ashkanfa Goto Github PK

ade4

Analysis of Ecological Data : Exploratory and Euclidean Methods in Environmental Sciences

amazon-sagemaker-examples

Example 📓 Jupyter notebooks that demonstrate how to build, train, and deploy machine learning models using 🧠 Amazon SageMaker.

artispotify

A platform for musicians in Spotify.

avant-garde-showtime

bindata

:exclamation: This is a read-only mirror of the CRAN R package repository. bindata — Generation of Artificial Binary Data

blog

Data, code, and scripts for the analysis in the Mode blog.

bnt

Bayes Net Toolbox for Matlab

causalinference

Causal Inference in Python

causallib

A Python package for modular causal inference analysis and model evaluations

clustmixtype

:exclamation: This is a read-only mirror of the CRAN R package repository. clustMixType — k-Prototypes Clustering for Mixed Variable-Type Data

code_snippets

courseramachinelearning

Coursera Machine Learning By Prof. Andrew Ng

covid-19

Novel Coronavirus (COVID-19) Cases, provided by JHU CSSE

covid1

Plot of COVID Spread in time for low to high vulnerable community based on CCVI index

covid19-forecast-hub

Projections of COVID-19, in standardized format

coviv19-cdcbrfss-chronic-condition-by-fips

CDC-BRFSS-CHRONIC-CONDITION-BY-FIPS

datasharing

The Leek group guide to data sharing

factoextra

Extract and Visualize the Results of Multivariate Data Analyses

flask-framework

Basic template for using Flask on Heroku

flusight

Influenza forecasts visualizer

generate.adaptive.treatment.regime.artificial.data

Inspired by dynamic treatment regime (DTR) or adaptive treatment strategy, we create artificial data that mimics the adaptive setting at each time slot. We can use the code to generate as many time slot as needed.

generate.artificial.data

We generate artificial data by assuming the true response follows an additive linear relationship with true predictors. 𝑦𝑖=Σ𝛽𝑗𝑥𝑖𝑗+ 𝜀𝑖` where 𝜀𝑖 ~ 𝑁(0,1). The simulation design can be customized considering five factors: (1) total number of variables p (2) number of observations n (3) proportion of true predictors among all variables. true.prop (4) correlation structure which controls not only the magnitude of the correlation within true predictors but also controls the intensity of the correlation between true predictors and spurious variables. This allows us to monitor the ability of different methodology in differentiating causation from correlation. (5) magnitude of the effects (coefficients).

gglasso

Automatically exported from code.google.com/p/gglasso

glmnet

:exclamation: This is a read-only mirror of the CRAN R package repository. glmnet — Lasso and Elastic-Net Regularized Generalized Linear Models. Homepage: http://www.jstatsoft.org/v33/i01/.

iterative.elastic.net

A feature selection technique which targets "True Underlying Features" rather than features for "pure predictive" purpose

kickscrape

Scrapes Kickstarter for detailed project metrics

markdown-here

Google Chrome, Firefox, and Thunderbird extension that lets you write email in Markdown and render it before sending.

ml_python_2019

numpy

Jupyter Notebook & Data Associated with my Tutorial video on the Python NumPy Library

object-detection-metrics

Most popular metrics used to evaluate object detection algorithms.