org.apache.spark.ml.classification
GBTClassifier
Related Docs:
object GBTClassifier
| package classification
org.apache.spark.ml.classification
An alias for getOrDefault().
An alias for getOrDefault().
If false, the algorithm will pass trees to executors to match instances with nodes.
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. (default = false)
Param for set checkpoint interval (>= 1) or disable checkpoint (-1).
Param for set checkpoint interval (>= 1) or disable checkpoint (-1). E.g. 10 means that the cache will get checkpointed every 10 iterations. Note: this setting will be ignored if the checkpoint directory is not set in the SparkContext.
Clears the user-supplied value for the input param.
Clears the user-supplied value for the input param.
Creates a copy of this instance with the same UID and some extra params.
Creates a copy of this instance with the same UID and some extra params.
Subclasses should implement this method and set the return type properly.
See defaultCopy().
Copies param values from this instance to another instance for params shared by them.
Copies param values from this instance to another instance for params shared by them.
This handles default Params and explicitly set Params separately.
Default Params are copied from and to defaultParamMap, and explicitly set Params are
copied from and to paramMap.
Warning: This implicitly assumes that this Params instance and the target instance
share the same set of default Params.
the target instance, which should work with the same set of default Params as this source instance
extra params to be copied to the target's paramMap
the target instance with param values copied
Default implementation of copy with extra params.
Default implementation of copy with extra params. It tries to create a new instance with the same UID. Then it copies the embedded and extra parameters over and returns the new instance.
Explains a param.
Explains a param.
input param, must belong to this instance.
a string that contains the input param name, doc, and optionally its default value and the user-supplied value
Explains all params of this instance.
Explains all params of this instance. See explainParam().
Extract labelCol and featuresCol from the given dataset, and put it in an RDD with strong types.
Extract labelCol and featuresCol from the given dataset, and put it in an RDD with strong types.
DataFrame with columns for labels (org.apache.spark.sql.types.NumericType)
and features (Vector).
Number of classes label can take. Labels must be integers in the range [0, numClasses).
Throws SparkException if any label is a non-integer or is negative
Extract labelCol and featuresCol from the given dataset, and put it in an RDD with strong types.
Extract labelCol and featuresCol from the given dataset, and put it in an RDD with strong types.
extractParamMap with no extra values.
extractParamMap with no extra values.
Extracts the embedded default param values and user-supplied values, and then merges them with extra values from input into a flat param map, where the latter value is used if there exist conflicts, i.e., with ordering: default param values less than user-supplied values less than extra.
Extracts the embedded default param values and user-supplied values, and then merges them with extra values from input into a flat param map, where the latter value is used if there exist conflicts, i.e., with ordering: default param values less than user-supplied values less than extra.
The number of features to consider for splits at each tree node.
The number of features to consider for splits at each tree node. Supported options:
These various settings are based on the following references:
Param for features column name.
Param for features column name.
Fits a model to the input data.
Fits multiple models to the input data with multiple sets of parameters.
Fits multiple models to the input data with multiple sets of parameters. The default implementation uses a for loop on each parameter map. Subclasses could override this to optimize multi-model training.
input dataset
An array of parameter maps. These values override any specified in this Estimator's embedded ParamMap.
fitted models, matching the input parameter maps
Fits a single model to the input data with provided parameter map.
Fits a single model to the input data with provided parameter map.
input dataset
Parameter map. These values override any specified in this Estimator's embedded ParamMap.
fitted model
Fits a single model to the input data with optional parameters.
Fits a single model to the input data with optional parameters.
input dataset
the first param pair, overrides embedded params
other param pairs. These values override any specified in this Estimator's embedded ParamMap.
fitted model
Optionally returns the user-supplied value of a param.
Optionally returns the user-supplied value of a param.
Gets the default value of a parameter.
Gets the default value of a parameter.
Get the number of classes.
Get the number of classes. This looks in column metadata first, and if that is missing, then this assumes classes are indexed 0,1,...,numClasses-1 and computes numClasses by finding the maximum label value.
Label validation (ensuring all labels are integers >= 0) needs to be handled elsewhere,
such as in extractLabeledPoints().
Dataset which contains a column labelCol
Maximum number of classes allowed when inferred from data. If numClasses is specified in the metadata, then maxNumClasses is ignored.
number of classes
IllegalArgumentException if metadata does not specify numClasses, and the
actual numClasses exceeds maxNumClasses
Gets the value of a param in the embedded param map or its default value.
Gets the value of a param in the embedded param map or its default value. Throws an exception if neither is set.
Gets a param by its name.
Gets a param by its name.
Tests whether the input param has a default value set.
Tests whether the input param has a default value set.
Tests whether this instance contains a param with a given name.
Tests whether this instance contains a param with a given name.
Criterion used for information gain calculation (case-insensitive).
Criterion used for information gain calculation (case-insensitive). Supported: "entropy" and "gini". (default = gini)
Checks whether a param is explicitly set or has a default value.
Checks whether a param is explicitly set or has a default value.
Checks whether a param is explicitly set.
Checks whether a param is explicitly set.
Param for label column name.
Param for label column name.
Loss function which GBT tries to minimize.
Loss function which GBT tries to minimize. (case-insensitive) Supported: "logistic" (default = logistic)
Maximum number of bins used for discretizing continuous features and for choosing how to split on features at each node.
Maximum number of bins used for discretizing continuous features and for choosing how to split on features at each node. More bins give higher granularity. Must be at least 2 and at least number of categories in any categorical feature. (default = 32)
Maximum depth of the tree (nonnegative).
Maximum depth of the tree (nonnegative). E.g., depth 0 means 1 leaf node; depth 1 means 1 internal node + 2 leaf nodes. (default = 5)
Param for maximum number of iterations (>= 0).
Param for maximum number of iterations (>= 0).
Maximum memory in MB allocated to histogram aggregation.
Maximum memory in MB allocated to histogram aggregation. If too small, then 1 node will be split per iteration, and its aggregates may exceed this size. (default = 256 MB)
Minimum information gain for a split to be considered at a tree node.
Minimum information gain for a split to be considered at a tree node. Should be at least 0.0. (default = 0.0)
Minimum number of instances each child must have after split.
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. Must be at least 1. (default = 1)
Returns all params sorted by their names.
Returns all params sorted by their names. The default implementation uses Java reflection to list all public methods that have no arguments and return Param.
Developer should not use this method in constructor because we cannot guarantee that this variable gets initialized before other params.
Param for prediction column name.
Param for prediction column name.
Param for Column name for predicted class conditional probabilities.
Param for Column name for predicted class conditional probabilities. Note: Not all models output well-calibrated probability estimates! These probabilities should be treated as confidences, not precise probabilities.
Param for raw prediction (a.k.a.
Param for raw prediction (a.k.a. confidence) column name.
Saves this ML instance to the input path, a shortcut of write.save(path).
Saves this ML instance to the input path, a shortcut of write.save(path).
Param for random seed.
Param for random seed.
Sets a parameter in the embedded param map.
Sets a parameter in the embedded param map.
Sets a parameter (by name) in the embedded param map.
Sets a parameter (by name) in the embedded param map.
Sets a parameter in the embedded param map.
Sets a parameter in the embedded param map.
Specifies how often to checkpoint the cached node IDs.
Specifies how often to checkpoint the cached node IDs. E.g. 10 means that the cache will get checkpointed every 10 iterations. This is only used if cacheNodeIds is true and if the checkpoint directory is set in org.apache.spark.SparkContext. Must be at least 1. (default = 10)
Sets default values for a list of params.
Sets default values for a list of params.
Note: Java developers should use the single-parameter setDefault.
Annotating this with varargs can cause compilation failures due to a Scala compiler bug.
See SPARK-9268.
a list of param pairs that specify params and their default values to set respectively. Make sure that the params are initialized before this method gets called.
Sets a default value for a param.
Sets a default value for a param.
param to set the default value. Make sure that this param is initialized before this method gets called.
the default value
The impurity setting is ignored for GBT models.
The impurity setting is ignored for GBT models. Individual trees are built using impurity "Variance."
Param for Step size (a.k.a.
Param for Step size (a.k.a. learning rate) in interval (0, 1] for shrinking the contribution of each estimator. (default = 0.1)
Fraction of the training data used for learning each decision tree, in range (0, 1].
Fraction of the training data used for learning each decision tree, in range (0, 1]. (default = 1.0)
Param for Thresholds in multi-class classification to adjust the probability of predicting each class.
Param for Thresholds in multi-class classification to adjust the probability of predicting each class. Array must have length equal to the number of classes, with values > 0 excepting that at most one value may be 0. The class with largest value p/t is predicted, where p is the original probability of that class and t is the class's threshold.
Train a model using the given dataset and parameters.
Train a model using the given dataset and parameters.
Developers can implement this instead of fit() to avoid dealing with schema validation
and copying parameters into the model.
Training dataset
Fitted model
:: DeveloperApi ::
:: DeveloperApi ::
Check transform validity and derive the output schema from the input schema.
We check validity for interactions between parameters during transformSchema and
raise an exception if any parameter value is invalid. Parameter value checks which
do not depend on other parameters are handled by Param.validate().
Typical implementation should first conduct verification on schema change and parameter validity, including complex parameter interaction checks.
:: DeveloperApi ::
:: DeveloperApi ::
Derives the output schema from the input schema and parameters, optionally with logging.
This should be optimistic. If it is unclear whether the schema will be valid, then it should be assumed valid until proven otherwise.
An immutable unique ID for the object and its derivatives.
An immutable unique ID for the object and its derivatives.
Validates and transforms the input schema with the provided param map.
Validates and transforms the input schema with the provided param map.
input schema
whether this is in fitting
SQL DataType for FeaturesType.
E.g., VectorUDT for vector features.
output schema
Param for name of the column that indicates whether each row is for training or for validation.
Param for name of the column that indicates whether each row is for training or for validation. False indicates training; true indicates validation..
Threshold for stopping early when fit with validation is used.
Threshold for stopping early when fit with validation is used. (This parameter is ignored when fit without validation is used.) The decision to stop early is decided based on this logic: If the current loss on the validation set is greater than 0.01, the diff of validation error is compared to relative tolerance which is validationTol * (current loss on the validation set). If the current loss on the validation set is less than or equal to 0.01, the diff of validation error is compared to absolute tolerance which is validationTol * 0.01.
validationIndicatorCol
Returns an MLWriter instance for this ML instance.
Returns an MLWriter instance for this ML instance.
A list of (hyper-)parameter keys this algorithm can take. Users can set and get the parameter values through setters and getters, respectively.
A list of advanced, expert-only (hyper-)parameter keys this algorithm can take. Users can set and get the parameter values through setters and getters, respectively.
Gradient-Boosted Trees (GBTs) (http://en.wikipedia.org/wiki/Gradient_boosting) learning algorithm for classification. It supports binary labels, as well as both continuous and categorical features.
The implementation is based upon: J.H. Friedman. "Stochastic Gradient Boosting." 1999.
Notes on Gradient Boosting vs. TreeBoost:
Multiclass labels are not currently supported.