From e976b55a5c2a83f4f2ab1221ea228c9b8737db4f Mon Sep 17 00:00:00 2001 From: Simeon Wong Date: Thu, 14 Nov 2024 20:32:09 -0500 Subject: [PATCH 1/8] 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 2/8] 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 b2b5a7b4fad417d7a27eda73de39074761f4b585 Mon Sep 17 00:00:00 2001 From: Afroz Popatiya Date: Mon, 10 Nov 2025 12:11:17 -0500 Subject: [PATCH 3/8] Answer question number 1 --- 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 44bf9cc48..d93e23c91 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -26,9 +26,9 @@ unzip -q rawdata.zip ########################################### # Complete assignment here -mkdir data -# 1. Create a directory named data +# 1. Create a directory named data +mkdir data # 2. Move the ./rawdata directory to ./data/raw # 3. List the contents of the ./data/raw directory From 3c05f3e960e3b50bce3edbcba657627da837e720 Mon Sep 17 00:00:00 2001 From: Afroz Popatiya Date: Mon, 10 Nov 2025 12:24:06 -0500 Subject: [PATCH 4/8] Answer question 2 --- 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 d93e23c91..b29a04ab1 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 - +mv rawdata data/raw # 3. List the contents of the ./data/raw directory # 4. In ./data/processed, create the following directories: server_logs, user_logs, and event_logs From d717963c6603ef17c209c93157b5bfb505e64f95 Mon Sep 17 00:00:00 2001 From: Afroz Popatiya Date: Mon, 10 Nov 2025 16:28:19 -0500 Subject: [PATCH 5/8] Finishing the assignment --- 02_activities/assignments/assignment.sh | 17 ++++++++++------- New Text Document.txt | 15 +++++++++++++++ 2 files changed, 25 insertions(+), 7 deletions(-) create mode 100644 New Text Document.txt diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index b29a04ab1..2a639390e 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -30,19 +30,22 @@ unzip -q rawdata.zip # 1. Create a directory named data mkdir data # 2. Move the ./rawdata directory to ./data/raw -mv rawdata data/raw +mv ./rawdata ./data/raw # 3. List the contents of the ./data/raw directory - +ls -ltr data/raw # 4. In ./data/processed, create the following directories: 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 ./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 - +touch ./data/inventory.txt +ls -R ./data/processed > ./data/inventory.txt ########################################### diff --git a/New Text Document.txt b/New Text Document.txt new file mode 100644 index 000000000..50d8a6224 --- /dev/null +++ b/New Text Document.txt @@ -0,0 +1,15 @@ +# 3. List the contents of the ./data/raw directory +ls -ltr data/raw +# 4. In ./data/processed, create the following directories: 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 ./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 +touch ./data/inventory.txt +ls -R ./data/processed > ./data/inventory.txt \ No newline at end of file From d516cf10bcc89353d6821b1238d74c9bce468de2 Mon Sep 17 00:00:00 2001 From: Afroz Popatiya Date: Mon, 10 Nov 2025 17:59:22 -0500 Subject: [PATCH 6/8] Completed Assignment with all the questions --- 02_activities/assignments/assignment.sh | 5 ----- 1 file changed, 5 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index b9bcd3d2c..efc3b7cf3 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -42,13 +42,8 @@ cp ./data/raw/server*.log ./data/processed/server_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 -<<<<<<< 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 touch ./data/inventory.txt ls -R ./data/processed > ./data/inventory.txt From f1cbc85f1f8007c7f99125b843e96ac5f4ce0301 Mon Sep 17 00:00:00 2001 From: Afroz Popatiya Date: Mon, 10 Nov 2025 18:21:38 -0500 Subject: [PATCH 7/8] Completion assignment --- 02_activities/assignments/assignment.sh | 1 - 1 file changed, 1 deletion(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index efc3b7cf3..c1c624877 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -43,7 +43,6 @@ 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 rf -rf ./data - # 8. Create a file named ./data/inventory.txt that lists all the files in the subfolders of ./data/processed touch ./data/inventory.txt ls -R ./data/processed > ./data/inventory.txt From d0cc8fce8b6420b25119e3e66845f86c69fbfe86 Mon Sep 17 00:00:00 2001 From: Afroz Popatiya Date: Mon, 10 Nov 2025 19:04:12 -0500 Subject: [PATCH 8/8] Assignment Completion --- 02_activities/assignments/assignment.sh | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index c1c624877..78e8cbb05 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -42,7 +42,8 @@ cp ./data/raw/server*.log ./data/processed/server_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 -rf -rf ./data +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 touch ./data/inventory.txt ls -R ./data/processed > ./data/inventory.txt