def _func_fit(sessionId, objs, datatype, has_weights, **kwargs):
from cuml.cluster.kmeans_mg import KMeansMG as cumlKMeans
handle = get_raft_comm_state(sessionId)["handle"]
if not has_weights:
inp_data = concatenate(objs)
inp_weights = None
else:
inp_data = concatenate([X for X, weights in objs])
inp_weights = concatenate([weights for X, weights in objs])
return cumlKMeans(handle=handle, output_type=datatype,
**kwargs).fit(inp_data, sample_weight=inp_weights)
def _func_fit(sessionId, objs, datatype, **kwargs):
from cuml.cluster.kmeans_mg import KMeansMG as cumlKMeans
handle = worker_state(sessionId)["handle"]
inp_data = concatenate(objs)
return cumlKMeans(handle=handle, output_type=datatype,
**kwargs).fit(inp_data)
def _func_predict_proba_partial(model, input_data, **kwargs):
"""
Whole dataset inference with part of the model (trees at disposal locally).
Transfer dataset instead of model. Interesting when model is larger
than dataset.
"""
X = concatenate(input_data)
with using_output_type('cupy'):
prediction = model.predict_proba(X, **kwargs)
return cp.expand_dims(prediction, axis=1)
def _func_fit(model, input_data, convert_dtype):
X = concatenate([item[0] for item in input_data])
y = concatenate([item[1] for item in input_data])
return model.fit(X, y, convert_dtype)