preston5789 Goto Github PK

austraila_radionuclide_mapping

An investigation of whether mining and milling operations at the Ranger Mine contaminated the surrounding Alligators River Region with radionuclides and heavy metals.

clustering-electrofacies

A k-means clustering script for python using well log data to classify rock types built with Keras

cnn-thin-section-identification

A Convolution Neural Network that classifies grain structure based on thin section images

cnn-whale-tail-identification

A CNN to identify individual whales from over 25,000 images of tails.

fars_analysis

An analysis of car crashes statistics and the prevalence of drugs over the past decade

generate-core-calibrated-thin-sections-and-pc-curves

This program queries a published carbonate core analysis database having Thomeer Capillary Pressure parameters and another with links to available Thin Sections to generate a widget showing both an estimated Capillary Pressure curve and representative Thin Sections for any reasonable user defined Porosity vs. Permeability combination for this particular reservoir.

machine-learning-tutorials

machine learning and deep learning tutorials, articles and other resources

nyc_taxi_tips

Prediction on the percentage of tips for every ride that NYC Yellow Taxi Drivers would receive with the help of models created using Multiple linear regression and Random forest regression

permeability_pyro_regression

Regression model of permeability as a function of of porosity and rock classification using the Pyro probabalistic programming package

riskquant

spotfire-depth-plot-module

A module for Spotfire that creates depths plots for reservoir logging analysis. The script is written in R and uses Spotfire's TERR function to create programable depth plots within Spotfire.

sr90_transport_model

Master's thesis that models remediation attempts of radioactive waste stored in depleted oil reservoirs that has migrated to nearby aquifers

stock_lstm

An LSTM neural network built in Keras to predict stock prices

stock_regression_algorithm

A stock trading algorithm that takes past stock prices and applies linear regression and the associated error to predict trends

stockpredictionai

In this noteboook I will create a complete process for predicting stock price movements. Follow along and we will achieve some pretty good results. For that purpose we will use a Generative Adversarial Network (GAN) with LSTM, a type of Recurrent Neural Network, as generator, and a Convolutional Neural Network, CNN, as a discriminator. We use LSTM for the obvious reason that we are trying to predict time series data. Why we use GAN and specifically CNN as a discriminator? That is a good question: there are special sections on that later.

thin_sect_generation

Prediction of a Representative Thin Sections from Core Permeability and Porosity Reference Data with Corresponding Thin Section Images