https://github.com/marianamartiyns/inep-educationperfomance

Data collection, processing, exploratory analysis, and predictive modeling of school performance rates using datasets from INEP.
https://github.com/marianamartiyns/inep-educationperfomance

data-analysis data-cleaning data-science inep predictive-modeling pyhton web-scraping

Last synced: 3 months ago
JSON representation

Data collection, processing, exploratory analysis, and predictive modeling of school performance rates using datasets from INEP.

• Host: GitHub
• URL: https://github.com/marianamartiyns/inep-educationperfomance
• Owner: marianamartiyns
• License: mit
• Created: 2025-03-16T11:37:50.000Z (3 months ago)
• Default Branch: main
• Last Pushed: 2025-03-16T12:10:34.000Z (3 months ago)
• Last Synced: 2025-03-16T12:38:22.149Z (3 months ago)
• Topics: data-analysis, data-cleaning, data-science, inep, predictive-modeling, pyhton, web-scraping
• Language: Jupyter Notebook
• Homepage:
• Size: 1.29 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# 📊 INEP-EducationPerformance  

> Data collection, processing, exploratory analysis, and predictive modeling of school performance rates using datasets from INEP (Instituto Nacional de Estudos e Pesquisas Educacionais Anísio Teixeira).  

## 📋 Description  

This project focuses on analyzing and predicting **school performance rates** (approval, failure, and dropout) using publicly available data from **INEP's Open Data platform**. These rates are crucial for monitoring educational indicators at the school and municipal levels in Brazil.  

The dataset is available in `.xlsx` format and is collected, processed, and transformed into `.csv` for better analysis. The project applies **exploratory data analysis (EDA)**, **machine learning models**, and **regression techniques** to forecast failure rates for the year **2023** based on historical data (2019-2022).  

## 🧩 Data Processing & Modeling  

- [x] **Data Collection:** Extract `.xlsx` files from the government website using `requests`, `zipfile`, and `glob`.  

- [x] **Data Transformation:** Convert raw spreadsheets into `.csv` format.  

- [x] **Exploratory Data Analysis (EDA):** Compare fundamental and high school data.  

- [x] **Data Preprocessing:** Keep only high school data, apply **Label Encoding**, and select best models using **LazyRegressor** and **LazyClassifier**.  

- [x] **Predictive Modeling:** Apply **Linear Regression** (Model Evaluation (R² & MAE), Normality of Residuals, Independent Residual & Homoscedasticity) to *failure rate* data (train: 2019-2022) to forecast 2023 (test).

      

## 📊 Results & Insights  

- Identification of trends in approval, failure, and dropout rates.  

- Performance comparison between **elementary and high school**.  

- Prediction of **2023 failure rates** using historical data.  

> [!NOTE]  

> The code and documentation are in **Portuguese 🇧🇷**, with variable names in Portuguese for consistency with the original dataset.  

```py

# Author Info

# LinkedIn: https://www.linkedin.com/in/profile-mariana-martins/

# GitHub: https://github.com/marianamartiyns

# Email: [email protected]

```