Ciência de dados aplicada ao mercado de trabalho de Pernambuco: processamento e visualização dos microdados da PNAD Contínua.

Abstract

This study describes the development of a Data Science-based solution applied to the acquisition, processing, integration, analysis, and visualization of microdata from the Continuous National Household Sample Survey (PNAD Contínua), conducted by the Brazilian Institute of Geography and Statistics (IBGE). The study focuses on exploring the characteristics and structural inequalities of the labor market in the state of Pernambuco, Brazil, from 2019 to 2025. The methodological approach involved the automated collection of microdata from the IBGE portal through a pipeline implemented in Python, as well as the local extraction and management of compressed files and the processing of fixed-width data into structured datasets using the pandas and numpy libraries. The results followed both an analytical and a technological approach. From the analytical perspective, exploratory data analysis revealed sociodemographic and income inequalities within the state. From the technological perspective, an interactive web application was developed using the Streamlit framework and the Plotly library, enabling the dynamic exploration of labor market indicators and access to socioeconomic information about the state. The study demonstrates the effectiveness of technology as an agile social diagnostic tool to support the investigation of the characteristics and inequalities present in the labor market.