Project 17 - Urban_Logistic_Demand_Forecasting#1729
Conversation
manya0033
left a comment
There was a problem hiding this comment.
Hi @YuvaraniD , great work on this use case! The structure is clear, visualisations are well-labelled with insightful interpretations, and the code is readable. A few things to address before approval:
- The data is being downloaded via direct ZIP URLs rather than API v2.1. Could you either confirm with leadership that this is acceptable given the API limitation, or upload CSV versions of the data to the repo as per the checklist requirement for external datasets?
- Please resolve the merge conflict in .gitignore so the branch can be merged.
Otherwise, the analysis is well-presented and the insights are clear. Happy to re-review once these are addressed!
|
Thanks for uploading the datasets @YuvaraniD ! Just one more thing - I noticed the entire .gitignore file has been deleted in this PR. I think this happened because the old .gitignore had *.zip in it which would have blocked your dataset uploads. Could you restore the .gitignore and instead add a specific exception for the DEPENDENCIES folder. |
|
Hi @manya0033 , I’ve updated the .gitignore file and restored it. Please let me know if anything else needs to be adjusted. |
|
Hey @YuvaraniD , thanks for updating this! A few small things before I can approve: There's a small typo on line 8 of the .gitignore - it should just be !datascience/usecases/DEPENDENCIES/**/*.zip (the .DS_Store at the end shouldn't be there). As it is now, it won't actually let your ZIP files through. |
|
I’ve made the requested changes: Please let me know if anything else is needed @manya0033 |
|
@YuvaraniD Changes addressed, well done. Happy to approve! |
manya0033
left a comment
There was a problem hiding this comment.
Changes addressed properly, well done!
This project focuses on Urban Logistics Demand Forecasting (Project 17). The work completed so far includes:
Performed Exploratory Data Analysis (EDA) to understand data distribution and patterns
Conducted data cleaning and preprocessing, including handling missing values and formatting time-based features
Performed temporal analysis to study demand trends over time (hourly/daily patterns)
Conducted spatial analysis to understand geographic distribution of demand
Derived key insights from the dataset to support demand forecasting and decision-making