public class LogisticRegressionModel extends ProbabilisticClassificationModel<Vector,LogisticRegressionModel> implements LogisticRegressionParams, MLWritable
LogisticRegression.| Modifier and Type | Method and Description |
|---|---|
BinaryLogisticRegressionTrainingSummary |
binarySummary()
Gets summary of model on training set.
|
Matrix |
coefficientMatrix() |
Vector |
coefficients()
A vector of model coefficients for "binomial" logistic regression.
|
LogisticRegressionModel |
copy(ParamMap extra)
Creates a copy of this instance with the same UID and some extra params.
|
LogisticRegressionSummary |
evaluate(Dataset<?> dataset)
Evaluates the model on a test dataset.
|
double |
getThreshold()
Get threshold for binary classification.
|
double[] |
getThresholds()
Get thresholds for binary or multiclass classification.
|
boolean |
hasSummary()
Indicates whether a training summary exists for this model instance.
|
double |
intercept()
The model intercept for "binomial" logistic regression.
|
Vector |
interceptVector() |
static LogisticRegressionModel |
load(String path) |
int |
numClasses()
Number of classes (values which the label can take).
|
int |
numFeatures()
Returns the number of features the model was trained on.
|
double |
predict(Vector features)
Predict label for the given feature vector.
|
static MLReader<LogisticRegressionModel> |
read() |
LogisticRegressionModel |
setThreshold(double value)
Set threshold in binary classification, in range [0, 1].
|
LogisticRegressionModel |
setThresholds(double[] value)
Set thresholds in multiclass (or binary) classification to adjust the probability of
predicting each class.
|
LogisticRegressionTrainingSummary |
summary()
Gets summary of model on training set.
|
String |
toString() |
String |
uid()
An immutable unique ID for the object and its derivatives.
|
MLWriter |
write()
Returns a
MLWriter instance for this ML instance. |
normalizeToProbabilitiesInPlace, setProbabilityCol, transformsetRawPredictionColsetFeaturesCol, setPredictionCol, transformSchematransform, transform, transformcheckThresholdConsistency, family, getFamily, getLowerBoundsOnCoefficients, getLowerBoundsOnIntercepts, getUpperBoundsOnCoefficients, getUpperBoundsOnIntercepts, lowerBoundsOnCoefficients, lowerBoundsOnIntercepts, upperBoundsOnCoefficients, upperBoundsOnIntercepts, usingBoundConstrainedOptimization, validateAndTransformSchemagetLabelCol, labelColfeaturesCol, getFeaturesColgetPredictionCol, predictionColclear, copyValues, defaultCopy, defaultParamMap, explainParam, explainParams, extractParamMap, extractParamMap, get, getDefault, getOrDefault, getParam, hasDefault, hasParam, isDefined, isSet, paramMap, params, set, set, set, setDefault, setDefault, shouldOwngetRawPredictionCol, rawPredictionColgetProbabilityCol, probabilityColthresholdsgetRegParam, regParamelasticNetParam, getElasticNetParamgetMaxIter, maxIterfitIntercept, getFitInterceptgetStandardization, standardizationgetWeightCol, weightColthresholdaggregationDepth, getAggregationDepthsaveinitializeLogging, initializeLogIfNecessary, initializeLogIfNecessary, isTraceEnabled, log_, log, logDebug, logDebug, logError, logError, logInfo, logInfo, logName, logTrace, logTrace, logWarning, logWarningpublic static MLReader<LogisticRegressionModel> read()
public static LogisticRegressionModel load(String path)
public String uid()
Identifiableuid in interface Identifiablepublic Matrix coefficientMatrix()
public Vector interceptVector()
public int numClasses()
ClassificationModelnumClasses in class ClassificationModel<Vector,LogisticRegressionModel>public Vector coefficients()
public double intercept()
public LogisticRegressionModel setThreshold(double value)
LogisticRegressionParamsIf the estimated probability of class label 1 is greater than threshold, then predict 1, else 0. A high threshold encourages the model to predict 0 more often; a low threshold encourages the model to predict 1 more often.
Note: Calling this with threshold p is equivalent to calling setThresholds(Array(1-p, p)).
When setThreshold() is called, any user-set value for thresholds will be cleared.
If both threshold and thresholds are set in a ParamMap, then they must be
equivalent.
Default is 0.5.
setThreshold in interface LogisticRegressionParamsvalue - (undocumented)public double getThreshold()
LogisticRegressionParams
If thresholds is set with length 2 (i.e., binary classification),
this returns the equivalent threshold:
1 / (1 + thresholds(0) / thresholds(1))getThreshold in interface LogisticRegressionParamsgetThreshold in interface HasThresholdpublic LogisticRegressionModel setThresholds(double[] value)
LogisticRegressionParams
Note: When setThresholds() is called, any user-set value for threshold will be cleared.
If both threshold and thresholds are set in a ParamMap, then they must be
equivalent.
setThresholds in interface LogisticRegressionParamssetThresholds in class ProbabilisticClassificationModel<Vector,LogisticRegressionModel>value - (undocumented)public double[] getThresholds()
LogisticRegressionParams
If thresholds is set, return its value.
Otherwise, if threshold is set, return the equivalent thresholds for binary
classification: (1-threshold, threshold).
If neither are set, throw an exception.
getThresholds in interface LogisticRegressionParamsgetThresholds in interface HasThresholdspublic int numFeatures()
PredictionModelnumFeatures in class PredictionModel<Vector,LogisticRegressionModel>public LogisticRegressionTrainingSummary summary()
trainingSummary == None.public BinaryLogisticRegressionTrainingSummary binarySummary()
trainingSummary == None or it is a multiclass model.public boolean hasSummary()
public LogisticRegressionSummary evaluate(Dataset<?> dataset)
dataset - Test dataset to evaluate model on.public double predict(Vector features)
thresholds.predict in class ClassificationModel<Vector,LogisticRegressionModel>features - (undocumented)public LogisticRegressionModel copy(ParamMap extra)
ParamsdefaultCopy().copy in interface Paramscopy in class Model<LogisticRegressionModel>extra - (undocumented)public MLWriter write()
MLWriter instance for this ML instance.
For LogisticRegressionModel, this does NOT currently save the training summary.
An option to save summary may be added in the future.
This also does not save the parent currently.
write in interface MLWritablepublic String toString()
toString in interface IdentifiabletoString in class Object