diff options
Diffstat (limited to 'python/pyspark/ml/classification.py')
-rw-r--r-- | python/pyspark/ml/classification.py | 17 |
1 files changed, 9 insertions, 8 deletions
diff --git a/python/pyspark/ml/classification.py b/python/pyspark/ml/classification.py index 603f2c7f79..4a2982e204 100644 --- a/python/pyspark/ml/classification.py +++ b/python/pyspark/ml/classification.py @@ -36,7 +36,8 @@ __all__ = ['LogisticRegression', 'LogisticRegressionModel', 'DecisionTreeClassif @inherit_doc class LogisticRegression(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredictionCol, HasMaxIter, HasRegParam, HasTol, HasProbabilityCol, HasRawPredictionCol, - HasElasticNetParam, HasFitIntercept, HasStandardization, HasThresholds): + HasElasticNetParam, HasFitIntercept, HasStandardization, HasThresholds, + HasWeightCol): """ Logistic regression. Currently, this class only supports binary classification. @@ -44,9 +45,9 @@ class LogisticRegression(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredicti >>> from pyspark.sql import Row >>> from pyspark.mllib.linalg import Vectors >>> df = sc.parallelize([ - ... Row(label=1.0, features=Vectors.dense(1.0)), - ... Row(label=0.0, features=Vectors.sparse(1, [], []))]).toDF() - >>> lr = LogisticRegression(maxIter=5, regParam=0.01) + ... Row(label=1.0, weight=2.0, features=Vectors.dense(1.0)), + ... Row(label=0.0, weight=2.0, features=Vectors.sparse(1, [], []))]).toDF() + >>> lr = LogisticRegression(maxIter=5, regParam=0.01, weightCol="weight") >>> model = lr.fit(df) >>> model.weights DenseVector([5.5...]) @@ -80,12 +81,12 @@ class LogisticRegression(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredicti def __init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", maxIter=100, regParam=0.1, elasticNetParam=0.0, tol=1e-6, fitIntercept=True, threshold=0.5, thresholds=None, probabilityCol="probability", - rawPredictionCol="rawPrediction", standardization=True): + rawPredictionCol="rawPrediction", standardization=True, weightCol=None): """ __init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", \ maxIter=100, regParam=0.1, elasticNetParam=0.0, tol=1e-6, fitIntercept=True, \ threshold=0.5, thresholds=None, probabilityCol="probability", \ - rawPredictionCol="rawPrediction", standardization=True) + rawPredictionCol="rawPrediction", standardization=True, weightCol=None) If the threshold and thresholds Params are both set, they must be equivalent. """ super(LogisticRegression, self).__init__() @@ -105,12 +106,12 @@ class LogisticRegression(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPredicti def setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", maxIter=100, regParam=0.1, elasticNetParam=0.0, tol=1e-6, fitIntercept=True, threshold=0.5, thresholds=None, probabilityCol="probability", - rawPredictionCol="rawPrediction", standardization=True): + rawPredictionCol="rawPrediction", standardization=True, weightCol=None): """ setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", \ maxIter=100, regParam=0.1, elasticNetParam=0.0, tol=1e-6, fitIntercept=True, \ threshold=0.5, thresholds=None, probabilityCol="probability", \ - rawPredictionCol="rawPrediction", standardization=True) + rawPredictionCol="rawPrediction", standardization=True, weightCol=None) Sets params for logistic regression. If the threshold and thresholds Params are both set, they must be equivalent. """ |