Skip to content

[SPARK-14714][ML][PYTHON] Fixed issues with non-kwarg typeConverter arg for Param constructor #12480

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

[SPARK-14714][ML][PYTHON] Fixed issues with non-kwarg typeConverter arg for Param constructor #12480

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion python/pyspark/ml/clustering.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,7 +92,8 @@ class KMeans(JavaEstimator, HasFeaturesCol, HasPredictionCol, HasMaxIter, HasTol
initMode = Param(Params._dummy(), "initMode",
"the initialization algorithm. This can be either \"random\" to " +
"choose random points as initial cluster centers, or \"k-means||\" " +
"to use a parallel variant of k-means++", TypeConverters.toString)
"to use a parallel variant of k-means++",
typeConverter=TypeConverters.toString)
initSteps = Param(Params._dummy(), "initSteps", "steps for k-means initialization mode",
typeConverter=TypeConverters.toInt)

Expand Down
17 changes: 10 additions & 7 deletions python/pyspark/ml/feature.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1317,9 +1317,9 @@ class RegexTokenizer(JavaTransformer, HasInputCol, HasOutputCol, JavaMLReadable,
typeConverter=TypeConverters.toInt)
gaps = Param(Params._dummy(), "gaps", "whether regex splits on gaps (True) or matches tokens")
pattern = Param(Params._dummy(), "pattern", "regex pattern (Java dialect) used for tokenizing",
TypeConverters.toString)
typeConverter=TypeConverters.toString)
toLowercase = Param(Params._dummy(), "toLowercase", "whether to convert all characters to " +
"lowercase before tokenizing", TypeConverters.toBoolean)
"lowercase before tokenizing", typeConverter=TypeConverters.toBoolean)

@keyword_only
def __init__(self, minTokenLength=1, gaps=True, pattern="\\s+", inputCol=None,
Expand Down Expand Up @@ -1430,7 +1430,8 @@ class SQLTransformer(JavaTransformer, JavaMLReadable, JavaMLWritable):
.. versionadded:: 1.6.0
"""

statement = Param(Params._dummy(), "statement", "SQL statement", TypeConverters.toString)
statement = Param(Params._dummy(), "statement", "SQL statement",
typeConverter=TypeConverters.toString)

@keyword_only
def __init__(self, statement=None):
Expand Down Expand Up @@ -1504,9 +1505,10 @@ class StandardScaler(JavaEstimator, HasInputCol, HasOutputCol, JavaMLReadable, J
.. versionadded:: 1.4.0
"""

withMean = Param(Params._dummy(), "withMean", "Center data with mean", TypeConverters.toBoolean)
withMean = Param(Params._dummy(), "withMean", "Center data with mean",
typeConverter=TypeConverters.toBoolean)
withStd = Param(Params._dummy(), "withStd", "Scale to unit standard deviation",
TypeConverters.toBoolean)
typeConverter=TypeConverters.toBoolean)

@keyword_only
def __init__(self, withMean=False, withStd=True, inputCol=None, outputCol=None):
Expand Down Expand Up @@ -1754,7 +1756,7 @@ class StopWordsRemover(JavaTransformer, HasInputCol, HasOutputCol, JavaMLReadabl
stopWords = Param(Params._dummy(), "stopWords", "The words to be filtered out",
typeConverter=TypeConverters.toListString)
caseSensitive = Param(Params._dummy(), "caseSensitive", "whether to do a case sensitive " +
"comparison over the stop words", TypeConverters.toBoolean)
"comparison over the stop words", typeConverter=TypeConverters.toBoolean)

@keyword_only
def __init__(self, inputCol=None, outputCol=None, stopWords=None,
Expand Down Expand Up @@ -2492,7 +2494,8 @@ class RFormula(JavaEstimator, HasFeaturesCol, HasLabelCol, JavaMLReadable, JavaM
.. versionadded:: 1.5.0
"""

formula = Param(Params._dummy(), "formula", "R model formula", TypeConverters.toString)
formula = Param(Params._dummy(), "formula", "R model formula",
typeConverter=TypeConverters.toString)

@keyword_only
def __init__(self, formula=None, featuresCol="features", labelCol="label"):
Expand Down
12 changes: 7 additions & 5 deletions python/pyspark/ml/recommendation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -107,16 +107,18 @@ class ALS(JavaEstimator, HasCheckpointInterval, HasMaxIter, HasPredictionCol, Ha
numItemBlocks = Param(Params._dummy(), "numItemBlocks", "number of item blocks",
typeConverter=TypeConverters.toInt)
implicitPrefs = Param(Params._dummy(), "implicitPrefs", "whether to use implicit preference",
TypeConverters.toBoolean)
typeConverter=TypeConverters.toBoolean)
alpha = Param(Params._dummy(), "alpha", "alpha for implicit preference",
typeConverter=TypeConverters.toFloat)
userCol = Param(Params._dummy(), "userCol", "column name for user ids", TypeConverters.toString)
itemCol = Param(Params._dummy(), "itemCol", "column name for item ids", TypeConverters.toString)
userCol = Param(Params._dummy(), "userCol", "column name for user ids",
typeConverter=TypeConverters.toString)
itemCol = Param(Params._dummy(), "itemCol", "column name for item ids",
typeConverter=TypeConverters.toString)
ratingCol = Param(Params._dummy(), "ratingCol", "column name for ratings",
TypeConverters.toString)
typeConverter=TypeConverters.toString)
nonnegative = Param(Params._dummy(), "nonnegative",
"whether to use nonnegative constraint for least squares",
TypeConverters.toBoolean)
typeConverter=TypeConverters.toBoolean)

@keyword_only
def __init__(self, rank=10, maxIter=10, regParam=0.1, numUserBlocks=10, numItemBlocks=10,
Expand Down