def predict(dataset, fitmodel_url, save_results=True, show=False):
"""
Predict the closest clusters for the datapoints in input.
"""
from disco.job import Job
from disco.worker.pipeline.worker import Worker, Stage
from disco.core import result_iterator
if "kmeans_fitmodel" not in fitmodel_url:
raise Exception("Incorrect fit model.")
job = Job(worker=Worker(save_results=save_results))
job.params = dict(dataset.params.items() + mean_point_center.items())
job.params["centers"] = [
(i, c) for i, c in result_iterator(fitmodel_url["kmeans_fitmodel"])
]
job.pipeline = [("split",
Stage("kmeans_predict",
input_chain=dataset.params["input_chain"],
init=simple_init,
process=predict_map))]
job.run(input=dataset.params["data_tag"], name="kmeans_predict")
return job.wait(show=show)
def predict(dataset, fitmodel_url, save_results=True, show=False):
"""
Predict the closest clusters for the datapoints in input.
"""
from disco.job import Job
from disco.worker.pipeline.worker import Worker, Stage
from disco.core import result_iterator
if "kmeans_fitmodel" not in fitmodel_url:
raise Exception("Incorrect fit model.")
job = Job(worker=Worker(save_results=save_results))
job.params = dict(dataset.params.items() + mean_point_center.items())
job.params["centers"] = [(i, c) for i, c in result_iterator(fitmodel_url["kmeans_fitmodel"])]
job.pipeline = [
(
"split",
Stage("kmeans_predict", input_chain=dataset.params["input_chain"], init=simple_init, process=predict_map),
)
]
job.run(input=dataset.params["data_tag"], name="kmeans_predict")
return job.wait(show=show)
def fit(dataset,
n_clusters=5,
max_iterations=10,
random_state=None,
save_results=True,
show=False):
"""
Optimize k-clustering for `iterations` iterations with cluster
center definitions as given in `center`.
"""
from disco.job import Job
from disco.worker.pipeline.worker import Worker, Stage
from disco.core import result_iterator
try:
n_clusters = int(n_clusters)
max_iterations = int(max_iterations)
if n_clusters < 2:
raise Exception("Parameter n_clusters should be greater than 1.")
if max_iterations < 1:
raise Exception(
"Parameter max_iterations should be greater than 0.")
except ValueError:
raise Exception("Parameters should be numerical.")
job = Job(worker=Worker(save_results=save_results))
job.pipeline = [("split",
Stage("kmeans_init_map",
input_chain=dataset.params["input_chain"],
init=map_init,
process=random_init_map)),
('group_label',
Stage("kmeans_init_reduce",
process=estimate_reduce,
init=simple_init,
combine=True))]
job.params = dict(dataset.params.items() + mean_point_center.items())
job.params['seed'] = random_state
job.params['k'] = n_clusters
job.run(input=dataset.params["data_tag"], name="kmeans_init")
init = job.wait(show=show)
centers = [(i, c) for i, c in result_iterator(init)]
for j in range(max_iterations):
job = Job(worker=Worker(save_results=save_results))
job.params = dict(dataset.params.items() + mean_point_center.items())
job.params['k'] = n_clusters
job.params['centers'] = centers
job.pipeline = [('split',
Stage("kmeans_map_iter_%s" % (j + 1, ),
input_chain=dataset.params["input_chain"],
process=estimate_map,
init=simple_init)),
('group_label',
Stage("kmeans_reduce_iter_%s" % (j + 1, ),
process=estimate_reduce,
init=simple_init,
combine=True))]
job.run(input=dataset.params["data_tag"],
name='kmeans_iter_%d' % (j + 1, ))
fitmodel_url = job.wait(show=show)
centers = [(i, c) for i, c in result_iterator(fitmodel_url)]
return {"kmeans_fitmodel": fitmodel_url} # return results url
def fit(dataset, n_clusters=5, max_iterations=10, random_state=None, save_results=True, show=False):
"""
Optimize k-clustering for `iterations` iterations with cluster
center definitions as given in `center`.
"""
from disco.job import Job
from disco.worker.pipeline.worker import Worker, Stage
from disco.core import result_iterator
try:
n_clusters = int(n_clusters)
max_iterations = int(max_iterations)
if n_clusters < 2:
raise Exception("Parameter n_clusters should be greater than 1.")
if max_iterations < 1:
raise Exception("Parameter max_iterations should be greater than 0.")
except ValueError:
raise Exception("Parameters should be numerical.")
job = Job(worker=Worker(save_results=save_results))
job.pipeline = [
(
"split",
Stage("kmeans_init_map", input_chain=dataset.params["input_chain"], init=map_init, process=random_init_map),
),
("group_label", Stage("kmeans_init_reduce", process=estimate_reduce, init=simple_init, combine=True)),
]
job.params = dict(dataset.params.items() + mean_point_center.items())
job.params["seed"] = random_state
job.params["k"] = n_clusters
job.run(input=dataset.params["data_tag"], name="kmeans_init")
init = job.wait(show=show)
centers = [(i, c) for i, c in result_iterator(init)]
for j in range(max_iterations):
job = Job(worker=Worker(save_results=save_results))
job.params = dict(dataset.params.items() + mean_point_center.items())
job.params["k"] = n_clusters
job.params["centers"] = centers
job.pipeline = [
(
"split",
Stage(
"kmeans_map_iter_%s" % (j + 1,),
input_chain=dataset.params["input_chain"],
process=estimate_map,
init=simple_init,
),
),
(
"group_label",
Stage("kmeans_reduce_iter_%s" % (j + 1,), process=estimate_reduce, init=simple_init, combine=True),
),
]
job.run(input=dataset.params["data_tag"], name="kmeans_iter_%d" % (j + 1,))
fitmodel_url = job.wait(show=show)
centers = [(i, c) for i, c in result_iterator(fitmodel_url)]
return {"kmeans_fitmodel": fitmodel_url} # return results url
