class VigraRandomForest(object):
def __init__(self, ntrees=255, use_feature_importance=False,
sample_classes_individually=False):
self.rf = BaseVigraRandomForest(treeCount=ntrees,
sample_classes_individually=sample_classes_individually)
self.use_feature_importance = use_feature_importance
self.sample_classes_individually = sample_classes_individually
def fit(self, features, labels):
features = self.check_features_vector(features)
labels = self.check_labels_vector(labels)
if self.use_feature_importance:
self.oob, self.feature_importance = \
self.rf.learnRFWithFeatureSelection(features, labels)
else:
self.oob = self.rf.learnRF(features, labels)
return self
def predict_proba(self, features):
features = self.check_features_vector(features)
return self.rf.predictProbabilities(features)
def predict(self, features):
features = self.check_features_vector(features)
return self.rf.predictLabels(features)
def check_features_vector(self, features):
if features.dtype != np.float32:
features = features.astype(np.float32)
if features.ndim == 1:
features = features[np.newaxis, :]
return features
def check_labels_vector(self, labels):
if labels.dtype != np.uint32:
if len(np.unique(labels[labels < 0])) == 1 \
and not (labels==0).any():
labels[labels < 0] = 0
else:
labels = labels + labels.min()
labels = labels.astype(np.uint32)
labels = labels.reshape((labels.size, 1))
return labels
def save_to_disk(self, fn, rfgroupname='rf'):
self.rf.writeHDF5(fn, rfgroupname)
attr_list = ['oob', 'feature_importance', 'use_feature_importance',
'feature_description']
f = h5py.File(fn)
for attr in attr_list:
if hasattr(self, attr):
f[rfgroupname].attrs[attr] = getattr(self, attr)
def load_from_disk(self, fn, rfgroupname='rf'):
self.rf = BaseVigraRandomForest(str(fn), rfgroupname)
f = h5py.File(fn, 'r')
for attr in f[rfgroupname].attrs:
print("f[%s] = %s" % (attr, f[rfgroupname].attrs[attr]))
setattr(self, attr, f[rfgroupname].attrs[attr])
class RandomForest(object):
def __init__(self, ntrees=255, use_feature_importance=False,
sample_classes_individually=False):
self.rf = VigraRandomForest(treeCount=ntrees,
sample_classes_individually=sample_classes_individually)
self.use_feature_importance = use_feature_importance
self.sample_classes_individually=sample_classes_individually
def fit(self, features, labels, **kwargs):
features = self.check_features_vector(features)
labels = self.check_labels_vector(labels)
if self.use_feature_importance:
self.oob, self.feature_importance = \
self.rf.learnRFWithFeatureSelection(features, labels)
else:
self.oob = self.rf.learnRF(features, labels)
return self
def predict_proba(self, features):
features = self.check_features_vector(features)
return self.rf.predictProbabilities(features)
def predict(self, features):
features = self.check_features_vector(features)
return self.rf.predictLabels(features)
def check_features_vector(self, features):
if features.dtype != float32:
features = features.astype(float32)
if features.ndim == 1:
features = features[newaxis,:]
return features
def check_labels_vector(self, labels):
if labels.dtype != uint32:
if len(unique(labels[labels < 0])) == 1 and not (labels==0).any():
labels[labels < 0] = 0
else:
labels = labels + labels.min()
labels = labels.astype(uint32)
labels = labels.reshape((labels.size, 1))
return labels
def save_to_disk(self, fn, rfgroupname='rf', overwrite=True):
self.rf.writeHDF5(fn, rfgroupname, overwrite)
attr_list = ['oob', 'feature_importance', 'use_feature_importance']
f = h5py.File(fn)
for attr in attr_list:
if hasattr(self, attr):
f[attr] = getattr(self, attr)
def load_from_disk(self, fn, rfgroupname='rf'):
self.rf = VigraRandomForest(fn, rfgroupname)
f = h5py.File(fn, 'r')
groups = []
f.visit(groups.append)
attrs = [g for g in groups if not g.startswith(rfgroupname)]
for attr in attrs:
setattr(self, attr, array(f[attr]))
class VigraRandomForest(object):
def __init__(self,
ntrees=255,
use_feature_importance=False,
sample_classes_individually=False):
self.rf = BaseVigraRandomForest(
treeCount=ntrees,
sample_classes_individually=sample_classes_individually)
self.use_feature_importance = use_feature_importance
self.sample_classes_individually = sample_classes_individually
def fit(self, features, labels):
features = self.check_features_vector(features)
labels = self.check_labels_vector(labels)
if self.use_feature_importance:
self.oob, self.feature_importance = \
self.rf.learnRFWithFeatureSelection(features, labels)
else:
self.oob = self.rf.learnRF(features, labels)
return self
def predict_proba(self, features):
features = self.check_features_vector(features)
return self.rf.predictProbabilities(features)
def predict(self, features):
features = self.check_features_vector(features)
return self.rf.predictLabels(features)
def check_features_vector(self, features):
if features.dtype != np.float32:
features = features.astype(np.float32)
if features.ndim == 1:
features = features[np.newaxis, :]
return features
def check_labels_vector(self, labels):
if labels.dtype != np.uint32:
if len(np.unique(labels[labels < 0])) == 1 \
and not (labels==0).any():
labels[labels < 0] = 0
else:
labels = labels + labels.min()
labels = labels.astype(np.uint32)
labels = labels.reshape((labels.size, 1))
return labels
def save_to_disk(self, fn, rfgroupname='rf'):
self.rf.writeHDF5(fn, rfgroupname)
attr_list = [
'oob', 'feature_importance', 'use_feature_importance',
'feature_description'
]
f = h5py.File(fn)
for attr in attr_list:
if hasattr(self, attr):
f[rfgroupname].attrs[attr] = getattr(self, attr)
def load_from_disk(self, fn, rfgroupname='rf'):
self.rf = BaseVigraRandomForest(str(fn), rfgroupname)
f = h5py.File(fn, 'r')
for attr in f[rfgroupname].attrs:
print("f[%s] = %s" % (attr, f[rfgroupname].attrs[attr]))
setattr(self, attr, f[rfgroupname].attrs[attr])
class RandomForest(object):
def __init__(self,
ntrees=255,
use_feature_importance=False,
sample_classes_individually=False):
self.rf = VigraRandomForest(
treeCount=ntrees,
sample_classes_individually=sample_classes_individually)
self.use_feature_importance = use_feature_importance
self.sample_classes_individually = sample_classes_individually
def fit(self, features, labels, **kwargs):
features = self.check_features_vector(features)
labels = self.check_labels_vector(labels)
if self.use_feature_importance:
self.oob, self.feature_importance = \
self.rf.learnRFWithFeatureSelection(features, labels)
else:
self.oob = self.rf.learnRF(features, labels)
return self
def predict_proba(self, features):
features = self.check_features_vector(features)
return self.rf.predictProbabilities(features)
def predict(self, features):
features = self.check_features_vector(features)
return self.rf.predictLabels(features)
def check_features_vector(self, features):
if features.dtype != float32:
features = features.astype(float32)
if features.ndim == 1:
features = features[newaxis, :]
return features
def check_labels_vector(self, labels):
if labels.dtype != uint32:
if len(unique(
labels[labels < 0])) == 1 and not (labels == 0).any():
labels[labels < 0] = 0
else:
labels = labels + labels.min()
labels = labels.astype(uint32)
labels = labels.reshape((labels.size, 1))
return labels
def save_to_disk(self, fn, rfgroupname='rf', overwrite=True):
self.rf.writeHDF5(fn, rfgroupname, overwrite)
attr_list = ['oob', 'feature_importance', 'use_feature_importance']
f = h5py.File(fn)
for attr in attr_list:
if hasattr(self, attr):
f[attr] = getattr(self, attr)
def load_from_disk(self, fn, rfgroupname='rf'):
self.rf = VigraRandomForest(fn, rfgroupname)
f = h5py.File(fn, 'r')
groups = []
f.visit(groups.append)
attrs = [g for g in groups if not g.startswith(rfgroupname)]
for attr in attrs:
setattr(self, attr, array(f[attr]))
