HDDM(Hierachical Drift Diffusion Model) is a python toolbox for hierarchical Bayesian parameter estimation of the Drift Diffusion Model (via PyMC), which is used widely in psychology and cognitive neuroscience to simulate the decision making process.
How to install HDDM via Conda
- Create conda environment and activate it
conda create --name hdmm-0.9 python=3.9
conda activate hdmm-0.9
PS. If you want to set the environment as default, go to ~/.zshrc or ~/.bashrc and add this line: conda activate hddm-0.9.
PSS. To remove any environment, go back to base environment conda activate base, then remove what you want by conda env remove -n hdmm-0.9.
- Install package using conda(do not use pip, incompatibile issues!)
conda install cython
conda install pymc==2.3.8
conda install git pip
pip install git+https://github.com/hddm-devs/kabuki
pip install git+https://github.com/hddm-devs/hddm
# Optional
conda install torch torchvision torchaudio -->
- Test if HDDM successfully installed
Test the codes below in a python script.
import hddm
# Load data from csv file into a NumPy structured array
data = hddm.load_csv('simple_difficulty.csv')
# Create a HDDM model multi object
model = hddm.HDDM(data, depends_on={'v':'difficulty'})
# Create model and start MCMC sampling
model.sample(2000, burn=20)
# Print fitted parameters and other model statistics
model.print_stats()
# Plot posterior distributions and theoretical RT distributions
model.plot_posteriors()
model.plot_posterior_predictive()