Community Demand Prediction
by cassie 
Updated: Nov 1, 2021
Solution Kit
This kit assist to development a web application for the donor to make a meaningful contribution to the community. This is a solution that developed by team blindSpot for Build with AI 2021 Hackathon. High-Level Concept An integrated management platform which will benefit all the parties (AGA/NGOs, Partners, Communities and Families). Strong analytics and predictions (backed by AI) to understand the trends in demands vs supply: Identification of unwanted donations Identification of required order items not being fulfilled Past/present trends across AGA/NGOs-Partners-Community locations and over period of time Real-time predictions of demand - continuously updated by tracking donations from Partners received, and new order for items are requested Real-time inventory data Findings/trends accessible to AGA/NGOs-Partners-Community to allow actionable items Work with AGA/NGOs-Partners-Community and provide consulting and advice on actionable items to address issues Analytics and Predictions Dashboard A centralised platform where AGA/NGOs-Partners-Community can tap into their own data to understand the behaviour of the supply/distribution of donations by the partners against the needs of the communities. The application will provide a dashboard/platform to conveniently and effectively display the various analytics and predictions. The outcome will be actionable items for the AGA/NGOs-Partners-Community to address the issues.
Development Environment
jupyterby jupyter
14381 Version:CurrentJupyter metapackage for installation, docs and chat
jupyterby jupyter
Python 14381 Version:Current License: Permissive (BSD-3-Clause)
Data Transformation & Analysis
The toolkit and libraries to explore and understand the dataset and make insights through data visualization.
pandasby pandas-dev
38499 Version:v2.0.2Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more
pandasby pandas-dev
Python 38499 Version:v2.0.2 License: Permissive (BSD-3-Clause)
numpyby numpy
23587 Version:v1.24.3The fundamental package for scientific computing with Python.
numpyby numpy
Python 23587 Version:v1.24.3 License: Permissive (BSD-3-Clause)
plotly.pyby plotly
13491 Version:v5.14.1The interactive graphing library for Python :sparkles: This project now includes Plotly Express!
plotly.pyby plotly
Python 13491 Version:v5.14.1 License: Permissive (MIT)
Machine Learning
Prophet is a procedure for forecasting time series data based on an additive model where non-linear trends are fit with yearly, weekly, and daily seasonality, plus holiday effects. It works best with time series that have strong seasonal effects and several seasons of historical data. Prophet is robust to missing data and shifts in the trend, and typically handles outliers well. We use Prophet to predict the food demands / needs from the Community.
prophetby facebook
15918 Version:v1.1.3-patchedTool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.
prophetby facebook
Python 15918 Version:v1.1.3-patched License: Permissive (MIT)
Web Development
Streamlit is an open-source app framework for Machine Learning and Data Science teams. Streamlit Sharing : https://share.streamlit.io/cassieleong/build-with-hack-2021/main/main.py
streamlitby streamlit
24920 Version:1.22.0Streamlit — A faster way to build and share data apps.
streamlitby streamlit
Python 24920 Version:1.22.0 License: Permissive (Apache-2.0)
Kit Solution Source
Community-Demand-Predictionby CassieLeong
0 Version:CurrentCommunity-Demand-Predictionby CassieLeong
Python 0 Version:Current License: Permissive (Apache-2.0)
Deployment Information
The entire solution is available as a package to download and install from the source code repository. Prerequisite: Python3 Follow below instructions to download and deploy the solution. 1. Open Command Line Interface 2. Run the command 'git clone https://github.com/CassieLeong/Community-Demand-Prediction.git' to clone the repository 3. Run the command 'pip install -r requirements.txt' to install all the dependencies 5. Run the command 'streamlit run main.py' If there're any challenges while installing dependencies, run the command below to upgrade pip and try again. python -m pip install --upgrade pip