb793d5e7fdd3877251da7b61321 Mon Sep 17 00:00:00 2001 From: jbrillantes Date: Fri, 6 Mar 2026 10:20:27 -0500 Subject: [PATCH 12/15] Fix file removal commands and inventory file creation Removed commands to delete files with 'ipaddr' in the filename and fixed the creation of inventory.txt. --- 02_activities/assignments/assignment.sh | 4 ---- 1 file changed, 4 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index bf93a749d..914e3f111 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -56,12 +56,8 @@ cp ./data/raw/*user* ./data/processed/user_logs cp ./data/raw/*event* ./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 mkdir -p data/inventory.txt From 1409f5c77c4a576083e85910a95b94a2f890bf74 Mon Sep 17 00:00:00 2001 From: jbrillantes Date: Fri, 6 Mar 2026 10:23:42 -0500 Subject: [PATCH 13/15] Update assignment.sh From 50f9674e7d696b24b43284d4ab98bb08b1cc02e4 Mon Sep 17 00:00:00 2001 From: jbrillantes Date: Fri, 6 Mar 2026 13:19:16 -0500 Subject: [PATCH 14/15] Fix path in inventory file creation command fixed question #8 --- 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 914e3f111..e7d2c65ba 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -61,7 +61,7 @@ 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 mkdir -p data/inventory.txt -find ./data/processed -mindepth 2 -type f > ./data/inventory.txt +find data/processed -mindepth 2 -type f > ./data/inventory.txt ########################################### From 6a170b10832e685020b9b7bb71327b755559ac9d Mon Sep 17 00:00:00 2001 From: jbrillantes Date: Fri, 6 Mar 2026 13:21:58 -0500 Subject: [PATCH 15/15] Fix inventory.txt file creation command fixed #8 --- 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 e7d2c65ba..4f7a20170 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -60,8 +60,7 @@ 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 -mkdir -p data/inventory.txt -find data/processed -mindepth 2 -type f > ./data/inventory.txt +find data/processed -type f > data/inventory.txt ###########################################