ㅤ
Python Handbook - A compilation of concise Python code snippets. It serves as a quick-reference guide, streamlining tasks like Exploratory Data Analysis (EDA), data manipulation and modeling. These compact codes enhance productivity by providing instant solutions for various activities in Python programming.
IBM HR analysis - Analysis and modeling of a fictitious dataset created by IBM data scientists with diverse data from almost 1500 employees. As a company's general objective should be to maintain its talents and strengthen its intellectual capital, this analysis seeks to understand which factors lead to greater dissatisfaction on the part of employees, allowing the company to intervene in certain aspects. KNN (87.7%)
Abalone age prediction - Predictive modeling to determine the age of abalones. Accurate age prediction is essential for sustainable harvesting and conservation efforts, ensuring the preservation of these marine species. It also saves a lot of time, because the most used method is to cut the abalone open and count its rings under a microscope.
Diabetes prediction - The main aim is to accurately forecast a patient's likelihood of having diabetes using specific diagnostic measurements, allowing for early intervention, potentially preventing complications and enabling proactive management. Random Forest (79.2%)
Titanic survivors - Inspired in the Kaggle competition Titanic: Machine Learning from Disaster, the goal is to predict whether a passenger survived the Titanic disaster based on passenger data like Sex, Age and Class. xGBoost (77.2%)
Keras + MNIST - Creation, training, and application of models for image classification on the famous MNIST dataset. The MNIST dataset is a large collection of handwritten digits, often used to train image processing systems and widely employed by individuals in the process of advancing their knowledge in the field of Machine Learning and image processing.
E-commerce da Olist - Data analysis and modeling using Olist's e-commerce dataset, available on Kaggle. The ultimate goal is to create a model capable of predicting the likelihood of a customer being satisfied when purchasing a product.
Football projects - Special folder for storing football-related projects, designed as an informal way to mix a hobby with learning, making the process lighter and more enjoyable. This folder currently has 2 projects, but this number will always be subject to expansion. This folder serves as a measure of personal evolution in the knowledge necessary for a data analyst.