def _daal4py_compute_starting_centroids(X, X_fptype, nClusters,
cluster_centers_0, verbose,
random_state):
def is_string(s, target_str):
return isinstance(s, str) and s == target_str
is_sparse = sp.isspmatrix(X)
deterministic = False
if is_string(cluster_centers_0, 'k-means++'):
_seed = random_state.randint(np.iinfo('i').max)
plus_plus_method = "plusPlusCSR" if is_sparse else "plusPlusDense"
daal_engine = daal4py.engines_mt19937(fptype=X_fptype,
method="defaultDense",
seed=_seed)
_n_local_trials = 2 + int(np.log(nClusters))
kmeans_init = daal4py.kmeans_init(nClusters,
fptype=X_fptype,
nTrials=_n_local_trials,
method=plus_plus_method,
engine=daal_engine)
kmeans_init_res = kmeans_init.compute(X)
centroids_ = kmeans_init_res.centroids
elif is_string(cluster_centers_0, 'random'):
_seed = random_state.randint(np.iinfo('i').max)
random_method = "randomCSR" if is_sparse else "randomDense"
daal_engine = daal4py.engines_mt19937(seed=_seed,
fptype=X_fptype,
method="defaultDense")
kmeans_init = daal4py.kmeans_init(nClusters,
fptype=X_fptype,
method=random_method,
engine=daal_engine)
kmeans_init_res = kmeans_init.compute(X)
centroids_ = kmeans_init_res.centroids
elif hasattr(cluster_centers_0, '__array__'):
deterministic = True
cc_arr = np.ascontiguousarray(cluster_centers_0, dtype=X.dtype)
_validate_center_shape(X, nClusters, cc_arr)
centroids_ = cc_arr
elif callable(cluster_centers_0):
cc_arr = cluster_centers_0(X, nClusters, random_state)
cc_arr = np.ascontiguousarray(cc_arr, dtype=X.dtype)
_validate_center_shape(X, nClusters, cc_arr)
centroids_ = cc_arr
elif is_string(cluster_centers_0, 'deterministic'):
deterministic = True
default_method = "lloydCSR" if is_sparse else "defaultDense"
kmeans_init = daal4py.kmeans_init(nClusters,
fptype=X_fptype,
method=default_method)
kmeans_init_res = kmeans_init.compute(X)
centroids_ = kmeans_init_res.centroids
else:
raise ValueError(
f"init should be either 'k-means++', 'random', a ndarray or a "
f"callable, got '{cluster_centers_0}' instead.")
if verbose:
print("Initialization complete")
return deterministic, centroids_
def _daal4py_compute_starting_centroids(X, X_fptype, nClusters,
cluster_centers_0, random_state):
def is_string(s, target_str):
return isinstance(s, string_types) and s == target_str
deterministic = False
if is_string(cluster_centers_0, 'k-means++'):
_seed = random_state.randint(np.iinfo('i').max)
daal_engine = daal4py.engines_mt19937(fptype=X_fptype,
method='defaultDense',
seed=_seed)
_n_local_trials = 2 + int(np.log(nClusters))
kmeans_init = daal4py.kmeans_init(nClusters,
fptype=X_fptype,
nTrials=_n_local_trials,
method='plusPlusDense',
engine=daal_engine)
kmeans_init_res = kmeans_init.compute(X)
centroids_ = kmeans_init_res.centroids
elif is_string(cluster_centers_0, 'random'):
_seed = random_state.randint(np.iinfo('i').max)
daal_engine = daal4py.engines_mt19937(seed=_seed,
fptype=X_fptype,
method='defaultDense')
kmeans_init = daal4py.kmeans_init(nClusters,
fptype=X_fptype,
method='randomDense',
engine=daal_engine)
kmeans_init_res = kmeans_init.compute(X)
centroids_ = kmeans_init_res.centroids
elif hasattr(cluster_centers_0, '__array__'):
deterministic = True
cc_arr = np.ascontiguousarray(cluster_centers_0, dtype=X.dtype)
_validate_center_shape(X, nClusters, cc_arr)
centroids_ = cc_arr
elif callable(cluster_centers_0):
cc_arr = cluster_centers_0(X, nClusters, random_state)
cc_arr = np.ascontiguousarray(cc_arr, dtype=X.dtype)
_validate_center_shape(X, nClusters, cc_arr)
centroids_ = cc_arr
elif is_string(cluster_centers_0, 'deterministic'):
deterministic = True
kmeans_init = daal4py.kmeans_init(nClusters,
fptype=X_fptype,
method='defaultDense')
kmeans_init_res = kmeans_init.compute(X)
centroids_ = kmeans_init_res.centroids
else:
raise ValueError(
"Cluster centers should either be 'k-means++', 'random', 'deterministic' or an array"
)
return deterministic, centroids_
def compute(train_data, train_labels, predict_data, method='defaultDense'):
# Configure a training object (5 classes)
train_algo = d4p.decision_forest_classification_training(
5,
fptype='float',
nTrees=10,
minObservationsInLeafNode=8,
featuresPerNode=3,
engine=d4p.engines_mt19937(seed=777),
varImportance='MDI',
bootstrap=True,
resultsToCompute='computeOutOfBagError',
method=method)
# Training result provides (depending on parameters) model,
# outOfBagError, outOfBagErrorPerObservation and/or variableImportance
train_result = train_algo.compute(train_data, train_labels)
# now predict using the model from the training above
predict_algo = d4p.decision_forest_classification_prediction(
nClasses=5,
fptype='float',
resultsToEvaluate="computeClassLabels|computeClassProbabilities",
votingMethod="unweighted")
predict_result = predict_algo.compute(predict_data, train_result.model)
return train_result, predict_result
def main():
# input data file
infile = "./data/batch/df_classification_train.csv"
testfile = "./data/batch/df_classification_test.csv"
# Configure a training object (5 classes)
train_algo = d4p.decision_forest_classification_training(
5,
nTrees=10,
minObservationsInLeafNode=8,
featuresPerNode=3,
engine=d4p.engines_mt19937(seed=777),
varImportance='MDI',
bootstrap=True,
resultsToCompute='computeOutOfBagError')
# Read data. Let's use 3 features per observation
data = read_csv(infile, range(3), t=np.float32)
labels = read_csv(infile, range(3, 4), t=np.float32)
train_result = train_algo.compute(data, labels)
# Traiing result provides (depending on parameters) model, outOfBagError, outOfBagErrorPerObservation and/or variableImportance
# Now let's do some prediction
predict_algo = d4p.decision_forest_classification_prediction(5)
# read test data (with same #features)
pdata = read_csv(testfile, range(3), t=np.float32)
plabels = read_csv(testfile, range(3, 4), t=np.float32)
# now predict using the model from the training above
predict_result = predict_algo.compute(pdata, train_result.model)
# Prediction result provides prediction
assert (predict_result.prediction.shape == (pdata.shape[0], 1))
return (train_result, predict_result, plabels)
def main(readcsv=None, method='defaultDense'):
# Create algorithm
algorithm = d4p.distributions_normal(engine=d4p.engines_mt19937(seed=777))
# Create array and fill with normal distribution
data = np.zeros((1,10))
res = algorithm.compute(data)
assert(np.allclose(data, res.randomNumbers))
assert(np.allclose(data, [[-0.74104167,-0.13616829,-0.13679562,2.40385531,-0.33556821,0.19041699,-0.61331181, 0.95958821,-0.42301092,0.09460208]]))
return data
def main(readcsv=None, method='defaultDense'):
# Create algorithm
algorithm = d4p.distributions_bernoulli(0.5, engine=d4p.engines_mt19937(seed=777))
# Create array and fill with bernoulli distribution
data = np.zeros((1,10))
res = algorithm.compute(data)
assert(np.allclose(data, res.randomNumbers))
assert(np.allclose(data, [[1.0,1.000,1.000,0.000,1.000,0.000,1.000,0.000,1.000,0.000]]))
return data
def main(readcsv=None, method='defaultDense'):
# Create algorithm
algorithm = d4p.distributions_uniform(engine=d4p.engines_mt19937(seed=777))
# Create array and fill with bernoulli distribution
data = np.zeros((1, 10))
res = algorithm.compute(data)
assert (np.allclose(data, res.randomNumbers))
assert (np.allclose(data, [[
0.22933409, 0.44584412, 0.44559617, 0.9918884, 0.36859825, 0.57550881,
0.26983509, 0.83136875, 0.33614365, 0.53768455
]]))
return data
def _daal_fit_regressor(self, X, y, sample_weight=None):
self.n_features_in_ = X.shape[1]
if not sklearn_check_version('1.0'):
self.n_features_ = self.n_features_in_
rs_ = check_random_state(self.random_state)
if not self.bootstrap and self.oob_score:
raise ValueError("Out of bag estimation only available"
" if bootstrap=True")
X_fptype = getFPType(X)
seed_ = rs_.randint(0, np.iinfo('i').max)
# limitation on the number of stream for mt2203 is 6024
# more details here:
# https://oneapi-src.github.io/oneDAL/daal/algorithms/engines/mt2203.html
max_stream_count = 6024
if self.n_estimators <= max_stream_count:
daal_engine = daal4py.engines_mt2203(seed=seed_, fptype=X_fptype)
else:
daal_engine = daal4py.engines_mt19937(seed=seed_, fptype=X_fptype)
_featuresPerNode = _to_absolute_max_features(self.max_features,
X.shape[1],
is_classification=False)
n_samples_bootstrap = _get_n_samples_bootstrap(
n_samples=X.shape[0], max_samples=self.max_samples)
if sample_weight is not None:
sample_weight = [sample_weight]
# create algorithm
dfr_algorithm = daal4py.decision_forest_regression_training(
fptype=getFPType(X),
method='hist' if daal_check_version(
(2021, 'P', 200)) else 'defaultDense',
nTrees=int(self.n_estimators),
observationsPerTreeFraction=n_samples_bootstrap
if self.bootstrap is True else 1.,
featuresPerNode=int(_featuresPerNode),
maxTreeDepth=int(0 if self.max_depth is None else self.max_depth),
minObservationsInLeafNode=(self.min_samples_leaf if isinstance(
self.min_samples_leaf, numbers.Integral) else int(
ceil(self.min_samples_leaf * X.shape[0]))),
engine=daal_engine,
impurityThreshold=float(0.0 if self.min_impurity_split is None else
self.min_impurity_split),
varImportance="MDI",
resultsToCompute="",
memorySavingMode=False,
bootstrap=bool(self.bootstrap),
minObservationsInSplitNode=(self.min_samples_split if isinstance(
self.min_samples_split, numbers.Integral) else int(
ceil(self.min_samples_split * X.shape[0]))),
minWeightFractionInLeafNode=self.min_weight_fraction_leaf,
minImpurityDecreaseInSplitNode=self.min_impurity_decrease,
maxLeafNodes=0 if self.max_leaf_nodes is None else self.max_leaf_nodes,
maxBins=self.maxBins,
minBinSize=self.minBinSize)
self._cached_estimators_ = None
dfr_trainingResult = dfr_algorithm.compute(X, y, sample_weight)
# get resulting model
model = dfr_trainingResult.model
self.daal_model_ = model
# compute oob_score_
#if self.oob_score:
# self.estimators_ = self._estimators_
# self._set_oob_score(X, y)
return self
def _daal_fit_classifier(self, X, y, sample_weight=None):
y = check_array(y, ensure_2d=False, dtype=None)
y, expanded_class_weight = self._validate_y_class_weight(y)
n_classes_ = self.n_classes_[0]
self.n_features_in_ = X.shape[1]
if not sklearn_check_version('1.0'):
self.n_features_ = self.n_features_in_
if expanded_class_weight is not None:
if sample_weight is not None:
sample_weight = sample_weight * expanded_class_weight
else:
sample_weight = expanded_class_weight
if sample_weight is not None:
sample_weight = [sample_weight]
rs_ = check_random_state(self.random_state)
seed_ = rs_.randint(0, np.iinfo('i').max)
if n_classes_ < 2:
raise ValueError(
"Training data only contain information about one class.")
# create algorithm
X_fptype = getFPType(X)
# limitation on the number of stream for mt2203 is 6024
# more details here:
# https://oneapi-src.github.io/oneDAL/daal/algorithms/engines/mt2203.html
max_stream_count = 6024
if self.n_estimators <= max_stream_count:
daal_engine = daal4py.engines_mt2203(seed=seed_, fptype=X_fptype)
else:
daal_engine = daal4py.engines_mt19937(seed=seed_, fptype=X_fptype)
features_per_node_ = _to_absolute_max_features(
self.max_features, X.shape[1], is_classification=True)
n_samples_bootstrap_ = _get_n_samples_bootstrap(
n_samples=X.shape[0],
max_samples=self.max_samples
)
if not self.bootstrap and self.oob_score:
raise ValueError("Out of bag estimation only available"
" if bootstrap=True")
dfc_algorithm = daal4py.decision_forest_classification_training(
nClasses=int(n_classes_),
fptype=X_fptype,
method='hist',
nTrees=int(self.n_estimators),
observationsPerTreeFraction=n_samples_bootstrap_
if self.bootstrap is True else 1.,
featuresPerNode=int(features_per_node_),
maxTreeDepth=int(0 if self.max_depth is None else self.max_depth),
minObservationsInLeafNode=(self.min_samples_leaf
if isinstance(
self.min_samples_leaf, numbers.Integral)
else int(ceil(
self.min_samples_leaf * X.shape[0]))),
engine=daal_engine,
impurityThreshold=float(
0.0 if self.min_impurity_split is None else self.min_impurity_split),
varImportance="MDI",
resultsToCompute=(
"computeOutOfBagErrorAccuracy|computeOutOfBagErrorDecisionFunction"
if self.oob_score
else ""),
memorySavingMode=False,
bootstrap=bool(self.bootstrap),
minObservationsInSplitNode=(self.min_samples_split
if isinstance(
self.min_samples_split, numbers.Integral)
else int(ceil(
self.min_samples_split * X.shape[0]))),
minWeightFractionInLeafNode=self.min_weight_fraction_leaf,
minImpurityDecreaseInSplitNode=self.min_impurity_decrease,
maxLeafNodes=0 if self.max_leaf_nodes is None else self.max_leaf_nodes,
maxBins=self.maxBins,
minBinSize=self.minBinSize
)
self._cached_estimators_ = None
# compute
dfc_trainingResult = dfc_algorithm.compute(X, y, sample_weight)
# get resulting model
model = dfc_trainingResult.model
self.daal_model_ = model
if self.oob_score:
self.oob_score_ = dfc_trainingResult.outOfBagErrorAccuracy[0][0]
self.oob_decision_function_ = dfc_trainingResult.outOfBagErrorDecisionFunction
if self.oob_decision_function_.shape[-1] == 1:
self.oob_decision_function_ = self.oob_decision_function_.squeeze(axis=-1)
return self