From e976b55a5c2a83f4f2ab1221ea228c9b8737db4f Mon Sep 17 00:00:00 2001 From: Simeon Wong Date: Thu, 14 Nov 2024 20:32:09 -0500 Subject: [PATCH 1/6] 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 2/6] 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 6382d2275a88c68c24b127c3e23e06f90f763a52 Mon Sep 17 00:00:00 2001 From: Nader Mostaghimi Date: Mon, 10 Nov 2025 17:07:04 -0800 Subject: [PATCH 3/6] Answers added to file --- 02_activities/assignments/assignment.sh | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 4b2baa7ae..231b29844 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -28,20 +28,29 @@ unzip -q rawdata.zip # Complete assignment here # 1. Create a directory named data - +mkdir data # 2. Move the ./rawdata directory to ./data/raw - +mv rawdata.zip raw.zip +mv raw.zip data/ # 3. List the contents of the ./data/raw directory - +cd raw +ls # 4. In ./data/processed, create the following directories: server_logs, user_logs, and event_logs +mkdir 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 +cp *server*.log ../processed/server_logs/ # 6. Repeat the above step for user logs and event logs - +cp *user*.log ../processed/user_logs/ +cp *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 +find . -type f -name "*ipaddr*" -delete # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed +find processed -type f | sort > inventory.txt +cat inventory.txt ########################################### From 0e7bfa994527591b9f75ced51a639fa11ae95c09 Mon Sep 17 00:00:00 2001 From: Nader Mostaghimi Date: Mon, 10 Nov 2025 17:14:14 -0800 Subject: [PATCH 4/6] Updated answers to file --- 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 231b29844..4e7467ba1 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -30,8 +30,7 @@ unzip -q rawdata.zip # 1. Create a directory named data mkdir data # 2. Move the ./rawdata directory to ./data/raw -mv rawdata.zip raw.zip -mv raw.zip data/ +mv rawdata data/raw # 3. List the contents of the ./data/raw directory cd raw ls @@ -53,6 +52,7 @@ find processed -type f | sort > inventory.txt cat inventory.txt + ########################################### echo "Project setup is complete!" From 46b8d5aa2c9482c3f39d475b8985988643ac86b5 Mon Sep 17 00:00:00 2001 From: Nader Mostaghimi Date: Mon, 10 Nov 2025 17:26:56 -0800 Subject: [PATCH 5/6] Updated answers in file --- 02_activities/assignments/assignment.sh | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 4e7467ba1..3dc75ff2c 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -32,18 +32,18 @@ mkdir data # 2. Move the ./rawdata directory to ./data/raw mv rawdata data/raw # 3. List the contents of the ./data/raw directory -cd raw -ls +ls data/raw # 4. In ./data/processed, create the following directories: server_logs, user_logs, and event_logs -mkdir processed -mkdir server_logs user_logs 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 -cp *server*.log ../processed/server_logs/ +cp data/raw/*server*.log data/processed/server_logs/ # 6. Repeat the above step for user logs and event logs -cp *user*.log ../processed/user_logs/ -cp *event*.log ../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 find . -type f -name "*ipaddr*" -delete From 180973a6a47d70add36c87cda0e96ca9cea682b0 Mon Sep 17 00:00:00 2001 From: Nader Mostaghimi Date: Mon, 10 Nov 2025 17:50:16 -0800 Subject: [PATCH 6/6] New update to answers --- 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 3dc75ff2c..b38b415b9 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -48,8 +48,9 @@ cp data/raw/*event*.log data/processed/event_logs/ find . -type f -name "*ipaddr*" -delete # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed -find processed -type f | sort > inventory.txt -cat inventory.txt +touch data/inventory.txt +find data/processed -type f | sort > data/inventory.txt +cat data/inventory.txt