Changes to documentation #49
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
shikhareddy
commented
Jun 2, 2021
| inputdim: int | ||
| Dimensionality of the input features. | ||
| optimizer: str | ||
| The choice of the gradient based optimization method. One of |
There was a problem hiding this comment.
One of from next line
shikhareddy
commented
Jun 2, 2021
| The choice of the gradient based optimization method. One of | ||
| 'Adam', 'RMSProp' or 'SGD'. | ||
| risks: int | ||
| Uncertainty as to whether the parameters are appropriate for |
There was a problem hiding this comment.
Remove risks doc
shikhareddy
commented
Jun 2, 2021
| @@ -74,8 +86,7 @@ def _gen_torch_model(self, inputdim, optimizer, risks): | |||
| def fit(self, x, t, e, vsize=0.15, val_data=None, | |||
| 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. | |||
shikhareddy
commented
Jun 2, 2021
| A numpy array of the input features, \( x \). | ||
|
|
||
| Returns: | ||
| Tensor: input features, \( x \). |
There was a problem hiding this comment.
torch.tensor
Detail more
shikhareddy
commented
Jun 2, 2021
| @@ -171,9 +181,40 @@ def compute_nll(self, x, t, e): | |||
| return loss | |||
|
|
|||
| def _prepocess_test_data(self, x): | |||
| """This function pre processes the test data. | |||
There was a problem hiding this comment.
converts numpy test data to torch tensor
shikhareddy
commented
Jun 2, 2021
| @@ -397,10 +464,41 @@ def _gen_torch_model(self, inputdim, optimizer, risks): | |||
| risks=risks) | |||
|
|
|||
| def _prepocess_test_data(self, x): | |||
There was a problem hiding this comment.
converts variable length numpy arrrays to tensors
Rec Neural networks require special pre processing to work with variable sized sequences. This function pads and creates appropriate sized torch tensors from input numpy arrays.
shikhareddy
commented
Jun 2, 2021
| return torch.from_numpy(_get_padded_features(x)) | ||
|
|
||
| def _prepocess_training_data(self, x, t, e, vsize, val_data, random_state): | ||
| """RNNs require different preprocessing for variable length sequences""" | ||
| """RNNs require different preprocessing for variable length sequences. |
shikhareddy
commented
Jun 2, 2021
| @@ -236,13 +239,13 @@ class DeepRecurrentSurvivalMachinesTorch(DeepSurvivalMachinesTorch): | |||
| Dimensionality of the input features. | |||
| k: int | |||
| The number of underlying parametric distributions. | |||
| typ: str | |||
There was a problem hiding this comment.
Choice of the recurrent neural architecture
One of 'LSTM' , 'RNN' , 'GRU'
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Hello @chiragnagpal . Made necessary changes to README.md, all python files in dsm and docs.