This repository contains the code for the Analytics Dashboard for STATS 507. The goal of this project is to create an analytics dashboard application to explore collected data and create predictive analysis models to predict the Gross Domestic Product (GDP) of the United States of America. We used Pandas to analyze the datasets, Plotly to graph the data, Dash to build the application, and Google Cloud Platform (GCP) to host the application.
- Clone this repository
- Install required packages from
requirements.txtusingpip install -r requirements.txt
- Run
main.pywithpython main.py - Access the dashboard by navigating to the localhost URL provided in the terminal (usually http://127.0.0.1:8080/ )
The dashboard is divided into several sections:
- Project Goals : A brief introduction to the project and its goals.
- Data Collection : A description of the data sources used in the project.
- Data Importing : Information about the data importing process.
- Data Cleaning : A summary of the data cleaning steps performed.
- Exploratory Data Analysis (EDA) : A section discussing the EDA process and visualizations.
- Predictive Analysis : A section outlining the predictive models used and their performance on the datasets.
- Final Conclusion : A summary of the conclusions reached from EDA and prediction.
Data is collected from the following sources:
main.py: The main script for running the Dash application.data_analysis: A folder containing the data analysis scripts and modules for each team member.data: A folder containing the data files in CSV format.prediction: A folder containing the prediction scripts and modules for each team member.
- Elena Sejin Chun
- Harshang Jayantibhai Patel
- Haowei Sun
- Jingyi Yan
- Runxuan Wang
- Wei Lee
- Zixue Zeng