modified: dsm/__init__.py

	modified:   dsm/datasets.py
	modified:   dsm/dsm_api.py
	modified:   dsm/dsm_torch.py
	modified:   dsm/losses.py
	modified:   dsm/utilities.py

dsm/__init__.py

@@ -18,6 +18,17 @@
 # If not, see <https://www.gnu.org/licenses/>.
 
 """
+[![Build Status](https://travis-ci.org/chiragnagpal/DeepSurvivalMachines.svg?\
+branch=master)](https://travis-ci.org/chiragnagpal/DeepSurvivalMachines)
+&nbsp;&nbsp;&nbsp;\
+[![License: GPL v3](https://img.shields.io/badge/License-GPLv3-blue.svg)]\
+(https://www.gnu.org/licenses/gpl-3.0)
+&nbsp;&nbsp;&nbsp;\
+[![GitHub Repo stars](https://img.shields.io/github/stars/autonlab/Deep\
+SurvivalMachines?style=social)](https://github.com/autonlab/DeepSurvival\
+Machines)
+
+
 Python package `dsm` provides an API to train the Deep Survival Machines
 and associated models for problems in survival analysis. The underlying model
 is implemented in `pytorch`.
@@ -54,11 +65,6 @@
 parametric distributions. The parameters of these mixture distributions as
 well as the mixing weights are modelled using Neural Networks.
 
-#### Usage Example
-    >>> from dsm import DeepSurvivalMachines
-    >>> model = DeepSurvivalMachines()
-    >>> model.fit()
-    >>> model.predict_risk()
 
 Deep Recurrent Survival Machines
 --------------------------------
@@ -71,9 +77,10 @@
 data like vital signs, degradation monitoring signals in predictive
 maintainance. **DRSM** allows the learnt representations at each time step to
 involve historical context from previous time steps. **DRSM** implementation in
-`dsm` is carried out through an easy to use API that accepts lists of data
-streams and corresponding failure times. The module automatically takes care of
-appropriate batching and padding of variable length sequences.
+`dsm` is carried out through an easy to use API, 
+`DeepRecurrentSurvivalMachines` that accepts lists of data streams and
+corresponding failure times. The module automatically takes care of appropriate
+batching and padding of variable length sequences.
 
 
 ..warning:: Not Implemented Yet!
@@ -90,6 +97,21 @@
 
 ..warning:: Not Implemented Yet!
 
+
+Example Usage
+-------------
+
+>>> from dsm import DeepSurvivalMachines
+>>> from dsm import datasets
+>>> # load the SUPPORT dataset.
+>>> x, t, e = datasets.load_dataset('SUPPORT')
+>>> # instantiate a DeepSurvivalMachines model.
+>>> model = DeepSurvivalMachines()
+>>> # fit the model to the dataset.
+>>> model.fit(x, t, e)
+>>> # estimate the predicted risks at the time
+>>> model.predict_risk(x, 10)
+
 References
 ----------
 
@@ -143,13 +165,14 @@
 
 
 
-<img style="float: right;" width ="200px" src="https://www.cmu.edu/brand/downloads/assets/images/wordmarks-600x600-min.jpg">
-<img style="float: right;padding-top:50px" src="https://www.autonlab.org/user/themes/auton/images/AutonLogo.png">
+<img style="float: right;" width ="200px" src="https://www.cmu.edu/brand/\
+downloads/assets/images/wordmarks-600x600-min.jpg">
+<img style="float: right;padding-top:50px" src="https://www.autonlab.org/\
+user/themes/auton/images/AutonLogo.png">
 
 <br><br><br><br><br>
 <br><br><br><br><br>
 
-
 """
 
 from dsm.dsm_api import DeepSurvivalMachines, DeepRecurrentSurvivalMachines

dsm/datasets.py

@@ -114,7 +114,6 @@ def _load_pbc_dataset(sequential):
     else, returns collapsed results for each time step. To train
     recurrent neural models you would typically use True.
 
-
   References
   ----------
   [1] Fleming, Thomas R., and David P. Harrington. Counting processes and
@@ -193,6 +192,36 @@ def _load_support_dataset():
 def load_dataset(dataset='SUPPORT', **kwargs):
   """Helper function to load datasets to test Survival Analysis models.
 
+  Currently implemented datasets include:
+
+  **SUPPORT**: This dataset comes from the Vanderbilt University study
+  to estimate survival for seriously ill hospitalized adults [1].
+  (Refer to http://biostat.mc.vanderbilt.edu/wiki/Main/SupportDesc.
+  for the original datasource.)
+
+  **PBC**: The Primary biliary cirrhosis dataset [2] is well known
+  dataset for evaluating survival analysis models with time
+  dependent covariates.
+
+  **FRAMINGHAM**: This dataset is a subset of 4,434 participants of the well
+  known, ongoing Framingham Heart study [3] for studying epidemiology for
+  hypertensive and arteriosclerotic cardiovascular disease. It is a popular
+  dataset for longitudinal survival analysis with time dependent covariates.
+
+  References
+  -----------
+
+  [1]: Knaus WA, Harrell FE, Lynn J et al. (1995): The SUPPORT prognostic
+  model: Objective estimates of survival for seriously ill hospitalized
+  adults. Annals of Internal Medicine 122:191-203.
+
+  [2] Fleming, Thomas R., and David P. Harrington. Counting processes and
+  survival analysis. Vol. 169. John Wiley & Sons, 2011.
+
+  [3] Dawber, Thomas R., Gilcin F. Meadors, and Felix E. Moore Jr.
+  "Epidemiological approaches to heart disease: the Framingham Study."
+  American Journal of Public Health and the Nations Health 41.3 (1951).
+
   Parameters
   ----------
   dataset: str