Use of Python language in the analysis of dengue data in Recife, capital of the state of Pernambuco, Northeast of Brazil and definition of trend line using Machine Learning

Abstract

The present work consists of a case study of dengue in Recife, capital of the state of Pernambuco, Northeast Brazil, using data science tools, Python language and its libraries. Firstly, data were extracted from official sources of public entities in the city of Recife about dengue cases in the year 2020. After this extraction, Python commands were applied to understand how the dengue outbreak in Recife happened in that specific year. It was possible to conclude that dengue is not one of the reasons for death and doesn´t cause hospitalization for patients. It was also possible to draw heat maps showing the neighborhoods that had the biggest outbreaks in 2020 (highlighting the Ibura and Cohab neighborhoods). In the second stage of this work, Machine Learning (using Linear Regression) was applied to analyze the time series of dengue in Recife between the years 2013 to 2020: a history was projected over these 7 years and a decreasing trend line of outbreaks was verified. dengue fever in Recife for the next few years.