Nelson F.'s repositories
Classifying-Songs-Genres-From-Audio-Data
Exploring a music dataset by examining correlations between numerical variables, running a principal component analysis for dimensionality reduction and finally fitting both scikit learn Decision Tree Classification and Logistic Regression models to compare their performance.
2018-CS109A
Repository for CS109A Fall 2018
AWS_JB-NAT-FZ
Jumpbox + NAT instance + private machine in AWS
AWS_Jupyter-Installation-on-Ubuntu-Server
Set up Jupyter on Ubuntu server running on AWS EC2 instance and configure two Python3 virtual environments
databricks-spark-certification
Guide for databricks spark certification
Flask-API-deploying-a-model-into-production
This repository describes the steps taken to deploy a model trained and tested with scikit-learn python library. This model predicts if a given song is of type "Rock" or "Hip-Hop" based on certain features. Check link : https://github.com/femtonelson/Classifying-Songs-Genres-From-Audio-Data. This deployment is done with a web service development framework in Python known as Flask.
image-classification-AlexNet-vs-DenseNet-vs-ResNet-vs-From-Scratch
Compare various models, one from scratch(keras) and three pretrained : AlexNet, ResNet, DenseNet models (Pytorch) to choose the best model for classification.
Kaggle-titanic-survival-prediction
Prediction of survival using sklearn XGBoost
Time-series-power-consumption-forecasting
Using a SARIMA model to predict electrical power consumption
db-readings
Readings in Databases
DeepLearningBookCode-Volume1
Python/Jupyter notebooks for Volume 1 of "Deep Learning - From Basics to Practice" by Andrew Glassner
getting_started_with_pyspark
Materials for class Getting Started with Pyspark
Linear-Regression-in-R
Predicting a startup's profitability with a linear regression model in R
Mayo-Clinic-Primary-Biliary-Cirrhos-Survival-Analysisis
Survival analysis of primary biliary cirrhosis patients
Mimic-SQL-Server-stored-procedure
Refresh a view when there are access restrictions to stored procedures/triggers
waiting-time-in-a-clinic-FIFO-queue
This is a model of contention-based (without prior booking) patient consultation in a clinic. It allows the simulation of the waiting time of patients in a queue of type FIFO (First In First Out) using adjustable variables such as the initial patient count, the number of available waiting seats, the arrival rate of new patients and the rate at which the clinic consults patients. This could help clinics (or similar institutions) understand the impact of these variables on the waiting time of their patients (or clients).