modified: dsm/__init__.py

	modified:   dsm/dsm_api.py
	modified:   dsm/dsm_torch.py

dsm/__init__.py

@@ -17,7 +17,7 @@
 # along with Deep Survival Machines.
 # If not, see <https://www.gnu.org/licenses/>.
 
-r"""
+"""
 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`.
@@ -67,7 +67,14 @@
 model and allows for learning of representations of the input covariates using
 **Recurrent Neural Networks** like **LSTMs, GRUs**. Deep Recurrent Survival
 Machines is a natural fit to model problems where there are time dependendent
-covariates.
+covariates. Examples include situations where we are working with streaming
+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.
+
 
 ..warning:: Not Implemented Yet!
 

dsm/dsm_api.py

@@ -100,7 +100,7 @@ def fit(self, x, t, e, vsize=0.15,
           iters=1, learning_rate=1e-3, batch_size=100,
           elbo=True, optimizer="Adam", random_state=100):
 
-    r"""This method is used to train an instance of the DSM model.
+    """This method is used to train an instance of the DSM model.
 
     Parameters
     ----------
@@ -175,7 +175,7 @@ def fit(self, x, t, e, vsize=0.15,
 
 
   def predict_risk(self, x, t):
-    r"""Returns the estimated risk of an event occuring before time \( t \)
+    """Returns the estimated risk of an event occuring before time \( t \)
       \( \widehat{\mathbb{P}}(T\leq t|X) \) for some input data \( x \).
 
     Parameters
@@ -199,7 +199,7 @@ def predict_risk(self, x, t):
 
 
   def predict_survival(self, x, t):
-    r"""Returns the estimated survival probability at time \( t \),
+    """Returns the estimated survival probability at time \( t \),
       \( \widehat{\mathbb{P}}(T > t|X) \) for some input data \( x \).
 
     Parameters
@@ -227,6 +227,7 @@ def predict_survival(self, x, t):
                       "before calling `predict_risk`.")
 
 class DeepRecurrentSurvivalMachines(DeepSurvivalMachines):
+
   __doc__ = "..warning:: Not Implemented"
   pass
 

dsm/dsm_torch.py

@@ -32,7 +32,7 @@
 
 
 def create_representation(inputdim, layers, activation):
-  r"""Helper function to generate the representation function for DSM.
+  """Helper function to generate the representation function for DSM.
 
   Deep Survival Machines learns a representation (\ Phi(X) \) for the input
   data. This representation is parameterized using a Non Linear Multilayer