Uh oh!
There was an error while loading. Please reload this page.
Add custom estimator for IP Insights algorithm - #493
Conversation
Codecov Report
@@ Coverage Diff @@## master #493 +/- ##
==========================================
+ Coverage 94.18% 94.24% +0.06%
==========================================
Files 58 59 +1 Lines 4400 4448 +48 ==========================================
+ Hits 4144 4192 +48
Misses 256 256
Continue to review full report at Codecov.
|
laurenyu
left a comment
There was a problem hiding this comment.
looks good! just a small handful of nitpicky comments
| batch_metrics_publish_interval=None, epochs=None, learning_rate=None, | ||
| num_ip_encoder_layers=None, random_negative_sampling_rate=None, | ||
| shuffled_negative_sampling_rate=None, weight_decay=None, **kwargs): | ||
| """IP Insights is :class:`Estimator` used for unsupervised learning. |
There was a problem hiding this comment.
nitpick: change this to either
``IPInsights`` is a :class:`Estimator` used for unsupervised learning.
or something like
This estimator is for IP Insights, an algorithm for unsupervised learning.
There was a problem hiding this comment.
Updated to:
This estimator is for IP Insights, an unsupervised algorithm that learns usage patterns of IP addresses.
| weight_decay (float): Optional. Weight decay coefficient. Adds L2 regularization. | ||
| **kwargs: base class keyword argument values. | ||
| """ | ||
There was a problem hiding this comment.
nitpick: don't need this newline
| self.weight_decay = weight_decay | ||
| def create_model(self, vpc_config_override=VPC_CONFIG_DEFAULT): | ||
| """Return a :class:`~sagemaker.amazon.IPInsightsModel`referencing the latest |
There was a problem hiding this comment.
this can go in a Returns section after Args. also, add a space after the last backtick
| @@ -0,0 +1,235 @@ | |||
* Estimators: add support for Amazon IP Insights algorithm
Issue #, if available:
Description of changes:
Merge Checklist
Put an
xin the boxes that apply. You can also fill these out after creating the PR. If you're unsure about any of them, don't hesitate to ask. We're here to help! This is simply a reminder of what we are going to look for before merging your pull request.By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.