From 87d69a01f027aa18718827f94f921b4a1eaa78a5 Mon Sep 17 00:00:00 2001
From: Zheng RuiFeng <ruifengz@foxmail.com>
Date: Fri, 13 May 2016 08:52:06 +0200
Subject: [PATCH] [MINOR][PYSPARK] update _shared_params_code_gen.py
## What changes were proposed in this pull request?
1, add arg-checkings for `tol` and `stepSize` to keep in line with `SharedParamsCodeGen.scala`
2, fix one typo
## How was this patch tested?
local build
Author: Zheng RuiFeng <ruifengz@foxmail.com>
Closes #12996 from zhengruifeng/py_args_checking.
---
python/pyspark/ml/clustering.py | 2 +-
python/pyspark/ml/param/_shared_params_code_gen.py | 6 +++---
python/pyspark/ml/param/shared.py | 12 ++++++------
3 files changed, 10 insertions(+), 10 deletions(-)
diff --git a/python/pyspark/ml/clustering.py b/python/pyspark/ml/clustering.py
index b90daf16e2..921633164b 100644
--- a/python/pyspark/ml/clustering.py
+++ b/python/pyspark/ml/clustering.py
@@ -517,7 +517,7 @@ class LDAModel(JavaModel):
def estimatedDocConcentration(self):
"""
Value for :py:attr:`LDA.docConcentration` estimated from data.
- If Online LDA was used and :py:attr::`LDA.optimizeDocConcentration` was set to false,
+ If Online LDA was used and :py:attr:`LDA.optimizeDocConcentration` was set to false,
then this returns the fixed (given) value for the :py:attr:`LDA.docConcentration` parameter.
"""
return self._call_java("estimatedDocConcentration")
diff --git a/python/pyspark/ml/param/_shared_params_code_gen.py b/python/pyspark/ml/param/_shared_params_code_gen.py
index 12f14534f4..c32dcc467d 100644
--- a/python/pyspark/ml/param/_shared_params_code_gen.py
+++ b/python/pyspark/ml/param/_shared_params_code_gen.py
@@ -124,12 +124,12 @@ if __name__ == "__main__":
"E.g. 10 means that the cache will get checkpointed every 10 iterations.", None,
"TypeConverters.toInt"),
("seed", "random seed.", "hash(type(self).__name__)", "TypeConverters.toInt"),
- ("tol", "the convergence tolerance for iterative algorithms.", None,
+ ("tol", "the convergence tolerance for iterative algorithms (>= 0).", None,
"TypeConverters.toFloat"),
- ("stepSize", "Step size to be used for each iteration of optimization.", None,
+ ("stepSize", "Step size to be used for each iteration of optimization (>= 0).", None,
"TypeConverters.toFloat"),
("handleInvalid", "how to handle invalid entries. Options are skip (which will filter " +
- "out rows with bad values), or error (which will throw an errror). More options may be " +
+ "out rows with bad values), or error (which will throw an error). More options may be " +
"added later.", None, "TypeConverters.toString"),
("elasticNetParam", "the ElasticNet mixing parameter, in range [0, 1]. For alpha = 0, " +
"the penalty is an L2 penalty. For alpha = 1, it is an L1 penalty.", "0.0",
diff --git a/python/pyspark/ml/param/shared.py b/python/pyspark/ml/param/shared.py
index 9ed63e48ae..c5ccf81540 100644
--- a/python/pyspark/ml/param/shared.py
+++ b/python/pyspark/ml/param/shared.py
@@ -328,10 +328,10 @@ class HasSeed(Params):
class HasTol(Params):
"""
- Mixin for param tol: the convergence tolerance for iterative algorithms.
+ Mixin for param tol: the convergence tolerance for iterative algorithms (>= 0).
"""
- tol = Param(Params._dummy(), "tol", "the convergence tolerance for iterative algorithms.", typeConverter=TypeConverters.toFloat)
+ tol = Param(Params._dummy(), "tol", "the convergence tolerance for iterative algorithms (>= 0).", typeConverter=TypeConverters.toFloat)
def __init__(self):
super(HasTol, self).__init__()
@@ -351,10 +351,10 @@ class HasTol(Params):
class HasStepSize(Params):
"""
- Mixin for param stepSize: Step size to be used for each iteration of optimization.
+ Mixin for param stepSize: Step size to be used for each iteration of optimization (>= 0).
"""
- stepSize = Param(Params._dummy(), "stepSize", "Step size to be used for each iteration of optimization.", typeConverter=TypeConverters.toFloat)
+ stepSize = Param(Params._dummy(), "stepSize", "Step size to be used for each iteration of optimization (>= 0).", typeConverter=TypeConverters.toFloat)
def __init__(self):
super(HasStepSize, self).__init__()
@@ -374,10 +374,10 @@ class HasStepSize(Params):
class HasHandleInvalid(Params):
"""
- Mixin for param handleInvalid: how to handle invalid entries. Options are skip (which will filter out rows with bad values), or error (which will throw an errror). More options may be added later.
+ Mixin for param handleInvalid: how to handle invalid entries. Options are skip (which will filter out rows with bad values), or error (which will throw an error). More options may be added later.
"""
- handleInvalid = Param(Params._dummy(), "handleInvalid", "how to handle invalid entries. Options are skip (which will filter out rows with bad values), or error (which will throw an errror). More options may be added later.", typeConverter=TypeConverters.toString)
+ handleInvalid = Param(Params._dummy(), "handleInvalid", "how to handle invalid entries. Options are skip (which will filter out rows with bad values), or error (which will throw an error). More options may be added later.", typeConverter=TypeConverters.toString)
def __init__(self):
super(HasHandleInvalid, self).__init__()
--
GitLab