From e976b55a5c2a83f4f2ab1221ea228c9b8737db4f Mon Sep 17 00:00:00 2001 From: Simeon Wong Date: Thu, 14 Nov 2024 20:32:09 -0500 Subject: [PATCH 1/4] 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 2/4] 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 f8f76db63b8d983f3e2d1e49bf4c7d78e71c067b Mon Sep 17 00:00:00 2001 From: Minal C Date: Wed, 4 Mar 2026 07:53:53 -0400 Subject: [PATCH 3/4] Complete Part 1: automated data ingest script --- 02_activities/assignments/assignment.sh | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 4b48cec8b..d15464393 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -28,22 +28,26 @@ 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 +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 -p 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 - +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/user_logs +cp data/raw/*event*.log data/processed/event_log # 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 - +ls -R data/processed > data/inventory.txt ########################################### From 37713a21d5260753e08723f47e80215f97b4db7b Mon Sep 17 00:00:00 2001 From: Minal C Date: Wed, 4 Mar 2026 15:42:53 -0400 Subject: [PATCH 4/4] fixed event_logs copy command --- 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 ad3c24292..0bfa0fd2d 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -43,7 +43,7 @@ mkdir -p data/processed/server_logs data/processed/user_logs data/processed/even 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/user_logs -cp data/raw/*event*.log data/processed/event_log +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*