Data science and machine learning project files were created using jupyter notebooks to showcase my ability to work with jupyter notebooks, pandas, joblib, matplotlib, Kaggle, bohek, and seaborn. I am a former Biotech Scientist who is looking to transition into software engineering and be employed as a software engineer.
This repository contains two project files: iris.ipynb and soccer.ipybn.
(1.) Machine Learning: iris.ipynb In this file, an iris dataset is imported and contains the attribute data for several flowers, including the specific species, using the scikit learn library in jupyter notebook.. I worked through the steps of splitting the data into a training set and a test set, creating a model, and checking the model. The joblib library was implemented to save the model for testing. The model was able to predict the correct species using the test set with high accuracy.
(2.) Data Science: soccer.ipynb I worked with a FIFA dataset to gain player insights to determine which players are high value but low wage. This would provide scouts and recuiters the information for players to target for recuitment. I imported a data set from Kaggle, using pandas. I pulled player name, wage and value into a new dataframe and used seaborn and bokeh to graph wage and value information. The hover tool functionality in bokeh was helpful to identify soccer players with low wage but high value. This would be helpful if teams wanted to draft certain soccer players that were high performing and lower cost, even with a raise