Traceback Library

gistfile1.txt

================================================
Failed to save <type 'numpy.ndarray'> to .npy file:
Traceback (most recent call last):
  File "/home/ubuntu/anaconda/lib/python2.7/site-packages/sklearn/externals/joblib/numpy_pickle.py", line 275, in save
    obj, filename = self._write_array(obj, filename)
  File "/home/ubuntu/anaconda/lib/python2.7/site-packages/sklearn/externals/joblib/numpy_pickle.py", line 236, in _write_array
    self.np.save(filename, array)
  File "/home/ubuntu/anaconda/lib/python2.7/site-packages/numpy/lib/npyio.py", line 491, in save
    pickle_kwargs=pickle_kwargs)
  File "/home/ubuntu/anaconda/lib/python2.7/site-packages/numpy/lib/format.py", line 585, in write_array
    array.tofile(fp)
IOError: 1946374200 requested and 1853623286 written

Traceback (most recent call last):
  File "model.py", line 105, in <module>
    run_staged()
  File "model.py", line 92, in run_staged
    sp.train(X, Y)
  File "/mnt/biggiggy/ers-models/src/shared/__init__.py", line 183, in train
    fit_model = grid.fit(X, this_Y)
  File "/home/ubuntu/anaconda/lib/python2.7/site-packages/sklearn/grid_search.py", line 804, in fit
    return self._fit(X, y, ParameterGrid(self.param_grid))
  File "/home/ubuntu/anaconda/lib/python2.7/site-packages/sklearn/grid_search.py", line 553, in _fit
    for parameters in parameter_iterable
  File "/home/ubuntu/anaconda/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.py", line 812, in __call__
    self.retrieve()
  File "/home/ubuntu/anaconda/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.py", line 731, in retrieve
    self._output.extend(job.get())
  File "/home/ubuntu/anaconda/lib/python2.7/multiprocessing/pool.py", line 567, in get
    raise self._value
IOError: [Errno 28] No space left on device

# FIXED (/run/shm) was getting full, setting the JOBLIB_TEMP_FOLDER
# environment variable to a larger volume (e.g, tmp) fixed it
================================================

================================================
Traceback (most recent call last):
  File "src/models.py", line 205, in <module>
    gridsearch_pipeline()
  File "/home/ubuntu/anaconda2/lib/python2.7/site-packages/click/core.py", line 716, in __call__
    return self.main(*args, **kwargs)
  File "/home/ubuntu/anaconda2/lib/python2.7/site-packages/click/core.py", line 696, in main
    rv = self.invoke(ctx)
  File "/home/ubuntu/anaconda2/lib/python2.7/site-packages/click/core.py", line 889, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/home/ubuntu/anaconda2/lib/python2.7/site-packages/click/core.py", line 534, in invoke
    return callback(*args, **kwargs)
  File "src/models.py", line 187, in gridsearch_pipeline
    fit_model = grid.fit(X, Y)
  File "/home/ubuntu/anaconda2/lib/python2.7/site-packages/sklearn/grid_search.py", line 804, in fit
    return self._fit(X, y, ParameterGrid(self.param_grid))
  File "/home/ubuntu/anaconda2/lib/python2.7/site-packages/sklearn/grid_search.py", line 553, in _fit
    for parameters in parameter_iterable
  File "/home/ubuntu/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.py", line 812, in __call__
    self.retrieve()
  File "/home/ubuntu/anaconda2/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.py", line 731, in retrieve
    self._output.extend(job.get())
  File "/home/ubuntu/anaconda2/lib/python2.7/multiprocessing/pool.py", line 567, in get
    raise self._value
struct.error: 'i' format requires -2147483648 <= number <= 2147483647
make: *** [models/339/rf_reg/model.pkl] Error 1

# FIXED: Looks like GridSearchCV fails once training set is large enough:
# https://github.com/scikit-learn/scikit-learn/issues/3313#issuecomment-47373219
# Swap out GridSearchCV for another method or train on a random subset
================================================