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 bad66d98aad88b32038dfa3f7fa77c370eabbd4d Mon Sep 17 00:00:00 2001 From: Rachel Date: Tue, 7 Oct 2025 11:12:07 -0400 Subject: [PATCH 3/6] added test comment to assignment.md file --- 02_activities/assignments/assignment_instructions.md | 5 ++++- README.md => READ_ME.md | 0 2 files changed, 4 insertions(+), 1 deletion(-) rename README.md => READ_ME.md (100%) diff --git a/02_activities/assignments/assignment_instructions.md b/02_activities/assignments/assignment_instructions.md index 1d6f1055a..18136fb31 100644 --- a/02_activities/assignments/assignment_instructions.md +++ b/02_activities/assignments/assignment_instructions.md @@ -1,4 +1,4 @@ -# Shell / Git Assignment +dd# Shell / Git Assignment You work in the data team at a consulting firm, and one of your team's products is helping companies optimize and manage their cloud hosting expenditures. Your team has an existing bash script that initializes an analysis directory for each new client. This script is shared amongst members of the team. @@ -102,3 +102,6 @@ Checklist: - [ ] Review [the PR description guidelines](https://github.com/UofT-DSI/onboarding/blob/main/onboarding_documents/submissions.md#guidelines-for-pull-request-descriptions) and adhere to them. - [ ] Verify that your link is accessible in a private browser window. - [ ] Verify the autograder has run and approved your pull request + + +## Hello \ No newline at end of file diff --git a/README.md b/READ_ME.md similarity index 100% rename from README.md rename to READ_ME.md From 13603b82efff253f7978757d0354a1b73bf773f4 Mon Sep 17 00:00:00 2001 From: Rachel Date: Tue, 7 Oct 2025 11:13:10 -0400 Subject: [PATCH 4/6] new hello comment --- 02_activities/assignments/assignment_instructions.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/02_activities/assignments/assignment_instructions.md b/02_activities/assignments/assignment_instructions.md index 18136fb31..af1b2624a 100644 --- a/02_activities/assignments/assignment_instructions.md +++ b/02_activities/assignments/assignment_instructions.md @@ -104,4 +104,5 @@ Checklist: - [ ] Verify the autograder has run and approved your pull request -## Hello \ No newline at end of file +## Hello +# helo \ No newline at end of file From 728eedc4a871c42825f28b75c026a1adb8b9820e Mon Sep 17 00:00:00 2001 From: Rachel Date: Tue, 7 Oct 2025 11:24:30 -0400 Subject: [PATCH 5/6] Finished assignment 1, part 1 --- 02_activities/assignments/assignment.sh | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index 8af8dc092..612204eae 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -1,4 +1,6 @@ #!/bin/bash + +## Student: Rachel Liu set -x ############################################ @@ -28,21 +30,32 @@ 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 data/raw # 3. List the contents of the ./data/raw directory +ls data/raw # 4. In ./data/processed, create the following directories: 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 +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/processed/user_logs/*ipaddr* +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 f951d81aad4b7ae54fe80d2ec11fa0a4c5cc0931 Mon Sep 17 00:00:00 2001 From: Rachel Date: Tue, 7 Oct 2025 11:53:36 -0400 Subject: [PATCH 6/6] Changes to question 8 to list all files under the subfolder --- 02_activities/assignments/assignment.sh | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/02_activities/assignments/assignment.sh b/02_activities/assignments/assignment.sh index eb64911ed..2dda1d461 100644 --- a/02_activities/assignments/assignment.sh +++ b/02_activities/assignments/assignment.sh @@ -51,13 +51,12 @@ 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/processed/user_logs/*ipaddr* -rm data/raw/*ipaddr* +rm -rf data/processed/user_logs/*ipaddr* +rm -rf 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 +find data/processed -type f > data/inventory.txt ###########################################