Data Analysis for Network Optimization
Explore the docs »
View Deploy
·
Report Bug
·
Request Feature
Table of Contents
ENACOM, a leading telecommunications company, seeks to improve its network optimization. This project aims to enhance the network performance by developing an effective data analysis and machine learning solution. The goal is to provide more efficient network routing, improve network performance, and ultimately increase the company's revenue.
This is an example of how you may give instructions on setting up your project locally. To get a local copy up and running follow these simple example steps.
This is an example of how to list things you need to use the software and how to install them.
- pip install requirements.txt
This is an example of how to list things you need to use the software and how to install them.
- pip
pip install requirements.txt
- Clone the repo
git clone https://github.com/Paniceres/PI_Data_Analytics.git
- Execute main.py
streamlit run 'PI_Data_Analytics/deploy/main.py'
The methodology employed in this project involved the following key steps: Data context and criterion; Extract, Transform and Load; Data Anlalysis; Deploy
Over 30 available datasets were analyzed, and a set of criteria was imposed to optimize efforts. The selected 12 datasets were processed through ETL processes, resulting in the creation of tables containing ratios and growth rates. Data Analysis
A comprehensive dataset, df_kpi, was generated from the processed data, serving as the basis for all visualizations and analyses. The economic landscape of modern Argentina was explored by understanding various correlations among technologies, growth rates, penetration totals (access rates, service availability), and speed (service quality). Deployment Challenges
The deployment phase presented several technical challenges, particularly during the creation of the multi-app interactive dashboard. One significant challenge involved standardizing the project's directory structure to streamline data processing. Ensuring the interactivity of the dashboard required considerable effort and attention to detail.
Efficient processing of multiple datasets was crucial.
Making the dashboard interactive and responsive to user inputs was a priority. This required implementing interactive widgets and ensuring seamless communication between different components of the dashboard.
Integrating diverse datasets and ensuring consistency across different data sources was a challenge. Data cleaning and transformation procedures were meticulously applied to harmonize the data and prevent inconsistencies.
Designing an intuitive and user-friendly interface was critical for ensuring a positive user experience. User interface elements were carefully chosen, and user feedback was incorporated to refine the design and enhance usability.
The project culminated in a multi-app interactive dashboard that enables users to explore and analyze the economic landscape of modern Argentina. The dashboard provides insights into various aspects of the country's economy, including growth rates, penetration totals, service availability, and speed. Conclusion
The methodology employed in this project effectively enabled the creation of a comprehensive and interactive dashboard that offers valuable insights into the landscape of modern Argentina. By understanding the correlations among different metrics and visualizing them on a single platform, users can make informed decisions and optimize their strategies accordingly.
Upon analyzing the net income trends in dollars, with its relative stability around $500,000 USD, we decided to interpret correlation patterns with other non-economic variables. We observed how Fiber Optics stands out as the central focus of the proposal, being the most cost-effective to install, increasing average speed, and enhancing connectivity rates for every province where it is implemented.
It is crucial to understand that Fiber Optics has an inverse correlation with ADSL, a technology that needs to be reduced. ADSL not only lacks technical features that favor accessibility or service quality but is also susceptible to theft due to its high copper content.
Wireless technology emerges as the one suggesting the highest connectivity, excelling in both rural and densely populated areas, owing to its wireless nature.
Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.
If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement". Don't forget to give the project a star! Thanks again!
- Fork the Project
- Create your Feature Branch (
git checkout -b feature/AmazingFeature) - Commit your Changes (
git commit -m 'Add some AmazingFeature') - Push to the Branch (
git push origin feature/AmazingFeature) - Open a Pull Request
Paniceres Lucio - [email protected]
Project Link: https://github.com/Paniceres/PI_Data_Analytics