SMOTE on pipeline

[flolas]

SMOTE on pipeline

[stavskal]

I would like to know that too. I'm trying to use UnderSampler in sklearn pipeline and I get some errors

[fmfn]

Hum, I forgot about this issue, I apologize. Can you please post the error msg?

[stavskal]

So the following error occurs when I add the UnderSampler to the pipeline, otherwise it works just fine:

File "pipeTrain.py", line 56, in
score = cross_val_score(pipe,X,Y,cv=3)
File "/home/tabrianos/Desktop/Thesis/Database/venv/local/lib/python2.7/site-packages/sklearn/cross_validation.py", line 1361, in cross_val_score
for train, test in cv)
File "/home/tabrianos/Desktop/Thesis/Database/venv/local/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.py", line 659, in call
self.dispatch(function, args, kwargs)
File "/home/tabrianos/Desktop/Thesis/Database/venv/local/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.py", line 406, in dispatch
job = ImmediateApply(func, args, kwargs)
File "/home/tabrianos/Desktop/Thesis/Database/venv/local/lib/python2.7/site-packages/sklearn/externals/joblib/parallel.py", line 140, in init
self.results = func(_args, *_kwargs)
File "/home/tabrianos/Desktop/Thesis/Database/venv/local/lib/python2.7/site-packages/sklearn/cross_validation.py", line 1459, in _fit_and_score
estimator.fit(X_train, y_train, *_fit_params)
File "/home/tabrianos/Desktop/Thesis/Database/venv/local/lib/python2.7/site-packages/sklearn/pipeline.py", line 141, in fit
self.steps[-1][-1].fit(Xt, y, *_fit_params)
File "/home/tabrianos/Desktop/Thesis/Database/venv/local/lib/python2.7/site-packages/sklearn/ensemble/forest.py", line 195, in fit
X = check_array(X, dtype=DTYPE, accept_sparse="csc")
File "/home/tabrianos/Desktop/Thesis/Database/venv/local/lib/python2.7/site-packages/sklearn/utils/validation.py", line 337, in check_array
array = np.atleast_2d(array)
File "/home/tabrianos/Desktop/Thesis/Database/venv/local/lib/python2.7/site-packages/numpy/core/shape_base.py", line 100, in atleast_2d
ary = asanyarray(ary)
File "/home/tabrianos/Desktop/Thesis/Database/venv/local/lib/python2.7/site-packages/numpy/core/numeric.py", line 525, in asanyarray
return array(a, dtype, copy=False, order=order, subok=True)
ValueError: could not broadcast input array from shape (200,26) into shape (200)

Code looks like this:

X=np.load('numdata/epochFeats.npy')
Y=np.load('numdata/epochLabels.npy')
forest = RandomForestClassifier(n_estimators=100, n_jobs = -1)
us = UnderSampler(verbose=True)
pipe = Pipeline(steps=[('UnderSampler',us) ,('forest',forest)])
score = cross_val_score(pipe,X,Y,cv=3)

Sorry for bad formating