This code that uses RandomizedSearchCV works fine in 0.15.2:
import pandas as pd
from sklearn.pipeline import Pipeline
from sklearn.datasets import load_iris
from sklearn.ensemble import RandomForestClassifier
from sklearn.grid_search import RandomizedSearchCV
iris = load_iris()
X = iris.data
y = iris.target
pipeline = Pipeline([("rf", RandomForestClassifier())])
params = { "rf__n_estimators": range(10,50),
"rf__max_depth": range(5,10),
"rf__max_features": range(1, 5),
"rf__min_samples_split": range(5,101),
"rf__min_samples_leaf": range(20,50),
"rf__max_leaf_nodes": range(200, 350)}
random_search = RandomizedSearchCV(pipeline, params).fit(X, y)
It does not work in 0.16.1. When I kill the process, here is the Traceback:
---------------------------------------------------------------------------
KeyboardInterrupt Traceback (most recent call last)
<ipython-input-108-8794e7d30469> in <module>()
24 random_search = RandomizedSearchCV(pipeline, params,
n_iter=n_iter_search, cv=2, refit=True, n_jobs=1)
25
---> 26 random_search.fit(X_iris, y_iris)
/.../lib/python2.7/site-packages/sklearn/grid_search.pyc in fit(self, X, y)
896 self.n_iter,
897
random_state=self.random_state)
--> 898 return self._fit(X, y, sampled_params)
/.../lib/python2.7/site-packages/sklearn/grid_search.pyc in _fit(self, X, y,
parameter_iterable)
503 self.fit_params,
return_parameters=True,
504 error_score=self.error_score)
--> 505 for parameters in parameter_iterable
506 for train, test in cv)
507
/.../lib/python2.7/site-packages/sklearn/externals/joblib/parallel.pyc in
__call__(self, iterable)
656 os.environ[JOBLIB_SPAWNED_PROCESS] = '1'
657 self._iterating = True
--> 658 for function, args, kwargs in iterable:
659 self.dispatch(function, args, kwargs)
660
/.../lib/python2.7/site-packages/sklearn/grid_search.pyc in <genexpr>(***failed
resolving arguments***)
499 pre_dispatch=pre_dispatch
500 )(
--> 501 delayed(_fit_and_score)(clone(base_estimator), X, y,
self.scorer_,
502 train, test, self.verbose,
parameters,
503 self.fit_params,
return_parameters=True,
/.../lib/python2.7/site-packages/sklearn/grid_search.pyc in __iter__(self)
180 if all_lists:
181 # get complete grid and yield from it
--> 182 param_grid = list(ParameterGrid(self.param_distributions))
183 grid_size = len(param_grid)
184
/.../lib/python2.7/site-packages/sklearn/grid_search.pyc in __iter__(self)
100 keys, values = zip(*items)
101 for v in product(*values):
--> 102 params = dict(zip(keys, v))
103 yield params
104
KeyboardInterrupt:
Any thoughts?
------------------------------------------------------------------------------
Monitor 25 network devices or servers for free with OpManager!
OpManager is web-based network management software that monitors
network devices and physical & virtual servers, alerts via email & sms
for fault. Monitor 25 devices for free with no restriction. Download now
http://ad.doubleclick.net/ddm/clk/292181274;119417398;o
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
