From e976b55a5c2a83f4f2ab1221ea228c9b8737db4f Mon Sep 17 00:00:00 2001 From: Simeon Wong Date: Thu, 14 Nov 2024 20:32:09 -0500 Subject: [PATCH 1/3] 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 2/3] 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 e5b0f64e5c51f35700d1cd8257ea93d8931819b0 Mon Sep 17 00:00:00 2001 From: Obed Mortey Date: Thu, 5 Mar 2026 00:53:17 -0330 Subject: [PATCH 3/3] Data Ingest Script Updated for Part 1 of assignment --- 02_activities/assignments/assignment.sh | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 70b798dfb..5fcceb5ec 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -1,4 +1,3 @@ -# I attempted to make a change. #!/bin/bash set -x @@ -10,6 +9,11 @@ set -x # project name and a brief description of the project. # Then it unzips the raw data provided by the client. +# Determine the directory where this script is located +SCRIPT_DIR="$(cd "$(dirname "$(readlink -f "$0")")" && pwd)" +cd "$SCRIPT_DIR" + + if [ -d newproject ]; then echo "Recreating the newproject directory" rm -rf newproject @@ -29,23 +33,34 @@ 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, +# 4. Create the directory ./data/processed, # then create the following sub-directories within it: server_logs, user_logs, and event_logs +mkdir data/processed 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_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 -f data/raw/*ipaddr* +rm -f 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 -type f > data/inventory.txt ########################################### echo "Project setup is complete!" +