PR after Rebase

Taweret/mix/trees.py

@@ -1,7 +1,7 @@
 """
 Name: trees.py
 Author: John Yannotty (yannotty.1@osu.edu)
-Desc: Defines the tree mixing class, which is an interface for MixBART 
+Desc: Defines the tree mixing class, which is an interface for BART-BMM 
 
 Start Date: 10/05/22
 Version: 1.0
@@ -15,6 +15,7 @@
 import tempfile 
 import shutil
 import os
+import typing
 
 import Taweret.core.setup
 
@@ -27,7 +28,7 @@
 
 class Trees(BaseMixer):
     # Overwrite base constructor
-    def __init__(self, model_dict, **kwargs):
+    def __init__(self, model_dict: dict, **kwargs):
         '''
         Constructor for the Trees mixing class.
 
@@ -131,7 +132,7 @@ def map(self):
         '''
         return super().map
 
-    # Done
+
     @property
     def posterior(self):
         '''
@@ -184,9 +185,9 @@ def prior(self):
 
         return hyper_params_dict
 
-    # DONE
-    def set_prior(self, ntree=1,ntreeh=1,k=2,power=2.0,base=0.95,overallsd=None, \
-                    overallnu=10,inform_prior=True,tauvec=None,betavec=None):
+
+    def set_prior(self, ntree: int = 1,ntreeh:int = 1, k: float=2,power: float=2.0,base:float=0.95,overallsd:float=None, \
+                    overallnu: int = 10,inform_prior: bool = True,tauvec: bool = None,betavec: bool = None):
         '''
         Sets the hyperparameters in the tree and terminal node priors. Also
         specfies if an informative or non-informative prior will be used.
@@ -266,15 +267,15 @@ def prior_predict(self):
         raise Exception("Not applicable for trees.")
 
 
-    def train(self,X, y, **kwargs):
+    def train(self,X: np.ndarray, y: np.ndarray, **kwargs):
         '''
         Train the mixed-model using a set of observations y at inputs x.
 
         Parameters:
         ----------
-        X : np.ndarray
+        X : np.ndarray (n X p)
             input parameter values.
-        y : np.1darray
+        y : np.ndarray (n X 1)
             observed data at inputs X.
         kwargs : dict
             Dictionary of arguments 
@@ -377,7 +378,7 @@ def train(self,X, y, **kwargs):
         return res
 
 
-    def predict(self, X, ci = 0.95):
+    def predict(self, X: np.ndarray, ci: float = 0.95):
         '''
         Obtain posterior predictive distribution of the mixed-model at a set
         of inputs X.
@@ -474,7 +475,7 @@ def predict(self, X, ci = 0.95):
         return pred_post, pred_mean, pred_credible_interval, pred_sd
 
 
-    def predict_weights(self, X, ci = 0.95):
+    def predict_weights(self, X: np.ndarray, ci: float = 0.95):
         '''
         Obtain posterior distribution of the weight functions at a set
         of inputs X.
@@ -548,14 +549,14 @@ def predict_weights(self, X, ci = 0.95):
         posterior = self.wdraws 
         post_mean = self.wts_mean 
         post_sd = self.wts_sd
-        post_credible_interval = (self.wts_lower,self.wts_upper) 
+        post_credible_interval = [self.wts_lower,self.wts_upper] 
 
-        return posterior, post_mean, post_sd, post_credible_interval
+        return posterior, post_mean, post_credible_interval, post_sd
 
 
     # -----------------------------------------------------------
     # Plotting
-    def plot_prediction(self, xdim = 0):
+    def plot_prediction(self, xdim: int = 0):
         '''
         Plot the predictions of the mixed-model. The x-axis of this plot
         can be any column of the design matrix X, which is passed into 
@@ -592,7 +593,7 @@ def plot_prediction(self, xdim = 0):
         plt.show()
 
 
-    def plot_weights(self, xdim = 0):
+    def plot_weights(self, xdim: int = 0):
         '''
         Plot the weight functions. The x-axis of this plot
         can be any column of the design matrix X, which is passed into 

docs/source/installation.rst

@@ -30,3 +30,95 @@ The pip installation is not available yet. We are working on it.
 .. code-block:: bash
 
         pip install Taweret
+
+Installation
+============
+
+Taweret requires the following for for basic functionality.
+    - python
+    - numpy
+    - seaborn
+    - jupyter
+    - bilby
+    - ptemcee
+
+Follow these steps to install Taweret from github. 
+
+.. code-block:: bash
+
+    git clone https://github.com/danOSU/Taweret.git
+    #If you want to use SMABA toy models please clone samba repo
+    #git clone https://github.com/asemposki/SAMBA.git
+    cd Taweret
+    conda env create -f environment.yml
+    conda activate test_env
+    cd doc/source/notebooks
+    jupyter notebook --browser=safari
+
+You can look at the available notebooks in the directory and modify it for your own use case. If \
+you need to add a new mixing method please refer to the **For Deveopers** section. 
+
+The pip instalation is not available yet. We are working on it. 
+
+.. code-block:: bash
+    pip install Taweret
+
+
+
+Additional Requirements
+-----------------------
+
+Certain Taweret modules may require additional steps to properly setup an environment which can \
+execute the code. These modules and their respective requirements are listed below.
+
+**Tree**
+^^^^^^^^^
+
+The Trees module is a Python interface which calls and executes a number of Ubuntu packages in order \
+to fit the mixing model and obtain the resulting predictions. This package is developed as a part of the \
+Open Bayesian Trees Project (OpenBT)[1,2]. To install the Ubuntu package, please follow the steps below \
+based on the operating system of choice.
+
+
+**Linux:**
+
+1. Download the OpenBT Ubuntu Linux 20.04 package:
+.. code-block:: bash
+    $ wget -q https://github.com/jcyannotty/OpenBT/raw/main/openbt_mixing0.current_amd64-MPI_Ubuntu_20.04.deb 
+
+
+2. Install the package and result the library cache:
+.. code-block:: bash
+    $ cd /location/of/downloaded/.deb
+    $ dpkg -i openbt_mixing0.current_amd64-MPI_Ubuntu_20.04.deb
+    $ ldconfig
+
+
+**Mac OS/:X
+
+1. Install the OS/X OpenMPI package by running the following `brew` commands in a terminal window:
+.. code-block:: bash
+    $ /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/master/install.sh)"
+    $ brew install open-mpi
+
+2. Download the OpenBT OSX binary package:
+
+3. Install the OpenBT OSX package by double-clicking on the downloaded .pkg file and follow the on-screen instructions.
+
+
+**Windows:**
+OpenBT will run within the Windows 10 Windows Subsystem for Linux (WSL) environment. For instructions on installing WSL,\
+please see [Ubuntu on WSL](https://ubuntu.com/wsl). We recommend installing the Ubuntu 20.04 WSL build. \
+There are also instructions \
+[here](https://wiki.ubuntu.com/WSL?action=subscribe&_ga=2.237944261.411635877.1601405226-783048612.1601405226#Installing_Packages_on_Ubuntu) \
+on keeping your Ubuntu WSL up to date, or installing additional features like X support. Once you have \
+installed the WSL Ubuntu layer, start the WSL Ubuntu shell from the start menu and then install the package:
+
+.. code-block:: bash
+    $ cd /mnt/c/location/of/downloaded/.deb
+    $ dpkg -i openbt_mixing0.current_amd64-MPI_Ubuntu_20.04.deb
+
+
+**OpenBT References**
+[1. OpenBT Repository](https://bitbucket.org/mpratola/openbt/src/master/).
+[2. OpenBT Repository with Model Mixing](https://github.com/jcyannotty/OpenBT).