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 419cbf3b7e0353abb03b41a46315c5e938219952 Mon Sep 17 00:00:00 2001 From: lightningminted Date: Tue, 5 May 2026 12:08:39 -0400 Subject: [PATCH 3/4] Updated assignment.sh --- 02_activities/assignments/assignment.sh | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 4b48cec8b..a72badbb8 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -1,3 +1,4 @@ + #!/bin/bash set -x @@ -28,22 +29,32 @@ 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 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_* 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 # 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* # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed - +touch data/inventory.txt +ls data/processed/* > data/inventory.txt ########################################### From 62dcb3d5f4f9135b5e9cbf2a4239550a19c74f52 Mon Sep 17 00:00:00 2001 From: lightningminted Date: Tue, 5 May 2026 14:01:37 -0400 Subject: [PATCH 4/4] small update to assignment.sh --- 02_activities/assignments/assignment.sh | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index a72badbb8..d2f7e03a8 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -43,14 +43,14 @@ 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_* 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/raw/*ipaddr* +rm data/raw/*ipaddr* data/processed/user_logs/*ipaddr* # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed touch data/inventory.txt