[SPARK-11875][ML][PYSPARK] Update doc for PySpark HasCheckpointInterval

yanboliang · mengxr · commit 0a878ad0e422 · 2015-11-19T22:14:26.000-08:00
* Update doc for PySpark ```HasCheckpointInterval``` that users can understand how to disable checkpoint. * Update doc for PySpark ```cacheNodeIds``` of ```DecisionTreeParams``` to notify the relationship between ```cacheNodeIds``` and ```checkpointInterval```. Author: Yanbo Liang <ybliang8@gmail.com> Closes apache#9856 from yanboliang/spark-11875. (cherry picked from commit 7216f40) Signed-off-by: Xiangrui Meng <meng@databricks.com>
diff --git a/python/pyspark/ml/param/_shared_params_code_gen.py b/python/pyspark/ml/param/_shared_params_code_gen.py
@@ -118,7 +118,8 @@ def get$Name(self):
         ("inputCols", "input column names.", None),
         ("outputCol", "output column name.", "self.uid + '__output'"),
         ("numFeatures", "number of features.", None),
-        ("checkpointInterval", "checkpoint interval (>= 1).", None),
+        ("checkpointInterval", "set checkpoint interval (>= 1) or disable checkpoint (-1). " +
+         "E.g. 10 means that the cache will get checkpointed every 10 iterations.", None),
         ("seed", "random seed.", "hash(type(self).__name__)"),
         ("tol", "the convergence tolerance for iterative algorithms.", None),
         ("stepSize", "Step size to be used for each iteration of optimization.", None),
@@ -157,7 +158,8 @@ def get$Name(self):
         ("maxMemoryInMB", "Maximum memory in MB allocated to histogram aggregation."),
         ("cacheNodeIds", "If false, the algorithm will pass trees to executors to match " +
          "instances with nodes. If true, the algorithm will cache node IDs for each instance. " +
-         "Caching can speed up training of deeper trees.")]
+         "Caching can speed up training of deeper trees. Users can set how often should the " +
+         "cache be checkpointed or disable it by setting checkpointInterval.")]
 
     decisionTreeCode = '''class DecisionTreeParams(Params):
     """
diff --git a/python/pyspark/ml/param/shared.py b/python/pyspark/ml/param/shared.py
@@ -325,16 +325,16 @@ def getNumFeatures(self):
 
 class HasCheckpointInterval(Params):
     """
-    Mixin for param checkpointInterval: checkpoint interval (>= 1).
+    Mixin for param checkpointInterval: set checkpoint interval (>= 1) or disable checkpoint (-1). E.g. 10 means that the cache will get checkpointed every 10 iterations.
     """
 
     # a placeholder to make it appear in the generated doc
-    checkpointInterval = Param(Params._dummy(), "checkpointInterval", "checkpoint interval (>= 1).")
+    checkpointInterval = Param(Params._dummy(), "checkpointInterval", "set checkpoint interval (>= 1) or disable checkpoint (-1). E.g. 10 means that the cache will get checkpointed every 10 iterations.")
 
     def __init__(self):
         super(HasCheckpointInterval, self).__init__()
-        #: param for checkpoint interval (>= 1).
-        self.checkpointInterval = Param(self, "checkpointInterval", "checkpoint interval (>= 1).")
+        #: param for set checkpoint interval (>= 1) or disable checkpoint (-1). E.g. 10 means that the cache will get checkpointed every 10 iterations.
+        self.checkpointInterval = Param(self, "checkpointInterval", "set checkpoint interval (>= 1) or disable checkpoint (-1). E.g. 10 means that the cache will get checkpointed every 10 iterations.")
 
     def setCheckpointInterval(self, value):
         """
@@ -636,7 +636,7 @@ class DecisionTreeParams(Params):
     minInstancesPerNode = Param(Params._dummy(), "minInstancesPerNode", "Minimum number of instances each child must have after split. If a split causes the left or right child to have fewer than minInstancesPerNode, the split will be discarded as invalid. Should be >= 1.")
     minInfoGain = Param(Params._dummy(), "minInfoGain", "Minimum information gain for a split to be considered at a tree node.")
     maxMemoryInMB = Param(Params._dummy(), "maxMemoryInMB", "Maximum memory in MB allocated to histogram aggregation.")
-    cacheNodeIds = Param(Params._dummy(), "cacheNodeIds", "If false, the algorithm will pass trees to executors to match instances with nodes. If true, the algorithm will cache node IDs for each instance. Caching can speed up training of deeper trees.")
+    cacheNodeIds = Param(Params._dummy(), "cacheNodeIds", "If false, the algorithm will pass trees to executors to match instances with nodes. If true, the algorithm will cache node IDs for each instance. Caching can speed up training of deeper trees. Users can set how often should the cache be checkpointed or disable it by setting checkpointInterval.")
     
 
     def __init__(self):
@@ -651,8 +651,8 @@ def __init__(self):
         self.minInfoGain = Param(self, "minInfoGain", "Minimum information gain for a split to be considered at a tree node.")
         #: param for Maximum memory in MB allocated to histogram aggregation.
         self.maxMemoryInMB = Param(self, "maxMemoryInMB", "Maximum memory in MB allocated to histogram aggregation.")
-        #: param for If false, the algorithm will pass trees to executors to match instances with nodes. If true, the algorithm will cache node IDs for each instance. Caching can speed up training of deeper trees.
-        self.cacheNodeIds = Param(self, "cacheNodeIds", "If false, the algorithm will pass trees to executors to match instances with nodes. If true, the algorithm will cache node IDs for each instance. Caching can speed up training of deeper trees.")
+        #: param for If false, the algorithm will pass trees to executors to match instances with nodes. If true, the algorithm will cache node IDs for each instance. Caching can speed up training of deeper trees. Users can set how often should the cache be checkpointed or disable it by setting checkpointInterval.
+        self.cacheNodeIds = Param(self, "cacheNodeIds", "If false, the algorithm will pass trees to executors to match instances with nodes. If true, the algorithm will cache node IDs for each instance. Caching can speed up training of deeper trees. Users can set how often should the cache be checkpointed or disable it by setting checkpointInterval.")
         
     def setMaxDepth(self, value):
         """
