def crossgrid(self, griddic, cv=None):
"""
perform a crossvalidation procedure for mparameters in grid and cv-sample cv
inputs
grid: dictionary of the form
dict(ESTIMATORNAME1__PARAMETER1 = PARAMLST1,
ESTIMATORNAME2__PARAMETER2 = PARAMLST2,
...
)
cv: crossvalidation array of the form [IDn1, IDn2,...IDnN]
"""
# initialize cv procedure
if cv != None:
# if cv not empty overwrite existing cv procedure
self.cv = cv
elif cv == None and self.cv == None:
# if no cv procedure has been specified set the classical l20o
print('ATTENTION:\tNo CV procedure specified, proceeding with reduced l20o.')
cv = cv.leave_x_out(self.Y,20)
# initialize the _gridsearch attribute
# need to include how to create the dictionary from the input
self._gridsearch = sk.grid_search.GridSearchCV(self._pipe, griddic, n_jobs=-1) # @UndefinedVariable
# fit the CV grid
self._gridsearch.fit(self.X,self.Y)
pipe.setpipe(['GB'])
# cvcounter test
print('Pipe.cvcounter =\t'+str(pipe.cvcounter))
print("X size: " + str(np.shape(X)))
print("Y size: " + str(np.shape(Y)))
# test initialization of grid parameters
# FFS + RF dic
# griddic = dict(FFS__k=[50,100],RF__n_estimators=[100,200])
# FFS + FDA dic
griddic = dict(GB__n_estimators=[100,200,300],GB__learning_rate=[0.1,0.3,0.5],GB__max_features=["Auto",100.],GB__max_depth=[3,5,10])
#griddic = dict();
pipe.crossgrid(griddic,crossval=cv.leave_x_out(pipe.Y, 50, nsamples=100))
#pipe.crossgrid(griddic,crossval=cv.leave_x_out(pipe.Y, 20, nsamples=300))
print(pipe.return_score())
print(pipe._gridsearch.grid_scores_)
print(pipe._pipe.named_steps.keys())
print(pipe._pipe)
pipe.return_rank()
pipe.return_ranks(.5,printtofile=True)
# prediction
df2 = pd.read_csv('data/test.csv')
X2, IDS, names2 = filtertrain(df2,'test')
Y2 = pipe._gridsearch.predict_proba(X2)
wids = ['week4','week5','week6','week10']
elif organ == 'liver' and isTargeted == True:
wids = ['4w','5w','6w','10w']
cvweeks = wids[0:2]
pns,cns,Xdata,Ydata = jmport.importdata(organ,isTargeted=isTargeted,LogConc=LogConc)
_, X, Y, _ = jmport.filterd(pns,Xdata,Ydata,wids)
# run automated tests
#run an initialization test for a pipeline with pca and fda
pipe = Pipe(X,Y,cns,wids,organ=organ,isTargeted=isTargeted,LogConc=LogConc)
pipe.setpipe(['FFS','GB'])
# cvcounter test
print('Pipe.cvcounter =\t'+str(pipe.cvcounter))
print(np.shape(np.array(X)))
# test initialization of grid parameters
#griddic = dict(FFS__k=[10,20,40,50,100,130,200,750,800],RF__n_estimators=[10,100,200,300],RF__criterion=["gini","entropy"],RF__max_features=["sqrt","log2"])
griddic = dict(FFS__k=[10,20,40,50,100,130,200,750,800],GB__n_estimators=[100,200,300,600],GB__learning_rate=[0.1,0.3,0.5],GB__max_features=["auto"],GB__max_depth=[3,5,10])
pipe.crossgrid(griddic,cv=cv.leave_x_out(pipe.Y,20,nsamples=200,testlst=[i for i,n in enumerate(pns) if any(j in n for j in cvweeks)]))
print(pipe.return_score())
print(pipe._gridsearch.grid_scores_)
print(pipe._pipe.named_steps.keys())
pipe.return_rank()
pipe.return_ranks(.9,printtofile=True)
# cvcounter test
print('Pipe.cvcounter =\t' + str(pipe.cvcounter))
print("X size: " + str(np.shape(X)))
print("Y size: " + str(np.shape(Y)))
# test initialization of grid parameters
# FFS + RF dic
# griddic = dict(FFS__k=[50,100],RF__n_estimators=[100,200])
# FFS + FDA dic
griddic = dict(GB__n_estimators=[100, 200, 300],
GB__learning_rate=[0.1, 0.3, 0.5],
GB__max_features=["Auto", 100.],
GB__max_depth=[3, 5, 10])
#griddic = dict();
pipe.crossgrid(griddic, crossval=cv.leave_x_out(pipe.Y, 50, nsamples=100))
#pipe.crossgrid(griddic,crossval=cv.leave_x_out(pipe.Y, 20, nsamples=300))
print(pipe.return_score())
print(pipe._gridsearch.grid_scores_)
print(pipe._pipe.named_steps.keys())
print(pipe._pipe)
pipe.return_rank()
pipe.return_ranks(.5, printtofile=True)
# prediction
df2 = pd.read_csv('data/test.csv')
X2, IDS, names2 = filtertrain(df2, 'test')
Y2 = pipe._gridsearch.predict_proba(X2)