George Pinto's repositories
Deterministic-and-Probabilistic-Regression
Study involving a challenging multivariate regression problem that explores deterministic regression first and then explores the use of probabilistic regression to get a better feel of the uncertainty in the predictions
Attention-for-Mental-Health
The intent here is to build a question and answer transformer model to answer people's questions in regards to mental health.
Relax-Inc-Take-Home-Challenge
Take Home Challenge: Defining an "adopted user" as a user who has logged into the product on three separate days in at least one seven day period , identify which factors predict future user adoption
Ultimate-Technologies
Ultimate Technologies Inc. is a transportation network company that has disrupted the taxi and logistics industry and is considered a prestigious company to work for. Ultimate Technologies is interested in predicting rider retention
cloudrepo
cloud computing exploration repo
Predicting-Covid-19-Positive-Cases-From-Lung-X-Ray-Images
Convolutional Neural Network Multiclass Classification Project involving X rays of normal lungs, lungs with Pneumonia and lungs with Covid-19 Feel free to scroll to through the Covid positive images on my first notebook to take a look or skip to the bottom for my notes!
Cowboy-Cigarretes-A-Time-Series-Investigation
Time series arima model study using pandas, numpy and statsmodels
Identifying-Appliances-From-Energy-Use-Spectrograms-TensorFlow-2
A dual input Convolutional Neural Network created using TensorFlow 2 and generators for scalability. Please view the notebook pdf if you cannot open the notebook, it's a large file! This data originally from Driven Data was part of my Microsoft Professional Program for Artificial Intelligence, but the program was discontinued before I could analyze the data. Luckily for the IBM Advanced Data Science Capstone we were allowed to pick our own data set and I was able to use TensorFlow 2!
Forecasting-CO2-Using-Mauna-Loa-Data
Forecasting Study using pandas, statsmodels Sarimax and pmdarima Auto Arima
Bayesian-Optimization-Case-Study
Bayesian parameter optimization in Python for a Light GBM model.
Grid-Search-KNN-Case-Study
Case study in hyperparameter optimization using numpy, pandas, scikit learn and matplotlib
Case-Study-Customer-Segmentation-using-Clustering
Customer Segmentation study using Sci-kit learn, Pandas and Seaborn
Cosine-Similarity-Case-Study
Cosine Similarity Case Study using Sci-kit Learn, Scipy and Matplotlib
Euclidean-and-Manhattan-Distances-Case-Study
Study on Euclidean and Manhattan Distances using python and matplotlib
Case-Study-Gradient-Boosting
Intuition and application of Gradient Boosting on Regression and Classification
Random-Forest-Case-Study-Covid-19
Study applying Random Forest Classification to understand the scope of the Coronavirus using data from December and January of 2020
Case-Study-RR-Diner-Coffee
Case study assisting purchasing decisions using decision trees and random forest estimators
Logistic-Regression-Advanced-Case-Study
Study on logistic regression, probability and hyperparameters
Case-Study-Linear-Regression
A Linear Regression Study on the Red Wine Dataset
Case-Study-Integrating-Apps
Statistical Significance Case Study
Frequentist-Statistics
Case Study on Frequentist Inference
SQL-Case-Study-Country-Club
Project involving MySQL and PHPMyAdmin using a country club database and performing SQL queries to gain insights from the data
API-Mini-Project-
Project using Jupyter notebook to connect to the Quandl API and using python data structures to extract financial information
DataScienceGuidedCapstone
Guided capstone based on a hypothetical request from a ski resort showing the correct sequence of data science steps in detail along with final the presentation
Predicting-County-Level-Rents
Project involving L1, L2 Regression and Support Vector Machine Regression. Please see report for details and view the notebook pdf if you are unable to view the notebook (close to size limits!)
Enhancing-The-Home-Buying-Experience
Project involving web scraping, geospatial data, APIs and K-Means clustering
Springboard
Project using Python, Pandas, Numpy and Matplotlib to explore which boroughs of London have seen the greatest increase in housing prices, on average, over the last two decades