Alien-XGBoost
view release on metacpan or search on metacpan
xgboost/jvm-packages/pom.xml view on Meta::CPAN
<failOnViolation>true</failOnViolation>
<includeTestSourceDirectory>true</includeTestSourceDirectory>
<sourceDirectory>${basedir}/src/main/scala</sourceDirectory>
<testSourceDirectory>${basedir}/src/test/scala</testSourceDirectory>
<configLocation>scalastyle-config.xml</configLocation>
<outputEncoding>UTF-8</outputEncoding>
</configuration>
<executions>
<execution>
<id>checkstyle</id>
<phase>validate</phase>
<goals>
<goal>check</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-javadoc-plugin</artifactId>
<version>2.10.3</version>
xgboost/jvm-packages/pom.xml view on Meta::CPAN
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-checkstyle-plugin</artifactId>
<version>2.17</version>
<configuration>
<configLocation>checkstyle.xml</configLocation>
<failOnViolation>true</failOnViolation>
</configuration>
<executions>
<execution>
<id>checkstyle</id>
<phase>validate</phase>
<goals>
<goal>check</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>net.alchim31.maven</groupId>
<artifactId>scala-maven-plugin</artifactId>
<version>3.2.2</version>
xgboost/jvm-packages/xgboost4j-spark/src/test/scala/ml/dmlc/xgboost4j/scala/spark/XGBoostGeneralSuite.scala view on Meta::CPAN
import ml.dmlc.xgboost4j.scala.DMatrix
import ml.dmlc.xgboost4j.scala.rabit.RabitTracker
import org.apache.spark.SparkContext
import org.apache.spark.ml.feature.{LabeledPoint => MLLabeledPoint}
import org.apache.spark.ml.linalg.{DenseVector, Vectors, Vector => SparkVector}
import org.apache.spark.rdd.RDD
import org.scalatest.FunSuite
class XGBoostGeneralSuite extends FunSuite with PerTest {
test("test Rabit allreduce to validate Scala-implemented Rabit tracker") {
val vectorLength = 100
val rdd = sc.parallelize(
(1 to numWorkers * vectorLength).toArray.map { _ => Random.nextFloat() }, numWorkers).cache()
val tracker = new RabitTracker(numWorkers)
tracker.start(0)
val trackerEnvs = tracker.getWorkerEnvs
val collectedAllReduceResults = new LinkedBlockingDeque[Array[Float]]()
val rawData = rdd.mapPartitions { iter =>
xgboost/jvm-packages/xgboost4j-spark/src/test/scala/ml/dmlc/xgboost4j/scala/spark/XGBoostGeneralSuite.scala view on Meta::CPAN
assert(loadedEvalResults == evalResults)
}
test("test save and load of different types of models") {
import DataUtils._
val tempDir = Files.createTempDirectory("xgboosttest-")
val tempFile = Files.createTempFile(tempDir, "", "")
val trainingRDD = sc.parallelize(Classification.train).map(_.asML)
var paramMap = Map("eta" -> "1", "max_depth" -> "6", "silent" -> "1",
"objective" -> "reg:linear")
// validate regression model
var xgBoostModel = XGBoost.trainWithRDD(trainingRDD, paramMap, round = 5,
nWorkers = numWorkers, useExternalMemory = false)
xgBoostModel.setFeaturesCol("feature_col")
xgBoostModel.setLabelCol("label_col")
xgBoostModel.setPredictionCol("prediction_col")
xgBoostModel.saveModelAsHadoopFile(tempFile.toFile.getAbsolutePath)
var loadedXGBoostModel = XGBoost.loadModelFromHadoopFile(tempFile.toFile.getAbsolutePath)
assert(loadedXGBoostModel.isInstanceOf[XGBoostRegressionModel])
assert(loadedXGBoostModel.getFeaturesCol == "feature_col")
assert(loadedXGBoostModel.getLabelCol == "label_col")
xgboost/python-package/xgboost/core.py view on Meta::CPAN
@feature_names.setter
def feature_names(self, feature_names):
"""Set feature names (column labels).
Parameters
----------
feature_names : list or None
Labels for features. None will reset existing feature names
"""
if feature_names is not None:
# validate feature name
if not isinstance(feature_names, list):
feature_names = list(feature_names)
if len(feature_names) != len(set(feature_names)):
raise ValueError('feature_names must be unique')
if len(feature_names) != self.num_col():
msg = 'feature_names must have the same length as data'
raise ValueError(msg)
# prohibit to use symbols may affect to parse. e.g. []<
if not all(isinstance(f, STRING_TYPES) and
not any(x in f for x in set(('[', ']', '<')))
xgboost/python-package/xgboost/core.py view on Meta::CPAN
params : dict
Parameters for boosters.
cache : list
List of cache items.
model_file : string
Path to the model file.
"""
for d in cache:
if not isinstance(d, DMatrix):
raise TypeError('invalid cache item: {}'.format(type(d).__name__))
self._validate_features(d)
dmats = c_array(ctypes.c_void_p, [d.handle for d in cache])
self.handle = ctypes.c_void_p()
_check_call(_LIB.XGBoosterCreate(dmats, c_bst_ulong(len(cache)),
ctypes.byref(self.handle)))
self.set_param({'seed': 0})
self.set_param(params or {})
if model_file is not None:
self.load_model(model_file)
xgboost/python-package/xgboost/core.py view on Meta::CPAN
----------
dtrain : DMatrix
Training data.
iteration : int
Current iteration number.
fobj : function
Customized objective function.
"""
if not isinstance(dtrain, DMatrix):
raise TypeError('invalid training matrix: {}'.format(type(dtrain).__name__))
self._validate_features(dtrain)
if fobj is None:
_check_call(_LIB.XGBoosterUpdateOneIter(self.handle, ctypes.c_int(iteration),
dtrain.handle))
else:
pred = self.predict(dtrain)
grad, hess = fobj(pred, dtrain)
self.boost(dtrain, grad, hess)
def boost(self, dtrain, grad, hess):
xgboost/python-package/xgboost/core.py view on Meta::CPAN
The training DMatrix.
grad : list
The first order of gradient.
hess : list
The second order of gradient.
"""
if len(grad) != len(hess):
raise ValueError('grad / hess length mismatch: {} / {}'.format(len(grad), len(hess)))
if not isinstance(dtrain, DMatrix):
raise TypeError('invalid training matrix: {}'.format(type(dtrain).__name__))
self._validate_features(dtrain)
_check_call(_LIB.XGBoosterBoostOneIter(self.handle, dtrain.handle,
c_array(ctypes.c_float, grad),
c_array(ctypes.c_float, hess),
c_bst_ulong(len(grad))))
def eval_set(self, evals, iteration=0, feval=None):
# pylint: disable=invalid-name
"""Evaluate a set of data.
xgboost/python-package/xgboost/core.py view on Meta::CPAN
Returns
-------
result: str
Evaluation result string.
"""
for d in evals:
if not isinstance(d[0], DMatrix):
raise TypeError('expected DMatrix, got {}'.format(type(d[0]).__name__))
if not isinstance(d[1], STRING_TYPES):
raise TypeError('expected string, got {}'.format(type(d[1]).__name__))
self._validate_features(d[0])
dmats = c_array(ctypes.c_void_p, [d[0].handle for d in evals])
evnames = c_array(ctypes.c_char_p, [c_str(d[1]) for d in evals])
msg = ctypes.c_char_p()
_check_call(_LIB.XGBoosterEvalOneIter(self.handle, ctypes.c_int(iteration),
dmats, evnames,
c_bst_ulong(len(evals)),
ctypes.byref(msg)))
res = msg.value.decode()
if feval is not None:
xgboost/python-package/xgboost/core.py view on Meta::CPAN
The name of the dataset.
iteration : int, optional
The current iteration number.
Returns
-------
result: str
Evaluation result string.
"""
self._validate_features(data)
return self.eval_set([(data, name)], iteration)
def predict(self, data, output_margin=False, ntree_limit=0, pred_leaf=False,
pred_contribs=False):
"""
Predict with data.
NOTE: This function is not thread safe.
For each booster object, predict can only be called from one thread.
If you want to run prediction using multiple thread, call bst.copy() to make copies
xgboost/python-package/xgboost/core.py view on Meta::CPAN
prediction : numpy array
"""
option_mask = 0x00
if output_margin:
option_mask |= 0x01
if pred_leaf:
option_mask |= 0x02
if pred_contribs:
option_mask |= 0x04
self._validate_features(data)
length = c_bst_ulong()
preds = ctypes.POINTER(ctypes.c_float)()
_check_call(_LIB.XGBoosterPredict(self.handle, data.handle,
ctypes.c_int(option_mask),
ctypes.c_uint(ntree_limit),
ctypes.byref(length),
ctypes.byref(preds)))
preds = ctypes2numpy(preds, length.value, np.float32)
if pred_leaf:
xgboost/python-package/xgboost/core.py view on Meta::CPAN
else:
fmap[fid] += 1
gmap[fid] += g
# calculate average value (gain/cover) for each feature
for fid in gmap:
gmap[fid] = gmap[fid] / fmap[fid]
return gmap
def _validate_features(self, data):
"""
Validate Booster and data's feature_names are identical.
Set feature_names and feature_types from DMatrix
"""
if self.feature_names is None:
self.feature_names = data.feature_names
self.feature_types = data.feature_types
else:
# Booster can't accept data with different feature names
if self.feature_names != data.feature_names:
xgboost/src/common/quantile.h view on Meta::CPAN
}
/*!
* \brief copy content from src
* \param src source sketch
*/
inline void CopyFrom(const WQSummary &src) {
size = src.size;
std::memcpy(data, src.data, sizeof(Entry) * size);
}
/*!
* \brief debug function, validate whether the summary
* run consistency check to check if it is a valid summary
* \param eps the tolerate error level, used when RType is floating point and
* some inconsistency could occur due to rounding error
*/
inline void CheckValid(RType eps) const {
for (size_t i = 0; i < size; ++i) {
data[i].CheckValid(eps);
if (i != 0) {
CHECK(data[i].rmin >= data[i - 1].rmin + data[i - 1].wmin) << "rmin range constraint";
CHECK(data[i].rmax >= data[i - 1].rmax + data[i].wmin) << "rmax range constraint";
( run in 0.341 second using v1.01-cache-2.11-cpan-a5abf4f5562 )