Merge branch 'develop' into lineage_semantics

Author: chcost

.github/pull_request_template.md

@@ -0,0 +1,25 @@
+**Related Issue**
+
+<!-- List any issues that this pr is related to, fixes or supports -->
+
+Supports #ISSUE_NUMBER
+
+**Related PRs**
+
+<!-- Does this pr depend on or replace an existing pr? Link it here -->
+
+This PR is not dependent on any other PR
+
+**What does this PR do?**
+
+<!-- The intent of this section is to help team members understand the scope of your changes and why you are making said changes. If there are any concerns or risks associated with your pull request, they should be documented here so your team members can give informative feedback in their reviews. -->
+
+**Description of Changes**
+
+<!-- The intent of this section is to describe the implementation details of the changes you made. Any architectural decisions made should be noted here as well as a short description of why you made that decision. -->
+
+**What gif most accurately describes how I feel towards this PR?**
+
+<!-- Cute animals are also acceptable. -->
+
+![Example of a gif](https://media.github.ibm.com/user/59/files/074da280-78ba-11ea-81d1-49ce0654c29d)

codeflare/pipelines/Datamodel.py

@@ -7,7 +7,6 @@
 from sklearn.base import TransformerMixin
 from sklearn.base import BaseEstimator
 
-
 class Xy:
     """
     Holder class for Xy, where X is array-like and y is array-like. This is the base
@@ -93,6 +92,7 @@ class Node(ABC):
     The hash code of this node is the name of the node and equality is defined if the
     node name and the type of the node match.
     """
+
     def __init__(self, node_name, node_input_type: NodeInputType, node_firing_type: NodeFiringType, node_state_type: NodeStateType):
         self.__node_name__ = node_name
         self.__node_input_type__ = node_input_type
@@ -125,6 +125,7 @@ def __hash__(self):
 
         :return: Hash code
         """
+
         return self.__id__.__hash__()
 
     def __eq__(self, other):
@@ -155,6 +156,7 @@ def __init__(self, node_name: str, estimator: BaseEstimator):
         :param node_name: Name of the node
         :param estimator: The base estimator
         """
+
         super().__init__(node_name, NodeInputType.OR, NodeFiringType.ANY, NodeStateType.IMMUTABLE)
         self.__estimator__ = estimator
 

codeflare/pipelines/Runtime.py

@@ -1,5 +1,6 @@
 import ray
 
+
 from codeflare.pipelines.Datamodel import EstimatorNode
 from codeflare.pipelines.Datamodel import AndNode
 from codeflare.pipelines.Datamodel import Edge
@@ -64,6 +65,7 @@ def execute_or_node_remote(node: EstimatorNode, train_mode: ExecutionType, xy_re
             res_Xref = ray.put(cloned_estimator.fit_transform(X, y))
             curr_node_ptr = ray.put(cloned_node)
             result = XYRef(res_Xref, xy_ref.get_yref(), prev_node_ptr, curr_node_ptr, [xy_ref])
+            
             return result
     elif train_mode == ExecutionType.PREDICT:
         # Test mode does not clone as it is a simple predict or transform

notebooks/Ray graph experiments.ipynb

@@ -137,7 +137,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 34,
    "id": "uniform-coordinator",
    "metadata": {},
    "outputs": [],
@@ -148,7 +148,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 35,
    "id": "romance-sender",
    "metadata": {},
    "outputs": [],
@@ -166,7 +166,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 36,
    "id": "handy-offset",
    "metadata": {},
    "outputs": [],

requirements.txt

@@ -1,4 +1,5 @@
 ray~=1.0.0
 setuptools~=52.0.0
 sklearn~=0.0
-scikit-learn~=0.24.1
+scikit-learn~=0.24.1
+pandas~=1.2.4