Materials for the StanCon 2018 Intro class for both R and Python users (thanks to @amaloney). See below for how to install an environment that can run the notebooks.
- See the reading-list.html or reading-list.pdf in this repo
- Aki Vehtari's model selection tutorial from StanCon 2018: https://github.com/avehtari/modelselection_tutorial
- Bob Carpenter's slides on MCMC convergence from StanCon 2018: http://mc-stan.org/workshops/stancon2018_intro/diagnosing-convergence.pdf
Installation (macOS using
We will be using
conda to facilitate the creation of virtual environments,
and the handling of dependencies used in the introduction class. Below outlines
how to create an environment that will run notebooks for Jupyter or RStudio on
Install brew if you have not already done so. We will be using it as our package manager for installing
miniconda. If you do not want to install
brewon your system, then follow the instructions on Anaconda for how to install
minicondaon your system.
minicondaand update your
PATHenvironment variable so that you have access to the newly installed
condais different than
condacan create virtual environments that are segregated from your system environment.
brew install miniconda
- Update your path by adding
export PATH=/usr/local/miniconda3/bin:$PATHto the end of your
~/.bash_profilefile, and then sourcing it.
Clone the StanCon2018 Intro repository someplace on your machine and change directories into it.
git clone https://github.com/jgabry/stancon2018_intro
Next we will install the conda virtual environment, which includes several packages: RStudio, Jupyter, a Python3 kernel for Jupyter, and an R kernel for Jupyter. Once the dependencies have been installed, we will need to activate the new virtual environment, so that we can access the newly installed packages.
conda env create --file environment.yml
- Activate the new environment with
source activate StanCon2018_Intro.
Start the notebook environment you are familiar with.
- Your default browser should navigate you to a page with the folder
structure of this repository. Select the
jupyter_notebooksfolder and open either the
StanCon2018 Intro-Python3.ipynbor the
StanCon2018 Intro-R.ipynbnotebook. The Python3 notebook should start with the Python3 kernel, while the R notebook should start with the R kernel.
- This will open the familiar RStudio platform.